[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-63e2ecb9ef81ee97-how-adam-s-variance-normalization-fixes-sgd-s-freq-summary":3,"summaries-facets-categories":109,"summary-related-63e2ecb9ef81ee97-how-adam-s-variance-normalization-fixes-sgd-s-freq-summary":5683},{"id":4,"title":5,"ai":6,"body":13,"categories":69,"created_at":71,"date_modified":71,"description":63,"extension":72,"faq":71,"featured":73,"kicker_label":71,"meta":74,"navigation":90,"path":91,"published_at":92,"question":71,"scraped_at":93,"seo":94,"sitemap":95,"source_id":96,"source_name":97,"source_type":98,"source_url":99,"stem":100,"tags":101,"thumbnail_url":71,"tldr":106,"tweet":71,"unknown_tags":107,"__hash__":108},"summaries\u002Fsummaries\u002F63e2ecb9ef81ee97-how-adam-s-variance-normalization-fixes-sgd-s-freq-summary.md","How Adam's Variance Normalization Fixes SGD's Frequency Bias",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","google\u002Fgemini-3.1-flash-lite",10587,561,3073,0.00348825,{"type":14,"value":15,"toc":62},"minimark",[16,21,25,29,32,55,59],[17,18,20],"h2",{"id":19},"the-frequency-bias-problem-in-sgd","The Frequency Bias Problem in SGD",[22,23,24],"p",{},"Modern language models rely on training data with highly uneven token distributions. In standard Stochastic Gradient Descent (SGD), every parameter is updated using a fixed learning rate. This creates a significant optimization bottleneck: common tokens receive frequent gradient signals and converge quickly, while rare tokens—which may appear in only 0.1% of batches—receive insufficient updates. Consequently, parameters associated with rare tokens often remain near their random initialization, leading to poor model performance on underrepresented data.",[17,26,28],{"id":27},"how-adam-normalizes-learning-dynamics","How Adam Normalizes Learning Dynamics",[22,30,31],{},"Adam addresses this imbalance through adaptive optimization, specifically via variance normalization. Unlike SGD, Adam maintains a running estimate of the squared gradients (variance) for each parameter independently.",[33,34,35,43,49],"ul",{},[36,37,38,42],"li",{},[39,40,41],"strong",{},"Variance Tracking:"," Adam tracks the historical magnitude of gradients for every parameter.",[36,44,45,48],{},[39,46,47],{},"Adaptive Scaling:"," Before applying an update, Adam divides the learning rate by the square root of the accumulated variance estimate.",[36,50,51,54],{},[39,52,53],{},"Automatic Amplification:"," For rare tokens, the variance estimate remains very small because updates are infrequent. This causes the effective learning rate to be automatically amplified. In a controlled experiment, rare tokens received an effective learning rate over 40 times higher than common tokens, allowing them to converge to the target weight (1.0) despite receiving sparse signals.",[17,56,58],{"id":57},"experimental-evidence","Experimental Evidence",[22,60,61],{},"In a comparative study using a six-token vocabulary with frequencies spanning four orders of magnitude, SGD failed to move rare token weights beyond 0.15–0.53, while Adam successfully pushed all weights toward the target of 1.0. The results demonstrate that Adam acts as an \"automatic equalizer,\" requiring no manual tuning to compensate for frequency imbalance; the variance normalization term derives the necessary scaling directly from the gradient history.",{"title":63,"searchDepth":64,"depth":64,"links":65},"",2,[66,67,68],{"id":19,"depth":64,"text":20},{"id":27,"depth":64,"text":28},{"id":57,"depth":64,"text":58},[70],"AI & LLMs",null,"md",false,{"content_references":75,"triage":84},[76,81],{"type":77,"title":78,"url":79,"context":80},"tool","NumPy","https:\u002F\u002Fnumpy.org\u002F","mentioned",{"type":77,"title":82,"url":83,"context":80},"Matplotlib","https:\u002F\u002Fmatplotlib.org\u002F",{"relevance":85,"novelty":86,"quality":86,"actionability":87,"composite":88,"reasoning":89},5,4,3,4.15,"Category: AI & LLMs. The article provides a deep dive into how Adam's optimization technique addresses a specific problem in training language models, which is highly relevant for AI developers. It presents new insights into variance normalization and its impact on rare token optimization, making it actionable for those looking to improve model performance.",true,"\u002Fsummaries\u002F63e2ecb9ef81ee97-how-adam-s-variance-normalization-fixes-sgd-s-freq-summary","2026-05-18 20:18:55","2026-05-18 23:00:19",{"title":5,"description":63},{"loc":91},"63e2ecb9ef81ee97","MarkTechPost","article","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F05\u002F18\u002Fstochastic-gradient-descent-sgds-frequency-bias-and-how-adam-fixes-it\u002F","summaries\u002F63e2ecb9ef81ee97-how-adam-s-variance-normalization-fixes-sgd-s-freq-summary",[102,103,104,105],"llm","machine-learning","python","optimization","Standard SGD fails to optimize rare tokens because they receive infrequent gradient updates. Adam solves this by using variance normalization to automatically amplify the effective learning rate for rare parameters.",[105],"_i3B42aRvOxuhgIJqWBCZrpm6JMn6VhobP9Wj9JNeok",[110,113,116,118,121,124,126,128,131,133,135,137,139,142,144,146,148,150,153,155,157,159,161,163,165,167,169,171,173,175,177,179,181,183,185,187,190,193,195,197,199,201,203,205,207,209,211,213,216,218,220,222,224,226,228,230,232,234,236,238,240,242,244,247,249,251,253,255,257,259,261,263,265,267,269,271,274,276,278,280,282,284,286,288,290,292,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,333,335,337,339,341,343,345,347,349,351,354,356,358,360,362,364,366,368,370,372,374,376,379,381,383,385,387,389,391,393,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,445,447,449,452,454,456,458,460,462,464,466,468,470,472,474,476,478,481,483,485,487,489,491,493,495,497,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,739,741,743,745,748,750,752,754,756,758,760,762,764,766,769,771,773,775,777,779,781,783,785,787,789,791,793,795,797,799,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991,993,995,997,999,1001,1003,1005,1007,1009,1011,1013,1015,1018,1020,1022,1024,1026,1028,1030,1032,1034,1036,1038,1040,1042,1044,1046,1048,1050,1052,1054,1056,1058,1060,1062,1064,1066,1068,1070,1072,1074,1076,1078,1080,1082,1084,1086,1088,1090,1092,1094,1096,1098,1100,1102,1104,1106,1108,1110,1112,1114,1116,1118,1120,1122,1124,1126,1128,1130,1132,1134,1136,1138,1140,1142,1144,1146,1148,1150,1152,1154,1156,1158,1160,1162,1164,1166,1168,1170,1172,1175,1177,1179,1181,1183,1185,1187,1189,1191,1193,1195,1197,1199,1201,1203,1205,1207,1209,1211,1213,1215,1217,1219,1221,1223,1225,1227,1229,1231,1233,1235,1237,1239,1241,1243,1245,1247,1249,1251,1253,1255,1257,1259,1261,1263,1265,1267,1269,1271,1273,1275,1277,1279,1281,1283,1285,1288,1290,1292,1294,1296,1298,1300,1302,1304,1306,1308,1310,1312,1314,1316,1318,1320,1322,1324,1326,1328,1330,1332,1334,1336,1338,1340,1342,1344,1346,1348,1350,1352,1354,1356,1358,1360,1362,1364,1366,1368,1370,1372,1374,1376,1378,1380,1382,1384,1386,1388,1390,1392,1394,1396,1398,1400,1402,1404,1406,1408,1410,1413,1415,1417,1419,1421,1423,1425,1427,1429,1431,1433,1435,1437,1439,1441,1443,1445,1447,1449,1451,1453,1455,1457,1459,1461,1464,1466,1468,1470,1472,1474,1476,1478,1480,1482,1484,1486,1488,1490,1492,1494,1496,1498,1500,1502,1504,1506,1508,1510,1512,1514,1516,1518,1520,1522,1524,1526,1528,1530,1532,1534,1536,1538,1540,1542,1544,1546,1548,1550,1552,1554,1556,1558,1560,1562,1564,1566,1568,1570,1572,1574,1576,1578,1580,1582,1584,1586,1588,1590,1592,1594,1596,1598,1600,1602,1604,1606,1608,1610,1612,1614,1616,1618,1620,1622,1624,1626,1628,1630,1632,1634,1636,1638,1640,1642,1644,1646,1648,1650,1652,1654,1656,1658,1660,1662,1664,1666,1668,1670,1672,1674,1676,1678,1680,1682,1684,1686,1688,1690,1692,1694,1696,1698,1700,1702,1704,1706,1708,1710,1712,1714,1716,1718,1720,1722,1724,1726,1728,1730,1732,1734,1736,1738,1740,1742,1744,1746,1748,1750,1752,1754,1756,1758,1760,1762,1764,1766,1768,1770,1772,1774,1776,1778,1780,1782,1784,1786,1788,1790,1792,1794,1796,1798,1800,1802,1804,1806,1808,1811,1813,1815,1817,1819,1821,1823,1825,1827,1829,1831,1833,1835,1837,1839,1841,1843,1845,1847,1849,1851,1853,1855,1857,1859,1861,1863,1865,1867,1869,1871,1873,1875,1877,1879,1881,1883,1886,1888,1890,1892,1894,1896,1898,1900,1902,1904,1906,1908,1910,1912,1914,1916,1918,1920,1922,1924,1926,1928,1930,1932,1934,1936,1938,1940,1942,1944,1946,1948,1950,1952,1954,1956,1958,1960,1962,1964,1966,1968,1970,1972,1974,1976,1978,1980,1982,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2022,2024,2026,2028,2030,2032,2034,2036,2038,2040,2042,2044,2046,2048,2050,2052,2054,2056,2058,2060,2062,2064,2066,2068,2070,2072,2074,2076,2078,2080,2082,2084,2086,2088,2090,2092,2094,2096,2098,2100,2102,2104,2106,2108,2110,2112,2114,2116,2118,2120,2122,2124,2126,2128,2130,2132,2134,2136,2138,2140,2142,2144,2146,2148,2150,2152,2154,2156,2158,2160,2162,2164,2166,2168,2170,2172,2174,2176,2178,2180,2182,2184,2186,2188,2190,2192,2194,2196,2198,2200,2202,2204,2206,2208,2210,2212,2214,2216,2218,2220,2222,2224,2226,2228,2230,2232,2234,2236,2238,2240,2242,2244,2246,2248,2250,2252,2254,2256,2258,2260,2262,2264,2266,2268,2270,2272,2274,2276,2278,2280,2282,2284,2286,2288,2290,2292,2294,2296,2298,2300,2302,2304,2306,2308,2310,2312,2314,2316,2318,2320,2322,2324,2326,2328,2330,2332,2334,2336,2338,2340,2342,2344,2346,2348,2350,2352,2354,2356,2358,2360,2362,2364,2366,2368,2370,2372,2374,2376,2378,2380,2382,2384,2386,2388,2390,2392,2394,2396,2398,2400,2402,2404,2406,2408,2410,2412,2414,2416,2418,2420,2422,2424,2426,2428,2430,2432,2434,2436,2438,2440,2442,2444,2446,2448,2450,2452,2454,2456,2458,2460,2462,2464,2466,2468,2470,2472,2474,2476,2478,2480,2482,2484,2486,2488,2490,2492,2494,2496,2498,2500,2502,2504,2506,2508,2510,2512,2514,2516,2518,2520,2522,2524,2526,2528,2530,2532,2534,2536,2538,2540,2543,2545,2547,2549,2551,2553,2555,2557,2559,2561,2563,2565,2567,2569,2571,2573,2575,2577,2579,2581,2583,2585,2587,2589,2591,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613,2615,2617,2619,2621,2623,2625,2627,2629,2631,2633,2635,2637,2640,2642,2644,2646,2648,2650,2652,2654,2656,2658,2660,2662,2664,2666,2668,2670,2672,2674,2676,2678,2680,2682,2684,2686,2688,2690,2692,2694,2696,2698,2700,2702,2704,2706,2708,2710,2712,2714,2716,2718,2720,2722,2724,2726,2728,2730,2732,2734,2736,2738,2740,2742,2744,2746,2748,2750,2752,2754,2756,2758,2760,2762,2764,2766,2768,2770,2772,2774,2776,2778,2780,2782,2784,2786,2788,2790,2792,2794,2796,2798,2800,2802,2804,2806,2808,2810,2812,2814,2816,2818,2820,2822,2824,2826,2828,2830,2832,2834,2836,2838,2840,2842,2844,2846,2848,2850,2852,2854,2856,2858,2860,2862,2864,2866,2868,2870,2872,2874,2876,2878,2880,2882,2884,2886,2888,2890,2892,2894,2896,2898,2900,2902,2904,2906,2908,2910,2912,2914,2916,2918,2920,2922,2924,2926,2928,2930,2932,2934,2936,2938,2940,2942,2944,2946,2948,2950,2952,2954,2956,2958,2960,2962,2964,2966,2968,2970,2972,2974,2976,2978,2980,2982,2984,2986,2988,2990,2992,2994,2996,2998,3000,3002,3004,3006,3008,3010,3012,3014,3016,3018,3020,3022,3024,3026,3028,3030,3032,3034,3036,3038,3040,3042,3044,3046,3048,3050,3052,3054,3056,3058,3060,3062,3064,3066,3068,3070,3072,3074,3076,3078,3080,3082,3084,3086,3088,3090,3092,3094,3096,3098,3100,3102,3104,3106,3108,3110,3112,3114,3116,3118,3120,3122,3124,3126,3128,3130,3132,3134,3136,3138,3140,3142,3144,3146,3148,3150,3152,3154,3156,3158,3160,3162,3164,3166,3168,3170,3172,3174,3176,3178,3180,3182,3184,3186,3188,3190,3192,3194,3196,3198,3200,3202,3204,3206,3208,3210,3212,3214,3216,3218,3220,3222,3224,3226,3228,3230,3232,3234,3236,3238,3240,3242,3244,3246,3248,3250,3252,3254,3256,3258,3260,3262,3264,3266,3268,3270,3272,3274,3276,3278,3280,3282,3284,3286,3288,3290,3292,3294,3296,3298,3300,3302,3304,3306,3308,3310,3312,3314,3316,3318,3320,3322,3324,3326,3328,3330,3332,3334,3336,3338,3340,3342,3344,3346,3348,3350,3352,3354,3356,3358,3360,3362,3364,3366,3368,3370,3372,3374,3376,3378,3380,3382,3384,3386,3388,3390,3392,3394,3396,3398,3400,3402,3404,3406,3408,3410,3412,3414,3416,3418,3420,3422,3424,3426,3428,3430,3432,3434,3436,3438,3440,3442,3444,3446,3448,3450,3452,3454,3456,3458,3460,3462,3464,3466,3468,3470,3472,3474,3476,3478,3480,3482,3484,3486,3488,3490,3492,3494,3496,3498,3500,3502,3504,3506,3508,3510,3512,3514,3516,3518,3520,3522,3524,3526,3528,3530,3532,3534,3536,3538,3540,3542,3544,3546,3548,3550,3552,3554,3556,3558,3560,3562,3564,3566,3568,3570,3572,3574,3576,3578,3580,3582,3584,3586,3588,3590,3592,3594,3596,3598,3600,3602,3604,3606,3608,3610,3612,3614,3616,3618,3620,3622,3624,3626,3628,3630,3632,3634,3636,3638,3640,3642,3644,3646,3648,3650,3652,3654,3656,3658,3660,3662,3664,3666,3668,3670,3673,3675,3677,3679,3681,3683,3685,3687,3689,3691,3693,3695,3697,3699,3701,3703,3705,3707,3709,3711,3713,3715,3717,3719,3721,3723,3725,3727,3729,3731,3733,3735,3737,3739,3741,3743,3745,3747,3749,3751,3753,3755,3757,3759,3761,3763,3765,3767,3769,3771,3773,3775,3777,3779,3781,3783,3785,3787,3789,3791,3793,3795,3797,3799,3801,3803,3805,3807,3809,3811,3813,3815,3817,3819,3821,3823,3825,3827,3829,3831,3833,3835,3837,3839,3841,3843,3845,3847,3849,3851,3853,3855,3857,3859,3861,3863,3865,3867,3869,3871,3873,3875,3877,3879,3881,3883,3885,3887,3889,3891,3893,3895,3897,3899,3901,3903,3905,3907,3909,3911,3913,3915,3917,3919,3921,3923,3925,3927,3929,3931,3933,3935,3937,3939,3941,3943,3945,3947,3949,3951,3953,3955,3957,3959,3961,3963,3965,3967,3969,3971,3973,3975,3977,3979,3981,3983,3985,3987,3989,3991,3993,3995,3997,3999,4001,4003,4005,4007,4009,4011,4013,4015,4017,4019,4021,4023,4025,4027,4029,4031,4033,4035,4037,4039,4041,4043,4045,4047,4049,4051,4053,4055,4057,4059,4061,4063,4065,4067,4069,4071,4073,4075,4077,4079,4081,4083,4085,4087,4089,4091,4093,4095,4097,4099,4101,4103,4105,4107,4109,4111,4113