AI Paper Atlas

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

Scaling by Diversified Experience for Vision-Language-Action Models

Leiyu Wang, Zhaofengnian Wang, Xueqi Li, Luoyi Fan, Cewu Lu, Nanyang Ye

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 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 Intention Decoupling (ablation)SyVLA · Folding Shirtaverage success rate: 0.43 -> 0.86Improved
add chain-of-thought reasoning together with Intention Decoupling (ablation)SyVLA · Folding Shirtaverage success rate: 0.79 -> 0.86Improved
add the RL stage (ablation)SyVLA · Folding Shirtaverage success rate: 0.71 -> 0.86Improved
add expert dataset samples during RL (ablation)SyVLA · Folding Shirtaverage success rate: 0.21 -> 0.86Improved
retrieve similar expert samples instead of random ones (ablation)SyVLA · Folding Shirtaverage success rate: 0.79 -> 0.86Improved
retrieve similar expert samples instead of random ones (ablation)SyVLA · Real-world Task 2 and Task 3success rate: 0.56 -> 0.68 (Task 2); 0.571 -> 0.643 (Task 3)Improved
use constant advantage 1.0 for expert samples instead of standard GAE (ablation)SyVLA RL · Folding Shirtaverage success rate: 0.00 -> 0.86Improved
raise mask threshold from 5% to 20% (ablation)Intention Decoupling · Folding Shirtaverage success rate: 0.86 -> 0.64Hurt
raise mask threshold from 3% to 5% (ablation)Intention Decoupling · Folding Shirtaverage success rate: 0.73 -> 0.86Improved
increase Feature Query Tokens from 5 to 20 (ablation)SyVLA · Folding Shirtaverage success rate: 0.39 -> 0.86Improved
increase Feature Query Tokens from 20 to 30 (ablation)SyVLA · Folding Shirtaverage success rate: 0.86 -> 0.87No clear effect
add Intention Decoupling (ablation)SyVLA · multimodal benchmarks (DocVQA, AI2D, MMMU, MME, HallBench)score: DocVQA 63.62 -> 80.01; AI2D 71.76 -> 67.7; MMMU 38.67 -> 35.78; MME 1648.12 -> 1795; HallBench 41.7 -> 42.53Mixed

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