Awesome Robotics Manipulation · full_paper

HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization

作者：Zeyang Li, Kaveh Alim, Navid Azizan · 单位：Massachusetts Institute of Technology · 会议/期刊：ICLRW 2026 · 日期：2025-11-11 · 来源：Low-Level Learning-Based Action Modelling / Policy Learning / Flow Matching Policy

任务规划流匹配机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization figure
AlphaXiv 中文论文页面（可滚动查看）