,4115,4117,4119,4121,4123,4125,4127,4129,4131,4133,4135,4137,4139,4141,4143,4145,4147,4149,4151,4153,4155,4157,4159,4161,4163,4165,4167,4169,4171,4173,4175,4177,4179,4181,4183,4185,4187,4189,4191,4193,4195,4197,4199,4201,4203,4205,4207,4209,4211,4213,4215,4217,4219,4221,4223,4225,4227,4229,4231,4233,4235,4237,4239,4241,4243,4245,4247,4249,4251,4253,4255,4257,4259,4261,4263,4265,4267,4269,4271,4273,4275,4277,4279,4281,4283,4285,4287,4289,4291,4293,4295,4297,4299,4301,4303,4305,4307,4309,4311,4313,4315,4317,4319,4321,4323,4325,4327,4329,4331,4333,4335,4337,4339,4341,4343,4345,4347,4349,4351,4353,4355,4357,4359,4361,4363,4365,4367,4370,4372,4374,4376,4378,4380,4382,4384,4386,4388,4390,4392,4394,4396,4398,4400,4402,4404,4406,4408,4410,4412,4414,4416,4418,4420,4422,4424,4426,4428,4430,4432,4434,4436,4438,4440,4442,4444,4446,4448,4450,4452,4454,4456,4458,4460,4462,4464,4466,4468,4470,4472,4474,4476,4478,4480,4482,4484,4486,4488,4490,4492,4494,4496,4498,4500,4502,4504,4506,4508,4510,4512,4514,4516,4518,4520,4522,4524,4526,4528,4530,4533,4535,4537,4539,4541,4543,4545,4547,4549,4551,4553,4555,4557,4559,4561,4563,4565,4567,4569,4571,4573,4575,4577,4579,4581,4583,4585,4587,4589,4591,4593,4595,4597,4599,4601,4603,4605,4607,4609,4611,4613,4615,4617,4619,4621,4623,4625,4627,4629,4631,4633,4635,4637,4639,4641,4643,4645,4647,4649,4651,4653,4655,4657,4659,4661,4663,4665,4667,4669,4671,4673,4675,4677,4679,4681,4683,4685,4687,4689,4691,4693,4695,4697,4699,4701,4703,4705,4707,4709,4711,4713,4715,4717,4719,4721,4723,4725,4727,4729,4731,4733,4735,4737,4739,4741,4743,4745,4747,4749,4751,4753,4755,4757,4759,4761,4763,4765,4767,4769,4771,4773,4775,4777,4779,4781,4783,4785,4787,4789,4791,4793,4795,4797,4799,4801,4803,4805,4807,4809,4811,4813,4815,4817,4819,4821,4823,4825,4827,4829,4831,4833,4835,4837,4839,4841,4843,4845,4847,4849,4851,4853,4855,4857,4859,4861,4863,4865,4867,4869,4871,4873,4875,4877,4879,4881,4883,4885,4887,4889,4891,4893,4895,4897,4899,4901,4903,4905,4907,4909,4911,4913,4915,4917,4919,4921,4923,4925,4927,4929,4931,4933,4935,4937,4939,4941,4943,4945,4947,4949,4951,4953,4955,4957,4959,4961,4963,4965,4967,4969,4971,4973,4975,4977,4979,4981,4983,4985,4987,4989,4991,4993,4995,4997,4999,5001,5003,5005,5007,5009,5011,5013,5015,5017,5019,5021,5023,5025,5027,5029,5031,5033,5035,5037,5039,5041,5043,5045,5047,5049,5051,5053,5055,5057,5059,5061,5063,5065,5067,5069,5071,5073,5075,5077,5079,5081,5083,5085,5087,5089,5091,5093,5095,5097,5099,5101,5103,5105,5107,5109,5111,5113,5115,5117,5119,5121,5123,5125,5127,5129,5131,5133,5135,5137,5139,5141,5143,5145,5147,5149,5151,5153,5155,5157,5159,5161,5163,5165,5167,5169,5171,5173,5175,5177,5179,5181,5183,5185,5187,5189,5191,5193,5195,5197,5199,5201,5203,5205,5207,5209,5211,5213,5215,5217,5219,5221,5223,5225,5227,5229,5231,5233,5235,5237,5239,5241,5243,5245,5247,5249,5251,5253,5255,5257,5259,5261,5263,5265,5267,5269,5271,5273,5275,5277,5279,5281,5283,5285,5287,5289,5291,5293,5295,5297,5299,5301,5303,5305,5307,5309,5311,5313,5315,5317,5319,5321,5323,5325,5327,5329,5331,5333,5335,5337,5339,5341,5343,5345,5347,5349,5351,5353,5355,5357,5359,5361,5363,5365,5367,5369,5371,5373,5375,5377,5379,5381,5383,5385,5387,5389,5391,5393,5395,5397,5399,5401,5403,5405,5407,5409,5411,5413,5415,5417,5419,5421,5423,5425,5427,5429,5431,5433,5435,5437,5439,5441,5443,5445,5447,5449,5451,5453,5455,5457,5459,5461,5463,5465,5467,5469,5471,5473,5475,5477,5479,5481,5483,5485,5487,5489,5491,5493,5495,5497,5499,5501,5503,5505,5507,5509,5511,5513,5515,5517,5519,5521,5523,5525,5527,5529,5531,5533,5535,5537,5539,5541,5543,5545,5547,5549,5551,5553,5555,5557,5559,5561,5563,5565,5567,5569,5571,5573,5575,5577,5579,5581,5583,5585,5587,5589,5591,5593,5595,5597,5599,5601,5603,5605,5607,5609,5611,5613,5615,5617,5619,5621,5623,5625,5627,5629,5631,5633,5635,5637,5639,5641,5643,5645,5647,5649,5651,5653,5655,5657,5659,5661,5663,5665,5667,5669,5671,5673,5675,5677,5679,5681],{"categories":111},[112],"Developer Productivity",{"categories":114},[115],"Business & SaaS",{"categories":117},[70],{"categories":119},[120],"AI Automation",{"categories":122},[123],"Product Strategy",{"categories":125},[70],{"categories":127},[112],{"categories":129},[130],"Software Engineering",{"categories":132},[70],{"categories":134},[115],{"categories":136},[],{"categories":138},[70],{"categories":140},[141],"Inference & Serving",{"categories":143},[70],{"categories":145},[70],{"categories":147},[120],{"categories":149},[],{"categories":151},[152],"AI News & Trends",{"categories":154},[120],{"categories":156},[70],{"categories":158},[115],{"categories":160},[70],{"categories":162},[120],{"categories":164},[152],{"categories":166},[120],{"categories":168},[120],{"categories":170},[70],{"categories":172},[120],{"categories":174},[70],{"categories":176},[70],{"categories":178},[70],{"categories":180},[152],{"categories":182},[70],{"categories":184},[70],{"categories":186},[],{"categories":188},[189],"Design & Frontend",{"categories":191},[192],"Data Science & Visualization",{"categories":194},[152],{"categories":196},[70],{"categories":198},[70],{"categories":200},[],{"categories":202},[70],{"categories":204},[120],{"categories":206},[130],{"categories":208},[70],{"categories":210},[120],{"categories":212},[70],{"categories":214},[215],"Marketing & Growth",{"categories":217},[189],{"categories":219},[70],{"categories":221},[120],{"categories":223},[70],{"categories":225},[],{"categories":227},[],{"categories":229},[189],{"categories":231},[70],{"categories":233},[120],{"categories":235},[112],{"categories":237},[130],{"categories":239},[189],{"categories":241},[70],{"categories":243},[130],{"categories":245},[246],"DevOps & Cloud",{"categories":248},[120],{"categories":250},[123],{"categories":252},[152],{"categories":254},[70],{"categories":256},[],{"categories":258},[70],{"categories":260},[],{"categories":262},[120],{"categories":264},[130],{"categories":266},[],{"categories":268},[130],{"categories":270},[70],{"categories":272},[273],"Governance & Standards",{"categories":275},[115],{"categories":277},[],{"categories":279},[],{"categories":281},[70],{"categories":283},[70],{"categories":285},[120],{"categories":287},[70],{"categories":289},[70],{"categories":291},[120],{"categories":293},[70],{"categories":295},[70],{"categories":297},[70],{"categories":299},[],{"categories":301},[130],{"categories":303},[],{"categories":305},[],{"categories":307},[130],{"categories":309},[],{"categories":311},[130],{"categories":313},[70],{"categories":315},[70],{"categories":317},[215],{"categories":319},[70],{"categories":321},[189],{"categories":323},[189],{"categories":325},[70],{"categories":327},[130],{"categories":329},[120],{"categories":331},[332],"GovTech & Public-Sector Adoption",{"categories":334},[130],{"categories":336},[70],{"categories":338},[70],{"categories":340},[120],{"categories":342},[120],{"categories":344},[192],{"categories":346},[70],{"categories":348},[152],{"categories":350},[120],{"categories":352},[353],"Legal AI Tools",{"categories":355},[120],{"categories":357},[215],{"categories":359},[120],{"categories":361},[123],{"categories":363},[130],{"categories":365},[332],{"categories":367},[],{"categories":369},[120],{"categories":371},[],{"categories":373},[120],{"categories":375},[120],{"categories":377},[378],"RAG & Retrieval",{"categories":380},[115],{"categories":382},[70],{"categories":384},[130],{"categories":386},[246],{"categories":388},[189],{"categories":390},[70],{"categories":392},[],{"categories":394},[395],"Agents & Orchestration",{"categories":397},[130],{"categories":399},[70],{"categories":401},[],{"categories":403},[120],{"categories":405},[115],{"categories":407},[],{"categories":409},[70],{"categories":411},[],{"categories":413},[112],{"categories":415},[130],{"categories":417},[115],{"categories":419},[70],{"categories":421},[70],{"categories":423},[152],{"categories":425},[70],{"categories":427},[],{"categories":429},[70],{"categories":431},[],{"categories":433},[130],{"categories":435},[192],{"categories":437},[],{"categories":439},[70],{"categories":441},[189],{"categories":443},[444],"Models & Frontier Labs",{"categories":446},[],{"categories":448},[189],{"categories":450},[451],"Regulation & Governance of AI",{"categories":453},[120],{"categories":455},[],{"categories":457},[70],{"categories":459},[70],{"categories":461},[120],{"categories":463},[152],{"categories":465},[115],{"categories":467},[70],{"categories":469},[],{"categories":471},[130],{"categories":473},[120],{"categories":475},[70],{"categories":477},[123],{"categories":479},[480],"AI Policy & Regulation",{"categories":482},[],{"categories":484},[70],{"categories":486},[123],{"categories":488},[120],{"categories":490},[70],{"categories":492},[120],{"categories":494},[],{"categories":496},[192],{"categories":498},[499],"Evals & Reliability",{"categories":501},[70],{"categories":503},[],{"categories":505},[112],{"categories":507},[332],{"categories":509},[480],{"categories":511},[70],{"categories":513},[115],{"categories":515},[70],{"categories":517},[120],{"categories":519},[70],{"categories":521},[120],{"categories":523},[395],{"categories":525},[70],{"categories":527},[130],{"categories":529},[70],{"categories":531},[],{"categories":533},[],{"categories":535},[70],{"categories":537},[332],{"categories":539},[70],{"categories":541},[70],{"categories":543},[],{"categories":545},[189],{"categories":547},[],{"categories":549},[70],{"categories":551},[],{"categories":553},[120],{"categories":555},[70],{"categories":557},[189],{"categories":559},[],{"categories":561},[70],{"categories":563},[120],{"categories":565},[70],{"categories":567},[115],{"categories":569},[120],{"categories":571},[70],{"categories":573},[70],{"categories":575},[130],{"categories":577},[189],{"categories":579},[120],{"categories":581},[],{"categories":583},[130],{"categories":585},[120],{"categories":587},[],{"categories":589},[152],{"categories":591},[],{"categories":593},[70],{"categories":595},[70],{"categories":597},[115,215],{"categories":599},[],{"categories":601},[70],{"categories":603},[70],{"categories":605},[120],{"categories":607},[],{"categories":609},[],{"categories":611},[70],{"categories":613},[189],{"categories":615},[70],{"categories":617},[],{"categories":619},[70],{"categories":621},[246],{"categories":623},[],{"categories":625},[120],{"categories":627},[152],{"categories":629},[70],{"categories":631},[189],{"categories":633},[],{"categories":635},[152],{"categories":637},[70],{"categories":639},[141],{"categories":641},[70],{"categories":643},[120],{"categories":645},[152],{"categories":647},[444],{"categories":649},[70],{"categories":651},[215],{"categories":653},[],{"categories":655},[120],{"categories":657},[115],{"categories":659},[130],{"categories":661},[70],{"categories":663},[120],{"categories":665},[],{"categories":667},[70,246],{"categories":669},[70],{"categories":671},[70],{"categories":673},[70],{"categories":675},[120],{"categories":677},[70,130],{"categories":679},[192],{"categories":681},[70],{"categories":683},[70],{"categories":685},[130],{"categories":687},[120],{"categories":689},[480],{"categories":691},[215],{"categories":693},[70],{"categories":695},[120],{"categories":697},[70],{"categories":699},[70],{"categories":701},[120],{"categories":703},[],{"categories":705},[70],{"categories":707},[120],{"categories":709},[70],{"categories":711},[70,115],{"categories":713},[115],{"categories":715},[],{"categories":717},[189],{"categories":719},[189],{"categories":721},[70],{"categories":723},[],{"categories":725},[],{"categories":727},[152],{"categories":729},[],{"categories":731},[112],{"categories":733},[70],{"categories":735},[130],{"categories":737},[738],"Generative UI & Design-to-Code",{"categories":740},[70],{"categories":742},[189],{"categories":744},[70],{"categories":746},[747],"Algorithmic Accountability",{"categories":749},[120],{"categories":751},[130],{"categories":753},[152],{"categories":755},[189],{"categories":757},[],{"categories":759},[70],{"categories":761},[70],{"categories":763},[70],{"categories":765},[120],{"categories":767},[768],"MLOps & Infrastructure",{"categories":770},[70],{"categories":772},[70],{"categories":774},[70],{"categories":776},[70],{"categories":778},[152],{"categories":780},[112],{"categories":782},[70],{"categories":784},[120],{"categories":786},[246],{"categories":788},[70],{"categories":790},[189],{"categories":792},[70],{"categories":794},[120],{"categories":796},[],{"categories":798},[],{"categories":800},[141],{"categories":802},[189],{"categories":804},[152],{"categories":806},[192],{"categories":808},[],{"categories":810},[70],{"categories":812},[70],{"categories":814},[115],{"categories":816},[70],{"categories":818},[70],{"categories":820},[70],{"categories":822},[152],{"categories":824},[141],{"categories":826},[70],{"categories":828},[189],{"categories":830},[],{"categories":832},[120],{"categories":834},[130],{"categories":836},[],{"categories":838},[70],{"categories":840},[70],{"categories":842},[120],{"categories":844},[130],{"categories":846},[70],{"categories":848},[192],{"categories":850},[],{"categories":852},[70],{"categories":854},[],{"categories":856},[70],{"categories":858},[],{"categories":860},[123],{"categories":862},[115],{"categories":864},[120],{"categories":866},[120],{"categories":868},[],{"categories":870},[112],{"categories":872},[70],{"categories":874},[115],{"categories":876},[152],{"categories":878},[112],{"categories":880},[],{"categories":882},[70],{"categories":884},[],{"categories":886},[],{"categories":888},[152],{"categories":890},[152],{"categories":892},[],{"categories":894},[395],{"categories":896},[70],{"categories":898},[189],{"categories":900},[130],{"categories":902},[],{"categories":904},[353],{"categories":906},[115],{"categories":908},[],{"categories":910},[],{"categories":912},[112],{"categories":914},[192],{"categories":916},[],{"categories":918},[215],{"categories":920},[120],{"categories":922},[115],{"categories":924},[120],{"categories":926},[115],{"categories":928},[130],{"categories":930},[],{"categories":932},[141],{"categories":934},[123],{"categories":936},[70],{"categories":938},[189],{"categories":940},[130],{"categories":942},[115],{"categories":944},[70],{"categories":946},[120],{"categories":948},[115],{"categories":950},[70],{"categories":952},[70],{"categories":954},[],{"categories":956},[],{"categories":958},[130],{"categories":960},[192],{"categories":962},[123],{"categories":964},[70],{"categories":966},[120],{"categories":968},[70],{"categories":970},[],{"categories":972},[152],{"categories":974},[123],{"categories":976},[70],{"categories":978},[499],{"categories":980},[246],{"categories":982},[],{"categories":984},[120],{"categories":986},[],{"categories":988},[112],{"categories":990},[],{"categories":992},[70],{"categories":994},[70],{"categories":996},[189],{"categories":998},[215],{"categories":1000},[130],{"categories":1002},[120],{"categories":1004},[],{"categories":1006},[130],{"categories":1008},[112],{"categories":1010},[],{"categories":1012},[152],{"categories":1014},[70,246],{"categories":1016},[1017],"Design