Kundaje thread (5/9): short-context models ill-suited for motif selectivity questions
anshulkundaje · x · 2026-11-19
Part 5 of Anshul Kundaje's thread: short-context models like BPNet are not trained for or strong at selectivity questions; genome-wide long-context models have much better discriminative performance. See thread-start item.
Related event: Stanford's Kundaje fires nine-tweet rebuttal over TF cooperativity study(10 posts)→
More from Research
- Churchland lab builds RNN implementation of GLM-HMM to model engagement fluctuations — anne_churchland · 2026-11-19
- Energy-Based Reasoners: 1.8M-param model hits 99.9% on Sudoku-Extreme with 345x less inference compute — LucaAmb · 2026-11-19
- New MAC Bench finds frontier agents coordinate poorly: 8-agent teams win by exploration, not teamwork — AlexGDimakis · 2026-11-19
- LLNL releases SciResearch-Eval, a benchmark testing AI scientific judgment with broken simulators — alex_verem · 2026-11-19
- LLNL benchmark: only 2 of 9 AI models stay accurate when the simulator is secretly wrong — alex_verem · 2026-11-19
- HiT image generator learns its own abstraction hierarchy, hits 1.48 FID on ImageNet 256 — LucaAmb · 2026-11-19