AI Paper Atlas

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

Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic Manipulation

Runyi Zhao, Sheng Xu, Ruixing Jin, Yueci Deng, Yunxin Tai, Kui Jia, Guiliang Liu

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models

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
use arm-decoupled control modules instead of joint learning (ablation)Sim2Real-VLA · Items Hand-Over and Place (real)real-world success rate: 0.15 -> 0.40Improved
use arm-decoupled control modules instead of joint learning (ablation)Sim2Real-VLA · Items Hand-Over and Place (sim)simulation success rate: 0.32 -> 0.62Improved
use arm-decoupled control modules instead of joint learning (ablation)Sim2Real-VLA · Single-Arm Water Pouring (real)real-world success rate: 0.75 -> 0.85Improved
lengthen affordance chain from K=1 to K=3 (ablation)Sim2Real-VLA · Single-Arm Water Pourreal-world successes out of 20: 17/20 -> 11/20Hurt
lengthen affordance chain from K=1 to K=3 (ablation)Sim2Real-VLA · Dual-Arm Water Pourreal-world successes out of 20: 16/20 -> 8/20Hurt
lengthen affordance chain from K=1 to K=3 (ablation)Sim2Real-VLA · Basket Pick-and-Placereal-world successes out of 20: 9/20 -> 4/20Hurt
lengthen affordance chain from K=1 to K=3 (ablation)Sim2Real-VLA · Items Hand-Over and Placereal-world successes out of 20: 8/20 -> 4/20Hurt
train on synthetic data with Sim2Real-VLA instead of best baseline pi0-FASTVLA policy fine-tuned on simulator data · Single-Arm Water Pour (real)real-world successes out of 20: 11/20 -> 17/20Improved
train on synthetic data with Sim2Real-VLA instead of GR00T N1.5VLA policy fine-tuned on simulator data · Dual-Arm Water Pour (real)real-world successes out of 20: 7/20 -> 16/20Improved
change background texture in real environmentSim2Real-VLA · Single-Arm Water Pourreal-world successes out of 20: 17/20 -> 17/20No clear effect
change object features in real environmentSim2Real-VLA · Table Rearrangementreal-world successes out of 20: 16/20 -> 14/20Hurt
change table texture in real environmentSim2Real-VLA · Items Hand-Over and Placereal-world successes out of 20: 8/20 -> 6/20Hurt

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