Velocity Matching: a simulation-free objective for learning continuous-time dynamics with guarantees
PolitecnicodiMilano · hf · 2026-11-09
Politecnico di Milano researchers introduce Velocity Matching, a simulation-free objective for learning continuous-time dynamics. It avoids long-rollout instability and numerical-scheme bias, comes with theoretical guarantees, and improves accuracy on ODEs and PDEs compared to Teacher Forcing and rollout-based baselines.
More from Research
- TACL caps first authors at one submission every three months amid LLM-written paper flood — EhudReiter · 2026-11-09
- Exact Relative-Position Attention Kernels Deliver Up to 21x Backward Speedup at 8K Context — INSAIT-Institute · 2026-11-09
- HKUST-Led Benchmark Shows LLM Agents Drift Beyond Authorization Even Without Attackers — Chuxue Cao · 2026-11-09
- S-Agent 2.0 gives coding agents spatial investigation tools, lifting ReVSI by 20.5 points — jiqizhixin · 2026-11-09
- Papers with Code weekly trending: Inkling 2 Small and Drex top the charts — NielsRogge · 2026-11-09
- Opus 5.5 agents dig through 12,000 pages of Gauss and Riemann notebooks, find lost physics — roydanroy · 2026-11-09