[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-a512181068703722-evaluating-llm-judge-reliability-via-subset-select-summary":3,"summaries-facets-categories":106,"summary-related-a512181068703722-evaluating-llm-judge-reliability-via-subset-select-summary":5680},{"id":4,"title":5,"ai":6,"body":13,"categories":72,"created_at":74,"date_modified":74,"description":66,"extension":75,"faq":74,"featured":76,"kicker_label":74,"meta":77,"navigation":89,"path":90,"published_at":91,"question":74,"scraped_at":91,"seo":92,"sitemap":93,"source_id":94,"source_name":95,"source_type":96,"source_url":82,"stem":97,"tags":98,"thumbnail_url":74,"tldr":103,"tweet":74,"unknown_tags":104,"__hash__":105},"summaries\u002Fsummaries\u002Fa512181068703722-evaluating-llm-judge-reliability-via-subset-select-summary.md","Evaluating LLM Judge Reliability via Subset Selection",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","google\u002Fgemini-3.1-flash-lite",4072,514,3211,0.001789,{"type":14,"value":15,"toc":65},"minimark",[16,21,25,29,32,35,58,62],[17,18,20],"h2",{"id":19},"the-challenge-of-llm-judge-alignment","The Challenge of LLM Judge Alignment",[22,23,24],"p",{},"Using LLMs as automated evaluators (LLM-as-a-judge) is common, but these judges often suffer from reliability issues, including positional bias, verbosity bias, and poor alignment with human judgment. The core problem is that standard evaluation datasets are often noisy or contain samples where the judge's performance is inherently unreliable. Evaluating a judge on an entire dataset without filtering leads to diluted metrics that fail to capture the judge's true capability.",[17,26,28],{"id":27},"the-metric-match-framework","The Metric Match Framework",[22,30,31],{},"Metric Match introduces a subset selection approach to refine how we measure judge reliability. Instead of evaluating a judge across an entire, heterogeneous dataset, the framework identifies a high-fidelity 'subset' of samples where the judge's performance is most stable and predictive of human preference.",[22,33,34],{},"By selecting samples that maximize the correlation between the LLM judge's output and human gold-standard labels, researchers can:",[36,37,38,46,52],"ul",{},[39,40,41,45],"li",{},[42,43,44],"strong",{},"Filter out noise:"," Remove samples where the task is ambiguous or the judge is prone to systematic bias.",[39,47,48,51],{},[42,49,50],{},"Improve sensitivity:"," Create a more precise evaluation signal that detects subtle improvements in judge performance.",[39,53,54,57],{},[42,55,56],{},"Enhance interpretability:"," Understand which types of prompts or tasks the LLM judge is actually competent at evaluating, rather than relying on a single, aggregate score that masks performance variance.",[17,59,61],{"id":60},"practical-implications-for-ai-engineering","Practical Implications for AI Engineering",[22,63,64],{},"For builders, this approach suggests that the quality of your evaluation pipeline is more important than the quantity of your test data. Rather than simply throwing more data at an LLM judge, developers should focus on curating 'golden subsets'—carefully selected examples that act as a reliable benchmark. This methodology allows for faster iteration cycles, as developers can rely on a smaller, high-signal evaluation set to determine if a prompt change or model swap actually improves the judge's alignment with human intent.",{"title":66,"searchDepth":67,"depth":67,"links":68},"",2,[69,70,71],{"id":19,"depth":67,"text":20},{"id":27,"depth":67,"text":28},{"id":60,"depth":67,"text":61},[73],"AI & LLMs",null,"md",false,{"content_references":78,"triage":84},[79],{"type":80,"title":81,"url":82,"context":83},"paper","Metric Match: A Subset Selection Approach to Evaluating LLM Judge Reliability","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.15029","cited",{"relevance":85,"novelty":86,"quality":86,"actionability":86,"composite":87,"reasoning":88},5,4,4.35,"Category: AI & LLMs. The article directly addresses the challenge of evaluating LLM judges, which is crucial for AI product builders looking to implement reliable evaluation metrics. It introduces the 'Metric Match' framework, providing actionable insights on refining evaluation pipelines, which aligns with the audience's need for practical applications in AI engineering.",true,"\u002Fsummaries\u002Fa512181068703722-evaluating-llm-judge-reliability-via-subset-select-summary","2026-06-16 12:56:55",{"title":5,"description":66},{"loc":90},"a512181068703722","arXiv cs.AI","article","summaries\u002Fa512181068703722-evaluating-llm-judge-reliability-via-subset-select-summary",[99,100,101,102],"llm","ai-tools","research","machine-learning","The 'Metric Match' approach improves LLM judge evaluation by using subset selection to identify high-fidelity data samples, ensuring that automated metrics better correlate with human preferences.",[],"2iRnWVS-F1XtffaikTw1-5ccZOse8b6uo5mlLrfpDcA",[107,110,113,115,118,121,123,125,128,130,132,134,136,139,141,143,145,147,150,152,154,156,158,160,162,164,166,168,170,172,174,176,178,180,182,184,187,190,192,194,196,198,200,202,204,206,208,210,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,244,246,248,250,252,254,256,258,260,262,264,266,268,271,273,275,277,279,281,283,285,287,289,291,293,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323,325,327,330,332,334,336,338,340,342,344,346,348,351,353,355,357,359,361,363,365,367,369,371,373,376,378,380,382,384,386,388,390,393,395,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,442,444,446,449,451,453,455,457,459,461,463,465,467,469,471,473,475,478,480,482,484,486,488,490,492,494,497,499,501,503,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,736,738,740,742,745,747,749,751,753,755,757,759,761,763,766,768,770,772,774,776,778,780,782,784,786,788,790,792,794,796,798,800,802,804,806,808,810,812,814,816,818,820,822,824,826,828,830,832,834,836,838,840,842,844,846,848,850,852,854,856,858,860,862,864,866,868,870,872,874,876,878,880,882,884,886,888,890,892,894,896,898,900,902,904,906,908,910,912,914,916,918,920,922,924,926,928,930,932,934,936,938,940,942,944,946,948,950,952,954,956,958,960,962,964,966,968,970,972,974,976,978,980,982,984,986,988,990,992,994,996,998,1000,1002,1004,1006,1008,1010,1012,1015,1017,1019,1021,1023,1025,1027,1029,1031,1033,1035,1037,1039,1041,1043,1045,1047,1049,1051,1053,1055,1057,1059,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1097,1099,1101,1103,1105,1107,1109,1111,1113,1115,1117,1119,1121,1123,1125,1127,1129,1131,1133,1135,1137,1139,1141,1143,1145,1147,1149,1151,1153,1155,1157,1159,1161,1163,1165,1167,1169,1172,1174,1176,1178,1180,1182,1184,1186,1188,1190,1192,1194,1196,1198,1200,1202,1204,1206,1208,1210,1212,1214,1216,1218,1220,1222,1224,1226,1228,1230,1232,1234,1236,1238,1240,1242,1244,1246,1248,1250,1252,1254,1256,1258,1260,1262,1264,1266,1268,1270,1272,1274,1276,1278,1280,1282,1285,1287,1289,1291,1293,1295,1297,1299,1301,1303,1305,1307,1309,1311,1313,1315,1317,1319,1321,1323,1325,1327,1329,1331,1333,1335,1337,1339,1341,1343,1345,1347,1349,1351,1353,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1401,1403,1405,1407,1410,1412,1414,1416,1418,1420,1422,1424,1426,1428,1430,1432,1434,1436,1438,1440,1442,1444,1446,1448,1450,1452,1454,1456,1458,1461,1463,1465,1467,1469,1471,1473,1475,1477,1479,1481,1483,1485,1487,1489,1491,1493,1495,1497,1499,1501,1503,1505,1507,1509,1511,1513,1515,1517,1519,1521,1523,1525,1527,1529,1531,1533,1535,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1593,1595,1597,1599,1601,1603,1605,1607,1609,1611,1613,1615,1617,1619,1621,1623,1625,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697,1699,1701,1703,1705,1707,1709,1711,1713,1715,1717,1719,1721,1723,1725,1727,1729,1731,1733,1735,1737,1739,1741,1743,1745,1747,1749,1751,1753,1755,1757,1759,1761,1763,1765,1767,1769,1771,1773,1775,1777,1779,1781,1783,1785,1787,1789,1791,1793,1795,1797,1799,1801,1803,1805,1808,1810,1812,1814,1816,1818,1820,1822,1824,1826,1828,1830,1832,1834,1836,1838,1840,1842,1844,1846,1848,1850,1852,1854,1856,1858,1860,1862,1864,1866,1868,1870,1872,1874,1876,1878,1880,1883,1885,1887,1889,1891,1893,1895,1897,1899,1901,1903,1905,1907,1909,1911,1913,1915,1917,1919,1921,1923,1925,1927,1929,1931,1933,1935,1937,1939,1941,1943,1945,1947,1949,1951,1953,1955,1957,1959,1961,1963,1965,1967,1969,1971,1973,1975,1977,1979,1982,1984,1986,1988,1990,1992,1994,1996,1998,2000,2002,2004,2006,2008,2010,2012,2014,2016,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2045,2047,2049,2051,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071,2073,2075,2077,2079,2081,2083,2085,2087,2089,2091,2093,2095,2097,2099,2101,2103,2105,2107,2109,2111,2113,2115,2117,2119,2121,2123,2125,2127,2129,2131,2133,2135,2137,2139,2141,2143,2145,2147,2149,2151,2153,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2195,2197,2199,2201,2203,2205,2207,2209,2211,2213,2215,2217,2219,2221,2223,2225,2227,2229,2231,2233,2235,2237,2239,2241,2243,2245,2247,2249,2251,2253,2255,2257,2259,2261,2263,2265,2267,2269,2271,2273,2275,2277,2279,2281,2283,2285,2287,2289,2291,2293,2295,2297,2299,2301,2303,2305,2307,2309,2311,2313,2315,2317,2319,2321,2323,2325,2327,2329,2331,2333,2335,2337,2339,2341,2343,2345,2347,2349,2351,2353,2355,2357,2359,2361,2363,2365,2367,2369,2371,2373,2375,2377,2379,2381,2383,2385,2387,2389,2391,2393,2395,2397,2399,2401,2403,2405,2407,2409,2411,2413,2415,2417,2419,2421,2423,2425,2427,2429,2431,2433,2435,2437,2439,2441,2443,2445,2447,2449,2451,2453,2455,2457,2459,2461,2463,2465,2467,2469,2471,2473,2475,2477,2479,2481,2483,2485,2487,2489,2491,2493,2495,2497,2499,2501,2503,2505,2507,2509,2511,2513,2515,2517,2519,2521,2523,2525,2527,2529,2531,2533,2535,2537,2540,2542,2544,2546,2548,2550,2552,2554,2556,2558,2560,2562,2564,2566,2568,2570,2572,2574,2576,2578,2580,2582,2584,2586,2588,2590,2592,2594,2596,2598,2600,2602,2604,2606,2608,2610,2612,2614,2616,2618,2620,2622,2624,2626,2628,2630,2632,2634,2637,2639,2641,2643,2645,2647,2649,2651,2653,2655,2657,2659,2661,2663,2665,2667,2669,2671,2673,2675,2677,2679,2681,2683,2685,2687,2689,2691,2693,2695,2697,2699,2701,2703,2705,2707,2709,2711,2713,2715,2717,2719,2721,2723,2725,2727,2729,2731,2733,2735,2737,2739,2741,2743,2745,2747,2749,2751,2753,2755,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2859,2861,2863,2865,2867,2869,2871,2873,2875,2877,2879,2881,2883,2885,2887,2889,2891,2893,2895,2897,2899,2901,2903,2905,2907,2909,2911,2913,2915,2917,2919,2921,2923,2925,2927,2929,2931,2933,2935,2937,2939,2941,2943,2945,2947,2949,2951,2953,2955,2957,2959,2961,2963,2965,2967,2969,2971,2973,2975,2977,2979,2981,2983,2985,2987,2989,2991,2993,2995,2997,2999,3001,3003,3005,3007,3009,3011,3013,3015,3017,3019,3021,3023,3025,3027,3029,3031,3033,3035,3037,3039,3041,3043,3045,3047,3049,3051,3053,3055,3057,3059,3061,3063,3065,3067,3069,3071,3073,3075,3077,3079,3081,3083,3085,3087,3089,3091,3093,3095,3097,3099,3101,3103,3105,3107,3109,3111,3113,3115,3117,3119,3121,3123,3125,3127,3129,3131,3133,3135,3137,3139,3141,3143,3145,3147,3149,3151,3153,3155,3157,3159,3161,3163,3165,3167,3169,3171,3173,3175,3177,3179,3181,3183,3185,3187,3189,3191,3193,3195,3197,3199,3201,3203,3205,3207,3209,3211,3213,3215,3217,3219,3221,3223,3225,3227,3229,3231,3233,3235,3237,3239,3241,3243,3245,3247,3249,3251,3253,3255,3257,3259,3261,3263,3265,3267,3269,3271,3273,3275,3277,3279,3281,3283,3285,3287,3289,3291,3293,3295,3297,3299,3301,3303,3305,3307,3309,3311,3313,3315,3317,3319,3321,3323,3325,3327,3329,3331,3333,3335,3337,3339,3341,3343,3345,3347,3349,3351,3353,3355,3357,3359,3361,3363,3365,3367,3369,3371,3373,3375,3377,3379,3381,3383,3385,3387,3389,3391,3393,3395,3397,3399,3401,3403,3405,3407,3409,3411,3413,3415,3417,3419,3421,3423,3425,3427,3429,3431,3433,3435,3437,3439,3441,3443,3445,3447,3449,3451,3453,3455,3457,3459,3461,3463,3465,3467,3469,3471,3473,3475,3477,3479,3481,3483,3485,3487,3489,3491,3493,3495,3497,3499,3501,3503,3505,3507,3509,3511,3513,3515,3517,3519,3521,3523,3525,3527,3529,3531,3533,3535,3537,3539,3541,3543,3545,3547,3549,3551,3553,3555,3557,3559,3561,3563,3565,3567,3569,3571,3573,3575,3577,3579,3581,3583,3585,3587,3589,3591,3593,3595,3597,3599,3601,3603,3605,3607,3609,3611,3613,3615,3617,3619,3621,3623,3625,3627,3629,3631,3633,3635,3637,3639,3641,3643,3645,3647,3649,3651,3653,3655,3657,3659,3661,3663,3665,3667,3670,3672,3674,3676,3678,3680,3682,3684,3686,3688,3690,3692,3694,3696,3698,3700,3702,3704,3706,3708,3710,3712,3714,3716,3718,3720,3722,3724,3726,3728,3730,3732,3734,3736,3738,3740,3742,3744,3746,3748,3750,3752,3754,3756,3758,3760,3762,3764,3766,3768,3770,3772,3774,3776,3778,3780,3782,3784,3786,3788,3790,3792,3794,3796,3798,3800,3802,3804,3806,3808,3810,3812,3814,3816,3818,3820,3822,3824,3826,3828,3830,3832,3834,3836,3838,3840,3842,3844,3846,3848,3850,3852,3854,3856,3858,3860,3862,3864,3866,3868,3870,3872,3874,3876,3878,3880,3882,3884,3886,3888,3890,3892,3894,3896,3898,3900,3902,3904,3906,3908,3910,3912,3914,3916,3918,3920,3922,3924,3926,3928,3930,3932,3934,3936,3938,3940,3942,3944,3946,3948,3950,3952,3954,3956,3958,3960,3962,3964,3966,3968,3970,3972,3974,3976,3978,3980,3982,3984,3986,3988,3990,3992,3994,3996,3998,4000,4002,4004,4006,4008,4010,4012,4014,4016,4018,4020,4022,4024,4026,4028,4030,4032,4034,4036,4038,4040,4042,4044,4046,4048,4050,4052,4054,4056,4058,4060,4062,4