AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

DexMove: Learning Tactile-Guided Non-Prehensile Manipulation with Dexterous Hands

Pei Lin, Yuzhe Huang, Wanlin Li, Chenxi Xiao, Ziyuan Jiao

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer

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 finger control (full dexterous hand) instead of wrist-only (ablation)DexMove · Ablation, Large Cansuccess rate (%): 0.0 -> 63.3Improved
add cross-finger attention in TaFo-Net (ablation)TaFo-Net · Booksuccess rate (%): 63.3 -> 90.0Improved
add cross-finger attention in TaFo-Net (ablation)TaFo-Net · Keyboardsuccess rate (%): 50.0 -> 90.0Improved
add shear force component to tactile vector field (ablation)TaFo-Net · Large Cansuccess rate (%): 0.0 -> 63.3Improved
add shear force component to tactile vector field (ablation)TaFo-Net · Legosuccess rate (%): 70.0 -> 66.7Hurt
replace heuristic force with learned TaFo-Net force (ablation)DexMove · Keyboardsuccess rate (%): 0.0 -> 90.0Improved
teleoperated wrist instead of policy wristWrist-Only · Mousesuccess rate (%): 0.0 -> 73.3Improved
unseen friction Fric. B vs Fric. ADexMove · yaw error 0-30success rate (%): 86.7 -> 86.7No clear effect
unseen friction Fric. B vs Fric. ADyWA · yaw error 0-30success rate (%): 50.0 -> 36.7Hurt
increase tactile noise sigma from 0 to 0.1 (ablation)DexMove · Booksuccess rate (%): 90.0% -> 80.0%Hurt
increase tactile noise sigma from 0 to 0.5 (ablation)DexMove · Large cansuccess rate (%): 63.3% -> 3.3%Hurt
multi-finger contact instead of gripperDexMove vs DyWA · pushing 0-15 cmexecution time (s): 36.1 -> 8.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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