Systems for AI",{"categories":1019},[70],{"categories":1021},[152],{"categories":1023},[70],{"categories":1025},[70],{"categories":1027},[115],{"categories":1029},[70],{"categories":1031},[],{"categories":1033},[70],{"categories":1035},[70],{"categories":1037},[115],{"categories":1039},[70],{"categories":1041},[],{"categories":1043},[120],{"categories":1045},[130],{"categories":1047},[130],{"categories":1049},[189],{"categories":1051},[152],{"categories":1053},[192],{"categories":1055},[70],{"categories":1057},[112],{"categories":1059},[480],{"categories":1061},[70],{"categories":1063},[120],{"categories":1065},[70],{"categories":1067},[130],{"categories":1069},[130],{"categories":1071},[],{"categories":1073},[],{"categories":1075},[120],{"categories":1077},[123],{"categories":1079},[],{"categories":1081},[70],{"categories":1083},[],{"categories":1085},[189],{"categories":1087},[120],{"categories":1089},[130],{"categories":1091},[189],{"categories":1093},[70],{"categories":1095},[189],{"categories":1097},[],{"categories":1099},[],{"categories":1101},[152],{"categories":1103},[120],{"categories":1105},[120],{"categories":1107},[70],{"categories":1109},[70],{"categories":1111},[70],{"categories":1113},[115],{"categories":1115},[70],{"categories":1117},[70],{"categories":1119},[],{"categories":1121},[130],{"categories":1123},[130],{"categories":1125},[70],{"categories":1127},[130],{"categories":1129},[115],{"categories":1131},[],{"categories":1133},[70],{"categories":1135},[70],{"categories":1137},[70],{"categories":1139},[120],{"categories":1141},[112],{"categories":1143},[115],{"categories":1145},[152],{"categories":1147},[120],{"categories":1149},[141],{"categories":1151},[215],{"categories":1153},[70],{"categories":1155},[120],{"categories":1157},[],{"categories":1159},[189],{"categories":1161},[],{"categories":1163},[70],{"categories":1165},[70],{"categories":1167},[],{"categories":1169},[130],{"categories":1171},[115],{"categories":1173},[1174],"Visual & Generative Media",{"categories":1176},[120],{"categories":1178},[],{"categories":1180},[70],{"categories":1182},[70],{"categories":1184},[246],{"categories":1186},[192],{"categories":1188},[480],{"categories":1190},[130],{"categories":1192},[215],{"categories":1194},[70],{"categories":1196},[189],{"categories":1198},[70],{"categories":1200},[130],{"categories":1202},[120],{"categories":1204},[],{"categories":1206},[],{"categories":1208},[120],{"categories":1210},[112],{"categories":1212},[120],{"categories":1214},[444],{"categories":1216},[70],{"categories":1218},[123],{"categories":1220},[115],{"categories":1222},[],{"categories":1224},[70],{"categories":1226},[123],{"categories":1228},[70],{"categories":1230},[70],{"categories":1232},[70],{"categories":1234},[70],{"categories":1236},[70],{"categories":1238},[215],{"categories":1240},[70],{"categories":1242},[395],{"categories":1244},[70],{"categories":1246},[70],{"categories":1248},[70],{"categories":1250},[70],{"categories":1252},[70],{"categories":1254},[189],{"categories":1256},[120],{"categories":1258},[],{"categories":1260},[120],{"categories":1262},[],{"categories":1264},[246],{"categories":1266},[130],{"categories":1268},[],{"categories":1270},[444],{"categories":1272},[120],{"categories":1274},[70],{"categories":1276},[189,70],{"categories":1278},[112],{"categories":1280},[],{"categories":1282},[70],{"categories":1284},[112],{"categories":1286},[1287],"Medical Imaging & Radiology",{"categories":1289},[189],{"categories":1291},[120],{"categories":1293},[130],{"categories":1295},[],{"categories":1297},[70],{"categories":1299},[70],{"categories":1301},[70],{"categories":1303},[],{"categories":1305},[],{"categories":1307},[70],{"categories":1309},[395],{"categories":1311},[70],{"categories":1313},[112],{"categories":1315},[70],{"categories":1317},[70],{"categories":1319},[],{"categories":1321},[120],{"categories":1323},[70],{"categories":1325},[123],{"categories":1327},[130],{"categories":1329},[70],{"categories":1331},[395],{"categories":1333},[70],{"categories":1335},[120],{"categories":1337},[70],{"categories":1339},[189],{"categories":1341},[120],{"categories":1343},[246],{"categories":1345},[189],{"categories":1347},[115],{"categories":1349},[120],{"categories":1351},[70],{"categories":1353},[70],{"categories":1355},[70],{"categories":1357},[70],{"categories":1359},[70],{"categories":1361},[120],{"categories":1363},[130],{"categories":1365},[70],{"categories":1367},[123],{"categories":1369},[],{"categories":1371},[152],{"categories":1373},[],{"categories":1375},[123],{"categories":1377},[120],{"categories":1379},[1017],{"categories":1381},[1017],{"categories":1383},[189],{"categories":1385},[70],{"categories":1387},[70],{"categories":1389},[120],{"categories":1391},[130],{"categories":1393},[189],{"categories":1395},[120],{"categories":1397},[152],{"categories":1399},[],{"categories":1401},[70],{"categories":1403},[],{"categories":1405},[70],{"categories":1407},[70],{"categories":1409},[70],{"categories":1411},[1412],"Contract Review & E-Discovery",{"categories":1414},[189],{"categories":1416},[70],{"categories":1418},[112],{"categories":1420},[152],{"categories":1422},[70],{"categories":1424},[70],{"categories":1426},[215],{"categories":1428},[130],{"categories":1430},[70],{"categories":1432},[70],{"categories":1434},[120],{"categories":1436},[120],{"categories":1438},[747],{"categories":1440},[120],{"categories":1442},[120],{"categories":1444},[70],{"categories":1446},[70],{"categories":1448},[120],{"categories":1450},[70],{"categories":1452},[395],{"categories":1454},[378],{"categories":1456},[70],{"categories":1458},[120],{"categories":1460},[70],{"categories":1462},[1463],"Law-Firm Practice & Adoption",{"categories":1465},[70],{"categories":1467},[120],{"categories":1469},[189],{"categories":1471},[70],{"categories":1473},[70],{"categories":1475},[],{"categories":1477},[],{"categories":1479},[130],{"categories":1481},[],{"categories":1483},[112],{"categories":1485},[246],{"categories":1487},[70],{"categories":1489},[],{"categories":1491},[112],{"categories":1493},[115],{"categories":1495},[70],{"categories":1497},[215],{"categories":1499},[],{"categories":1501},[115],{"categories":1503},[115],{"categories":1505},[],{"categories":1507},[70],{"categories":1509},[70],{"categories":1511},[130],{"categories":1513},[],{"categories":1515},[],{"categories":1517},[],{"categories":1519},[],{"categories":1521},[70],{"categories":1523},[120],{"categories":1525},[246],{"categories":1527},[70],{"categories":1529},[112],{"categories":1531},[130],{"categories":1533},[70],{"categories":1535},[70],{"categories":1537},[130],{"categories":1539},[123],{"categories":1541},[70],{"categories":1543},[768],{"categories":1545},[70],{"categories":1547},[215],{"categories":1549},[130],{"categories":1551},[115],{"categories":1553},[70],{"categories":1555},[70],{"categories":1557},[189],{"categories":1559},[70],{"categories":1561},[70],{"categories":1563},[70],{"categories":1565},[120],{"categories":1567},[70,112],{"categories":1569},[395],{"categories":1571},[70],{"categories":1573},[130],{"categories":1575},[130],{"categories":1577},[189],{"categories":1579},[120],{"categories":1581},[130],{"categories":1583},[70],{"categories":1585},[70],{"categories":1587},[],{"categories":1589},[],{"categories":1591},[70],{"categories":1593},[],{"categories":1595},[70],{"categories":1597},[130],{"categories":1599},[192],{"categories":1601},[152],{"categories":1603},[189],{"categories":1605},[70],{"categories":1607},[130],{"categories":1609},[],{"categories":1611},[120],{"categories":1613},[70],{"categories":1615},[70],{"categories":1617},[70],{"categories":1619},[70],{"categories":1621},[],{"categories":1623},[120],{"categories":1625},[70],{"categories":1627},[70],{"categories":1629},[],{"categories":1631},[120],{"categories":1633},[70],{"categories":1635},[70],{"categories":1637},[115],{"categories":1639},[70],{"categories":1641},[],{"categories":1643},[112],{"categories":1645},[70],{"categories":1647},[189],{"categories":1649},[130],{"categories":1651},[70],{"categories":1653},[112],{"categories":1655},[70],{"categories":1657},[130],{"categories":1659},[215],{"categories":1661},[120],{"categories":1663},[120],{"categories":1665},[70,189],{"categories":1667},[70],{"categories":1669},[152],{"categories":1671},[70],{"categories":1673},[152],{"categories":1675},[120],{"categories":1677},[189],{"categories":1679},[],{"categories":1681},[130],{"categories":1683},[246],{"categories":1685},[189],{"categories":1687},[130],{"categories":1689},[70],{"categories":1691},[123],{"categories":1693},[70],{"categories":1695},[120],{"categories":1697},[],{"categories":1699},[],{"categories":1701},[70],{"categories":1703},[],{"categories":1705},[],{"categories":1707},[123],{"categories":1709},[130],{"categories":1711},[70],{"categories":1713},[120],{"categories":1715},[120],{"categories":1717},[115],{"categories":1719},[120],{"categories":1721},[246],{"categories":1723},[70],{"categories":1725},[70],{"categories":1727},[141],{"categories":1729},[70],{"categories":1731},[70],{"categories":1733},[120],{"categories":1735},[70],{"categories":1737},[70],{"categories":1739},[353],{"categories":1741},[747],{"categories":1743},[],{"categories":1745},[189],{"categories":1747},[1463],{"categories":1749},[130],{"categories":1751},[],{"categories":1753},[],{"categories":1755},[120],{"categories":1757},[],{"categories":1759},[],{"categories":1761},[215],{"categories":1763},[215],{"categories":1765},[120],{"categories":1767},[130],{"categories":1769},[],{"categories":1771},[70],{"categories":1773},[70],{"categories":1775},[130],{"categories":1777},[1412],{"categories":1779},[189],{"categories":1781},[189],{"categories":1783},[70],{"categories":1785},[120],{"categories":1787},[112],{"categories":1789},[70],{"categories":1791},[70],{"categories":1793},[189],{"categories":1795},[189],{"categories":1797},[120],{"categories":1799},[120],{"categories":1801},[70],{"categories":1803},[],{"categories":1805},[70],{"categories":1807},[],{"categories":1809},[1810],"Interaction & Product Design",{"categories":1812},[70],{"categories":1814},[120],{"categories":1816},[273],{"categories":1818},[152],{"categories":1820},[130],{"categories":1822},[70],{"categories":1824},[70],{"categories":1826},[130],{"categories":1828},[112],{"categories":1830},[70],{"categories":1832},[],{"categories":1834},[120],{"categories":1836},[120],{"categories":1838},[],{"categories":1840},[130],{"categories":1842},[70],{"categories":1844},[112],{"categories":1846},[1810],{"categories":1848},[70],{"categories":1850},[112],{"categories":1852},[112],{"categories":1854},[],{"categories":1856},[130],{"categories":1858},[],{"categories":1860},[120],{"categories":1862},[152],{"categories":1864},[70],{"categories":1866},[120],{"categories":1868},[70],{"categories":1870},[120],{"categories":1872},[70],{"categories":1874},[152],{"categories":1876},[192],{"categories":1878},[70],{"categories":1880},[123],{"categories":1882},[130],{"categories":1884},[1885],"Coding Agents & Dev Productivity",{"categories":1887},[152],{"categories":1889},[189],{"categories":1891},[],{"categories":1893},[70],{"categories":1895},[747],{"categories":1897},[],{"categories":1899},[70],{"categories":1901},[70],{"categories":1903},[152],{"categories":1905},[],{"categories":1907},[],{"categories":1909},[70],{"categories":1911},[],{"categories":1913},[120],{"categories":1915},[70],{"categories":1917},[],{"categories":1919},[130],{"categories":1921},[130],{"categories":1923},[70],{"categories":1925},[192],{"categories":1927},[],{"categories":1929},[70],{"categories":1931},[70],{"categories":1933},[70],{"categories":1935},[192],{"categories":1937},[130],{"categories":1939},[],{"categories":1941},[],{"categories":1943},[120],{"categories":1945},[120],{"categories":1947},[332],{"categories":1949},[130],{"categories":1951},[130],{"categories":1953},[120],{"categories":1955},[152],{"categories":1957},[152],{"categories":1959},[120],{"categories":1961},[120],{"categories":1963},[70],{"categories":1965},[112],{"categories":1967},[1810],{"categories":1969},[70,246],{"categories":1971},[],{"categories":1973},[189],{"categories":1975},[130],{"categories":1977},[112],{"categories":1979},[70],{"categories":1981},[120],{"categories":1983},[1984],"The