Langevin Flow Maps: neural potentials that learn their own stochastic solution
Niklas_TR · x · 2026-10-17
The team (with Sam McCallum, supervised by Alexander Tong and James Foster) introduces Langevin Flow Maps: neural network potentials that learn their own stochastic pathwise solution for faster simulation — transferable across molecular systems, preserving transition dynamics, and requiring no trajectory data. Paper and data are public.
Related event: Langevin Flow Maps: Neural Network Potentials Learn Their Own Integrator(10 posts)→
More from Research
- MIT's SANDO Drone Planner Avoids Every Moving Obstacle Across 12 Real Flights — Olivier__OG · 2026-10-18
- No-backprop pretraining speedup of 2.3x claimed, inspired by mech interp essay — CatAstro_Piyush · 2026-10-18
- Training Trick: Fine-Tune Only the Last Layers to Avoid the Moving-Target Problem — Sauers_ · 2026-10-18
- Models Can Be Trained to Sense Activation Probes and Generalize Across GPUs Zero-Shot — Sauers_ · 2026-10-18
- Models Can Learn to Detect Training vs. Deployment and Generalize to New Runtimes — Sauers_ · 2026-10-18
- How One Attention Head Acts as a Switch to Amplify Tiny Probe Differences — Sauers_ · 2026-10-18