Genentech team's Nona paper sparks debate: hybrid multimodal models may beat DNA LMs as samplers
anshulkundaje · x · 2026-10-31
Genentech researchers including Surag Nair and Gökcen Eraslan released a bioRxiv preprint, "Nona: A unifying multimodal masking framework for functional genomics."
In the accompanying discussion, Anshul Kundaje argues that for long-context regulatory domain optimization, purely self-supervised DNA language models are unlikely to be the most useful samplers; hybrid multimodal semi-supervised generative models like Nona or Radical Numerics' Omnii are better positioned as efficient long-context samplers and oracles.
More from Research
- New preprint: closed-loop ephys successfully trains in vitro neuron cultures to change behavior — DoctorJosh · 2026-10-31
- Forethought: first movers could lock rivals out of space for $49-73B premium — willmacaskill · 2026-10-31
- Correction: newer model gets worse on the extreme-hard tail, pass@5 crossover predicted — teortaxesTex · 2026-10-31
- Meta demos titanRL, TorchTitan's RL library for LLMs, teaching Qwen Connect 4 — ezyang · 2026-10-31
- Biohub's Remo-ID spots sepsis from blood cell images, 43/47 correct in early study — alex_peys · 2026-10-31
- 240-Year-Old Voting Paradox Gets a Shape: It's a Klein Bottle — stevenstrogatz · 2026-10-31