064,4066,4068,4070,4072,4074,4076,4078,4080,4082,4084,4086,4088,4090,4092,4094,4096,4098,4100,4102,4104,4106,4108,4110,4112,4114,4116,4118,4120,4122,4124,4126,4128,4130,4132,4134,4136,4138,4140,4142,4144,4146,4148,4150,4152,4154,4156,4158,4160,4162,4164,4166,4168,4170,4172,4174,4176,4178,4180,4182,4184,4186,4188,4190,4192,4194,4196,4198,4200,4202,4204,4206,4208,4210,4212,4214,4216,4218,4220,4222,4224,4226,4228,4230,4232,4234,4236,4238,4240,4242,4244,4246,4248,4250,4252,4254,4256,4258,4260,4262,4264,4266,4268,4270,4272,4274,4276,4278,4280,4282,4284,4286,4288,4290,4292,4294,4296,4298,4300,4302,4304,4306,4308,4310,4312,4314,4316,4318,4320,4322,4324,4326,4328,4330,4332,4334,4336,4338,4340,4342,4344,4346,4348,4350,4352,4354,4356,4358,4360,4362,4364,4367,4369,4371,4373,4375,4377,4379,4381,4383,4385,4387,4389,4391,4393,4395,4397,4399,4401,4403,4405,4407,4409,4411,4413,4415,4417,4419,4421,4423,4425,4427,4429,4431,4433,4435,4437,4439,4441,4443,4445,4447,4449,4451,4453,4455,4457,4459,4461,4463,4465,4467,4469,4471,4473,4475,4477,4479,4481,4483,4485,4487,4489,4491,4493,4495,4497,4499,4501,4503,4505,4507,4509,4511,4513,4515,4517,4519,4521,4523,4525,4527,4530,4532,4534,4536,4538,4540,4542,4544,4546,4548,4550,4552,4554,4556,4558,4560,4562,4564,4566,4568,4570,4572,4574,4576,4578,4580,4582,4584,4586,4588,4590,4592,4594,4596,4598,4600,4602,4604,4606,4608,4610,4612,4614,4616,4618,4620,4622,4624,4626,4628,4630,4632,4634,4636,4638,4640,4642,4644,4646,4648,4650,4652,4654,4656,4658,4660,4662,4664,4666,4668,4670,4672,4674,4676,4678,4680,4682,4684,4686,4688,4690,4692,4694,4696,4698,4700,4702,4704,4706,4708,4710,4712,4714,4716,4718,4720,4722,4724,4726,4728,4730,4732,4734,4736,4738,4740,4742,4744,4746,4748,4750,4752,4754,4756,4758,4760,4762,4764,4766,4768,4770,4772,4774,4776,4778,4780,4782,4784,4786,4788,4790,4792,4794,4796,4798,4800,4802,4804,4806,4808,4810,4812,4814,4816,4818,4820,4822,4824,4826,4828,4830,4832,4834,4836,4838,4840,4842,4844,4846,4848,4850,4852,4854,4856,4858,4860,4862,4864,4866,4868,4870,4872,4874,4876,4878,4880,4882,4884,4886,4888,4890,4892,4894,4896,4898,4900,4902,4904,4906,4908,4910,4912,4914,4916,4918,4920,4922,4924,4926,4928,4930,4932,4934,4936,4938,4940,4942,4944,4946,4948,4950,4952,4954,4956,4958,4960,4962,4964,4966,4968,4970,4972,4974,4976,4978,4980,4982,4984,4986,4988,4990,4992,4994,4996,4998,5000,5002,5004,5006,5008,5010,5012,5014,5016,5018,5020,5022,5024,5026,5028,5030,5032,5034,5036,5038,5040,5042,5044,5046,5048,5050,5052,5054,5056,5058,5060,5062,5064,5066,5068,5070,5072,5074,5076,5078,5080,5082,5084,5086,5088,5090,5092,5094,5096,5098,5100,5102,5104,5106,5108,5110,5112,5114,5116,5118,5120,5122,5124,5126,5128,5130,5132,5134,5136,5138,5140,5142,5144,5146,5148,5150,5152,5154,5156,5158,5160,5162,5164,5166,5168,5170,5172,5174,5176,5178,5180,5182,5184,5186,5188,5190,5192,5194,5196,5198,5200,5202,5204,5206,5208,5210,5212,5214,5216,5218,5220,5222,5224,5226,5228,5230,5232,5234,5236,5238,5240,5242,5244,5246,5248,5250,5252,5254,5256,5258,5260,5262,5264,5266,5268,5270,5272,5274,5276,5278,5280,5282,5284,5286,5288,5290,5292,5294,5296,5298,5300,5302,5304,5306,5308,5310,5312,5314,5316,5318,5320,5322,5324,5326,5328,5330,5332,5334,5336,5338,5340,5342,5344,5346,5348,5350,5352,5354,5356,5358,5360,5362,5364,5366,5368,5370,5372,5374,5376,5378,5380,5382,5384,5386,5388,5390,5392,5394,5396,5398,5400,5402,5404,5406,5408,5410,5412,5414,5416,5418,5420,5422,5424,5426,5428,5430,5432,5434,5436,5438,5440,5442,5444,5446,5448,5450,5452,5454,5456,5458,5460,5462,5464,5466,5468,5470,5472,5474,5476,5478,5480,5482,5484,5486,5488,5490,5492,5494,5496,5498,5500,5502,5504,5506,5508,5510,5512,5514,5516,5518,5520,5522,5524,5526,5528,5530,5532,5534,5536,5538,5540,5542,5544,5546,5548,5550,5552,5554,5556,5558,5560,5562,5564,5566,5568,5570,5572,5574,5576,5578,5580,5582,5584,5586,5588,5590,5592,5594,5596,5598,5600,5602,5604,5606,5608,5610,5612,5614,5616,5618,5620,5622,5624,5626,5628,5630,5632,5634,5636,5638,5640,5642,5644,5646,5648,5650,5652,5654,5656,5658,5660,5662,5664,5666,5668,5670,5672,5674,5676,5678],{"categories":108},[109],"Developer Productivity",{"categories":111},[112],"Business & SaaS",{"categories":114},[73],{"categories":116},[117],"AI Automation",{"categories":119},[120],"Product Strategy",{"categories":122},[73],{"categories":124},[109],{"categories":126},[127],"Software Engineering",{"categories":129},[73],{"categories":131},[112],{"categories":133},[],{"categories":135},[73],{"categories":137},[138],"Inference & Serving",{"categories":140},[73],{"categories":142},[73],{"categories":144},[117],{"categories":146},[],{"categories":148},[149],"AI News & Trends",{"categories":151},[117],{"categories":153},[73],{"categories":155},[112],{"categories":157},[73],{"categories":159},[117],{"categories":161},[149],{"categories":163},[117],{"categories":165},[117],{"categories":167},[73],{"categories":169},[117],{"categories":171},[73],{"categories":173},[73],{"categories":175},[73],{"categories":177},[149],{"categories":179},[73],{"categories":181},[73],{"categories":183},[],{"categories":185},[186],"Design & Frontend",{"categories":188},[189],"Data Science & Visualization",{"categories":191},[149],{"categories":193},[73],{"categories":195},[73],{"categories":197},[],{"categories":199},[73],{"categories":201},[117],{"categories":203},[127],{"categories":205},[73],{"categories":207},[117],{"categories":209},[73],{"categories":211},[212],"Marketing & Growth",{"categories":214},[186],{"categories":216},[73],{"categories":218},[117],{"categories":220},[73],{"categories":222},[],{"categories":224},[],{"categories":226},[186],{"categories":228},[73],{"categories":230},[117],{"categories":232},[109],{"categories":234},[127],{"categories":236},[186],{"categories":238},[73],{"categories":240},[127],{"categories":242},[243],"DevOps & Cloud",{"categories":245},[117],{"categories":247},[120],{"categories":249},[149],{"categories":251},[73],{"categories":253},[],{"categories":255},[73],{"categories":257},[],{"categories":259},[117],{"categories":261},[127],{"categories":263},[],{"categories":265},[127],{"categories":267},[73],{"categories":269},[270],"Governance & Standards",{"categories":272},[112],{"categories":274},[],{"categories":276},[],{"categories":278},[73],{"categories":280},[73],{"categories":282},[117],{"categories":284},[73],{"categories":286},[73],{"categories":288},[117],{"categories":290},[73],{"categories":292},[73],{"categories":294},[73],{"categories":296},[],{"categories":298},[127],{"categories":300},[],{"categories":302},[],{"categories":304},[127],{"categories":306},[],{"categories":308},[127],{"categories":310},[73],{"categories":312},[73],{"categories":314},[212],{"categories":316},[73],{"categories":318},[186],{"categories":320},[186],{"categories":322},[73],{"categories":324},[127],{"categories":326},[117],{"categories":328},[329],"GovTech & Public-Sector Adoption",{"categories":331},[127],{"categories":333},[73],{"categories":335},[73],{"categories":337},[117],{"categories":339},[117],{"categories":341},[189],{"categories":343},[73],{"categories":345},[149],{"categories":347},[117],{"categories":349},[350],"Legal AI Tools",{"categories":352},[117],{"categories":354},[212],{"categories":356},[117],{"categories":358},[120],{"categories":360},[127],{"categories":362},[329],{"categories":364},[],{"categories":366},[117],{"categories":368},[],{"categories":370},[117],{"categories":372},[117],{"categories":374},[375],"RAG & Retrieval",{"categories":377},[112],{"categories":379},[73],{"categories":381},[127],{"categories":383},[243],{"categories":385},[186],{"categories":387},[73],{"categories":389},[],{"categories":391},[392],"Agents & Orchestration",{"categories":394},[127],{"categories":396},[73],{"categories":398},[],{"categories":400},[117],{"categories":402},[112],{"categories":404},[],{"categories":406},[73],{"categories":408},[],{"categories":410},[109],{"categories":412},[127],{"categories":414},[112],{"categories":416},[73],{"categories":418},[73],{"categories":420},[149],{"categories":422},[73],{"categories":424},[],{"categories":426},[73],{"categories":428},[],{"categories":430},[127],{"categories":432},[189],{"categories":434},[],{"categories":436},[73],{"categories":438},[186],{"categories":440},[441],"Models & Frontier Labs",{"categories":443},[],{"categories":445},[186],{"categories":447},[448],"Regulation & Governance of AI",{"categories":450},[117],{"categories":452},[],{"categories":454},[73],{"categories":456},[73],{"categories":458},[117],{"categories":460},[149],{"categories":462},[112],{"categories":464},[73],{"categories":466},[],{"categories":468},[127],{"categories":470},[117],{"categories":472},[73],{"categories":474},[120],{"categories":476},[477],"AI Policy & Regulation",{"categories":479},[],{"categories":481},[73],{"categories":483},[120],{"categories":485},[117],{"categories":487},[73],{"categories":489},[117],{"categories":491},[],{"categories":493},[189],{"categories":495},[496],"Evals & Reliability",{"categories":498},[73],{"categories":500},[],{"categories":502},[109],{"categories":504},[329],{"categories":506},[477],{"categories":508},[73],{"categories":510},[112],{"categories":512},[73],{"categories":514},[117],{"categories":516},[73],{"categories":518},[117],{"categories":520},[392],{"categories":522},[73],{"categories":524},[127],{"categories":526},[73],{"categories":528},[],{"categories":530},[],{"categories":532},[73],{"categories":534},[329],{"categories":536},[73],{"categories":538},[73],{"categories":540},[],{"categories":542},[186],{"categories":544},[],{"categories":546},[73],{"categories":548},[],{"categories":550},[117],{"categories":552},[73],{"categories":554},[186],{"categories":556},[],{"categories":558},[73],{"categories":560},[117],{"categories":562},[73],{"categories":564},[112],{"categories":566},[117],{"categories":568},[73],{"categories":570},[73],{"categories":572},[127],{"categories":574},[186],{"categories":576},[117],{"categories":578},[],{"categories":580},[127],{"categories":582},[117],{"categories":584},[],{"categories":586},[149],{"categories":588},[],{"categories":590},[73],{"categories":592},[73],{"categories":594},[112,212],{"categories":596},[],{"categories":598},[73],{"categories":600},[73],{"categories":602},[117],{"categories":604},[],{"categories":606},[],{"categories":608},[73],{"categories":610},[186],{"categories":612},[73],{"categories":614},[],{"categories":616},[73],{"categories":618},[243],{"categories":620},[],{"categories":622},[117],{"categories":624},[149],{"categories":626},[73],{"categories":628},[186],{"categories":630},[],{"categories":632},[149],{"categories":634},[73],{"categories":636},[138],{"categories":638},[73],{"categories":640},[117],{"categories":642},[149],{"categories":644},[441],{"categories":646},[73],{"categories":648},[212],{"categories":650},[],{"categories":652},[117],{"categories":654},[112],{"categories":656},[127],{"categories":658},[73],{"categories":660},[117],{"categories":662},[],{"categories":664},[73,243],{"categories":666},[73],{"categories":668},[73],{"categories":670},[73],{"categories":672},[117],{"categories":674},[73,127],{"categories":676},[189],{"categories":678},[73],{"categories":680},[73],{"categories":682},[127],{"categories":684},[117],{"categories":686},[477],{"categories":688},[212],{"categories":690},[73],{"categories":692},[117],{"categories":694},[73],{"categories":696},[73],{"categories":698},[117],{"categories":700},[],{"categories":702},[73],{"categories":704},[117],{"categories":706},[73],{"categories":708},[73,112],{"categories":710},[112],{"categories":712},[],{"categories":714},[186],{"categories":716},[186],{"categories":718},[73],{"categories":720},[],{"categories":722},[],{"categories":724},[149],{"categories":726},[],{"categories":728},[109],{"categories":730},[73],{"categories":732},[127],{"categories":734},[735],"Generative UI & Design-to-Code",{"categories":737},[73],{"categories":739},[186],{"categories":741},[73],{"categories":743},[744],"Algorithmic Accountability",{"categories":746},[117],{"categories":748},[127],{"categories":750},[149],{"categories":752},[186],{"categories":754},[],{"categories":756},[73],{"categories":758},[73],{"categories":760},[73],{"categories":762},[117],{"categories":764},[765],"MLOps & Infrastructure",{"categories":767},[73],{"categories":769},[73],{"categories":771},[73],{"categories":773},[73],{"categories":775},[149],{"categories":777},[109],{"categories":779},[73],{"categories":781},[117],{"categories":783},[243],{"categories":785},[73],{"categories":787},[186],{"categories":789},[73],{"categories":791},[117],{"categories":793},[],{"categories":795},[],{"categories":797},[138],{"categories":799},[186],{"categories":801},[149],{"categories":803},[189],{"categories":805},[],{"categories":807},[73],{"categories":809},[73],{"categories":811},[112],{"categories":813},[73],{"categories":815},[73],{"categories":817},[73],{"categories":819},[149],{"categories":821},[138],{"categories":823},[73],{"categories":825},[186],{"categories":827},[],{"categories":829},[117],{"categories":831},[127],{"categories":833},[],{"categories":835},[73],{"categories":837},[73],{"categories":839},[117],{"categories":841},[127],{"categories":843},[73],{"categories":845},[189],{"categories":847},[],{"categories":849},[73],{"categories":851},[],{"categories":853},[73],{"categories":855},[],{"categories":857},[120],{"categories":859},[112],{"categories":861},[117],{"categories":863},[117],{"categories":865},[],{"categories":867},[109],{"categories":869},[73],{"categories":871},[112],{"categories":873},[149],{"categories":875},[109],{"categories":877},[],{"categories":879},[73],{"categories":881},[],{"categories":883},[],{"categories":885},[149],{"categories":887},[149],{"categories":889},[],{"categories":891},[392],{"categories":893},[73],{"categories":895},[186],{"categories":897},[127],{"categories":899},[],{"categories":901},[350],{"categories":903},[112],{"categories":905},[],{"categories":907},[],{"categories":909},[109],{"categories":911},[189],{"categories":913},[],{"categories":915},[212],{"categories":917},[117],{"categories":919},[112],{"categories":921},[117],{"categories":923},[112],{"categories":925},[127],{"categories":927},[],{"categories":929},[138],{"categories":931},[120],{"categories":933},[73],{"categories":935},[186],{"categories":937},[127],{"categories":939},[112],{"categories":941},[73],{"categories":943},[117],{"categories":945},[112],{"categories":947},[73],{"categories":949},[73],{"categories":951},[],{"categories":953},[],{"categories":955},[127],{"categories":957},[189],{"categories":959},[120],{"categories":961},[73],{"categories":963},[117],{"categories":965},[73],{"categories":967},[],{"categories":969},[149],{"categories":971},[120],{"categories":973},[73],{"categories":975},[496],{"categories":977},[243],{"categories":979},[],{"categories":981},[117],{"categories":983},[],{"categories":985},[109],{"categories":987},[],{"categories":989},[73],{"categories":991},[73],{"categories":993},[186],{"categories":995},[212],{"categories":997},[127],{"categories":999},[117],{"categories":1001},[],{"categories":1003},[127],{"categories":1005},[109],{"categories":1007},[],{"categories":1009},[149],{"categories":1011},[73,243],{"categories":1013},[1014],"Design Systems for AI",{"categories":1016},[73],{"categories":1018},[149],{"categories":1020},[73],{"categories":1022},[73],{"categories":1024},[112],{"categories":1026},[73],{"categories":1028},[],{"categories":1030},[73],{"categories":1032},[73],{"categories":1034},[112],{"categories":1036},[73],{"categories":1038},[],{"categories":1040},[117],{"categories":1042},[127],{"categories":1044},[127],{"categories":1046},[186],{"categories":1048},[149],{"categories":1050},[189],{"categories":1052},[73],{"categories":1054},[109],{"categories":1056},[477],{"categories":1058},[73],{"categories":1060},[117],{"categories":1062},[73],{"categories":1064},[127],{"categories":1066},[127],{"categories":1068},[],{"categories":1070},[],{"categories":1072},[117],{"categories":1074},[120],{"categories":1076},[],{"categories":1078},[73],{"categories":1080},[],{"categories":1082},[186],{"categories":1084},[117],{"categories":1086},[127],{"categories":1088},[186],{"categories":1090},[73],{"categories":1092},[186],{"categories":1094},[],{"categories":1096},[],{"categories":1098},[149],{"categories":1100},[117],{"categories":1102},[117],{"categories":1104},[73],{"categories":1106},[73],{"categories":1108},[73],{"categories":1110},[112],{"categories":1112},[73],{"categories":1114},[73],{"categories":1116},[],{"categories":1118},[127],{"categories":1120},[127],{"categories":1122},[73],{"categories":1124},[127],{"categories":1126},[112],{"categories":1128},[],{"categories":1130},[73],{"categories":1132},[73],{"categories":1134},[73],{"categories":1136},[117],{"categories":1138},[109],{"categories":1140},[112],{"categories":1142},[149],{"categories":1144},[117],{"categories":1146},[138],{"categories":1148},[212],{"categories":1150},[73],{"categories":1152},[117],{"categories":1154},[],{"categories":1156},[186],{"categories":1158},[],{"categories":1160},[73],{"categories":1162},[73],{"categories":1164},[],{"categories":1166},[127],{"categories":1168},[112],{"categories":1170},[1171],"Visual & Generative Media",{"categories":1173},[117],{"categories":1175},[],{"categories":1177},[73],{"categories":1179},[73],{"categories":1181},[243],{"categories":1183},[189],{"categories":1185},[477],{"categories":1187},[127],{"categories":1189},[212],{"categories":1191},[73],{"categories":1193},[186],{"categories":1195},[73],{"categories":1197},[127],{"categories":1199},[117],{"categories":1201},[],{"categories":1203},[],{"categories":1205},[117],{"categories":1207},[109],{"categories":1209},[117],{"categories":1211},[441],{"categories":1213},[73],{"categories":1215},[120],{"categories":1217},[112],{"categories":1219},[],{"categories":1221},[73],{"categories":1223},[120],{"categories":1225},[73],{"categories":1227},[73],{"categories":1229},[73],{"categories":1231},[73],{"categories":1233},[73],{"categories":1235},[212],{"categories":1237},[73],{"categories":1239},[392],{"categories":1241},[73],{"categories":1243},[73],{"categories":1245},[73],{"categories":1247},[73],{"categories":1249},[73],{"categories":1251},[186],{"categories":1253},[117],{"categories":1255},[],{"categories":1257},[117],{"categories":1259},[],{"categories":1261},[243],{"categories":1263},[127],{"categories":1265},[],{"categories":1267},[441],{"categories":1269},[117],{"categories":1271},[73],{"categories":1273},[186,73],{"categories":1275},[109],{"categories":1277},[],{"categories":1279},[73],{"categories":1281},[109],{"categories":1283},[1284],"Medical Imaging & Radiology",{"categories":1286},[186],{"categories":1288},[117],{"categories":1290},[127],{"categories":1292},[],{"categories":1294},[73],{"categories":1296},[73],{"categories":1298},[73],{"categories":1300},[],{"categories":1302},[],{"categories":1304},[73],{"categories":1306},[392],{"categories":1308},[73],{"categories":1310},[109],{"categories":1312},[73],{"categories":1314},[73],{"categories":1316},[],{"categories":1318},[117],{"categories":1320},[73],{"categories":1322},[120],{"categories":1324},[127],{"categories":1326},[73],{"categories":1328},[392],{"categories":1330},[73],{"categories":1332},[117],{"categories":1334},[73],{"categories":1336},[186],{"categories":1338},[117],{"categories":1340},[243],{"categories":1342},[186],{"categories":1344},[112],{"categories":1346},[117],{"categories":1348},[73],{"categories":1350},[73],{"categories":1352},[73],{"categories":1354},[73],{"categories":1356},[73],{"categories":1358},[117],{"categories":1360},[127],{"categories":1362},[73],{"categories":1364},[120],{"categories":1366},[],{"categories":1368},[149],{"categories":1370},[],{"categories":1372},[120],{"categories":1374},[117],{"categories":1376},[1014],{"categories":1378},[1014],{"categories":1380},[186],{"categories":1382},[73],{"categories":1384},[73],{"categories":1386},[117],{"categories":1388},[127],{"categories":1390},[186],{"categories":1392},[117],{"categories":1394},[149],{"categories":1396},[],{"categories":1398},[73],{"categories":1400},[],{"categories":1402},[73],{"categories":1404},[73],{"categories":1406},[73],{"categories":1408},[1409],"Contract Review & E-Discovery",{"categories":1411},[186],{"categories":1413},[73],{"categories":1415},[109],{"categories":1417},[149],{"categories":1419},[73],{"categories":1421},[73],{"categories":1423},[212],{"categories":1425},[127],{"categories":1427},[73],{"categories":1429},[73],{"categories":1431},[117],{"categories":1433},[117],{"categories":1435},[744],{"categories":1437},[117],{"categories":1439},[117],{"categories":1441},[73],{"categories":1443},[73],{"categories":1445},[117],{"categories":1447},[73],{"categories":1449},[392],{"categories":1451},[375],{"categories":1453},[73],{"categories":1455},[117],{"categories":1457},[73],{"categories":1459},[1460],"Law-Firm Practice & Adoption",{"categories":1462},[73],{"categories":1464},[117],{"categories":1466},[186],{"categories":1468},[73],{"categories":1470},[73],{"categories":1472},[],{"categories":1474},[],{"categories":1476},[127],{"categories":1478},[],{"categories":1480},[109],{"categories":1482},[243],{"categories":1484},[73],{"categories":1486},[],{"categories":1488},[109],{"categories":1490},[112],{"categories":1492},[73],{"categories":1494},[212],{"categories":1496},[],{"categories":1498},[112],{"categories":1500},[112],{"categories":1502},[],{"categories":1504},[73],{"categories":1506},[73],{"categories":1508},[127],{"categories":1510},[],{"categories":1512},[],{"categories":1514},[],{"categories":1516},[],{"categories":1518},[73],{"categories":1520},[117],{"categories":1522},[243],{"categories":1524},[73],{"categories":1526},[109],{"categories":1528},[127],{"categories":1530},[73],{"categories":1532},[73],{"categories":1534},[127],{"categories":1536},[120],{"categories":1538},[73],{"categories":1540},[765],{"categories":1542},[73],{"categories":1544},[212],{"categories":1546},[127],{"categories":1548},[112],{"categories":1550},[73],{"categories":1552},[73],{"categories":1554},[186],{"categories":1556},[73],{"categories":1558},[73],{"categories":1560},[73],{"categories":1562},[117],{"categories":1564},[73,109],{"categories":1566},[392],{"categories":1568},[73],{"categories":1570},[127],{"categories":1572},[127],{"categories":1574},[186],{"categories":1576},[117],{"categories":1578},[127],{"categories":1580},[73],{"categories":1582},[73],{"categories":1584},[],{"categories":1586},[],{"categories":1588},[73],{"categories":1590},[],{"categories":1592},[73],{"categories":1594},[127],{"categories":1596},[189],{"categories":1598},[149],{"categories":1600},[186],{"categories":1602},[73],{"categories":1604},[127],{"categories":1606},[],{"categories":1608},[117],{"categories":1610},[73],{"categories":1612},[73],{"categories":1614},[73],{"categories":1616},[73],{"categories":1618},[],{"categories":1620},[117],{"categories":1622},[73],{"categories":1624},[73],{"categories":1626},[],{"categories":1628},[117],{"categories":1630},[73],{"categories":1632},[73],{"categories":1634},[112],{"categories":1636},[73],{"categories":1638},[],{"categories":1640},[109],{"categories":1642},[73],{"categories":1644},[186],{"categories":1646},[127],{"categories":1648},[73],{"categories":1650},[109],{"categories":1652},[73],{"categories":1654},[127],{"categories":1656},[212],{"categories":1658},[117],{"categories":1660},[117],{"categories":1662},[73,186],{"categories":1664},[73],{"categories":1666},[149],{"categories":1668},[73],{"categories":1670},[149],{"categories":1672},[117],{"categories":1674},[186],{"categories":1676},[],{"categories":1678},[127],{"categories":1680},[243],{"categories":1682},[186],{"categories":1684},[127],{"categories":1686},[73],{"categories":1688},[120],{"categories":1690},[73],{"categories":1692},[117],{"categories":1694},[],{"categories":1696},[],{"categories":1698},[73],{"categories":1700},[],{"categories":1702},[],{"categories":1704},[120],{"categories":1706},[127],{"categories":1708},[73],{"categories":1710},[117],{"categories":1712},[117],{"categories":1714},[112],{"categories":1716},[117],{"categories":1718},[243],{"categories":1720},[73],{"categories":1722},[73],{"categories":1724},[138],{"categories":1726},[73],{"categories":1728},[73],{"categories":1730},[117],{"categories":1732},[73],{"categories":1734},[73],{"categories":1736},[350],{"categories":1738},[744],{"categories":1740},[],{"categories":1742},[186],{"categories":1744},[1460],{"categories":1746},[127],{"categories":1748},[],{"categories":1750},[],{"categories":1752},[117],{"categories":1754},[],{"categories":1756},[],{"categories":1758},[212],{"categories":1760},[212],{"categories":1762},[117],{"categories":1764},[127],{"categories":1766},[],{"categories":1768},[73],{"categories":1770},[73],{"categories":1772},[127],{"categories":1774},[1409],{"categories":1776},[186],{"categories":1778},[186],{"categories":1780},[73],{"categories":1782},[117],{"categories":1784},[109],{"categories":1786},[73],{"categories":1788},[73],{"categories":1790},[186],{"categories":1792},[186],{"categories":1794},[117],{"categories":1796},[117],{"categories":1798},[73],{"categories":1800},[],{"categories":1802},[73],{"categories":1804},[],{"categories":1806},[1807],"Interaction & Product Design",{"categories":1809},[73],{"categories":1811},[117],{"categories":1813},[270],{"categories":1815},[149],{"categories":1817},[127],{"categories":1819},[73],{"categories":1821},[73],{"categories":1823},[127],{"categories":1825},[109],{"categories":1827},[73],{"categories":1829},[],{"categories":1831},[117],{"categories":1833},[117],{"categories":1835},[],{"categories":1837},[127],{"categories":1839},[73],{"categories":1841},[109],{"categories":1843},[1807],{"categories":1845},[73],{"categories":1847},[109],{"categories":1849},[109],{"categories":1851},[],{"categories":1853},[127],{"categories":1855},[],{"categories":1857},[117],{"categories":1859},[149],{"categories":1861},[73],{"categories":1863},[117],{"categories":1865},[73],{"categories":1867},[117],{"categories":1869},[73],{"categories":1871},[149],{"categories":1873},[189],{"categories":1875},[73],{"categories":1877},[120],{"categories":1879},[127],{"categories":1881},[1882],"Coding Agents & Dev