Designer's Role & Craft",{"categories":1986},[189],{"categories":1988},[],{"categories":1990},[120],{"categories":1992},[70],{"categories":1994},[120],{"categories":1996},[120],{"categories":1998},[70],{"categories":2000},[215],{"categories":2002},[70],{"categories":2004},[130],{"categories":2006},[189],{"categories":2008},[70],{"categories":2010},[],{"categories":2012},[120],{"categories":2014},[189],{"categories":2016},[70],{"categories":2018},[70],{"categories":2020},[2021],"AI UX Patterns",{"categories":2023},[120],{"categories":2025},[120],{"categories":2027},[120],{"categories":2029},[120],{"categories":2031},[215],{"categories":2033},[192],{"categories":2035},[70],{"categories":2037},[120],{"categories":2039},[70],{"categories":2041},[1017],{"categories":2043},[],{"categories":2045},[215],{"categories":2047},[152],{"categories":2049},[130],{"categories":2051},[70],{"categories":2053},[120],{"categories":2055},[],{"categories":2057},[],{"categories":2059},[70],{"categories":2061},[120],{"categories":2063},[70],{"categories":2065},[120],{"categories":2067},[332],{"categories":2069},[189],{"categories":2071},[152],{"categories":2073},[130],{"categories":2075},[70],{"categories":2077},[120],{"categories":2079},[120],{"categories":2081},[],{"categories":2083},[70],{"categories":2085},[],{"categories":2087},[],{"categories":2089},[70],{"categories":2091},[70],{"categories":2093},[120],{"categories":2095},[130],{"categories":2097},[],{"categories":2099},[],{"categories":2101},[192],{"categories":2103},[141],{"categories":2105},[70],{"categories":2107},[192],{"categories":2109},[152],{"categories":2111},[70],{"categories":2113},[70],{"categories":2115},[120],{"categories":2117},[120],{"categories":2119},[70],{"categories":2121},[120],{"categories":2123},[],{"categories":2125},[],{"categories":2127},[70],{"categories":2129},[246],{"categories":2131},[70],{"categories":2133},[],{"categories":2135},[],{"categories":2137},[189],{"categories":2139},[768],{"categories":2141},[120],{"categories":2143},[112],{"categories":2145},[1984],{"categories":2147},[],{"categories":2149},[],{"categories":2151},[70],{"categories":2153},[],{"categories":2155},[],{"categories":2157},[130],{"categories":2159},[152],{"categories":2161},[215],{"categories":2163},[115],{"categories":2165},[70],{"categories":2167},[70],{"categories":2169},[115],{"categories":2171},[],{"categories":2173},[189],{"categories":2175},[70],{"categories":2177},[120],{"categories":2179},[115],{"categories":2181},[70],{"categories":2183},[70],{"categories":2185},[112],{"categories":2187},[70],{"categories":2189},[],{"categories":2191},[112],{"categories":2193},[70],{"categories":2195},[215],{"categories":2197},[120],{"categories":2199},[152],{"categories":2201},[70],{"categories":2203},[115],{"categories":2205},[70],{"categories":2207},[70],{"categories":2209},[70],{"categories":2211},[120],{"categories":2213},[],{"categories":2215},[70],{"categories":2217},[130],{"categories":2219},[112],{"categories":2221},[70],{"categories":2223},[70],{"categories":2225},[],{"categories":2227},[395],{"categories":2229},[152],{"categories":2231},[70],{"categories":2233},[70],{"categories":2235},[],{"categories":2237},[115],{"categories":2239},[115],{"categories":2241},[70],{"categories":2243},[70],{"categories":2245},[123],{"categories":2247},[70],{"categories":2249},[70],{"categories":2251},[130],{"categories":2253},[130],{"categories":2255},[70],{"categories":2257},[],{"categories":2259},[130],{"categories":2261},[70],{"categories":2263},[130],{"categories":2265},[480],{"categories":2267},[],{"categories":2269},[],{"categories":2271},[70],{"categories":2273},[152],{"categories":2275},[],{"categories":2277},[246],{"categories":2279},[70],{"categories":2281},[70],{"categories":2283},[189],{"categories":2285},[738],{"categories":2287},[],{"categories":2289},[70],{"categories":2291},[70],{"categories":2293},[130],{"categories":2295},[70],{"categories":2297},[70],{"categories":2299},[70,246],{"categories":2301},[70],{"categories":2303},[70],{"categories":2305},[189],{"categories":2307},[120],{"categories":2309},[],{"categories":2311},[120],{"categories":2313},[120],{"categories":2315},[70],{"categories":2317},[70],{"categories":2319},[70],{"categories":2321},[192],{"categories":2323},[70],{"categories":2325},[2021],{"categories":2327},[112],{"categories":2329},[192],{"categories":2331},[112],{"categories":2333},[130],{"categories":2335},[189],{"categories":2337},[120],{"categories":2339},[70],{"categories":2341},[],{"categories":2343},[70],{"categories":2345},[152],{"categories":2347},[70],{"categories":2349},[120],{"categories":2351},[70],{"categories":2353},[70],{"categories":2355},[115],{"categories":2357},[],{"categories":2359},[246],{"categories":2361},[70],{"categories":2363},[332],{"categories":2365},[189],{"categories":2367},[189],{"categories":2369},[130],{"categories":2371},[120],{"categories":2373},[70],{"categories":2375},[115],{"categories":2377},[152],{"categories":2379},[70],{"categories":2381},[189],{"categories":2383},[120],{"categories":2385},[70],{"categories":2387},[70],{"categories":2389},[444],{"categories":2391},[],{"categories":2393},[70],{"categories":2395},[70],{"categories":2397},[70],{"categories":2399},[],{"categories":2401},[],{"categories":2403},[70],{"categories":2405},[70],{"categories":2407},[70],{"categories":2409},[70],{"categories":2411},[130],{"categories":2413},[70],{"categories":2415},[70],{"categories":2417},[120],{"categories":2419},[70],{"categories":2421},[70],{"categories":2423},[70],{"categories":2425},[70],{"categories":2427},[],{"categories":2429},[130],{"categories":2431},[192],{"categories":2433},[70],{"categories":2435},[120],{"categories":2437},[70],{"categories":2439},[],{"categories":2441},[],{"categories":2443},[70],{"categories":2445},[70],{"categories":2447},[70],{"categories":2449},[152],{"categories":2451},[],{"categories":2453},[70],{"categories":2455},[189],{"categories":2457},[70],{"categories":2459},[246],{"categories":2461},[1463],{"categories":2463},[152],{"categories":2465},[130],{"categories":2467},[130],{"categories":2469},[130],{"categories":2471},[152],{"categories":2473},[152],{"categories":2475},[246],{"categories":2477},[],{"categories":2479},[152],{"categories":2481},[70],{"categories":2483},[112],{"categories":2485},[130],{"categories":2487},[70],{"categories":2489},[152],{"categories":2491},[],{"categories":2493},[70],{"categories":2495},[130],{"categories":2497},[192],{"categories":2499},[70],{"categories":2501},[152],{"categories":2503},[70],{"categories":2505},[130],{"categories":2507},[120],{"categories":2509},[152],{"categories":2511},[120],{"categories":2513},[246],{"categories":2515},[120],{"categories":2517},[70],{"categories":2519},[70],{"categories":2521},[130],{"categories":2523},[70],{"categories":2525},[],{"categories":2527},[115],{"categories":2529},[130],{"categories":2531},[],{"categories":2533},[],{"categories":2535},[70],{"categories":2537},[120],{"categories":2539},[70],{"categories":2541},[2542],"Frameworks & Tooling",{"categories":2544},[70],{"categories":2546},[70],{"categories":2548},[130],{"categories":2550},[70],{"categories":2552},[70],{"categories":2554},[],{"categories":2556},[192],{"categories":2558},[192],{"categories":2560},[112],{"categories":2562},[120],{"categories":2564},[189],{"categories":2566},[],{"categories":2568},[1463],{"categories":2570},[70],{"categories":2572},[130],{"categories":2574},[70],{"categories":2576},[246],{"categories":2578},[246],{"categories":2580},[],{"categories":2582},[120],{"categories":2584},[152],{"categories":2586},[152],{"categories":2588},[70],{"categories":2590},[120],{"categories":2592},[],{"categories":2594},[189],{"categories":2596},[70],{"categories":2598},[70],{"categories":2600},[],{"categories":2602},[70],{"categories":2604},[],{"categories":2606},[130],{"categories":2608},[70],{"categories":2610},[130],{"categories":2612},[246],{"categories":2614},[70],{"categories":2616},[130],{"categories":2618},[115],{"categories":2620},[70],{"categories":2622},[1463],{"categories":2624},[],{"categories":2626},[120],{"categories":2628},[112],{"categories":2630},[112],{"categories":2632},[],{"categories":2634},[120],{"categories":2636},[70],{"categories":2638},[2639],"AI Design Tooling",{"categories":2641},[189],{"categories":2643},[70],{"categories":2645},[70],{"categories":2647},[130],{"categories":2649},[189],{"categories":2651},[70],{"categories":2653},[130],{"categories":2655},[152],{"categories":2657},[123],{"categories":2659},[130],{"categories":2661},[120],{"categories":2663},[],{"categories":2665},[70],{"categories":2667},[70],{"categories":2669},[120],{"categories":2671},[70],{"categories":2673},[70],{"categories":2675},[],{"categories":2677},[120],{"categories":2679},[2542],{"categories":2681},[70],{"categories":2683},[120],{"categories":2685},[120],{"categories":2687},[130],{"categories":2689},[130],{"categories":2691},[],{"categories":2693},[130],{"categories":2695},[70],{"categories":2697},[70],{"categories":2699},[120],{"categories":2701},[115],{"categories":2703},[70],{"categories":2705},[],{"categories":2707},[70],{"categories":2709},[1810],{"categories":2711},[],{"categories":2713},[70],{"categories":2715},[70],{"categories":2717},[],{"categories":2719},[70],{"categories":2721},[70],{"categories":2723},[70],{"categories":2725},[215],{"categories":2727},[152],{"categories":2729},[70],{"categories":2731},[70],{"categories":2733},[1463],{"categories":2735},[112],{"categories":2737},[70],{"categories":2739},[70],{"categories":2741},[192],{"categories":2743},[70],{"categories":2745},[152],{"categories":2747},[120],{"categories":2749},[],{"categories":2751},[70],{"categories":2753},[189],{"categories":2755},[70],{"categories":2757},[215],{"categories":2759},[70],{"categories":2761},[120],{"categories":2763},[],{"categories":2765},[],{"categories":2767},[],{"categories":2769},[112],{"categories":2771},[152],{"categories":2773},[120],{"categories":2775},[70],{"categories":2777},[70],{"categories":2779},[70],{"categories":2781},[353],{"categories":2783},[189],{"categories":2785},[120],{"categories":2787},[70],{"categories":2789},[],{"categories":2791},[120],{"categories":2793},[120],{"categories":2795},[],{"categories":2797},[70],{"categories":2799},[120],{"categories":2801},[70],{"categories":2803},[],{"categories":2805},[70],{"categories":2807},[70],{"categories":2809},[152],{"categories":2811},[189],{"categories":2813},[120],{"categories":2815},[189],{"categories":2817},[120],{"categories":2819},[115],{"categories":2821},[],{"categories":2823},[],{"categories":2825},[70],{"categories":2827},[70],{"categories":2829},[112],{"categories":2831},[120],{"categories":2833},[152],{"categories":2835},[],{"categories":2837},[189],{"categories":2839},[],{"categories":2841},[130],{"categories":2843},[130],{"categories":2845},[189],{"categories":2847},[130],{"categories":2849},[70],{"categories":2851},[],{"categories":2853},[70],{"categories":2855},[70],{"categories":2857},[],{"categories":2859},[215],{"categories":2861},[70],{"categories":2863},[246],{"categories":2865},[130],{"categories":2867},[],{"categories":2869},[120],{"categories":2871},[70],{"categories":2873},[112],{"categories":2875},[444],{"categories":2877},[120],{"categories":2879},[120],{"categories":2881},[70],{"categories":2883},[70],{"categories":2885},[],{"categories":2887},[112],{"categories":2889},[70],{"categories":2891},[115],{"categories":2893},[130],{"categories":2895},[189],{"categories":2897},[],{"categories":2899},[],{"categories":2901},[],{"categories":2903},[120],{"categories":2905},[130],{"categories":2907},[189],{"categories":2909},[152],{"categories":2911},[70],{"categories":2913},[152],{"categories":2915},[120],{"categories":2917},[189],{"categories":2919},[70],{"categories":2921},[],{"categories":2923},[70],{"categories":2925},[141],{"categories":2927},[120],{"categories":2929},[189],{"categories":2931},[152],{"categories":2933},[115],{"categories":2935},[130],{"categories":2937},[70],{"categories":2939},[152],{"categories":2941},[215],{"categories":2943},[],{"categories":2945},[],{"categories":2947},[192],{"categories":2949},[395],{"categories":2951},[70],{"categories":2953},[120],{"categories":2955},[70,130],{"categories":2957},[152],{"categories":2959},[70],{"categories":2961},[70],{"categories":2963},[120],{"categories":2965},[70],{"categories":2967},[120],{"categories":2969},[70],{"categories":2971},[70],{"categories":2973},[],{"categories":2975},[1017],{"categories":2977},[130],{"categories":2979},[189],{"categories":2981},[70],{"categories":2983},[70],{"categories":2985},[70],{"categories":2987},[192],{"categories":2989},[120],{"categories":2991},[215],{"categories":2993},[246],{"categories":2995},[],{"categories":2997},[70],{"categories":2999},[115],{"categories":3001},[120],{"categories":3003},[112],{"categories":3005},[120],{"categories":3007},[70],{"categories":3009},[120],{"categories":3011},[123],{"categories":3013},[130],{"categories":3015},[70],{"categories":3017},[70],{"categories":3019},[],{"categories":3021},[],{"categories":3023},[],{"categories":3025},[246],{"categories":3027},[70],{"categories":3029},[152],{"categories":3031},[70],{"categories":3033},[70],{"categories":3035},[70],{"categories":3037},[70],{"categories":3039},[],{"categories":3041},[192],{"categories":3043},[115],{"categories":3045},[120],{"categories":3047},[70],{"categories":3049},[],{"categories":3051},[70],{"categories":3053},[120],{"categories":3055},[70],{"categories":3057},[246],{"categories":3059},[],{"categories":3061},[189],{"categories":3063},[189],{"categories":3065},[],{"categories":3067