Researcher slams NeurIPS reviews as BioReason top-20 pick called a farce
anshulkundaje · x · 2026-10-03
Stanford researcher Anshul Kundaje criticized ML conference peer review after BioReason ranked top-20 at NeurIPS, calling the bio-review quality "a complete farce." He says the model isn't really a multimodal biological reasoning system, and its benchmark tasks have problematic task definitions and prompt-based information leakage — advising others not to use or build on those task definitions.
Related event: Stanford's Kundaje blasts AI×Bio rigor gaps and NeurIPS review quality(11 posts)→
More from Research
- Math PhD Trains AI to Crack Open Research Problems, Reports Progress in Arithmetic Physics — shuchaobi · 2026-10-03
- childes-db 2026.1 Released: Child Language Database Grows to 24.2M Utterances with New Annotations — najoungkim · 2026-10-03
- SETA Terminal Agent Training Suite Accepted at NeurIPS, Open-Sources 4,500+ Verifiable RL Environments — Thom_Wolf · 2026-10-03
- MedARC journal club: pretraining foundation models for intracranial EEG — iScienceLuvr · 2026-10-03
- Mosaic: exact constrained decoding for diffusion LLMs via finite automata, NeurIPS paper — StefanoErmon · 2026-10-03
- NYU Researchers Challenge Anthropic's Claim That LLMs Can Introspect — tallinzen · 2026-10-03