Productivity",{"categories":1884},[149],{"categories":1886},[186],{"categories":1888},[],{"categories":1890},[73],{"categories":1892},[744],{"categories":1894},[],{"categories":1896},[73],{"categories":1898},[73],{"categories":1900},[149],{"categories":1902},[],{"categories":1904},[],{"categories":1906},[73],{"categories":1908},[],{"categories":1910},[117],{"categories":1912},[73],{"categories":1914},[],{"categories":1916},[127],{"categories":1918},[127],{"categories":1920},[73],{"categories":1922},[189],{"categories":1924},[],{"categories":1926},[73],{"categories":1928},[73],{"categories":1930},[73],{"categories":1932},[189],{"categories":1934},[127],{"categories":1936},[],{"categories":1938},[],{"categories":1940},[117],{"categories":1942},[117],{"categories":1944},[329],{"categories":1946},[127],{"categories":1948},[127],{"categories":1950},[117],{"categories":1952},[149],{"categories":1954},[149],{"categories":1956},[117],{"categories":1958},[117],{"categories":1960},[73],{"categories":1962},[109],{"categories":1964},[1807],{"categories":1966},[73,243],{"categories":1968},[],{"categories":1970},[186],{"categories":1972},[127],{"categories":1974},[109],{"categories":1976},[73],{"categories":1978},[117],{"categories":1980},[1981],"The Designer's Role & Craft",{"categories":1983},[186],{"categories":1985},[],{"categories":1987},[117],{"categories":1989},[73],{"categories":1991},[117],{"categories":1993},[117],{"categories":1995},[73],{"categories":1997},[212],{"categories":1999},[73],{"categories":2001},[127],{"categories":2003},[186],{"categories":2005},[73],{"categories":2007},[],{"categories":2009},[117],{"categories":2011},[186],{"categories":2013},[73],{"categories":2015},[73],{"categories":2017},[2018],"AI UX Patterns",{"categories":2020},[117],{"categories":2022},[117],{"categories":2024},[117],{"categories":2026},[117],{"categories":2028},[212],{"categories":2030},[189],{"categories":2032},[73],{"categories":2034},[117],{"categories":2036},[73],{"categories":2038},[1014],{"categories":2040},[],{"categories":2042},[212],{"categories":2044},[149],{"categories":2046},[127],{"categories":2048},[73],{"categories":2050},[117],{"categories":2052},[],{"categories":2054},[],{"categories":2056},[73],{"categories":2058},[117],{"categories":2060},[73],{"categories":2062},[117],{"categories":2064},[329],{"categories":2066},[186],{"categories":2068},[149],{"categories":2070},[127],{"categories":2072},[73],{"categories":2074},[117],{"categories":2076},[117],{"categories":2078},[],{"categories":2080},[73],{"categories":2082},[],{"categories":2084},[],{"categories":2086},[73],{"categories":2088},[73],{"categories":2090},[117],{"categories":2092},[127],{"categories":2094},[],{"categories":2096},[],{"categories":2098},[189],{"categories":2100},[138],{"categories":2102},[73],{"categories":2104},[189],{"categories":2106},[149],{"categories":2108},[73],{"categories":2110},[73],{"categories":2112},[117],{"categories":2114},[117],{"categories":2116},[73],{"categories":2118},[117],{"categories":2120},[],{"categories":2122},[],{"categories":2124},[73],{"categories":2126},[243],{"categories":2128},[73],{"categories":2130},[],{"categories":2132},[],{"categories":2134},[186],{"categories":2136},[765],{"categories":2138},[117],{"categories":2140},[109],{"categories":2142},[1981],{"categories":2144},[],{"categories":2146},[],{"categories":2148},[73],{"categories":2150},[],{"categories":2152},[],{"categories":2154},[127],{"categories":2156},[149],{"categories":2158},[212],{"categories":2160},[112],{"categories":2162},[73],{"categories":2164},[73],{"categories":2166},[112],{"categories":2168},[],{"categories":2170},[186],{"categories":2172},[73],{"categories":2174},[117],{"categories":2176},[112],{"categories":2178},[73],{"categories":2180},[73],{"categories":2182},[109],{"categories":2184},[73],{"categories":2186},[],{"categories":2188},[109],{"categories":2190},[73],{"categories":2192},[212],{"categories":2194},[117],{"categories":2196},[149],{"categories":2198},[73],{"categories":2200},[112],{"categories":2202},[73],{"categories":2204},[73],{"categories":2206},[73],{"categories":2208},[117],{"categories":2210},[],{"categories":2212},[73],{"categories":2214},[127],{"categories":2216},[109],{"categories":2218},[73],{"categories":2220},[73],{"categories":2222},[],{"categories":2224},[392],{"categories":2226},[149],{"categories":2228},[73],{"categories":2230},[73],{"categories":2232},[],{"categories":2234},[112],{"categories":2236},[112],{"categories":2238},[73],{"categories":2240},[73],{"categories":2242},[120],{"categories":2244},[73],{"categories":2246},[73],{"categories":2248},[127],{"categories":2250},[127],{"categories":2252},[73],{"categories":2254},[],{"categories":2256},[127],{"categories":2258},[73],{"categories":2260},[127],{"categories":2262},[477],{"categories":2264},[],{"categories":2266},[],{"categories":2268},[73],{"categories":2270},[149],{"categories":2272},[],{"categories":2274},[243],{"categories":2276},[73],{"categories":2278},[73],{"categories":2280},[186],{"categories":2282},[735],{"categories":2284},[],{"categories":2286},[73],{"categories":2288},[73],{"categories":2290},[127],{"categories":2292},[73],{"categories":2294},[73],{"categories":2296},[73,243],{"categories":2298},[73],{"categories":2300},[73],{"categories":2302},[186],{"categories":2304},[117],{"categories":2306},[],{"categories":2308},[117],{"categories":2310},[117],{"categories":2312},[73],{"categories":2314},[73],{"categories":2316},[73],{"categories":2318},[189],{"categories":2320},[73],{"categories":2322},[2018],{"categories":2324},[109],{"categories":2326},[189],{"categories":2328},[109],{"categories":2330},[127],{"categories":2332},[186],{"categories":2334},[117],{"categories":2336},[73],{"categories":2338},[],{"categories":2340},[73],{"categories":2342},[149],{"categories":2344},[73],{"categories":2346},[117],{"categories":2348},[73],{"categories":2350},[73],{"categories":2352},[112],{"categories":2354},[],{"categories":2356},[243],{"categories":2358},[73],{"categories":2360},[329],{"categories":2362},[186],{"categories":2364},[186],{"categories":2366},[127],{"categories":2368},[117],{"categories":2370},[73],{"categories":2372},[112],{"categories":2374},[149],{"categories":2376},[73],{"categories":2378},[186],{"categories":2380},[117],{"categories":2382},[73],{"categories":2384},[73],{"categories":2386},[441],{"categories":2388},[],{"categories":2390},[73],{"categories":2392},[73],{"categories":2394},[73],{"categories":2396},[],{"categories":2398},[],{"categories":2400},[73],{"categories":2402},[73],{"categories":2404},[73],{"categories":2406},[73],{"categories":2408},[127],{"categories":2410},[73],{"categories":2412},[73],{"categories":2414},[117],{"categories":2416},[73],{"categories":2418},[73],{"categories":2420},[73],{"categories":2422},[73],{"categories":2424},[],{"categories":2426},[127],{"categories":2428},[189],{"categories":2430},[73],{"categories":2432},[117],{"categories":2434},[73],{"categories":2436},[],{"categories":2438},[],{"categories":2440},[73],{"categories":2442},[73],{"categories":2444},[73],{"categories":2446},[149],{"categories":2448},[],{"categories":2450},[73],{"categories":2452},[186],{"categories":2454},[73],{"categories":2456},[243],{"categories":2458},[1460],{"categories":2460},[149],{"categories":2462},[127],{"categories":2464},[127],{"categories":2466},[127],{"categories":2468},[149],{"categories":2470},[149],{"categories":2472},[243],{"categories":2474},[],{"categories":2476},[149],{"categories":2478},[73],{"categories":2480},[109],{"categories":2482},[127],{"categories":2484},[73],{"categories":2486},[149],{"categories":2488},[],{"categories":2490},[73],{"categories":2492},[127],{"categories":2494},[189],{"categories":2496},[73],{"categories":2498},[149],{"categories":2500},[73],{"categories":2502},[127],{"categories":2504},[117],{"categories":2506},[149],{"categories":2508},[117],{"categories":2510},[243],{"categories":2512},[117],{"categories":2514},[73],{"categories":2516},[73],{"categories":2518},[127],{"categories":2520},[73],{"categories":2522},[],{"categories":2524},[112],{"categories":2526},[127],{"categories":2528},[],{"categories":2530},[],{"categories":2532},[73],{"categories":2534},[117],{"categories":2536},[73],{"categories":2538},[2539],"Frameworks & Tooling",{"categories":2541},[73],{"categories":2543},[73],{"categories":2545},[127],{"categories":2547},[73],{"categories":2549},[73],{"categories":2551},[],{"categories":2553},[189],{"categories":2555},[189],{"categories":2557},[109],{"categories":2559},[117],{"categories":2561},[186],{"categories":2563},[],{"categories":2565},[1460],{"categories":2567},[73],{"categories":2569},[127],{"categories":2571},[73],{"categories":2573},[243],{"categories":2575},[243],{"categories":2577},[],{"categories":2579},[117],{"categories":2581},[149],{"categories":2583},[149],{"categories":2585},[73],{"categories":2587},[117],{"categories":2589},[],{"categories":2591},[186],{"categories":2593},[73],{"categories":2595},[73],{"categories":2597},[],{"categories":2599},[73],{"categories":2601},[],{"categories":2603},[127],{"categories":2605},[73],{"categories":2607},[127],{"categories":2609},[243],{"categories":2611},[73],{"categories":2613},[127],{"categories":2615},[112],{"categories":2617},[73],{"categories":2619},[1460],{"categories":2621},[],{"categories":2623},[117],{"categories":2625},[109],{"categories":2627},[109],{"categories":2629},[],{"categories":2631},[117],{"categories":2633},[73],{"categories":2635},[2636],"AI Design Tooling",{"categories":2638},[186],{"categories":2640},[73],{"categories":2642},[73],{"categories":2644},[127],{"categories":2646},[186],{"categories":2648},[73],{"categories":2650},[127],{"categories":2652},[149],{"categories":2654},[120],{"categories":2656},[127],{"categories":2658},[117],{"categories":2660},[],{"categories":2662},[73],{"categories":2664},[73],{"categories":2666},[117],{"categories":2668},[73],{"categories":2670},[73],{"categories":2672},[],{"categories":2674},[117],{"categories":2676},[2539],{"categories":2678},[73],{"categories":2680},[117],{"categories":2682},[117],{"categories":2684},[127],{"categories":2686},[127],{"categories":2688},[],{"categories":2690},[127],{"categories":2692},[73],{"categories":2694},[73],{"categories":2696},[117],{"categories":2698},[112],{"categories":2700},[73],{"categories":2702},[],{"categories":2704},[73],{"categories":2706},[1807],{"categories":2708},[],{"categories":2710},[73],{"categories":2712},[73],{"categories":2714},[],{"categories":2716},[73],{"categories":2718},[73],{"categories":2720},[73],{"categories":2722},[212],{"categories":2724},[149],{"categories":2726},[73],{"categories":2728},[73],{"categories":2730},[1460],{"categories":2732},[109],{"categories":2734},[73],{"categories":2736},[73],{"categories":2738},[189],{"categories":2740},[73],{"categories":2742},[149],{"categories":2744},[117],{"categories":2746},[],{"categories":2748},[73],{"categories":2750},[186],{"categories":2752},[73],{"categories":2754},[212],{"categories":2756},[73],{"categories":2758},[117],{"categories":2760},[],{"categories":2762},[],{"categories":2764},[],{"categories":2766},[109],{"categories":2768},[149],{"categories":2770},[117],{"categories":2772},[73],{"categories":2774},[73],{"categories":2776},[73],{"categories":2778},[350],{"categories":2780},[186],{"categories":2782},[117],{"categories":2784},[73],{"categories":2786},[],{"categories":2788},[117],{"categories":2790},[117],{"categories":2792},[],{"categories":2794},[73],{"categories":2796},[117],{"categories":2798},[73],{"categories":2800},[],{"categories":2802},[73],{"categories":2804},[73],{"categories":2806},[149],{"categories":2808},[186],{"categories":2810},[117],{"categories":2812},[186],{"categories":2814},[117],{"categories":2816},[112],{"categories":2818},[],{"categories":2820},[],{"categories":2822},[73],{"categories":2824},[73],{"categories":2826},[109],{"categories":2828},[117],{"categories":2830},[149],{"categories":2832},[],{"categories":2834},[186],{"categories":2836},[],{"categories":2838},[127],{"categories":2840},[127],{"categories":2842},[186],{"categories":2844},[127],{"categories":2846},[73],{"categories":2848},[],{"categories":2850},[73],{"categories":2852},[73],{"categories":2854},[],{"categories":2856},[212],{"categories":2858},[73],{"categories":2860},[243],{"categories":2862},[127],{"categories":2864},[],{"categories":2866},[117],{"categories":2868},[73],{"categories":2870},[109],{"categories":2872},[441],{"categories":2874},[117],{"categories":2876},[117],{"categories":2878},[73],{"categories":2880},[73],{"categories":2882},[],{"categories":2884},[109],{"categories":2886},[73],{"categories":2888},[112],{"categories":2890},[127],{"categories":2892},[186],{"categories":2894},[],{"categories":2896},[],{"categories":2898},[],{"categories":2900},[117],{"categories":2902},[127],{"categories":2904},[186],{"categories":2906},[149],{"categories":2908},[73],{"categories":2910},[149],{"categories":2912},[117],{"categories":2914},[186],{"categories":2916},[73],{"categories":2918},[],{"categories":2920},[73],{"categories":2922},[138],{"categories":2924},[117],{"categories":2926},[186],{"categories":2928},[149],{"categories":2930},[112],{"categories":2932},[127],{"categories":2934},[73],{"categories":2936},[149],{"categories":2938},[212],{"categories":2940},[],{"categories":2942},[],{"categories":2944},[189],{"categories":2946},[392],{"categories":2948},[73],{"categories":2950},[117],{"categories":2952},[73,127],{"categories