},[130],{"categories":3069},[70],{"categories":3071},[189],{"categories":3073},[70],{"categories":3075},[115],{"categories":3077},[120],{"categories":3079},[70],{"categories":3081},[],{"categories":3083},[152],{"categories":3085},[70],{"categories":3087},[70],{"categories":3089},[70],{"categories":3091},[189],{"categories":3093},[120],{"categories":3095},[152],{"categories":3097},[],{"categories":3099},[120],{"categories":3101},[120],{"categories":3103},[189],{"categories":3105},[70],{"categories":3107},[70],{"categories":3109},[70],{"categories":3111},[395],{"categories":3113},[70],{"categories":3115},[],{"categories":3117},[70],{"categories":3119},[70],{"categories":3121},[246],{"categories":3123},[152],{"categories":3125},[192],{"categories":3127},[480],{"categories":3129},[192],{"categories":3131},[],{"categories":3133},[],{"categories":3135},[],{"categories":3137},[120],{"categories":3139},[120],{"categories":3141},[130],{"categories":3143},[70],{"categories":3145},[378],{"categories":3147},[130],{"categories":3149},[70],{"categories":3151},[70],{"categories":3153},[70],{"categories":3155},[70],{"categories":3157},[120],{"categories":3159},[],{"categories":3161},[],{"categories":3163},[70],{"categories":3165},[],{"categories":3167},[70],{"categories":3169},[120],{"categories":3171},[189],{"categories":3173},[70],{"categories":3175},[70],{"categories":3177},[],{"categories":3179},[123],{"categories":3181},[70],{"categories":3183},[189],{"categories":3185},[70],{"categories":3187},[120],{"categories":3189},[115],{"categories":3191},[70],{"categories":3193},[215],{"categories":3195},[120],{"categories":3197},[70],{"categories":3199},[738],{"categories":3201},[70],{"categories":3203},[120],{"categories":3205},[70],{"categories":3207},[130],{"categories":3209},[70],{"categories":3211},[444],{"categories":3213},[189],{"categories":3215},[],{"categories":3217},[152],{"categories":3219},[395],{"categories":3221},[120],{"categories":3223},[70],{"categories":3225},[],{"categories":3227},[152],{"categories":3229},[332],{"categories":3231},[120],{"categories":3233},[120],{"categories":3235},[70],{"categories":3237},[70],{"categories":3239},[120],{"categories":3241},[],{"categories":3243},[115],{"categories":3245},[120],{"categories":3247},[],{"categories":3249},[130],{"categories":3251},[70],{"categories":3253},[112],{"categories":3255},[152],{"categories":3257},[246],{"categories":3259},[141],{"categories":3261},[120],{"categories":3263},[120],{"categories":3265},[70],{"categories":3267},[120],{"categories":3269},[112],{"categories":3271},[],{"categories":3273},[70],{"categories":3275},[70],{"categories":3277},[],{"categories":3279},[],{"categories":3281},[189],{"categories":3283},[70,115],{"categories":3285},[120],{"categories":3287},[70],{"categories":3289},[],{"categories":3291},[112],{"categories":3293},[192],{"categories":3295},[115],{"categories":3297},[70],{"categories":3299},[130],{"categories":3301},[70],{"categories":3303},[120],{"categories":3305},[70],{"categories":3307},[70],{"categories":3309},[70],{"categories":3311},[152],{"categories":3313},[1017],{"categories":3315},[120],{"categories":3317},[70],{"categories":3319},[],{"categories":3321},[],{"categories":3323},[120],{"categories":3325},[70],{"categories":3327},[246],{"categories":3329},[],{"categories":3331},[70],{"categories":3333},[120],{"categories":3335},[141],{"categories":3337},[120],{"categories":3339},[395],{"categories":3341},[],{"categories":3343},[353],{"categories":3345},[120],{"categories":3347},[70],{"categories":3349},[215],{"categories":3351},[70],{"categories":3353},[192],{"categories":3355},[120],{"categories":3357},[70],{"categories":3359},[395],{"categories":3361},[70],{"categories":3363},[246],{"categories":3365},[],{"categories":3367},[70],{"categories":3369},[215],{"categories":3371},[189],{"categories":3373},[70],{"categories":3375},[70],{"categories":3377},[],{"categories":3379},[215],{"categories":3381},[152],{"categories":3383},[70],{"categories":3385},[70],{"categories":3387},[480],{"categories":3389},[112],{"categories":3391},[70],{"categories":3393},[],{"categories":3395},[],{"categories":3397},[189],{"categories":3399},[70],{"categories":3401},[192],{"categories":3403},[215],{"categories":3405},[120],{"categories":3407},[215],{"categories":3409},[152],{"categories":3411},[],{"categories":3413},[70],{"categories":3415},[],{"categories":3417},[70],{"categories":3419},[499],{"categories":3421},[70],{"categories":3423},[70],{"categories":3425},[120],{"categories":3427},[395],{"categories":3429},[70],{"categories":3431},[70],{"categories":3433},[70],{"categories":3435},[],{"categories":3437},[70,130],{"categories":3439},[152],{"categories":3441},[120],{"categories":3443},[130],{"categories":3445},[120],{"categories":3447},[768],{"categories":3449},[130],{"categories":3451},[70],{"categories":3453},[112],{"categories":3455},[],{"categories":3457},[],{"categories":3459},[120],{"categories":3461},[70],{"categories":3463},[130],{"categories":3465},[112],{"categories":3467},[130],{"categories":3469},[130],{"categories":3471},[70],{"categories":3473},[215],{"categories":3475},[70],{"categories":3477},[130],{"categories":3479},[],{"categories":3481},[70],{"categories":3483},[189,70],{"categories":3485},[246],{"categories":3487},[112],{"categories":3489},[],{"categories":3491},[70],{"categories":3493},[70],{"categories":3495},[115],{"categories":3497},[115],{"categories":3499},[70],{"categories":3501},[70],{"categories":3503},[332],{"categories":3505},[70],{"categories":3507},[130],{"categories":3509},[192],{"categories":3511},[120],{"categories":3513},[70],{"categories":3515},[70],{"categories":3517},[152],{"categories":3519},[215],{"categories":3521},[189],{"categories":3523},[70],{"categories":3525},[70],{"categories":3527},[70],{"categories":3529},[70],{"categories":3531},[112],{"categories":3533},[70],{"categories":3535},[120],{"categories":3537},[120],{"categories":3539},[130],{"categories":3541},[152],{"categories":3543},[130],{"categories":3545},[],{"categories":3547},[],{"categories":3549},[192],{"categories":3551},[70],{"categories":3553},[130],{"categories":3555},[70],{"categories":3557},[189],{"categories":3559},[395],{"categories":3561},[353],{"categories":3563},[332],{"categories":3565},[70],{"categories":3567},[70],{"categories":3569},[70],{"categories":3571},[192],{"categories":3573},[70],{"categories":3575},[70],{"categories":3577},[70],{"categories":3579},[120],{"categories":3581},[112],{"categories":3583},[120],{"categories":3585},[70,115],{"categories":3587},[],{"categories":3589},[189],{"categories":3591},[],{"categories":3593},[123],{"categories":3595},[70],{"categories":3597},[152],{"categories":3599},[112],{"categories":3601},[112],{"categories":3603},[120],{"categories":3605},[120],{"categories":3607},[120],{"categories":3609},[70],{"categories":3611},[70],{"categories":3613},[115],{"categories":3615},[130],{"categories":3617},[215],{"categories":3619},[70],{"categories":3621},[],{"categories":3623},[152],{"categories":3625},[70],{"categories":3627},[70],{"categories":3629},[70],{"categories":3631},[70],{"categories":3633},[70],{"categories":3635},[130],{"categories":3637},[152],{"categories":3639},[130],{"categories":3641},[130],{"categories":3643},[70],{"categories":3645},[70],{"categories":3647},[353],{"categories":3649},[70],{"categories":3651},[120],{"categories":3653},[152],{"categories":3655},[70],{"categories":3657},[70],{"categories":3659},[70],{"categories":3661},[120],{"categories":3663},[70],{"categories":3665},[70],{"categories":3667},[70],{"categories":3669},[2542],{"categories":3671},[3672],"Clinical AI",{"categories":3674},[189],{"categories":3676},[70],{"categories":3678},[70],{"categories":3680},[70],{"categories":3682},[246],{"categories":3684},[2021],{"categories":3686},[70],{"categories":3688},[123],{"categories":3690},[70],{"categories":3692},[120],{"categories":3694},[70],{"categories":3696},[70],{"categories":3698},[152],{"categories":3700},[70],{"categories":3702},[120],{"categories":3704},[215],{"categories":3706},[70],{"categories":3708},[70],{"categories":3710},[115],{"categories":3712},[70],{"categories":3714},[444],{"categories":3716},[70],{"categories":3718},[],{"categories":3720},[70],{"categories":3722},[130],{"categories":3724},[70],{"categories":3726},[],{"categories":3728},[],{"categories":3730},[70],{"categories":3732},[],{"categories":3734},[115],{"categories":3736},[70],{"categories":3738},[120],{"categories":3740},[152],{"categories":3742},[152],{"categories":3744},[152],{"categories":3746},[152],{"categories":3748},[],{"categories":3750},[112],{"categories":3752},[120],{"categories":3754},[152],{"categories":3756},[70],{"categories":3758},[499],{"categories":3760},[123],{"categories":3762},[70],{"categories":3764},[112],{"categories":3766},[120],{"categories":3768},[70],{"categories":3770},[70],{"categories":3772},[70,120],{"categories":3774},[120],{"categories":3776},[246],{"categories":3778},[152],{"categories":3780},[120],{"categories":3782},[152],{"categories":3784},[120],{"categories":3786},[70],{"categories":3788},[],{"categories":3790},[152],{"categories":3792},[215],{"categories":3794},[112],{"categories":3796},[70],{"categories":3798},[70],{"categories":3800},[],{"categories":3802},[130],{"categories":3804},[],{"categories":3806},[112],{"categories":3808},[120],{"categories":3810},[152],{"categories":3812},[70],{"categories":3814},[152],{"categories":3816},[112],{"categories":3818},[152],{"categories":3820},[152],{"categories":3822},[],{"categories":3824},[115],{"categories":3826},[120],{"categories":3828},[152],{"categories":3830},[152],{"categories":3832},[152],{"categories":3834},[152],{"categories":3836},[152],{"categories":3838},[152],{"categories":3840},[152],{"categories":3842},[152],{"categories":3844},[152],{"categories":3846},[152],{"categories":3848},[192],{"categories":3850},[112],{"categories":3852},[70],{"categories":3854},[70],{"categories":3856},[120],{"categories":3858},[120],{"categories":3860},[],{"categories":3862},[70,112],{"categories":3864},[],{"categories":3866},[120],{"categories":3868},[152],{"categories":3870},[120],{"categories":3872},[768],{"categories":3874},[70],{"categories":3876},[70],{"categories":3878},[70],{"categories":3880},[70],{"categories":3882},[332],{"categories":3884},[70],{"categories":3886},[120],{"categories":3888},[115],{"categories":3890},[120],{"categories":3892},[120],{"categories":3894},[],{"categories":3896},[120],{"categories":3898},[189],{"categories":3900},[152],{"categories":3902},[70],{"categories":3904},[],{"categories":3906},[],{"categories":3908},[120],{"categories":3910},[189],{"categories":3912},[70],{"categories":3914},[],{"categories":3916},[70],{"categories":3918},[],{"categories":3920},[215],{"categories":3922},[70],{"categories":3924},[],{"categories":3926},[],{"categories":3928},[152],{"categories":3930},[112],{"categories":3932},[70],{"categories":3934},[70],{"categories":3936},[115],{"categories":3938},[70],{"categories":3940},[70],{"categories":3942},[70],{"categories":3944},[115],{"categories":3946},[189],{"categories":3948},[],{"categories":3950},[70],{"categories":3952},[152],{"categories":3954},[],{"categories":3956},[70],{"categories":3958},[70],{"categories":3960},[189],{"categories":3962},[70],{"categories":3964},[215],{"categories":3966},[70],{"categories":3968},[246],{"categories":3970},[],{"categories":3972},[120],{"categories":3974},[215],{"categories":3976},[130],{"categories":3978},[],{"categories":3980},[70],{"categories":3982},[],{"categories":3984},[120],{"categories":3986},[189],{"categories":3988},[130],{"categories":3990},[],{"categories":3992},[2542],{"categories":3994},[115],{"categories":3996},[112],{"categories":3998},[192],{"categories":4000},[120],{"categories":4002},[189],{"categories":4004},[130],{"categories":4006},[],{"categories":4008},[],{"categories":4010},[70],{"categories":4012},[112],{"categories":4014},[70],{"categories":4016},[215],{"categories":4018},[],{"categories":4020},[120],{"categories":4022},[120],{"categories":4024},[120],{"categories":4026},[70],{"categories":4028},[152],{"categories":4030},[130],{"categories":4032},[70],{"categories":4034},[120],{"categories":4036},[123],{"categories":4038},[70],{"categories":4040},[120],{"categories":4042},[70],{"categories":4044},[123],{"categories":4046},[215],{"categories":4048},[152],{"categories":4050},[],{"categories":4052},[215],{"categories":4054},[],{"categories":4056},[130],{"categories":4058},[120],{"categories":4060},[],{"categories":4062},[70],{"categories":4064},[70],{"categories":4066},[70],{"categories":4068},[70],{"categories":4070},[120],{"categories":4072},[115],{"categories":4074},[112],{"categories":4076},[70],{"categories":4078},[189],{"categories":4080},[130],{"categories":4082},[130],{"categories":4084},[70],{"categories":4086},[192],{"categories":4088},[120],{"categories":4090},[70],{"categories":4092},[120],{"categories":4094},[70],{"categories":4096},[115],{"categories":4098},[189],{"categories":4100},[130],{"categories":4102},[120],{"categories":4104},[70],{"categories":4106},[123],{"categories":4108},[70],{"categories":4110},[120],{"categories":4112},[70],{"categories":4114},[152],{"categories":4116},[],{"categories":4118},[112],{"categories":4120},[70],{"categories":4122},[70],{"categories":4124},[70],{"categories":4126},[130],{"categories":4128},[70],{"categories":4130},[130],{"categories":4132},[70],{"categories":4134},[120],{"categories":4136},[70],{"categories":4138},[70],{"categories":4140},[70],{"categories":4142},[70],{"categories":4144},[],{"categories":4146},[70],{"categories":4148},[189],{"categories":4150},[115],{"categories":