Stanford's Anshul Kundaje Slams 'Universal Virtual Cell': Perturbation Prediction Is the Wrong Metric
anshulkundaje · x · 2026-10-08
Stanford professor Anshul Kundaje criticized vague 'universal virtual cell' claims: perturbation prediction performance is the wrong metric by itself. Model building must be grounded in real biological systems with varying prior knowledge, experimental tractability and malleability, and honestly defined levels of generalization of increasing difficulty—no more cheating by cherry-picking favorable scenarios.
Related event: Stanford Professor Questions Universal Virtual Cell(3 posts)→
More from Research
- KITE transfers robot task knowledge across hands zero-shot, hitting 7/10 on real hardware — qinzytech · 2026-10-08
- NeurIPS paper: humanoids should imagine in 360° instead of thinking longer to find objects — _vztu · 2026-10-08
- Kernaut: coding agents design Gaussian process kernels via program search — sirbayes · 2026-10-08
- Kernaut's discovered kernels stay interpretable: 16 scalar functions, inner-product form — sirbayes · 2026-10-08
- iOSWorld brings computer-use agent benchmarking to iOS at COLM 2026 — kohjingyu · 2026-10-08
- Epoch's InnovationEval: AI agents still far from producing real research innovations — Afinetheorem · 2026-10-08