One Trajectory, Two Requirements: Accuracy and Local Stability in Euler Sampling for Flow Matching Policies
cs.LG, cs.RO
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/Physical-Intelligence/openpi
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge
- Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies
- ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models
- Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
- On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching
- From Euler to Dormand-Prince: ODE Solvers for Flow Matching Generative Models
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis