AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Structural Action Transformer for 3D Dexterous Manipulation

Xiaohan Lei, Min Wang, Bohong Weng, Wengang Zhou, Houqiang Li

CVPR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 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 structural-centric action representation instead of temporal-centric (ablation)SAT · 11 simulation taskssuccess rate: 0.64 -> 0.71Improved
add the joint embedding (Embodied Joint Codebook) (ablation)SAT · 11 simulation taskssuccess rate: 0.01 -> 0.71Improved
add the Functional Category embedding (ablation)SAT · 11 simulation taskssuccess rate: 0.02 -> 0.71Improved
add the Embodiment ID embedding (ablation)SAT · 11 simulation taskssuccess rate: 0.57 -> 0.71Improved
add the Rotation Axis embedding (ablation)SAT · 11 simulation taskssuccess rate: 0.62 -> 0.71Improved
add the global point cloud token (ablation)SAT · 11 simulation taskssuccess rate: 0.68 -> 0.71Improved
add the local point cloud tokens (ablation)SAT · 11 simulation taskssuccess rate: 0.69 -> 0.71Improved
add the causal mask (ablation)SAT · 11 simulation taskssuccess rate: 0.68 -> 0.71Improved
increase token dimension from 16 to 32 (ablation)SAT · 11 simulation taskssuccess rate: 0.66 -> 0.71Improved
increase token dimension from 64 to 256 (ablation)SAT · 11 simulation taskssuccess rate: 0.71 -> 0.70No clear effect
pre-train on human, robot and simulation data instead of human only (ablation)SAT · 11 simulation taskssuccess rate: 0.68 -> 0.71Improved
pre-train on human data instead of robot data (ablation)SAT · 11 simulation taskssuccess rate: 0.66 -> 0.68Improved

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