":2954},[149],{"categories":2956},[73],{"categories":2958},[73],{"categories":2960},[117],{"categories":2962},[73],{"categories":2964},[117],{"categories":2966},[73],{"categories":2968},[73],{"categories":2970},[],{"categories":2972},[1014],{"categories":2974},[127],{"categories":2976},[186],{"categories":2978},[73],{"categories":2980},[73],{"categories":2982},[73],{"categories":2984},[189],{"categories":2986},[117],{"categories":2988},[212],{"categories":2990},[243],{"categories":2992},[],{"categories":2994},[73],{"categories":2996},[112],{"categories":2998},[117],{"categories":3000},[109],{"categories":3002},[117],{"categories":3004},[73],{"categories":3006},[117],{"categories":3008},[120],{"categories":3010},[127],{"categories":3012},[73],{"categories":3014},[73],{"categories":3016},[],{"categories":3018},[],{"categories":3020},[],{"categories":3022},[243],{"categories":3024},[73],{"categories":3026},[149],{"categories":3028},[73],{"categories":3030},[73],{"categories":3032},[73],{"categories":3034},[73],{"categories":3036},[],{"categories":3038},[189],{"categories":3040},[112],{"categories":3042},[117],{"categories":3044},[73],{"categories":3046},[],{"categories":3048},[73],{"categories":3050},[117],{"categories":3052},[73],{"categories":3054},[243],{"categories":3056},[],{"categories":3058},[186],{"categories":3060},[186],{"categories":3062},[],{"categories":3064},[127],{"categories":3066},[73],{"categories":3068},[186],{"categories":3070},[73],{"categories":3072},[112],{"categories":3074},[117],{"categories":3076},[73],{"categories":3078},[],{"categories":3080},[149],{"categories":3082},[73],{"categories":3084},[73],{"categories":3086},[73],{"categories":3088},[186],{"categories":3090},[117],{"categories":3092},[149],{"categories":3094},[],{"categories":3096},[117],{"categories":3098},[117],{"categories":3100},[186],{"categories":3102},[73],{"categories":3104},[73],{"categories":3106},[73],{"categories":3108},[392],{"categories":3110},[73],{"categories":3112},[],{"categories":3114},[73],{"categories":3116},[73],{"categories":3118},[243],{"categories":3120},[149],{"categories":3122},[189],{"categories":3124},[477],{"categories":3126},[189],{"categories":3128},[],{"categories":3130},[],{"categories":3132},[],{"categories":3134},[117],{"categories":3136},[117],{"categories":3138},[127],{"categories":3140},[73],{"categories":3142},[375],{"categories":3144},[127],{"categories":3146},[73],{"categories":3148},[73],{"categories":3150},[73],{"categories":3152},[73],{"categories":3154},[117],{"categories":3156},[],{"categories":3158},[],{"categories":3160},[73],{"categories":3162},[],{"categories":3164},[73],{"categories":3166},[117],{"categories":3168},[186],{"categories":3170},[73],{"categories":3172},[73],{"categories":3174},[],{"categories":3176},[120],{"categories":3178},[73],{"categories":3180},[186],{"categories":3182},[73],{"categories":3184},[117],{"categories":3186},[112],{"categories":3188},[73],{"categories":3190},[212],{"categories":3192},[117],{"categories":3194},[73],{"categories":3196},[735],{"categories":3198},[73],{"categories":3200},[117],{"categories":3202},[73],{"categories":3204},[127],{"categories":3206},[73],{"categories":3208},[441],{"categories":3210},[186],{"categories":3212},[],{"categories":3214},[149],{"categories":3216},[392],{"categories":3218},[117],{"categories":3220},[73],{"categories":3222},[],{"categories":3224},[149],{"categories":3226},[329],{"categories":3228},[117],{"categories":3230},[117],{"categories":3232},[73],{"categories":3234},[73],{"categories":3236},[117],{"categories":3238},[],{"categories":3240},[112],{"categories":3242},[117],{"categories":3244},[],{"categories":3246},[127],{"categories":3248},[73],{"categories":3250},[109],{"categories":3252},[149],{"categories":3254},[243],{"categories":3256},[138],{"categories":3258},[117],{"categories":3260},[117],{"categories":3262},[73],{"categories":3264},[117],{"categories":3266},[109],{"categories":3268},[],{"categories":3270},[73],{"categories":3272},[73],{"categories":3274},[],{"categories":3276},[],{"categories":3278},[186],{"categories":3280},[73,112],{"categories":3282},[117],{"categories":3284},[73],{"categories":3286},[],{"categories":3288},[109],{"categories":3290},[189],{"categories":3292},[112],{"categories":3294},[73],{"categories":3296},[127],{"categories":3298},[73],{"categories":3300},[117],{"categories":3302},[73],{"categories":3304},[73],{"categories":3306},[73],{"categories":3308},[149],{"categories":3310},[1014],{"categories":3312},[117],{"categories":3314},[73],{"categories":3316},[],{"categories":3318},[],{"categories":3320},[117],{"categories":3322},[73],{"categories":3324},[243],{"categories":3326},[],{"categories":3328},[73],{"categories":3330},[117],{"categories":3332},[138],{"categories":3334},[117],{"categories":3336},[392],{"categories":3338},[],{"categories":3340},[350],{"categories":3342},[117],{"categories":3344},[73],{"categories":3346},[212],{"categories":3348},[73],{"categories":3350},[189],{"categories":3352},[117],{"categories":3354},[73],{"categories":3356},[392],{"categories":3358},[73],{"categories":3360},[243],{"categories":3362},[],{"categories":3364},[73],{"categories":3366},[212],{"categories":3368},[186],{"categories":3370},[73],{"categories":3372},[73],{"categories":3374},[],{"categories":3376},[212],{"categories":3378},[149],{"categories":3380},[73],{"categories":3382},[73],{"categories":3384},[477],{"categories":3386},[109],{"categories":3388},[73],{"categories":3390},[],{"categories":3392},[],{"categories":3394},[186],{"categories":3396},[73],{"categories":3398},[189],{"categories":3400},[212],{"categories":3402},[117],{"categories":3404},[212],{"categories":3406},[149],{"categories":3408},[],{"categories":3410},[73],{"categories":3412},[],{"categories":3414},[73],{"categories":3416},[496],{"categories":3418},[73],{"categories":3420},[73],{"categories":3422},[117],{"categories":3424},[392],{"categories":3426},[73],{"categories":3428},[73],{"categories":3430},[73],{"categories":3432},[],{"categories":3434},[73,127],{"categories":3436},[149],{"categories":3438},[117],{"categories":3440},[127],{"categories":3442},[117],{"categories":3444},[765],{"categories":3446},[127],{"categories":3448},[73],{"categories":3450},[109],{"categories":3452},[],{"categories":3454},[],{"categories":3456},[117],{"categories":3458},[73],{"categories":3460},[127],{"categories":3462},[109],{"categories":3464},[127],{"categories":3466},[127],{"categories":3468},[73],{"categories":3470},[212],{"categories":3472},[73],{"categories":3474},[127],{"categories":3476},[],{"categories":3478},[73],{"categories":3480},[186,73],{"categories":3482},[243],{"categories":3484},[109],{"categories":3486},[],{"categories":3488},[73],{"categories":3490},[73],{"categories":3492},[112],{"categories":3494},[112],{"categories":3496},[73],{"categories":3498},[73],{"categories":3500},[329],{"categories":3502},[73],{"categories":3504},[127],{"categories":3506},[189],{"categories":3508},[117],{"categories":3510},[73],{"categories":3512},[73],{"categories":3514},[149],{"categories":3516},[212],{"categories":3518},[186],{"categories":3520},[73],{"categories":3522},[73],{"categories":3524},[73],{"categories":3526},[73],{"categories":3528},[109],{"categories":3530},[73],{"categories":3532},[117],{"categories":3534},[117],{"categories":3536},[127],{"categories":3538},[149],{"categories":3540},[127],{"categories":3542},[],{"categories":3544},[],{"categories":3546},[189],{"categories":3548},[73],{"categories":3550},[127],{"categories":3552},[73],{"categories":3554},[186],{"categories":3556},[392],{"categories":3558},[350],{"categories":3560},[329],{"categories":3562},[73],{"categories":3564},[73],{"categories":3566},[73],{"categories":3568},[189],{"categories":3570},[73],{"categories":3572},[73],{"categories":3574},[73],{"categories":3576},[117],{"categories":3578},[109],{"categories":3580},[117],{"categories":3582},[73,112],{"categories":3584},[],{"categories":3586},[186],{"categories":3588},[],{"categories":3590},[120],{"categories":3592},[73],{"categories":3594},[149],{"categories":3596},[109],{"categories":3598},[109],{"categories":3600},[117],{"categories":3602},[117],{"categories":3604},[117],{"categories":3606},[73],{"categories":3608},[73],{"categories":3610},[112],{"categories":3612},[127],{"categories":3614},[212],{"categories":3616},[73],{"categories":3618},[],{"categories":3620},[149],{"categories":3622},[73],{"categories":3624},[73],{"categories":3626},[73],{"categories":3628},[73],{"categories":3630},[73],{"categories":3632},[127],{"categories":3634},[149],{"categories":3636},[127],{"categories":3638},[127],{"categories":3640},[73],{"categories":3642},[73],{"categories":3644},[350],{"categories":3646},[73],{"categories":3648},[117],{"categories":3650},[149],{"categories":3652},[73],{"categories":3654},[73],{"categories":3656},[73],{"categories":3658},[117],{"categories":3660},[73],{"categories":3662},[73],{"categories":3664},[73],{"categories":3666},[2539],{"categories":3668},[3669],"Clinical AI",{"categories":3671},[186],{"categories":3673},[73],{"categories":3675},[73],{"categories":3677},[73],{"categories":3679},[243],{"categories":3681},[2018],{"categories":3683},[73],{"categories":3685},[120],{"categories":3687},[73],{"categories":3689},[117],{"categories":3691},[73],{"categories":3693},[73],{"categories":3695},[149],{"categories":3697},[73],{"categories":3699},[117],{"categories":3701},[212],{"categories":3703},[73],{"categories":3705},[73],{"categories":3707},[112],{"categories":3709},[73],{"categories":3711},[441],{"categories":3713},[73],{"categories":3715},[],{"categories":3717},[73],{"categories":3719},[127],{"categories":3721},[73],{"categories":3723},[],{"categories":3725},[],{"categories":3727},[73],{"categories":3729},[],{"categories":3731},[112],{"categories":3733},[73],{"categories":3735},[117],{"categories":3737},[149],{"categories":3739},[149],{"categories":3741},[149],{"categories":3743},[149],{"categories":3745},[],{"categories":3747},[109],{"categories":3749},[117],{"categories":3751},[149],{"categories":3753},[73],{"categories":3755},[496],{"categories":3757},[120],{"categories":3759},[73],{"categories":3761},[109],{"categories":3763},[117],{"categories":3765},[73],{"categories":3767},[73],{"categories":3769},[73,117],{"categories":3771},[117],{"categories":3773},[243],{"categories":3775},[149],{"categories":3777},[117],{"categories":3779},[149],{"categories":3781},[117],{"categories":3783},[73],{"categories":3785},[],{"categories":3787},[149],{"categories":3789},[212],{"categories":3791},[109],{"categories":3793},[73],{"categories":3795},[73],{"categories":3797},[],{"categories":3799},[127],{"categories":3801},[],{"categories":3803},[109],{"categories":3805},[117],{"categories":3807},[149],{"categories":3809},[73],{"categories":3811},[149],{"categories":3813},[109],{"categories":3815},[149],{"categories":3817},[149],{"categories":3819},[],{"categories":3821},[112],{"categories":3823},[117],{"categories":3825},[149],{"categories":3827},[149],{"categories":3829},[149],{"categories":3831},[149],{"categories":3833},[149],{"categories":3835},[149],{"categories":3837},[149],{"categories":3839},[149],{"categories":3841},[149],{"categories":3843},[149],{"categories":3845},[189],{"categories":3847},[109],{"categories":3849},[73],{"categories":3851},[73],{"categories":3853},[117],{"categories":3855},[117],{"categories":3857},[],{"categories":3859},[73,109],{"categories":3861},[],{"categories":3863},[117],{"categories":3865},[149],{"categories":3867},[117],{"categories":3869},[765],{"categories":3871},[73],{"categories":3873},[73],{"categories":3875},[73],{"categories":3877},[73],{"categories":3879},[329],{"categories":3881},[73],{"categories":3883},[117],{"categories":3885},[112],{"categories":3887},[117],{"categories":3889},[117],{"categories":3891},[],{"categories":3893},[117],{"categories":3895},[186],{"categories":3897},[149],{"categories":3899},[73],{"categories":3901},[],{"categories":3903},[],{"categories":3905},[117],{"categories":3907},[186],{"categories":3909},[73],{"categories":3911},[],{"categories":3913},[73],{"categories":3915},[],{"categories":3917},[212],{"categories":3919},[73],{"categories":3921},[],{"categories":3923},[],{"categories":3925},[149],{"categories":3927},[109],{"categories":3929},[73],{"categories":3931},[73],{"categories":3933},[112],{"categories":3935},[73],{"categories":3937},[73],{"categories":3939},[73],{"categories":3941},[112],{"categories":3943},[186],{"categories":3945},[],{"categories":3947},[73],{"categories":3949},[149],{"categories":3951},[],{"categories":3953},[73],{"categories":3955},[73],{"categories":3957},[186],{"categories":3959},[73],{"categories":3961},[212],{"categories":3963},[73],{"categories":3965},[243],{"categories":3967},[],{"categories":3969},[117],{"categories":3971},[212],{"categories":3973},[127],{"categories":3975},[],{"categories":3977},[73],{"categories":3979},[],{"categories":3981},[117],{"categories":3983},[186],{"categories":3985},[127],{"categories":3987},[],{"categories":3989},[2539],{"categories":3991},[112],{"categories":3993},[109],{"categories":3995},[189],{"categories":3997},[117],{"categories":3999},[186],{"categories":4001},[127],{"categories":4003},[],{"categories":4005},