# HKUST proposes W2-VLA: predicting future wrist latent variables enables 80Hz fine manipulation

- Source: 3D视觉工坊 · 微信公众号
- Published: 2026-10-24T16:00:00.000Z
- RoboHot: https://robohot.news/en/items/qrt2njsxb2y3ubuns8mtywidr
- Original: https://mp.weixin.qq.com/s?__biz=MzU1MjY4MTA1MQ==&mid=2247752539&idx=2&sn=4c1ff4c5301c6473536f4b4a5bd3c2ad&chksm=fabf4b9f385292a513da01624120cabaf270ff2f0935e31b626ff85ef1f5b792edddbbb314e5&scene=126&sessionid=1792860120#rd

## Summary

Authors from the Hong Kong University of Science and Technology propose World-to-Wrist VLA (W2-VLA), which uses global task context to predict future wrist latent variables and then guide fine action generation. The method achieves 98.5% average success rate on LIBERO, 60.71% and 18.21% on the Easy/Hard settings of RoboTwin 2.0, respectively, and outperforms baselines under standard and OOD conditions on three real-world tasks: tabletop cleanup, occluded placement, and dual-arm plug insertion.