AI Paper Atlas

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

WholeBodyVLA: Towards Unified Latent VLA for Whole-body Loco-manipulation Control

Haoran Jiang, Jin Chen, Qingwen Bu, Li Chen, Modi Shi, Yanjie Zhang, Delong Li, Chuanzhe Suo, wang chuang, zhihui peng, Hongyang Li

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 41 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
add latent action model pretraining on human videos (ablation)WholeBodyVLA · Real-robot suites avgsuccess rate: 39.3% -> 78.0%; +38.7%Improved
add LMO discrete-command RL policy instead of velocity-based RL (ablation)WholeBodyVLA · Real-robot suites avgsuccess rate: 54.0% -> 78.0%; 24% lowerImproved
add locomotion video pretraining to manipulation-only LAM (ablation)WholeBodyVLA · Real-robot suites avgsuccess rate: 63.3% -> 78.0%; +14.7%Improved
use separate locomotion and manipulation LAMs instead of shared LAM (ablation)WholeBodyVLA · Real-robot suites avgsuccess rate: 66.0% -> 78.0%Improved
add directional accuracy reward to LMO (ablation)LMO · MuJoCo turningorientation error: 0.28 -> 0.19Improved
add stage 2 refinement to LMO (ablation)LMO · MuJoCo turningposition error: 0.20 -> 0.05Improved
add stage 2 refinement to LMO (ablation)LMO · MuJoCo squattingCoM sway: 0.07 -> 0.03Improved
add stage 1 minimal gait training to LMO (ablation)LMO · MuJoCo turningposition error: 0.46 -> 0.05Improved
replace velocity-based RL with LMO (ablation)RL controller · MuJoCo turningposition error: 0.26 -> 0.05Improved
replace velocity-based RL with LMORL controller · MuJoCo forward&backwardposition error: 0.24 -> 0.21No clear effect
use more human egocentric video pretraining (0 to 100%)WholeBodyVLA · locomotion generalizationavg success rateImproved
use more AgibotWorld data for latent learningWholeBodyVLA · manipulation generalizationavg success rateImproved

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