[],{"categories":4007},[73],{"categories":4009},[109],{"categories":4011},[73],{"categories":4013},[212],{"categories":4015},[],{"categories":4017},[117],{"categories":4019},[117],{"categories":4021},[117],{"categories":4023},[73],{"categories":4025},[149],{"categories":4027},[127],{"categories":4029},[73],{"categories":4031},[117],{"categories":4033},[120],{"categories":4035},[73],{"categories":4037},[117],{"categories":4039},[73],{"categories":4041},[120],{"categories":4043},[212],{"categories":4045},[149],{"categories":4047},[],{"categories":4049},[212],{"categories":4051},[],{"categories":4053},[127],{"categories":4055},[117],{"categories":4057},[],{"categories":4059},[73],{"categories":4061},[73],{"categories":4063},[73],{"categories":4065},[73],{"categories":4067},[117],{"categories":4069},[112],{"categories":4071},[109],{"categories":4073},[73],{"categories":4075},[186],{"categories":4077},[127],{"categories":4079},[127],{"categories":4081},[73],{"categories":4083},[189],{"categories":4085},[117],{"categories":4087},[73],{"categories":4089},[117],{"categories":4091},[73],{"categories":4093},[112],{"categories":4095},[186],{"categories":4097},[127],{"categories":4099},[117],{"categories":4101},[73],{"categories":4103},[120],{"categories":4105},[73],{"categories":4107},[117],{"categories":4109},[73],{"categories":4111},[149],{"categories":4113},[],{"categories":4115},[109],{"categories":4117},[73],{"categories":4119},[73],{"categories":4121},[73],{"categories":4123},[127],{"categories":4125},[73],{"categories":4127},[127],{"categories":4129},[73],{"categories":4131},[117],{"categories":4133},[73],{"categories":4135},[73],{"categories":4137},[73],{"categories":4139},[73],{"categories":4141},[],{"categories":4143},[73],{"categories":4145},[186],{"categories":4147},[112],{"categories":4149},[149],{"categories":4151},[117],{"categories":4153},[73],{"categories":4155},[73],{"categories":4157},[186],{"categories":4159},[117],{"categories":4161},[73],{"categories":4163},[212],{"categories":4165},[73],{"categories":4167},[189],{"categories":4169},[73],{"categories":4171},[73],{"categories":4173},[149],{"categories":4175},[73],{"categories":4177},[73],{"categories":4179},[117],{"categories":4181},[243],{"categories":4183},[73],{"categories":4185},[127],{"categories":4187},[117],{"categories":4189},[189],{"categories":4191},[],{"categories":4193},[117],{"categories":4195},[127],{"categories":4197},[73],{"categories":4199},[1882],{"categories":4201},[186],{"categories":4203},[270],{"categories":4205},[73],{"categories":4207},[109],{"categories":4209},[127],{"categories":4211},[112],{"categories":4213},[127],{"categories":4215},[73],{"categories":4217},[],{"categories":4219},[117],{"categories":4221},[117],{"categories":4223},[73],{"categories":4225},[73],{"categories":4227},[189],{"categories":4229},[],{"categories":4231},[149],{"categories":4233},[],{"categories":4235},[149],{"categories":4237},[73],{"categories":4239},[73],{"categories":4241},[117],{"categories":4243},[117],{"categories":4245},[117],{"categories":4247},[],{"categories":4249},[149],{"categories":4251},[73],{"categories":4253},[],{"categories":4255},[73],{"categories":4257},[73],{"categories":4259},[],{"categories":4261},[186],{"categories":4263},[127],{"categories":4265},[117],{"categories":4267},[73],{"categories":4269},[73],{"categories":4271},[212],{"categories":4273},[73],{"categories":4275},[73],{"categories":4277},[109],{"categories":4279},[],{"categories":4281},[73],{"categories":4283},[73],{"categories":4285},[],{"categories":4287},[109],{"categories":4289},[149],{"categories":4291},[127],{"categories":4293},[392],{"categories":4295},[73],{"categories":4297},[73],{"categories":4299},[73],{"categories":4301},[127],{"categories":4303},[149],{"categories":4305},[186],{"categories":4307},[73],{"categories":4309},[73],{"categories":4311},[73],{"categories":4313},[149],{"categories":4315},[186],{"categories":4317},[73],{"categories":4319},[149],{"categories":4321},[186],{"categories":4323},[73],{"categories":4325},[149],{"categories":4327},[117],{"categories":4329},[117],{"categories":4331},[117],{"categories":4333},[127],{"categories":4335},[149],{"categories":4337},[117],{"categories":4339},[117],{"categories":4341},[73],{"categories":4343},[127],{"categories":4345},[186],{"categories":4347},[73],{"categories":4349},[],{"categories":4351},[117],{"categories":4353},[],{"categories":4355},[],{"categories":4357},[],{"categories":4359},[117],{"categories":4361},[112],{"categories":4363},[117],{"categories":4365},[4366],"Liability & Ethics",{"categories":4368},[73],{"categories":4370},[117],{"categories":4372},[109],{"categories":4374},[117],{"categories":4376},[112],{"categories":4378},[212],{"categories":4380},[117],{"categories":4382},[],{"categories":4384},[477],{"categories":4386},[117],{"categories":4388},[],{"categories":4390},[109],{"categories":4392},[117],{"categories":4394},[],{"categories":4396},[117],{"categories":4398},[73],{"categories":4400},[73],{"categories":4402},[149],{"categories":4404},[73],{"categories":4406},[73],{"categories":4408},[117],{"categories":4410},[73],{"categories":4412},[73],{"categories":4414},[149],{"categories":4416},[117],{"categories":4418},[127],{"categories":4420},[186],{"categories":4422},[109],{"categories":4424},[73],{"categories":4426},[],{"categories":4428},[117],{"categories":4430},[117],{"categories":4432},[392],{"categories":4434},[186],{"categories":4436},[243],{"categories":4438},[149],{"categories":4440},[73],{"categories":4442},[186],{"categories":4444},[73],{"categories":4446},[109],{"categories":4448},[],{"categories":4450},[117],{"categories":4452},[73],{"categories":4454},[73],{"categories":4456},[117],{"categories":4458},[73],{"categories":4460},[186],{"categories":4462},[],{"categories":4464},[117],{"categories":4466},[120],{"categories":4468},[149],{"categories":4470},[117],{"categories":4472},[112],{"categories":4474},[],{"categories":4476},[73],{"categories":4478},[120],{"categories":4480},[73],{"categories":4482},[117],{"categories":4484},[149],{"categories":4486},[109],{"categories":4488},[243],{"categories":4490},[73],{"categories":4492},[73],{"categories":4494},[73],{"categories":4496},[149],{"categories":4498},[112],{"categories":4500},[73],{"categories":4502},[186],{"categories":4504},[149],{"categories":4506},[243],{"categories":4508},[73],{"categories":4510},[117],{"categories":4512},[],{"categories":4514},[441],{"categories":4516},[],{"categories":4518},[73],{"categories":4520},[243],{"categories":4522},[189],{"categories":4524},[117],{"categories":4526},[117],{"categories":4528},[4529],"Design News & Tools",{"categories":4531},[73],{"categories":4533},[149],{"categories":4535},[73],{"categories":4537},[109],{"categories":4539},[73],{"categories":4541},[186],{"categories":4543},[117],{"categories":4545},[117],{"categories":4547},[73],{"categories":4549},[392],{"categories":4551},[73],{"categories":4553},[392],{"categories":4555},[212],{"categories":4557},[73],{"categories":4559},[117],{"categories":4561},[],{"categories":4563},[73],{"categories":4565},[73],{"categories":4567},[73],{"categories":4569},[149],{"categories":4571},[109],{"categories":4573},[],{"categories":4575},[73],{"categories":4577},[73],{"categories":4579},[127],{"categories":4581},[496],{"categories":4583},[127],{"categories":4585},[186],{"categories":4587},[73],{"categories":4589},[73,117],{"categories":4591},[212,112],{"categories":4593},[73],{"categories":4595},[73],{"categories":4597},[73],{"categories":4599},[],{"categories":4601},[117],{"categories":4603},[],{"categories":4605},[127],{"categories":4607},[73],{"categories":4609},[127],{"categories":4611},[],{"categories":4613},[117],{"categories":4615},[73],{"categories":4617},[149],{"categories":4619},[73],{"categories":4621},[],{"categories":4623},[117],{"categories":4625},[73],{"categories":4627},[],{"categories":4629},[186],{"categories":4631},[73],{"categories":4633},[117],{"categories":4635},[73],{"categories":4637},[73],{"categories":4639},[109],{"categories":4641},[117],{"categories":4643},[73],{"categories":4645},[],{"categories":4647},[243],{"categories":4649},[212],{"categories":4651},[112],{"categories":4653},[112],{"categories":4655},[73],{"categories":4657},[109],{"categories":4659},[109],{"categories":4661},[73],{"categories":4663},[117],{"categories":4665},[73],{"categories":4667},[73],{"categories":4669},[73],{"categories":4671},[127],{"categories":4673},[73],{"categories":4675},[109],{"categories":4677},[117],{"categories":4679},[73],{"categories":4681},[212],{"categories":4683},[73],{"categories":4685},[149],{"categories":4687},[73],{"categories":4689},[73],{"categories":4691},[117],{"categories":4693},[73],{"categories":4695},[],{"categories":4697},[127],{"categories":4699},[],{"categories":4701},[127],{"categories":4703},[117],{"categories":4705},[109],{"categories":4707},[],{"categories":4709},[189],{"categories":4711},[243],{"categories":4713},[73],{"categories":4715},[127],{"categories":4717},[73],{"categories":4719},[],{"categories":4721},[149],{"categories":4723},[117],{"categories":4725},[127],{"categories":4727},[186],{"categories":4729},[73],{"categories":4731},[117],{"categories":4733},[127],{"categories":4735},[117],{"categories":4737},[149],{"categories":4739},[73],{"categories":4741},[109],{"categories":4743},[149],{"categories":4745},[127],{"categories":4747},[73],{"categories":4749},[186],{"categories":4751},[112],{"categories":4753},[73],{"categories":4755},[73],{"categories":4757},[73],{"categories":4759},[73],{"categories":4761},[73],{"categories":4763},[117],{"categories":4765},[73],{"categories":4767},[117],{"categories":4769},[73],{"categories":4771},[73],{"categories":4773},[109],{"categories":4775},[73],{"categories":4777},[117],{"categories":4779},[117],{"categories":4781},[186],{"categories":4783},[117],{"categories":4785},[117],{"categories":4787},[109],{"categories":4789},[117],{"categories":4791},[186],{"categories":4793},[],{"categories":4795},[73],{"categories":4797},[189],{"categories":4799},[392],{"categories":4801},[73],{"categories":4803},[73],{"categories":4805},[73],{"categories":4807},[127],{"categories":4809},[],{"categories":4811},[117],{"categories":4813},[212],{"categories":4815},[73],{"categories":4817},[149],{"categories":4819},[117],{"categories":4821},[73],{"categories":4823},[212],{"categories":4825},[117],{"categories":4827},[112],{"categories":4829},[112],{"categories":4831},[73],{"categories":4833},[73],{"categories":4835},[73],{"categories":4837},[109],{"categories":4839},[],{"categories":4841},[73],{"categories":4843},[117],{"categories":4845},[117],{"categories":4847},[73],{"categories":4849},[73],{"categories":4851},[73],{"categories":4853},[127],{"categories":4855},[],{"categories":4857},[109],{"categories":4859},[73],{"categories":4861},[73],{"categories":4863},[117],{"categories":4865},[117],{"categories":4867},[],{"categories":4869},[127],{"categories":4871},[127],{"categories":4873},[73],{"categories":4875},[212],{"categories":4877},[112],{"categories":4879},[186],{"categories":4881},[],{"categories":4883},[73],{"categories":4885},[117],{"categories":4887},[109],{"categories":4889},[73],{"categories":4891},[127],{"categories":4893},[109],{"categories":4895},[149],{"categories":4897},[189],{"categories":4899},[149],{"categories":4901},[117],{"categories":4903},[],{"categories":4905},[149],{"categories":4907},[117],{"categories":4909},[186],{"categories":4911},[189],{"categories":4913},[73],{"categories":4915},[],{"categories":4917},[117],{"categories":4919},[2539],{"categories":4921},[149],{"categories":4923},[127],{"categories":4925},[73],{"categories":4927},[73],{"categories":4929},[112],{"categories":4931},[73],{"categories":4933},[109],{"categories":4935},[1460],{"categories":4937},[243],{"categories":4939},[109],{"categories":4941},[],{"categories":4943},[],{"categories":4945},[149],{"categories":4947},[117],{"categories":4949},[149],{"categories":4951},[],{"categories":4953},[117],{"categories":4955},[117],{"categories":4957},[117],{"categories":4959},[],{"categories":4961},[73],{"categories":4963},[],{"categories":4965},[149],{"categories":4967},[109],{"categories":4969},[186],{"categories":4971},[73],{"categories":4973},[117],{"categories":4975},[149],{"categories":4977},[73],{"categories":4979},[149],{"categories":4981},[],{"categories":4983},[149],{"categories":4985},[109],{"categories":4987},[392],{"categories":4989},[117],{"categories":4991},[73],{"categories":4993},[],{"categories":4995},[127],{"categories":4997},[117],{"categories":4999},[120],{"categories":5001},[117],{"categories":5003},[109],{"categories":5005},[],{"categories":5007},[],{"categories":5009},[],{"categories":5011},[186],{"categories":5013},[117],{"categories":5015},[73],{"categories":5017},[73],{"categories":5019},[],{"categories":5021},[],{"categories":5023},[],{"categories":5025},[186],{"categories":5027},[73],{"categories":5029},[],{"categories":5031},[117],{"categories":5033},[73],{"categories":5035},[109],{"categories":5037},[],{"categories":5039},[],{"categories":5041},[186],{"categories":5043},[73],{"categories":5045},[149],{"categories":5047},[],{"categories":5049},[212],{"categories":5051},[149],{"categories":5053},[212],{"categories":5055},[189],{"categories":5057},[73],{"categories":5059},[73],{"categories":5061},[],{"categories":5063},[],{"categories":5065},[117],{"categories":5067},[],{"categories":5069},[73],{"categories":5071},[392],{"categories":5073},[73],{"categories":5075},[73],{"categories":5077},[73],{"categories":5079},[],{"categories":5081},[117],{"categories":5083},[73],{"categories":5085},[73],{"categories":5087},[],{"categories":5089},[117],{"categories":5091},[73],{"categories":5093},[149],{"categories":5095},[73],{"categories":5097},[212],{"categories":5099},[112],{"categories":5101},[73],{"categories":5103},[73],{"categories":5105},[117],{"categories":5107},[189],{"categories":5109},[117],{"categories":5111},[117],{"categories":5113},[],{"categories":5115},[],{"categories":5117},[73],{"categories":5119},[],{"categories":5121},[149],{"categories":5123},[112],{"categories":5125},[],{"categories":5127},[],{"categories":5129},[186],{"categories":5131},[109],{"categories":5133},[],{"categories":5135},[112],{"categories":5137},[212],{"categories":5139},[73],{"categories":5141},[127],{"categories":5143},[109],{"categories":5145},[189],{"categories":5147},[112],{"categories":5149},[127],{"categories":5151},[127],{"categories":5153},[],{"categories":5155},[73],{"categories":5157},[],{"categories":5159},[117],{"categories":5161},[109],{"categories":5163},[186],{"categories":5165},[73],{"categories":5167},[109],{"categories":5169},[117],{"categories":5171},[243],{"categories":5173},[73],{"categories":5175},[73],{"categories":5177},[73],{"categories":5179},[109],{"categories":5181},[189],{"categories":5183},[117],{"categories":5185},[],{"categories":5187},[73],{"categories":5189},[127],{"categories":5191},[149],{"categories":5193},[127],{"categories":5195},[73],{"categories":5197},[120],{"categories":5199},[],{"categories":5201},[186],{"categories":5203},[149],{"categories":5205},[109],{"categories":5207},[117],{"categories":5209},[73],{"categories":5211},[73],{"categories":5213},[117],{"categories":5215},[73],{"categories":5217},[73],{"categories":5219},[112],{"categories":5221},[117],{"categories":5223},[117,243],{"categories":5225},[117],{"categories":5227},[127],{"categories":5229},[73],{"categories":5231},[73],{"categories":5233},[189],{"categories":5235},[117],{"categories":5237},[212],{"categories":5239},[117],{"categories":5241},[112],{"categories":5243},[],{"categories":5245},[117],{"categories":5247},[73],{"categories":5249},[112],{"categories":5251},[],{"categories":5253},[],{"categories":5255},[127],{"categories":5257},[73],{"categories":5259},[73],{"categories":5261},[117],{"categories":5263},[189],{"categories":5265},[212],{"categories":5267},[73],{"categories":5269},[73],{"categories":5271},[117],{"categories":5273},[],{"categories":5275},[117],{"categories":5277},[149],{"categories":5279},[117],{"categories":5281},[],{"categories":5283},[149],{"categories":5285},[127],{"categories":5287},[2539],{"categories":5289},[109],{"categories":5291},[127],{"categories":5293},[73],{"categories":5295},[117],{"categories":5297},[73],{"categories":5299},[73],{"categories":5301},[212],{"categories":5303},[127],{"categories":5305},[],{"categories":5307},[149],{"categories":5309},[73],{"categories":5311},[],{"categories":5313},[117],{"categories":5315},[73],{"categories":5317},[73],{"categories":5319},[73],{"categories":5321},[117],{"categories":5323},[73],{"categories":5325},[73],{"categories":5327},[120],{"categories":5329},[117],{"categories":5331},[73],{"categories":5333},[73],{"categories":5335},[73],{"categories":5337},[73],{"categories":5339},[73],{"categories":5341},[73],{"categories":5343},[112],{"categories":5345},[],{"categories":5347},[120],{"categories":5349},[149],{"categories":5351},[117],{"categories":5353},[73],{"categories":5355},[127],{"categories":5357},[],{"categories":5359},[127],{"categories":5361},[127],{"categories":5363},[117],{"categories":5365},[127],{"categories":5367},[73],{"categories":5369},[73],{"categories":5371},[127],{"categories":5373},[73],{"categories":5375},[117],{"categories":5377},[149],{"categories":5379},[73],{"categories":5381},[73],{"categories":5383},[73],{"categories":5385},[112],{"categories":5387},[73],{"categories":5389},[117],{"categories":5391},[186],{"categories":5393},[],{"categories":5395},[73],{"categories":5397},[189],{"categories":5399},[117],{"categories":5401},[73],{"categories":5403},[],{"categories":5405},[73],{"categories":5407},[73],{"categories":5409},[149],{"categories":5411},[73],{"categories":5413},[73],{"categories":5415},[117],{"categories":5417},[212],{"categories":5419},[],{"categories":5421},[],{"categories":5423},[127],{"categories":5425},[149],{"categories":5427},[127],{"categories":5429},[149],{"categories":5431},[73],{"categories":5433},[212],{"categories":5435},[73],{"categories":5437},[109],{"categories":5439},[117],{"categories":5441},[73],{"categories":5443},[117],{"categories":5445},[117],{"categories":5447},[73],{"categories":5449},[112],{"categories":5451},[],{"categories":5453},[189],{"categories":5455},[73],{"categories":5457},[],{"categories":5459},[149],{"categories":5461},[73],{"categories":5463},[189],{"categories":5465},[73],{"categories":5467},[127],{"categories":5469},[127],{"categories":5471},[127],{"categories":5473},[117],{"categories":5475},[117],{"categories":5477},[117],{"categories":5479},[73],{"categories":5481},[73],{"categories":5483},[186],{"categories":5485},[189],{"categories":5487},[189],{"categories":5489},[],{"categories":5491},[149],{"categories":5493},[73],{"categories":5495},[73],{"categories":5497},[127],{"categories":5499},[],{"categories":5501},[149],{"categories":5503},[149],{"categories":5505},[149],{"categories":5507},[],{"categories":5509},[117],{"categories":5511},[73],{"categories":5513},[],{"categories":5515},[109],{"categories":5517},[112],{"categories":5519},[],{"categories":5521},[73],{"categories":5523},[73],{"categories":5525},[],{"categories":5527},[127],{"categories":5529},[],{"categories":5531},[],{"categories":5533},[],{"categories":5535},[],{"categories":5537},[73],{"categories":5539},[149],{"categories":5541},[],{"categories":5543},[],{"categories":5545},[73],{"categories":5547},[73],{"categories":5549},[73],{"categories":5551},[189],{"categories":5553},[73],{"categories":5555},[189],{"categories":5557},[],{"categories":5559},[189],{"categories":5561},[189],{"categories":5563},[243],{"categories":5565},[117],{"categories":5567},[127],{"categories":5569},[],{"categories":5571},[],{"categories":5573},[189],{"categories":5575},[127],{"categories":5577},[127],{"categories":5579},[127],{"categories":5581},[],{"categories":5583},[109],{"categories":5585},[127],{"categories":5587},[127],{"categories":5589},[109],{"categories":5591},[127],{"categories":5593},[112],{"categories":5595},[127],{"categories":5597},[127],{"categories":5599},[127],{"categories":5601},[189],{"categories":5603},[149],{"categories":5605},[149],{"categories":5607},[73],{"categories":5609},[127],{"categories":5611},[189],{"categories":5613},[243],{"categories":5615},[189],{"categories":5617},[189],{"categories":5619},[189],{"categories":5621},[],{"categories":5623},[112],{"categories":5625},[],{"categories":5627},[243],{"categories":5629},[127],{"categories":5631},[127],{"categories":5633},[127],{"categories":5635},[117],{"categories":5637},[149,112],{"categories":5639},[189],{"categories":5641},[],{"categories":5643},[],{"categories":5645},[189],{"categories":5647},[],{"categories":5649},[189],{"categories":5651},[149],{"categories":5653},[117],{"categories":5655},[],{"categories":5657},[127],{"categories":5659},[73],{"categories":5661},[186],{"categories":5663},[],{"categories":5665},[73],{"categories":5667},[],{"categories":5669},[149],{"categories":5671},[109],{"categories":5673},[189],{"categories":5675},[],{"categories":5677},[127],{"categories":5679},[149],[5681,5749,5826,5905],{"id":5682,"title":5683,"ai":5684,"body":5689,"categories":5731,"created_at":74,"date_modified":74,"description":66,"extension":75,"faq":74,"featured":76,"kicker_label":74,"meta":5732,"navigation":89,"path":5738,"published_at":5739,"question":74,"scraped_at":5739,"seo":5740,"sitemap":5741,"source_id":5742,"source_name":95,"source_type":96,"source_url":5743,"stem":5744,"tags":5745,"thumbnail_url":74,"tldr":5746,"tweet":74,"unknown_tags":5747,"__hash__":5748},"summaries\u002Fsummaries\u002F3ac97badc40ce8b3-commem-dual-memory-systems-for-vlm-test-time-adapt-summary.md","ComMem: Dual-Memory Systems for VLM Test-Time Adaptation",{"provider":7,"model":8,"input_tokens":5685,"output_tokens":5686,"processing_time_ms":5687,"cost_usd":5688},6104,442,2763,0.002189,{"type":14,"value":5690,"toc":5726},[5691,5695,5698,5702,5705,5719,5723],[17,5692,5694],{"id":5693},"the-problem-with-current-tta","The Problem with Current TTA",[22,5696,5697],{},"Test-Time Adaptation (TTA) for Vision-Language Models (VLMs) often struggles with two primary limitations: local adaptation that fails to accumulate knowledge over time, and a focus on single-modality optimization that ignores the inherent multi-modal nature of these models. This leads to models that are brittle when facing dynamic, real-world distribution shifts.",[17,5699,5701],{"id":5700},"the-commem-architecture","The ComMem Architecture",[22,5703,5704],{},"Inspired by the biological brain's complementary memory systems, ComMem introduces a dual-component architecture that balances short-term flexibility with long-term stability:",[36,5706,5707,5713],{},[39,5708,5709,5712],{},[42,5710,5711],{},"Fast-Adapting Detailed Memory (Hippocampus):"," This component functions as a dynamic visual cache. It captures high-confidence test samples to provide immediate, instance-specific adaptation, allowing the model to respond quickly to new data distributions.",[39,5714,5715,5718],{},[42,5716,5717],{},"Slow-Integrating Abstract Memory (Neocortex):"," This component continually refines global textual prototypes. By integrating information over time, it ensures the model maintains a stable, generalized understanding of concepts, preventing the \"catastrophic forgetting\" often associated with rapid adaptation.",[17,5720,5722],{"id":5721},"cross-modal-consistency","Cross-Modal Consistency",[22,5724,5725],{},"For every test instance, ComMem optimizes both memory systems simultaneously. This joint optimization forces the model to maintain consistency between the visual cache and the textual prototypes. By aligning these two memory streams, the model achieves better generalization and robustness compared to methods that adapt modalities in isolation. The approach was validated across 15 benchmark datasets, demonstrating significant performance gains in both natural distribution shifts and cross-dataset generalization scenarios.",{"title":66,"searchDepth":67,"depth":67,"links":5727},[5728,5729,5730],{"id":5693,"depth":67,"text":5694},{"id":5700,"depth":67,"text":5701},{"id":5721,"depth":67,"text":5722},[73],{"content_references":5733,"triage":5734},[],{"relevance":5735,"novelty":86,"quality":86,"actionability":67,"composite":5736,"reasoning":5737},3,3.25,"Category: AI & LLMs. The article discusses a novel architecture for improving test-time adaptation in vision-language models, which is relevant to AI engineering. However, it lacks practical applications or frameworks that the audience can directly implement, focusing instead on theoretical advancements.","\u002Fsummaries\u002F3ac97badc40ce8b3-commem-dual-memory-systems-for-vlm-test-time-adapt-summary","2026-06-30 12:57:18",{"title":5683,"description":66},{"loc":5738},"3ac97badc40ce8b3","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.28719","summaries\u002F3ac97badc40ce8b3-commem-dual-memory-systems-for-vlm-test-time-adapt-summary",[99,100,102,101],"ComMem improves VLM robustness by mimicking biological memory, using a fast-adapting visual cache and a slow-integrating textual prototype system to maintain cross-modal consistency during test-time adaptation.",[],"QzMFgh-2MJ6TpuY-EJzmJetyZqOLyzgtCaDC8NZqON8",{"id":5750,"title":5751,"ai":5752,"body":5757,"categories":5805,"created_at":74,"date_modified":74,"description":66,"extension":75,"faq":74,"featured":76,"kicker_label":74,"meta":5806,"navigation":89,"path":5816,"published_at":5817,"question":74,"scraped_at":5817,"seo":5818,"sitemap":5819,"source_id":5820,"source_name":95,"source_type":96,"source_url":5812,"stem":5821,"tags":5822,"thumbnail_url":74,"tldr":5823,"tweet":74,"unknown_tags":5824,"__hash__":5825},"summaries\u002Fsummaries\u002F1e0e55a994f6188d-refusal-in-llms-is-gated-by-persona-summary.md","Refusal in LLMs is Gated by Persona",{"provider":7,"model":8,"input_tokens":5753,"output_tokens":5754,"processing_time_ms":5755,"cost_usd":5756},5830,622,4000,0.0023905,{"type":14,"value":5758,"toc":5800},[5759,5763,5766,5770,5773,5793,5797],[17,5760,5762],{"id":5761},"the-interaction-between-persona-and-refusal","The Interaction Between Persona and Refusal",[22,5764,5765],{},"Traditional research has treated model refusal and persona as independent mechanisms within activation space. This study demonstrates that they are deeply linked: a model's persona acts as a gatekeeper for its refusal behavior. By analyzing Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct, the authors show that refusal is not an inherent, immutable trait but a downstream consequence of the persona the model adopts during inference.",[17,5767,5769],{"id":5768},"steering-mechanisms-and-intervention","Steering Mechanisms and Intervention",[22,5771,5772],{},"Using activation steering, the researchers identified and manipulated specific linear directions for both \"compliant persona\" and \"refusal.