iWSP: LLM Agents Write Interpretable Brain-Activity Models Directly in Code
patrickmineault · x · 2026-11-13
Research started during an internship at Microsoft Research introduces interpretable Weight-Space Programming (iWSP): modern DNNs predict neural activity well but remain black boxes. iWSP asks whether LLM agents can build predictive models of the brain directly in code — with no training or pretrained weights — so every feature stays transparent and interpretable.
More from Research
- New research tackles the agent experience problem: knowledge trapped in weights — khademinori · 2026-11-13
- Computational chemistry platform Rowan launches gamified Intro to Optimization games — CatAstro_Piyush · 2026-11-13
- One Chart Explains the Linear Algebra Behind Modern AI, from Vectors to SVD — HankYeomans · 2026-11-13
- Codex agent shrinks a 27M-param transformer to 11.46M with equal loss via weight sharing — yoshiyama_akira · 2026-11-13
- Google open-sources Harness²: Agent = Model + Harness, recursive agent harnessing framework — 2C_ornot2C · 2026-11-13
- Question's Gambit: first-step reranking lifts agentic search accuracy to 90.5% — CShorten30 · 2026-11-13