NeurIPS 2026 paper: neuron universality and selectivity scale systematically up to 30B
CSProfKGD · x · 2026-09-25
A NeurIPS 2026 paper, "Neuron Populations Exhibit Divergent Selectivity with Scale," asks: scaling laws describe how loss changes with scale — but do neurons inside models change predictably too?
Studying vision and language models up to 30B parameters (a collaboration involving Yasaman Bahri, Yunzhi Gandelsman, and Alyosha Efros), the authors find systematic scaling in neuron universality, specialization, and selectivity. Paper and code are public; topics span representation alignment/universality, scaling laws, and superposition.
More from Research
- New Research Examines How AI Agents Enter Markets and How Markets Should Be Designed for Them — sethlazar · 2026-09-25
- Vite core member finds methodology flaws inflating oj's memory benchmarks by 100MB+ — cnakazawa · 2026-09-25
- DeepMind Paper: One Misleading Hint Drops Coding Agent Scores by Up to 46.7% — dair_ai · 2026-09-25
- NeurIPS paper shows self-improving, self-replicating agents evolve cooperation from scratch — maxhkw · 2026-09-25
- Continuous diffusion LM RePlaid accepted at NeurIPS 2026, matches discrete diffusion scaling — ArashVahdat · 2026-09-25
- AAAI 2027 phase 1 reviews are out — CSProfKGD · 2026-09-25