4152},[152],{"categories":4154},[120],{"categories":4156},[70],{"categories":4158},[70],{"categories":4160},[189],{"categories":4162},[120],{"categories":4164},[70],{"categories":4166},[215],{"categories":4168},[70],{"categories":4170},[192],{"categories":4172},[70],{"categories":4174},[70],{"categories":4176},[152],{"categories":4178},[70],{"categories":4180},[70],{"categories":4182},[120],{"categories":4184},[246],{"categories":4186},[70],{"categories":4188},[130],{"categories":4190},[120],{"categories":4192},[192],{"categories":4194},[],{"categories":4196},[120],{"categories":4198},[130],{"categories":4200},[70],{"categories":4202},[1885],{"categories":4204},[189],{"categories":4206},[273],{"categories":4208},[70],{"categories":4210},[112],{"categories":4212},[130],{"categories":4214},[115],{"categories":4216},[130],{"categories":4218},[70],{"categories":4220},[],{"categories":4222},[120],{"categories":4224},[120],{"categories":4226},[70],{"categories":4228},[70],{"categories":4230},[192],{"categories":4232},[],{"categories":4234},[152],{"categories":4236},[],{"categories":4238},[152],{"categories":4240},[70],{"categories":4242},[70],{"categories":4244},[120],{"categories":4246},[120],{"categories":4248},[120],{"categories":4250},[],{"categories":4252},[152],{"categories":4254},[70],{"categories":4256},[],{"categories":4258},[70],{"categories":4260},[70],{"categories":4262},[],{"categories":4264},[189],{"categories":4266},[130],{"categories":4268},[120],{"categories":4270},[70],{"categories":4272},[70],{"categories":4274},[215],{"categories":4276},[70],{"categories":4278},[70],{"categories":4280},[112],{"categories":4282},[],{"categories":4284},[70],{"categories":4286},[70],{"categories":4288},[],{"categories":4290},[112],{"categories":4292},[152],{"categories":4294},[130],{"categories":4296},[395],{"categories":4298},[70],{"categories":4300},[70],{"categories":4302},[70],{"categories":4304},[130],{"categories":4306},[152],{"categories":4308},[189],{"categories":4310},[70],{"categories":4312},[70],{"categories":4314},[70],{"categories":4316},[152],{"categories":4318},[189],{"categories":4320},[70],{"categories":4322},[152],{"categories":4324},[189],{"categories":4326},[70],{"categories":4328},[152],{"categories":4330},[120],{"categories":4332},[120],{"categories":4334},[120],{"categories":4336},[130],{"categories":4338},[152],{"categories":4340},[120],{"categories":4342},[120],{"categories":4344},[70],{"categories":4346},[130],{"categories":4348},[189],{"categories":4350},[70],{"categories":4352},[],{"categories":4354},[120],{"categories":4356},[],{"categories":4358},[],{"categories":4360},[],{"categories":4362},[120],{"categories":4364},[115],{"categories":4366},[120],{"categories":4368},[4369],"Liability & Ethics",{"categories":4371},[70],{"categories":4373},[120],{"categories":4375},[112],{"categories":4377},[120],{"categories":4379},[115],{"categories":4381},[215],{"categories":4383},[120],{"categories":4385},[],{"categories":4387},[480],{"categories":4389},[120],{"categories":4391},[],{"categories":4393},[112],{"categories":4395},[120],{"categories":4397},[],{"categories":4399},[120],{"categories":4401},[70],{"categories":4403},[70],{"categories":4405},[152],{"categories":4407},[70],{"categories":4409},[70],{"categories":4411},[120],{"categories":4413},[70],{"categories":4415},[70],{"categories":4417},[152],{"categories":4419},[120],{"categories":4421},[130],{"categories":4423},[189],{"categories":4425},[112],{"categories":4427},[70],{"categories":4429},[],{"categories":4431},[120],{"categories":4433},[120],{"categories":4435},[395],{"categories":4437},[189],{"categories":4439},[246],{"categories":4441},[152],{"categories":4443},[70],{"categories":4445},[189],{"categories":4447},[70],{"categories":4449},[112],{"categories":4451},[],{"categories":4453},[120],{"categories":4455},[70],{"categories":4457},[70],{"categories":4459},[120],{"categories":4461},[70],{"categories":4463},[189],{"categories":4465},[],{"categories":4467},[120],{"categories":4469},[123],{"categories":4471},[152],{"categories":4473},[120],{"categories":4475},[115],{"categories":4477},[],{"categories":4479},[70],{"categories":4481},[123],{"categories":4483},[70],{"categories":4485},[120],{"categories":4487},[152],{"categories":4489},[112],{"categories":4491},[246],{"categories":4493},[70],{"categories":4495},[70],{"categories":4497},[70],{"categories":4499},[152],{"categories":4501},[115],{"categories":4503},[70],{"categories":4505},[189],{"categories":4507},[152],{"categories":4509},[246],{"categories":4511},[70],{"categories":4513},[120],{"categories":4515},[],{"categories":4517},[444],{"categories":4519},[],{"categories":4521},[70],{"categories":4523},[246],{"categories":4525},[192],{"categories":4527},[120],{"categories":4529},[120],{"categories":4531},[4532],"Design News & Tools",{"categories":4534},[70],{"categories":4536},[152],{"categories":4538},[70],{"categories":4540},[112],{"categories":4542},[70],{"categories":4544},[189],{"categories":4546},[120],{"categories":4548},[120],{"categories":4550},[70],{"categories":4552},[395],{"categories":4554},[70],{"categories":4556},[395],{"categories":4558},[215],{"categories":4560},[70],{"categories":4562},[120],{"categories":4564},[],{"categories":4566},[70],{"categories":4568},[70],{"categories":4570},[70],{"categories":4572},[152],{"categories":4574},[112],{"categories":4576},[],{"categories":4578},[70],{"categories":4580},[70],{"categories":4582},[130],{"categories":4584},[499],{"categories":4586},[130],{"categories":4588},[189],{"categories":4590},[70],{"categories":4592},[70,120],{"categories":4594},[215,115],{"categories":4596},[70],{"categories":4598},[70],{"categories":4600},[70],{"categories":4602},[],{"categories":4604},[120],{"categories":4606},[],{"categories":4608},[130],{"categories":4610},[70],{"categories":4612},[130],{"categories":4614},[],{"categories":4616},[120],{"categories":4618},[70],{"categories":4620},[152],{"categories":4622},[70],{"categories":4624},[],{"categories":4626},[120],{"categories":4628},[70],{"categories":4630},[],{"categories":4632},[189],{"categories":4634},[70],{"categories":4636},[120],{"categories":4638},[70],{"categories":4640},[70],{"categories":4642},[112],{"categories":4644},[120],{"categories":4646},[70],{"categories":4648},[],{"categories":4650},[246],{"categories":4652},[215],{"categories":4654},[115],{"categories":4656},[115],{"categories":4658},[70],{"categories":4660},[112],{"categories":4662},[112],{"categories":4664},[70],{"categories":4666},[120],{"categories":4668},[70],{"categories":4670},[70],{"categories":4672},[70],{"categories":4674},[130],{"categories":4676},[70],{"categories":4678},[112],{"categories":4680},[120],{"categories":4682},[70],{"categories":4684},[215],{"categories":4686},[70],{"categories":4688},[152],{"categories":4690},[70],{"categories":4692},[70],{"categories":4694},[120],{"categories":4696},[70],{"categories":4698},[],{"categories":4700},[130],{"categories":4702},[],{"categories":4704},[130],{"categories":4706},[120],{"categories":4708},[112],{"categories":4710},[],{"categories":4712},[192],{"categories":4714},[246],{"categories":4716},[70],{"categories":4718},[130],{"categories":4720},[70],{"categories":4722},[],{"categories":4724},[152],{"categories":4726},[120],{"categories":4728},[130],{"categories":4730},[189],{"categories":4732},[70],{"categories":4734},[120],{"categories":4736},[130],{"categories":4738},[120],{"categories":4740},[152],{"categories":4742},[70],{"categories":4744},[112],{"categories":4746},[152],{"categories":4748},[130],{"categories":4750},[70],{"categories":4752},[189],{"categories":4754},[115],{"categories":4756},[70],{"categories":4758},[70],{"categories":4760},[70],{"categories":4762},[70],{"categories":4764},[70],{"categories":4766},[120],{"categories":4768},[70],{"categories":4770},[120],{"categories":4772},[70],{"categories":4774},[70],{"categories":4776},[112],{"categories":4778},[70],{"categories":4780},[120],{"categories":4782},[120],{"categories":4784},[189],{"categories":4786},[120],{"categories":4788},[120],{"categories":4790},[112],{"categories":4792},[120],{"categories":4794},[189],{"categories":4796},[],{"categories":4798},[70],{"categories":4800},[192],{"categories":4802},[395],{"categories":4804},[70],{"categories":4806},[70],{"categories":4808},[70],{"categories":4810},[130],{"categories":4812},[],{"categories":4814},[120],{"categories":4816},[215],{"categories":4818},[70],{"categories":4820},[152],{"categories":4822},[120],{"categories":4824},[70],{"categories":4826},[215],{"categories":4828},[120],{"categories":4830},[115],{"categories":4832},[115],{"categories":4834},[70],{"categories":4836},[70],{"categories":4838},[70],{"categories":4840},[112],{"categories":4842},[],{"categories":4844},[70],{"categories":4846},[120],{"categories":4848},[120],{"categories":4850},[70],{"categories":4852},[70],{"categories":4854},[70],{"categories":4856},[130],{"categories":4858},[],{"categories":4860},[112],{"categories":4862},[70],{"categories":4864},[70],{"categories":4866},[120],{"categories":4868},[120],{"categories":4870},[],{"categories":4872},[130],{"categories":4874},[130],{"categories":4876},[70],{"categories":4878},[215],{"categories":4880},[115],{"categories":4882},[189],{"categories":4884},[],{"categories":4886},[70],{"categories":4888},[120],{"categories":4890},[112],{"categories":4892},[70],{"categories":4894},[130],{"categories":4896},[112],{"categories":4898},[152],{"categories":4900},[192],{"categories":4902},[152],{"categories":4904},[120],{"categories":4906},[],{"categories":4908},[152],{"categories":4910},[120],{"categories":4912},[189],{"categories":4914},[192],{"categories":4916},[70],{"categories":4918},[],{"categories":4920},[120],{"categories":4922},[2542],{"categories":4924},[152],{"categories":4926},[130],{"categories":4928},[70],{"categories":4930},[70],{"categories":4932},[115],{"categories":4934},[70],{"categories":4936},[112],{"categories":4938},[1463],{"categories":4940},[246],{"categories":4942},[112],{"categories":4944},[],{"categories":4946},[],{"categories":4948},[152],{"categories":4950},[120],{"categories":4952},[152],{"categories":4954},[],{"categories":4956},[120],{"categories":4958},[120],{"categories":4960},[120],{"categories":4962},[],{"categories":4964},[70],{"categories":4966},[],{"categories":4968},[152],{"categories":4970},[112],{"categories":4972},[189],{"categories":4974},[70],{"categories":4976},[120],{"categories":4978},[152],{"categories":4980},[70],{"categories":4982},[152],{"categories":4984},[],{"categories":4986},[152],{"categories":4988},[112],{"categories":4990},[395],{"categories":4992},[120],{"categories":4994},[70],{"categories":4996},[],{"categories":4998},[130],{"categories":5000},[120],{"categories":5002},[123],{"categories":5004},[120],{"categories":5006},[112],{"categories":5008},[],{"categories":5010},[],{"categories":5012},[],{"categories":5014},[189],{"categories":5016},[120],{"categories":5018},[70],{"categories":5020},[70],{"categories":5022},[],{"categories":5024},[],{"categories":5026},[],{"categories":5028},[189],{"categories":5030},[70],{"categories":5032},[],{"categories":5034},[120],{"categories":5036},[70],{"categories":5038},[112],{"categories":5040},[],{"categories":5042},[],{"categories":5044},[189],{"categories":5046},[70],{"categories":5048},[152],{"categories":5050},[],{"categories":5052},[215],{"categories":5054},[152],{"categories":5056},[215],{"categories":5058},[192],{"categories":5060},[70],{"categories":5062},[70],{"categories":5064},[],{"categories":5066},[],{"categories":5068},[120],{"categories":5070},[],{"categories":5072},[70],{"categories":5074},[395],{"categories":5076},[70],{"categories":5078},[70],{"categories":5080},[70],{"categories":5082},[],{"categories":5084},[120],{"categories":5086},[70],{"categories":5088},[70],{"categories":5090},[],{"categories":5092},[120],{"categories":5094},[70],{"categories":5096},[152],{"categories":5098},[70],{"categories":5100},[215],{"categories":5102},[115],{"categories":5104},[70],{"categories":5106},[70],{"categories":5108},[120],{"categories":5110},[192],{"categories":5112},[120],{"categories":5114},[120],{"categories":5116},[],{"categories":5118},[],{"categories":5120},[70],{"categories":5122},[],{"categories":5124},[152],{"categories":5126},[115],{"categories":5128},[],{"categories":5130},[],{"categories":5132},[189],{"categories":5134},[112],{"categories":5136},[],{"categories":5138},[115],{"categories":5140},[215],{"categories":5142},[70],{"categories":5144},[130],{"categories":5146},[112],{"categories":5148},[192],{"categories":5150},[115],{"categories":5152},[130],{"categories":5154},[130],{"categories":5156},[],{"categories":5158},[70],{"categories":5160},[],{"categories":5162},[120],{"categories":5164},[112],{"categories":5166},[189],{"categories":5168},[70],{"categories":5170},[112],{"categories":5172},[120],{"categories":5174},[246],{"categories":5176},[70],{"categories":5178},[70],{"categories":5180},[70],{"categories":5182},[112],{"categories":5184},[192],{"categories":5186},[120],{"categories":5188},[],{"categories":5190},[70],{"categories":5192},[130],{"categories":5194},[152],{"categories":5196},[130],{"categories":5198},[70],{"categories":5200},[123],{"categories":5202},[],{"categories":5204},[189],{"categories":5206},[152],{"categories":5208},[112],{"categories":5210},[120],{"categories":5212},[70],{"categories":5214},[70],{"categories":5216},[120],{"categories":5218},[70],{"categories":5220},[70],{"categories":5222},[115],{"categories":5224},[120],{"categories":5226},[120,246],{"categories":5228},[120],{"categories":5230},[130],{"categories":5232},[70],{"categories":5234},[70],{"categories