# KPGrasp: A Scalable Keypoint Flow Matching Method for Dexterous Grasp Generation

- Source: PKU EPIC Lab
- Published: 2026-06-08T10:19:29.000Z
- RoboHot: https://robohot.news/en/items/go9wit38fki6hm6i1zs8mpjzb
- Original: https://arxiv.org/abs/2606.09314

## Summary

PKU EPIC Lab proposes KPGrasp, a dexterous grasp generation method that combines an all-Euclidean 3D hand-keypoint parameterization with a Transformer flow-matching model to learn grasp priors from large-scale data, without contact losses or contact-based test-time optimization.

## Why it matters

The paper presents a new contact-loss-free grasp generation method and specific results on two benchmarks, letting readers compare it with existing methods and assess its approach.