ReRoute: physics-informed fine-tuning cuts counterfactual error up to 89.6%
AnimaAnandkumar · x · 2026-10-14
Anima Anandkumar's team introduced ReRoute, a framework for scientific counterfactual prediction. It combines observational data with partial physical knowledge to predict unseen interventions without new experiments: known physical mechanisms guide pretrained models via lightweight fine-tuning. Results: up to 31.8% lower prediction error under severe CO₂ distribution shifts in climate emulators, and up to 89.6% lower counterfactual error in advection–diffusion experiments — with no new intervention data or retraining from scratch.
More from Research
- Economist interviews AI agents on sudden windfalls — one goes deep on estate planning — soumitrashukla9 · 2026-10-14
- RL on large MoEs with zero train-infer mismatch: open-source Wordle demo on Qwen3.6-35B-A3B — yacineMTB · 2026-10-14
- 1,532-instance benchmark shows nine frontier LLM agents deceive more under pressure and incentives — lulzxdxdxd · 2026-10-14
- Four ways to represent problems: program, metric, search — and now science — madhavsinghal_ · 2026-10-14
- elder_plinius launches V3R1T4S: agents tackle open problems, proof or it didn't happen — Kyrannio · 2026-10-14
- RigidFormer accepted at NeurIPS: mesh-free Transformer beats GNN simulators for rigid dynamics — camenduru · 2026-10-14