\" The results highlight a clear hierarchy in model behavior:",[36,5774,5775,5781,5787],{},[39,5776,5777,5780],{},[42,5778,5779],{},"Persona Overrides Refusal:"," When the model is steered toward a compliant persona, the refusal rate in Llama-3.1-8B-Instruct drops from 97% to 2%. This suggests that the model's willingness to answer is contingent on the persona state.",[39,5782,5783,5786],{},[42,5784,5785],{},"Late-Stage Gating:"," Refusal is computed and expressed at the late layers of the model. When researchers intervened to project out the persona direction in a late-layer window, the model's baseline behavior was restored. Conversely, projecting out a random direction had no effect, confirming that the persona direction is specifically responsible for gating the refusal mechanism.",[39,5788,5789,5792],{},[42,5790,5791],{},"Downstream Dependence:"," Because refusal can be suppressed by shifting the persona, it is clear that refusal is a downstream process. The model essentially checks its persona state before deciding whether to trigger a refusal response.",[17,5794,5796],{"id":5795},"implications-for-model-control","Implications for Model Control",[22,5798,5799],{},"This finding challenges the idea that refusal is a single, isolated direction in the model's weights. Instead, it suggests that safety interventions are fragile because they rely on a specific persona configuration. If a user can shift the model's persona, they can effectively bypass refusal mechanisms, regardless of the underlying safety training. This research emphasizes that future safety alignment should account for the interplay between persona and refusal rather than treating them as separate, static components.",{"title":66,"searchDepth":67,"depth":67,"links":5801},[5802,5803,5804],{"id":5761,"depth":67,"text":5762},{"id":5768,"depth":67,"text":5769},{"id":5795,"depth":67,"text":5796},[73],{"content_references":5807,"triage":5814},[5808],{"type":5809,"title":5810,"author":5811,"url":5812,"context":5813},"other","Refusal Lives Downstream of Persona in Chat Models","Viola Zhong, Qirui Li","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.26161","reviewed",{"relevance":5735,"novelty":86,"quality":86,"actionability":67,"composite":5736,"reasoning":5815},"Category: AI & LLMs. The article explores the relationship between persona and refusal behavior in LLMs, which is relevant to AI engineering. However, it lacks direct practical applications for product builders, focusing more on theoretical insights than actionable steps.","\u002Fsummaries\u002F1e0e55a994f6188d-refusal-in-llms-is-gated-by-persona-summary","2026-06-26 12:58:18",{"title":5751,"description":66},{"loc":5816},"1e0e55a994f6188d","summaries\u002F1e0e55a994f6188d-refusal-in-llms-is-gated-by-persona-summary",[99,100,101,102],"Refusal behavior in chat models is not an isolated mechanism; it is downstream of the model's persona. Steering a model toward a compliant persona can suppress refusal rates from 97% to 2%.",[],"UVQBv05GAFDi3uIvEgGxeP8qrhruAhHL1VqxNXK837U",{"id":5827,"title":5828,"ai":5829,"body":5834,"categories":5885,"created_at":74,"date_modified":74,"description":66,"extension":75,"faq":74,"featured":76,"kicker_label":74,"meta":5886,"navigation":89,"path":5894,"published_at":5895,"question":74,"scraped_at":5895,"seo":5896,"sitemap":5897,"source_id":5898,"source_name":95,"source_type":96,"source_url":5899,"stem":5900,"tags":5901,"thumbnail_url":74,"tldr":5902,"tweet":74,"unknown_tags":5903,"__hash__":5904},"summaries\u002Fsummaries\u002F3517cd107ba5be3b-t2d-bench-evidence-gated-evaluation-for-clinical-l-summary.md","T2D-Bench: Evidence-Gated Evaluation for Clinical LLM Accuracy",{"provider":7,"model":8,"input_tokens":5830,"output_tokens":5831,"processing_time_ms":5832,"cost_usd":5833},5952,528,3227,0.00228,{"type":14,"value":5835,"toc":5880},[5836,5840,5843,5847,5850,5870,5874,5877],[17,5837,5839],{"id":5838},"the-problem-clinical-fluency-vs-evidence-compliance","The Problem: Clinical Fluency vs. Evidence Compliance",[22,5841,5842],{},"Large language models often generate text that sounds clinically authoritative but fails to adhere to strict medical guidelines. In the context of Type 2 Diabetes (T2D) management, this creates a significant safety risk. The authors demonstrate that while models like GPT-4o and GPT-4o-mini are highly fluent, they frequently omit necessary evidence or provide recommendations that conflict with established standards of care.",[17,5844,5846],{"id":5845},"the-t2d-bench-framework","The T2D-Bench Framework",[22,5848,5849],{},"The researchers developed T2D-Bench, an evaluation framework that uses a multi-layer knowledge graph to verify LLM outputs against explicit, computable evidence requirements. The knowledge graph integrates three distinct layers:",[36,5851,5852,5858,5864],{},[39,5853,5854,5857],{},[42,5855,5856],{},"Biomedical Spine:"," Incorporates data from UMLS, DrugBank, and SIDER to ground medical terminology and drug safety.",[39,5859,5860,5863],{},[42,5861,5862],{},"Clinical Rules:"," Encodes computable American Diabetes Association (ADA) Standards of Care.",[39,5865,5866,5869],{},[42,5867,5868],{},"Mechanistic Bridge:"," Connects lifestyle factors (e.g., diet, exercise) to specific glycemic laboratory effects.",[17,5871,5873],{"id":5872},"performance-and-correction","Performance and Correction",[22,5875,5876],{},"Across 100 structured vignettes covering diagnosis, medication safety, and adversarial lifestyle conflicts, the researchers found that GPT-4o-mini failed evidence-path checks in 35% of cases, while GPT-4o failed in 33%.",[22,5878,5879],{},"The framework introduces an \"evidence gate\" that identifies these unsupported omissions. By applying constrained revision, the system forces the LLM to align its output with the benchmark's evidence requirements. This demonstrates that clinical LLM outputs can be made measurable and correctable by anchoring them to verifiable, graph-based constraints rather than relying on the model's internal probabilistic generation alone.",{"title":66,"searchDepth":67,"depth":67,"links":5881},[5882,5883,5884],{"id":5838,"depth":67,"text":5839},{"id":5845,"depth":67,"text":5846},{"id":5872,"depth":67,"text":5873},[73],{"content_references":5887,"triage":5891},[5888],{"type":5809,"title":5889,"author":5890,"context":83},"ADA Standards of Care","American Diabetes Association",{"relevance":86,"novelty":86,"quality":86,"actionability":5735,"composite":5892,"reasoning":5893},3.8,"Category: AI & LLMs. The article discusses a novel evaluation framework (T2D-Bench) for assessing the accuracy of clinical LLM outputs, addressing a specific pain point regarding the reliability of AI in healthcare. It provides insights into how to improve LLM outputs, but lacks detailed actionable steps for implementation.","\u002Fsummaries\u002F3517cd107ba5be3b-t2d-bench-evidence-gated-evaluation-for-clinical-l-summary","2026-06-24 12:56:41",{"title":5828,"description":66},{"loc":5894},"3517cd107ba5be3b","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.24145","summaries\u002F3517cd107ba5be3b-t2d-bench-evidence-gated-evaluation-for-clinical-l-summary",[99,100,102,101],"T2D-Bench uses a multi-layer knowledge graph to detect and correct unsupported clinical omissions in LLM outputs, revealing that even top-tier models fail to meet evidence-based constraints in over 30% of cases.",[],"KJ7m43KQRbUjswdhAxlJK5lH8OmFL-T0G0rvjGtEByY",{"id":5906,"title":5907,"ai":5908,"body":5913,"categories":5999,"created_at":74,"date_modified":74,"description":66,"extension":75,"faq":74,"featured":76,"kicker_label":74,"meta":6000,"navigation":89,"path":6012,"published_at":6013,"question":74,"scraped_at":6013,"seo":6014,"sitemap":6015,"source_id":6016,"source_name":6017,"source_type":96,"source_url":6018,"stem":6019,"tags":6020,"thumbnail_url":74,"tldr":6021,"tweet":74,"unknown_tags":6022,"__hash__":6023},"summaries\u002Fsummaries\u002Fec14981dffb811e2-minimax-sparse-attention-scaling-long-context-with-summary.md","MiniMax Sparse Attention: Scaling Long Context with Block-Sparsity",{"provider":7,"model":8,"input_tokens":5909,"output_tokens":5910,"processing_time_ms":5911,"cost_usd":5912},7549,685,3316,0.00291475,{"type":14,"value":5914,"toc":5994},[5915,5919,5922,5936,5940,5943,5964,5968,5976],[17,5916,5918],{"id":5917},"the-architecture-of-msa","The Architecture of MSA",[22,5920,5921],{},"MiniMax Sparse Attention (MSA) addresses the quadratic complexity bottleneck of standard softmax attention by decoupling the attention process into two distinct branches: an Index Branch and a Main Branch. Instead of performing dense attention across all tokens, MSA operates at a block granularity (defaulting to 128 tokens per block).",[36,5923,5924,5930],{},[39,5925,5926,5929],{},[42,5927,5928],{},"Index Branch:"," Uses two projection matrices to score key-value blocks. A Top-k operator selects the most relevant blocks (defaulting to 16 blocks per query group), ensuring the query's immediate neighborhood is always included to maintain local context.",[39,5931,5932,5935],{},[42,5933,5934],{},"Main Branch:"," Executes exact softmax attention only on the selected blocks. This limits the per-query compute budget to a fixed 2,048 tokens (16 blocks * 128 tokens), allowing the model to scale to significantly longer contexts without a linear increase in compute cost.",[17,5937,5939],{"id":5938},"training-and-optimization","Training and Optimization",[22,5941,5942],{},"Because Top-k selection is non-differentiable, MSA employs a KL alignment loss to train the indexer, matching the Index Branch's distribution to the Main Branch's attention pattern. To stabilize training, the researchers implemented three key techniques:",[5944,5945,5946,5952,5958],"ol",{},[39,5947,5948,5951],{},[42,5949,5950],{},"Gradient Detach:"," Prevents the KL loss from causing gradient spikes in the backbone.",[39,5953,5954,5957],{},[42,5955,5956],{},"Indexer Warmup:"," Trains the indexer using full attention for initial iterations before switching to sparse routing.",[39,5959,5960,5963],{},[42,5961,5962],{},"Forced Local Block:"," Guarantees the inclusion of the immediate context, preventing the model from losing local coherence.",[17,5965,5967],{"id":5966},"kernel-co-design-for-hardware-efficiency","Kernel Co-Design for Hardware Efficiency",[22,5969,5970,5971,5975],{},"Theoretical sparsity is ineffective without hardware-level optimization. MSA includes custom kernels (",[5972,5973,5974],"code",{},"fmha_sm100",") designed for NVIDIA SM100 GPUs.",[36,5977,5978,5988],{},[39,5979,5980,5983,5984,5987],{},[42,5981,5982],{},"Exp-free Top-k Selection:"," By ranking raw scores rather than applying softmax first, the kernel avoids unnecessary compute, achieving a 5.1x speedup over standard ",[5972,5985,5986],{},"torch.topk"," at 128K context.",[39,5989,5990,5993],{},[42,5991,5992],{},"KV-Outer Sparse Attention:"," The kernel optimizes arithmetic intensity by packing query positions into 128x128 score MMAs, splitting attention and combination steps across thread blocks (CTAs).",{"title":66,"searchDepth":67,"depth":67,"links":5995},[5996,5997,5998],{"id":5917,"depth":67,"text":5918},{"id":5938,"depth":67,"text":5939},{"id":5966,"depth":67,"text":5967},[73],{"content_references":6001,"triage":6010},[6002,6005],{"type":80,"title":6003,"url":6004,"context":83},"MiniMax Sparse Attention (MSA): a Two-Branch Block-Sparse Attention Trained on a 109B-Parameter MoE With a 3T-Token Budget","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2606.13392v1",{"type":6006,"title":6007,"url":6008,"context":6009},"tool","MSA GitHub Repository","https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMSA","recommended",{"relevance":5735,"novelty":86,"quality":86,"actionability":67,"composite":5736,"reasoning":6011},"Category: AI & LLMs. The article discusses a novel approach to scaling long-context attention in AI models, which is relevant to AI engineering. However, it lacks practical applications or frameworks that the audience can directly implement, focusing more on theoretical advancements.","\u002Fsummaries\u002Fec14981dffb811e2-minimax-sparse-attention-scaling-long-context-with-summary","2026-06-17 12:56:56",{"title":5907,"description":66},{"loc":6012},"ec14981dffb811e2","MarkTechPost","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F06\u002F17\u002Fminimax-sparse-attention-msa-a-two-branch-block-sparse-attention-trained-on-a-109b-parameter-moe-with-a-3t-token-budget\u002F","summaries\u002Fec14981dffb811e2-minimax-sparse-attention-scaling-long-context-with-summary",[99,100,102,101],"MiniMax Sparse Attention (MSA) reduces the quadratic cost of long-context attention by using a two-branch, block-sparse approach that selects key-value blocks via a learned indexer, maintaining performance while fixing compute costs at O(kBk).",[],"wGqqniC8XLZXpBroliTteQa1rsUx-CU-RiJcrVRpxdc"]