AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

DemoFunGrasp: Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning

Chuan Mao, Haoqi Yuan, Ziye Huang, Chaoyi Xu, Kai Ma, Zongqing Lu

CVPR 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 affordance reward (ablation)DemoFunGrasp · state-based simSAD (cm): 4.60 -> 3.02Improved
add affordance reward (ablation)DemoFunGrasp · state-based simGSR (%): 78.28 -> 77.04Hurt
add style disturbance (ablation)DemoFunGrasp · state-based simGSR (%): 58.67 -> 77.04Improved
add object size clipping (ablation)DemoFunGrasp · state-based simSAD (cm): 3.63 -> 3.02Improved
add object size clipping (ablation)DemoFunGrasp · state-based simGSR (%): 81.67 -> 77.04Hurt
add close reward (ablation)DemoFunGrasp · state-based simSA (%): 90.58 -> 94.74Improved
add qpos style reward (ablation)DemoFunGrasp · state-based simGSR (%): 74.38 -> 77.04Improved
condition on affordance and style vs DemoGraspDemoFunGrasp · sim, seen categoriesSAD (cm): 6.27 -> 3.02Improved
style/affordance conditioning vs UniDexGraspDemoFunGrasp · sim, unseen categoriesStyle Diversity: 1.00 -> 1.44Improved
style/affordance conditioning vs UniDexGraspDemoFunGrasp · sim, seen categoriesGSR (%): 74.3 -> 76.26No clear effect
use VLM-predicted instead of human affordanceDemoFunGrasp · real world, 9 daily objectsGSR (%): 71 -> 64Hurt
select best style per objectDemoFunGrasp · sim, unseen categoriesStyle Diversity: 1.44 -> 1.36Hurt

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