":5236},[192],{"categories":5238},[120],{"categories":5240},[215],{"categories":5242},[120],{"categories":5244},[115],{"categories":5246},[],{"categories":5248},[120],{"categories":5250},[70],{"categories":5252},[115],{"categories":5254},[],{"categories":5256},[],{"categories":5258},[130],{"categories":5260},[70],{"categories":5262},[70],{"categories":5264},[120],{"categories":5266},[192],{"categories":5268},[215],{"categories":5270},[70],{"categories":5272},[70],{"categories":5274},[120],{"categories":5276},[],{"categories":5278},[120],{"categories":5280},[152],{"categories":5282},[120],{"categories":5284},[],{"categories":5286},[152],{"categories":5288},[130],{"categories":5290},[2542],{"categories":5292},[112],{"categories":5294},[130],{"categories":5296},[70],{"categories":5298},[120],{"categories":5300},[70],{"categories":5302},[70],{"categories":5304},[215],{"categories":5306},[130],{"categories":5308},[],{"categories":5310},[152],{"categories":5312},[70],{"categories":5314},[],{"categories":5316},[120],{"categories":5318},[70],{"categories":5320},[70],{"categories":5322},[70],{"categories":5324},[120],{"categories":5326},[70],{"categories":5328},[70],{"categories":5330},[123],{"categories":5332},[120],{"categories":5334},[70],{"categories":5336},[70],{"categories":5338},[70],{"categories":5340},[70],{"categories":5342},[70],{"categories":5344},[70],{"categories":5346},[115],{"categories":5348},[],{"categories":5350},[123],{"categories":5352},[152],{"categories":5354},[120],{"categories":5356},[70],{"categories":5358},[130],{"categories":5360},[],{"categories":5362},[130],{"categories":5364},[130],{"categories":5366},[120],{"categories":5368},[130],{"categories":5370},[70],{"categories":5372},[70],{"categories":5374},[130],{"categories":5376},[70],{"categories":5378},[120],{"categories":5380},[152],{"categories":5382},[70],{"categories":5384},[70],{"categories":5386},[70],{"categories":5388},[115],{"categories":5390},[70],{"categories":5392},[120],{"categories":5394},[189],{"categories":5396},[],{"categories":5398},[70],{"categories":5400},[192],{"categories":5402},[120],{"categories":5404},[70],{"categories":5406},[],{"categories":5408},[70],{"categories":5410},[70],{"categories":5412},[152],{"categories":5414},[70],{"categories":5416},[70],{"categories":5418},[120],{"categories":5420},[215],{"categories":5422},[],{"categories":5424},[],{"categories":5426},[130],{"categories":5428},[152],{"categories":5430},[130],{"categories":5432},[152],{"categories":5434},[70],{"categories":5436},[215],{"categories":5438},[70],{"categories":5440},[112],{"categories":5442},[120],{"categories":5444},[70],{"categories":5446},[120],{"categories":5448},[120],{"categories":5450},[70],{"categories":5452},[115],{"categories":5454},[],{"categories":5456},[192],{"categories":5458},[70],{"categories":5460},[],{"categories":5462},[152],{"categories":5464},[70],{"categories":5466},[192],{"categories":5468},[70],{"categories":5470},[130],{"categories":5472},[130],{"categories":5474},[130],{"categories":5476},[120],{"categories":5478},[120],{"categories":5480},[120],{"categories":5482},[70],{"categories":5484},[70],{"categories":5486},[189],{"categories":5488},[192],{"categories":5490},[192],{"categories":5492},[],{"categories":5494},[152],{"categories":5496},[70],{"categories":5498},[70],{"categories":5500},[130],{"categories":5502},[],{"categories":5504},[152],{"categories":5506},[152],{"categories":5508},[152],{"categories":5510},[],{"categories":5512},[120],{"categories":5514},[70],{"categories":5516},[],{"categories":5518},[112],{"categories":5520},[115],{"categories":5522},[],{"categories":5524},[70],{"categories":5526},[70],{"categories":5528},[],{"categories":5530},[130],{"categories":5532},[],{"categories":5534},[],{"categories":5536},[],{"categories":5538},[],{"categories":5540},[70],{"categories":5542},[152],{"categories":5544},[],{"categories":5546},[],{"categories":5548},[70],{"categories":5550},[70],{"categories":5552},[70],{"categories":5554},[192],{"categories":5556},[70],{"categories":5558},[192],{"categories":5560},[],{"categories":5562},[192],{"categories":5564},[192],{"categories":5566},[246],{"categories":5568},[120],{"categories":5570},[130],{"categories":5572},[],{"categories":5574},[],{"categories":5576},[192],{"categories":5578},[130],{"categories":5580},[130],{"categories":5582},[130],{"categories":5584},[],{"categories":5586},[112],{"categories":5588},[130],{"categories":5590},[130],{"categories":5592},[112],{"categories":5594},[130],{"categories":5596},[115],{"categories":5598},[130],{"categories":5600},[130],{"categories":5602},[130],{"categories":5604},[192],{"categories":5606},[152],{"categories":5608},[152],{"categories":5610},[70],{"categories":5612},[130],{"categories":5614},[192],{"categories":5616},[246],{"categories":5618},[192],{"categories":5620},[192],{"categories":5622},[192],{"categories":5624},[],{"categories":5626},[115],{"categories":5628},[],{"categories":5630},[246],{"categories":5632},[130],{"categories":5634},[130],{"categories":5636},[130],{"categories":5638},[120],{"categories":5640},[152,115],{"categories":5642},[192],{"categories":5644},[],{"categories":5646},[],{"categories":5648},[192],{"categories":5650},[],{"categories":5652},[192],{"categories":5654},[152],{"categories":5656},[120],{"categories":5658},[],{"categories":5660},[130],{"categories":5662},[70],{"categories":5664},[189],{"categories":5666},[],{"categories":5668},[70],{"categories":5670},[],{"categories":5672},[152],{"categories":5674},[112],{"categories":5676},[192],{"categories":5678},[],{"categories":5680},[130],{"categories":5682},[152],[5684,5782,5865,5986],{"id":5685,"title":5686,"ai":5687,"body":5693,"categories":5749,"created_at":71,"date_modified":71,"description":63,"extension":72,"faq":71,"featured":73,"kicker_label":71,"meta":5750,"navigation":90,"path":5770,"published_at":5771,"question":71,"scraped_at":5772,"seo":5773,"sitemap":5774,"source_id":5775,"source_name":97,"source_type":98,"source_url":5776,"stem":5777,"tags":5778,"thumbnail_url":71,"tldr":5779,"tweet":71,"unknown_tags":5780,"__hash__":5781},"summaries\u002Fsummaries\u002F79f82c07ea7441fe-trl-code-guide-sft-to-grpo-llm-alignment-on-t4-gpu-summary.md","TRL Code Guide: SFT to GRPO LLM Alignment on T4 GPU",{"provider":7,"model":5688,"input_tokens":5689,"output_tokens":5690,"processing_time_ms":5691,"cost_usd":5692},"x-ai\u002Fgrok-4.1-fast",9458,2615,35753,0.00269195,{"type":14,"value":5694,"toc":5743},[5695,5699,5707,5711,5721,5725,5731,5735],[17,5696,5698],{"id":5697},"lora-and-trl-setup-enables-post-training-on-limited-hardware","LoRA and TRL Setup Enables Post-Training on Limited Hardware",[22,5700,5701,5702,5706],{},"Use LoRA (r=8, alpha=16, dropout=0.05, targets=",[5703,5704,5705],"span",{},"'q_proj','k_proj','v_proj','o_proj'",") with TRL trainers to adapt Qwen\u002FQwen2.5-0.5B-Instruct on T4 GPU (16GB). Common args across stages: num_train_epochs=1, gradient_checkpointing=True, bf16 if supported else fp16, logging_steps=10, report_to=\"none\", save_strategy=\"no\". Install stack: torchao>=0.16, trl>=0.20, transformers>=4.45, peft>=0.13, bitsandbytes. Helpers like chat_generate apply chat template, generate with temp=0.7\u002Ftop_p=0.9. Cleanup VRAM with gc.collect() + torch.cuda.empty_cache() between stages to fit in Colab.",[17,5708,5710],{"id":5709},"sft-and-rm-build-imitation-and-reward-signals","SFT and RM Build Imitation and Reward Signals",[22,5712,5713,5714,5717,5718,5720],{},"For Supervised Fine-Tuning, load trl-lib\u002FCapybara (train",[5703,5715,5716],{},":300","), use SFTConfig(per_device_train_batch_size=2, gradient_accumulation_steps=4, learning_rate=2e-4, max_length=768). Trainer imitates high-quality chat responses; post-train inference on \"Explain bias-variance tradeoff in two sentences\" yields coherent output. Reward Modeling on trl-lib\u002Fultrafeedback_binarized (train",[5703,5719,5716],{},") uses RewardConfig(batch_size=2, accum_steps=2, lr=1e-4, max_length=512), LoRA task_type=\"SEQ_CLS\". Trains to score chosen vs. rejected pairs, producing a preference-based reward without explicit RL.",[17,5722,5724],{"id":5723},"dpo-skips-rm-for-direct-preference-alignment","DPO Skips RM for Direct Preference Alignment",[22,5726,5727,5728,5730],{},"DPOTrainer on same ultrafeedback_binarized",[5703,5729,5716],{}," simplifies via implicit rewards: DPOConfig(batch_size=1, accum_steps=4, lr=5e-6, beta=0.1, max_length=512, max_prompt_length=256). Beta controls KL-divergence from reference policy, preventing mode collapse. Optimizes policy to prefer chosen over rejected responses directly, reducing steps vs. traditional RM+PPO.",[17,5732,5734],{"id":5733},"grpo-uses-custom-rewards-to-sharpen-reasoning","GRPO Uses Custom Rewards to Sharpen Reasoning",[22,5736,5737,5738,5742],{},"GRPOTrainer generates num_generations=4 completions per prompt (max_prompt_length=128, max_completion_length=96, max_steps=15), ranks via reward_funcs. Custom dataset: 200 synthetic math problems (e.g., \"Solve 17 + 28 =\", gold=eval). Rewards: correctness_reward (1.0 if last extracted number matches gold else 0), brevity_reward (max(0,1-len(c)\u002F200)",[5739,5740,5741],"em",{},"0.2). GRPOConfig(lr=1e-5, batch=2, accum=2). Inference on \"17+28?\", \"9","7?\", \"100-47?\" produces accurate, concise answers like final numbers, improving verifiable task performance over base.",{"title":63,"searchDepth":64,"depth":64,"links":5744},[5745,5746,5747,5748],{"id":5697,"depth":64,"text":5698},{"id":5709,"depth":64,"text":5710},{"id":5723,"depth":64,"text":5724},{"id":5733,"depth":64,"text":5734},[70],{"content_references":5751,"triage":5767},[5752,5755,5758,5760,5762],{"type":77,"title":5753,"url":5754,"context":80},"TRL","https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftrl",{"type":5756,"title":5757,"context":80},"dataset","trl-lib\u002FCapybara",{"type":5756,"title":5759,"context":80},"trl-lib\u002Fultrafeedback_binarized",{"type":77,"title":5761,"context":80},"Qwen\u002FQwen2.5-0.5B-Instruct",{"type":5763,"title":5764,"url":5765,"context":5766},"other","trl_llm_post_training_sft_dpo_grpo_marktechpost.py","https:\u002F\u002Fgithub.com\u002FMarktechpost\u002FAI-Agents-Projects-Tutorials\u002Fblob\u002Fmain\u002FLLM%20Projects\u002Ftrl_llm_post_training_sft_dpo_grpo_marktechpost.py","recommended",{"relevance":85,"novelty":86,"quality":86,"actionability":85,"composite":5768,"reasoning":5769},4.55,"Category: AI & LLMs. The article provides a detailed guide on using TRL and LoRA for LLM post-training, addressing practical applications for developers looking to implement AI features. It includes specific configurations and techniques that can be directly applied in production, making it highly actionable.","\u002Fsummaries\u002F79f82c07ea7441fe-trl-code-guide-sft-to-grpo-llm-alignment-on-t4-gpu-summary","2026-05-01 20:52:08","2026-05-03 17:01:49",{"title":5686,"description":63},{"loc":5770},"79f82c07ea7441fe","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F05\u002F01\u002Fa-coding-guide-on-llm-post-training-with-trl-from-supervised-fine-tuning-to-dpo-and-grpo-reasoning\u002F","summaries\u002F79f82c07ea7441fe-trl-code-guide-sft-to-grpo-llm-alignment-on-t4-gpu-summary",[102,104,103],"Train Qwen2.5-0.5B via SFT, RM, DPO, GRPO using TRL+LoRA on Colab T4: configs include r=8 LoRA, 300-sample datasets, epochs=1, small batches\u002Faccum for memory efficiency, custom math rewards boost reasoning.",[],"py8Fe1-Noi99CHywKy61Q363dqRBmUxl6tZ9TDJOp3E",{"id":5783,"title":5784,"ai":5785,"body":5790,"categories":5844,"created_at":71,"date_modified":71,"description":63,"extension":72,"faq":71,"featured":73,"kicker_label":71,"meta":5845,"navigation":90,"path":5853,"published_at":5854,"question":71,"scraped_at":5854,"seo":5855,"sitemap":5856,"source_id":5857,"source_name":97,"source_type":98,"source_url":5858,"stem":5859,"tags":5860,"thumbnail_url":71,"tldr":5862,"tweet":71,"unknown_tags":5863,"__hash__":5864},"summaries\u002Fsummaries\u002F89df0446e415c993-diffusiongemma-parallel-text-generation-via-diffus-summary.md","DiffusionGemma: Parallel Text Generation via Diffusion",{"provider":7,"model":8,"input_tokens":5786,"output_tokens":5787,"processing_time_ms":5788,"cost_usd":5789},9607,615,4079,0.001500625,{"type":14,"value":5791,"toc":5839},[5792,5796,5799,5803,5806,5832,5836],[17,5793,5795],{"id":5794},"parallel-decoding-via-text-diffusion","Parallel Decoding via Text Diffusion",[22,5797,5798],{},"DiffusionGemma departs from the standard autoregressive paradigm—where tokens are generated sequentially, one at a time—by utilizing text diffusion. Inspired by image generation models, it begins with a canvas of random placeholder tokens and iteratively refines them in parallel. This approach allows the model to finalize approximately 15–20 tokens per forward pass, significantly increasing throughput on dedicated GPUs.",[17,5800,5802],{"id":5801},"architecture-and-performance","Architecture and Performance",[22,5804,5805],{},"Built on the Gemma 4 26B-A4B backbone, the model is a Mixture of Experts (MoE) architecture that activates only 3.8B parameters during inference. Key technical features include:",[33,5807,5808,5814,5820,5826],{},[36,5809,5810,5813],{},[39,5811,5812],{},"Bidirectional Attention:"," Unlike autoregressive models restricted to causal (backward-looking) attention, DiffusionGemma uses bidirectional attention during denoising, allowing tokens to attend to the entire sequence.",[36,5815,5816,5819],{},[39,5817,5818],{},"Self-Correction:"," The model can re-noise and refine low-confidence tokens during the denoising process, a capability impossible in standard autoregressive decoding where tokens are committed once