AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Cross-Hand Latent Representation for Vision-Language-Action Models

Guangqi Jiang, Yutong Liang, Jianglong Ye, Jia-Yang Huang, Changwei Jing, Rocky Duan, Pieter Abbeel, Xiaolong Wang, Xueyan Zou

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace raw joint-space actions with a shared latent action space in the VLApi0 · 10 real-world tasks, 4 dexterous handsmean success rate: 0.32 -> 0.72Improved
use shared latent action space on the most distinct hand (XHand)pi0 · XHand, 10 tasksmean success rate: 0.29 -> 0.70Improved
zero-shot unseen task transfer with latent space versus pi0 plus kinematic retargetingXL-VLA · unseen task-hand combinationssuccess rateImproved
co-train xArm and G1 data in latent action space instead of raw actionspi0 · G1 humanoid, 4 taskssuccess rate: +57%Improved
use unsupervised latent space instead of supervised LAD for latent replaylatent retargeting · Ability+Inspire replaymean replay success: 0.60 -> 0.82Improved
use unsupervised latent space instead of LADlatent retargeting · Paxini+XHand replaymean replay success: 0.61 -> 0.81Improved
add retargeting loss L2 (distance and direction) (ablation)latent autoencoder · cross-embodiment pinch direction errordirection error: 62.733 -> 11.857Improved
add retargeting loss L2 (ablation)latent autoencoder · reconstruction joint RMSEjoint RMSE: 3.781 -> 5.476Mixed
add reconstruction loss L1 (ablation)latent autoencoder · reconstruction joint RMSEjoint RMSE: 61.672 -> 5.476Improved
increase latent dimension from 32 to 128 (ablation)latent autoencoder · latent space ablationlatent quality: 5.476 -> 5.324No clear effect
reduce latent dimension to 8 (ablation)latent autoencoder · latent space ablationreconstruction joint RMSE: 5.476 -> 20.913Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy