AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Beyond Mimicry: Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations

Wei-Jin Huang, Yue-Yi Zhang, Yi-Lin Wei, Zhi-Wei Xia, Juantao Tan, Yuan-Ming Li, Zhilin Zhao, Wei-Shi Zheng

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 contact preservation loss Lcon (ablation)PAIR · contact@0.35mcontact F1: 0.821 -> 0.841Improved
add human partner adaptation (ablation)PAIR · contact@0.35mcontact F1: 0.823 -> 0.841Improved
use two-stage coarse-to-fine optimization instead of single stage (ablation)PAIR · contact@0.35mcontact F1: 0.788 -> 0.841Improved
add contact loss and two-stage on smoothness (ablation)PAIR · retargetingjerk mean: 0.0008 vs 0.0007-0.0008 withoutNo clear effect
PAIR vs ImitationNetPAIR · contact@0.35mcontact F1: 0.502 -> 0.841Improved
add Phase Attention (when to act) (ablation)D-STAR · HHoI sim, avg 6 taskssuccess rate (%): 65.9 -> 75.4Improved
add Multi-Scale Spatial module (where to act) (ablation)D-STAR · HHoI sim, avg 6 taskssuccess rate (%): 64.3 -> 75.4Improved
remove both PA and MSS vs removing one (ablation)D-STAR · HHoI sim, avg 6 taskssuccess rate (%): w/o PA+MSS 68.3 vs w/o PA 65.9 and w/o MSS 64.3Mixed
D-STAR vs Transformer policyD-STAR · HHoI sim, avg 6 taskssuccess rate (%): 64.3 -> 75.4Improved
D-STAR vs Diffusion Policy on High-FiveD-STAR · HHoI sim, High-Fivesuccess rate (%): 3.7 -> 40.7Improved
Naive mimicry (BC only) without decouplingNaive Mimicry · HHoI simsuccess rate (%): 0.0 averageHurt

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