generated.",[36,5821,5822,5825],{},[39,5823,5824],{},"Hardware Utilization:"," By shifting the bottleneck from memory bandwidth to compute, the model achieves 1000+ tokens per second on an NVIDIA H100 and 700+ tokens per second on an NVIDIA GeForce RTX 5090.",[36,5827,5828,5831],{},[39,5829,5830],{},"Hybrid Inference:"," For longer sequences, it employs 'Block Autoregressive Diffusion,' where 256-token blocks are denoised in parallel and then committed to the KV cache before starting a new canvas.",[17,5833,5835],{"id":5834},"trade-offs-and-use-cases","Trade-offs and Use Cases",[22,5837,5838],{},"Google explicitly positions DiffusionGemma for local, low-latency, single-user workloads like in-line editing and rapid iteration. It is not intended to replace standard autoregressive models for high-quality production tasks, as its overall output quality is lower. Furthermore, the speed advantages diminish in high-concurrency cloud environments where autoregressive models already saturate compute resources efficiently. When quantized, the model fits within 18GB of VRAM, making it accessible for high-end consumer hardware.",{"title":63,"searchDepth":64,"depth":64,"links":5840},[5841,5842,5843],{"id":5794,"depth":64,"text":5795},{"id":5801,"depth":64,"text":5802},{"id":5834,"depth":64,"text":5835},[70],{"content_references":5846,"triage":5850},[5847],{"type":77,"title":5848,"url":5849,"context":80},"DiffusionGemma 26B-A4B-it","https:\u002F\u002Fhuggingface.co\u002Fgoogle\u002Fdiffusiongemma-26B-A4B-it",{"relevance":86,"novelty":87,"quality":86,"actionability":87,"composite":5851,"reasoning":5852},3.6,"Category: AI & LLMs. The article discusses a new model, DiffusionGemma, which offers a novel approach to text generation, addressing a specific audience pain point regarding performance and efficiency in AI workflows. It provides technical insights and potential use cases, but lacks detailed actionable steps for implementation.","\u002Fsummaries\u002F89df0446e415c993-diffusiongemma-parallel-text-generation-via-diffus-summary","2026-06-11 12:57:14",{"title":5784,"description":63},{"loc":5853},"89df0446e415c993","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F06\u002F10\u002Fgoogle-ai-releases-diffusiongemma-a-26b-moe-open-model-using-text-diffusion-for-up-to-4x-faster-generation\u002F","summaries\u002F89df0446e415c993-diffusiongemma-parallel-text-generation-via-diffus-summary",[102,5861,103,104],"ai-tools","Google's DiffusionGemma is a 26B MoE model that uses text diffusion instead of autoregressive decoding, enabling up to 4x faster generation for local, interactive workflows.",[],"OL0OihGMYCueQkJpZPFWtH3pz-h8zXIoCVFe0j46zGI",{"id":5866,"title":5867,"ai":5868,"body":5873,"categories":5958,"created_at":71,"date_modified":71,"description":63,"extension":72,"faq":71,"featured":73,"kicker_label":71,"meta":5959,"navigation":90,"path":5970,"published_at":5971,"question":71,"scraped_at":5972,"seo":5973,"sitemap":5974,"source_id":5975,"source_name":5976,"source_type":5977,"source_url":5978,"stem":5979,"tags":5980,"thumbnail_url":5981,"tldr":5982,"tweet":5983,"unknown_tags":5984,"__hash__":5985},"summaries\u002Fsummaries\u002F1ac17c99e1a87b1f-scaling-transformer-training-to-5-million-tokens-summary.md","Scaling Transformer Training to 5 Million Tokens",{"provider":7,"model":8,"input_tokens":5869,"output_tokens":5870,"processing_time_ms":5871,"cost_usd":5872},6017,673,3862,0.00251375,{"type":14,"value":5874,"toc":5952},[5875,5879,5882,5886,5889,5921,5925,5928,5932],[17,5876,5878],{"id":5877},"the-memory-bottleneck-in-long-context-training","The Memory Bottleneck in Long-Context Training",[22,5880,5881],{},"Training standard transformer models with massive context windows (e.g., 3M+ tokens) faces two primary constraints: quadratic computational complexity and linear memory growth. Even on high-end hardware like an 8xH100 node, standard implementations fail because the model parameters and attention activations quickly exceed available GPU memory.",[17,5883,5885],{"id":5884},"the-stack-of-optimization-techniques","The Stack of Optimization Techniques",[22,5887,5888],{},"To reach a 3-million token context, a layered approach is required to manage memory usage:",[33,5890,5891,5897,5903,5909,5915],{},[36,5892,5893,5896],{},[39,5894,5895],{},"Fully Sharded Data Parallelism (FSDP):"," Distributes model parameters across all available GPUs to prevent memory exhaustion from the model weights alone.",[36,5898,5899,5902],{},[39,5900,5901],{},"DeepSpeed Ulysses:"," A context parallelism technique that distributes attention heads across GPUs. Instead of every GPU computing the full sequence, each GPU handles specific heads, reducing activation memory by approximately 8x.",[36,5904,5905,5908],{},[39,5906,5907],{},"Activation Checkpointing:"," Recomputes activations during the backward pass rather than storing them, providing another 8x reduction in memory usage.",[36,5910,5911,5914],{},[39,5912,5913],{},"CPU Offloading:"," Moves transformer block inputs to CPU memory when not actively needed for backpropagation, prefetching them just-in-time to minimize performance impact.",[36,5916,5917,5920],{},[39,5918,5919],{},"Chunked Sequence Training:"," Tiles element-wise operations (like loss calculations and MLPs) across the sequence length to avoid allocating massive buffers that scale linearly with the token count.",[17,5922,5924],{"id":5923},"untied-ulysses-pushing-to-5-million-tokens","Untied Ulysses: Pushing to 5 Million Tokens",[22,5926,5927],{},"To surpass the 3-million token limit, the team developed \"Untied Ulysses.\" This technique refines context parallelism by further chunking attention heads. Instead of allocating a single large buffer per head group, the system iterates through smaller chunks of heads, reusing the same memory buffers across iterations. This significantly lowers activation memory requirements with negligible impact on throughput.",[17,5929,5931],{"id":5930},"practical-implementation-advice","Practical Implementation Advice",[33,5933,5934,5940,5946],{},[36,5935,5936,5939],{},[39,5937,5938],{},"Profiling is critical:"," Use tools like the PyTorch Profiler to identify exactly where memory is being consumed, as bottlenecks often appear in unexpected places.",[36,5941,5942,5945],{},[39,5943,5944],{},"Trade-offs:"," There is a direct relationship between chunk size and throughput. Larger chunks increase memory utilization but can improve overall training speed.",[36,5947,5948,5951],{},[39,5949,5950],{},"Reinvesting Memory:"," By stacking these optimizations, you can free up memory that can be reinvested into other training stages or used to push context lengths even further.",{"title":63,"searchDepth":64,"depth":64,"links":5953},[5954,5955,5956,5957],{"id":5877,"depth":64,"text":5878},{"id":5884,"depth":64,"text":5885},{"id":5923,"depth":64,"text":5924},{"id":5930,"depth":64,"text":5931},[70],{"content_references":5960,"triage":5967},[5961,5965],{"type":77,"title":5962,"author":5963,"context":5964},"DeepSpeed Ulysses","Microsoft","cited",{"type":77,"title":5966,"context":5766},"PyTorch Profiler",{"relevance":85,"novelty":86,"quality":86,"actionability":86,"composite":5968,"reasoning":5969},4.35,"Category: AI & LLMs. The article provides in-depth techniques for optimizing transformer training, directly addressing the audience's need for practical applications in AI model development. It discusses specific methods like Fully Sharded Data Parallelism and Untied Ulysses, which are actionable for developers looking to implement long-context training.","\u002Fsummaries\u002F1ac17c99e1a87b1f-scaling-transformer-training-to-5-million-tokens-summary","2026-06-08 17:00:21","2026-06-09 12:56:17",{"title":5867,"description":63},{"loc":5970},"1ac17c99e1a87b1f","AI Engineer","video","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TUnPNY4E2fw","summaries\u002F1ac17c99e1a87b1f-scaling-transformer-training-to-5-million-tokens-summary",[102,103,104,5861],"https:\u002F\u002Fi.ytimg.com\u002Fvi\u002FTUnPNY4E2fw\u002Fhqdefault.jpg","To train models with multi-million token contexts, you must stack memory-optimization techniques—including context parallelism, activation checkpointing, and a novel method called 'Untied Ulysses'—to bypass GPU memory bottlenecks.","This is a technical breakdown of the memory-optimization stack required to train models on extremely long context windows (up to 5 million tokens). The speaker details how to combine standard techniques like [DeepSpeed Ulysses](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FDeepSpeed) and activation checkpointing with their own \"Untied Ulysses\" method to reduce memory overhead by chunking and reusing attention buffers.",[],"vdZh7ZzpnTzdTG3G79QASc2ywoHe_prr-WYngZH8xkI",{"id":5987,"title":5988,"ai":5989,"body":5994,"categories":6062,"created_at":71,"date_modified":71,"description":63,"extension":72,"faq":71,"featured":73,"kicker_label":71,"meta":6063,"navigation":90,"path":6074,"published_at":6075,"question":71,"scraped_at":6076,"seo":6077,"sitemap":6078,"source_id":6079,"source_name":97,"source_type":98,"source_url":6080,"stem":6081,"tags":6082,"thumbnail_url":71,"tldr":6083,"tweet":71,"unknown_tags":6084,"__hash__":6085},"summaries\u002Fsummaries\u002Fbeb19294561867ca-benchmarking-llm-compression-fp8-gptq-and-smoothqu-summary.md","Benchmarking LLM Compression: FP8, GPTQ, and SmoothQuant",{"provider":7,"model":8,"input_tokens":5990,"output_tokens":5991,"processing_time_ms":5992,"cost_usd":5993},10756,674,2766,0.0037,{"type":14,"value":5995,"toc":6058},[5996,6000,6008,6028,6032,6035,6055],[17,5997,5999],{"id":5998},"quantization-strategies-for-llm-efficiency","Quantization Strategies for LLM Efficiency",[22,6001,6002,6003,6007],{},"Post-training quantization (PTQ) is essential for deploying LLMs in resource-constrained environments. This tutorial demonstrates three distinct approaches using the ",[6004,6005,6006],"code",{},"llmcompressor"," library to reduce model footprint and improve inference speed while maintaining output quality:",[33,6009,6010,6016,6022],{},[36,6011,6012,6015],{},[39,6013,6014],{},"FP8 Dynamic Quantization:"," A data-free approach that compresses linear layers into 8-bit precision while keeping the language modeling head in higher precision. It is the fastest to implement and provides a baseline for efficiency gains.",[36,6017,6018,6021],{},[39,6019,6020],{},"GPTQ W4A16:"," A more aggressive compression method that reduces weights to 4-bit while maintaining 16-bit activation precision. This requires a calibration dataset (in this case, 256 samples from UltraChat) to minimize reconstruction error, resulting in significantly smaller model sizes.",[36,6023,6024,6027],{},[39,6025,6026],{},"SmoothQuant + GPTQ W8A8:"," An advanced pipeline that addresses activation outliers using SmoothQuant (smoothing strength 0.8) before applying 8-bit quantization. This combination balances accuracy recovery with the performance benefits of 8-bit operations.",[17,6029,6031],{"id":6030},"benchmarking-and-deployment-workflow","Benchmarking and Deployment Workflow",[22,6033,6034],{},"To evaluate these methods, the implementation establishes a standardized benchmarking suite that measures:",[33,6036,6037,6043,6049],{},[36,6038,6039,6042],{},[39,6040,6041],{},"Disk Size:"," Total storage footprint in GB.",[36,6044,6045,6048],{},[39,6046,6047],{},"Perplexity (PPL):"," Evaluated on the WikiText-2 dataset to ensure compression hasn't degraded model reasoning.",[36,6050,6051,6054],{},[39,6052,6053],{},"Generation Latency & Throughput:"," Measured in seconds and tokens per second (tok\u002Fs) using a consistent prompt.",[22,6056,6057],{},"The workflow emphasizes a \"save-and-test\" cycle, where each compressed model is saved as a reusable artifact. By comparing the FP16 baseline against these quantized variants, developers can make informed trade-offs between model size and inference performance, creating a repeatable pipeline for production-ready model deployment.",{"title":63,"searchDepth":64,"depth":64,"links":6059},[6060,6061],{"id":5998,"depth":64,"text":5999},{"id":6030,"depth":64,"text":6031},[70],{"content_references":6064,"triage":6072},[6065,6067,6070],{"type":77,"title":6006,"url":6066,"context":5766},"https:\u002F\u002Fgithub.com\u002Fvllm-project\u002Fllm-compressor",{"type":5756,"title":6068,"url":6069,"context":5964},"UltraChat 200k","https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FHuggingFaceH4\u002Fultrachat_200k",{"type":5756,"title":6071,"context":5964},"WikiText-2",{"relevance":85,"novelty":86,"quality":86,"actionability":85,"composite":5768,"reasoning":6073},"Category: AI & LLMs. The article provides a detailed practical guide on compressing LLMs, addressing a core topic of AI engineering with actionable insights on quantization strategies. It includes specific methods and a benchmarking workflow that developers can implement directly in their projects.","\u002Fsummaries\u002Fbeb19294561867ca-benchmarking-llm-compression-fp8-gptq-and-smoothqu-summary","2026-05-17 18:19:09","2026-05-17 18:48:19",{"title":5988,"description":63},{"loc":6074},"beb19294561867ca","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F05\u002F17\u002Fa-coding-implementation-to-compress-and-benchmark-instruction-tuned-llms-with-fp8-gptq-and-smoothquant-quantization-using-llmcompressor\u002F","summaries\u002Fbeb19294561867ca-benchmarking-llm-compression-fp8-gptq-and-smoothqu-summary",[102,5861,104,103],"A practical guide to compressing instruction-tuned LLMs using llmcompressor, comparing FP8 dynamic, GPTQ W4A16, and SmoothQuant W8A8 quantization strategies across size, latency, and perplexity.",[],"30L_xT8fTg-Uhmof_yAXXdldKTf6tCZLD87bHm4DkII"]