Stanford's Anshul Kundaje: gene expression AI models capped by data, not scale
anshulkundaje · x · 2026-09-19
Stanford professor Anshul Kundaje argues that larger models are failing to showcase their power in gene expression prediction because there isn't enough of the right kind of data — which is why his group has stuck with smaller models for local signals. He sees the current approach as near its ceiling until we get large-scale cis perturbation datasets, leverage evolutionary information, or incorporate other inductive biophysical biases.
More from Research
- JEPA-Anything: one predictive framework spanning vision, biology, weather and more — rbhar90 · 2026-09-19
- Tsinghua's C2C Lets LLMs Skip Text and Merge KV-Caches Directly, 2.5x Faster with +14.2% Accuracy — anselm · 2026-09-19
- Summer School Debunks SOTA Autonomous Driving Tricks for Failing to Generalize — ftm_guney · 2026-09-19
- Professor Zhiting Hu Links New Jev Model to Her Three-Year-Old Discriminative Generalist Work ALIGN — ZhitingHu · 2026-09-19
- Tsinghua paper: RL fine-tuning prunes exploration, letting base LLMs beat RL models at high pass@k — burny_tech · 2026-09-19
- Async RL is just horizontal scaling with sticky routing, one dev argues — dosco · 2026-09-19