Kinematic Interpolants: A Simple, Scalable Framework for Dynamics From Snapshots
mmbronstein · x · 2026-10-28
New work led by @rogeryj001 introduces Kinematic Interpolants (KI), a simulation-free method for learning smooth dynamics from position–velocity snapshots — e.g., recovering flocking-bird motion from just a few frames, and modeling acceleration in irregular snapshots.
The authors describe the framework as beautifully simple and substantially more scalable than prior approaches like MFM and Curly Flow Matching; amplified by Meta's Michael Bronstein.
More from Research
- Google DeepMind engineer shows five CUDA optimizations that speed up 3D Gaussian Splatting by 10.5x — janusch_patas · 2026-10-29
- AI Audit Finds 2,035 Errors in 138 Papers by Economists Saez and Zucman — sebkrier · 2026-10-29
- Granary-v2 open speech model expands to 48 languages with open data and pipeline — rdesh26 · 2026-10-29
- Tinker launches Dimuon, a Muon-based optimizer that beats AdamW on LoRA fine-tuning — xennygrimmato_ · 2026-10-29
- Cross-lingual LLM effects paper wins Outstanding Paper award at EMNLP 2026 — anas_ant · 2026-10-29
- Lie detector compiled into Qwen3.5 weights flags 91% of lies with zero false positives — teortaxesTex · 2026-10-29