'RNA alone is the wrong input': Kundaje on causal regulatory models
anshulkundaje · x · 2026-10-14
Part 8 of Anshul Kundaje's thread: genes don't regulate genes, and RNAs of regulators don't regulate RNAs of targets—so using RNA alone as input for 'causal regulatory models' is fundamentally wrong, since proteins do the actual regulatory work.
Related event: Stanford professor slams AI gene regulation models as fundamentally flawed(2 posts)→
More from Research
- NTU team has Claude write robot control code, hitting 70.24% success in sim — aigclink · 2026-10-14
- Six training strategies compared: can LLMs reason over graphs at scale? — burkov · 2026-10-14
- VisInteract: NeurIPS Spotlight reframes text-to-visualization as multi-turn intent retrieval — jiqizhixin · 2026-10-14
- WorldRecon reconstructs large-scale 3D scenes from unposed multi-view images, cutting Chamfer distance 43% — ZhejiangUniversity · 2026-10-14
- RSI-Nav: recursive self-improvement for navigation agents hits 68.6% SR on R2R-CE — OpenGVLab · 2026-10-14
- NUS proposes Jeva, a decision-native architecture with near-perfect null detection at thousands of candidates — NationalUniversityofSingapore · 2026-10-14