AI Paper Atlas

Research map / Video / Video generation

RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control

Junpeng Yue, Zepeng Wang, Jiangxing Wang, Yuxuan Wang, Yu Zhang, Xinrun Xu, Bin Cao, Sipeng Zheng, gang ding, Zongqing Lu

ECCV 2026 · Video › Video generation · approach: Text-to-motion diffusion · 23 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 motion tracking reward (ablation)RLPF · CMU test, IsaacGymSuccess rate: 0.32 -> 0.95Improved
add motion tracking reward (ablation)RLPF · AMASS test, IsaacGymSuccess rate: 0.30 -> 0.92Improved
add motion tracking reward (ablation)RLPF · CMU test, MuJoCoSuccess rate: 0.24 -> 0.75Improved
use Exbody2 tracker instead of PHC for the reward (ablation)RLPF · CMU test, IsaacGymSuccess rate: 0.91 -> 0.95Improved
use Exbody2 tracker instead of PHC for the reward (ablation)RLPF · AMASS test, IsaacGymSuccess rate: 0.80 -> 0.92Improved
use Exbody2 tracker instead of PHC for the reward (ablation)RLPF · AMASS test, high-levelFID: 1.84 -> 3.34Mixed
add alignment verification (ablation)RLPF · CMU test, high-levelFID: 32.53 -> 3.61Improved
add alignment verification (ablation)RLPF · AMASS test, high-levelR@1: 0.07 -> 0.28Improved
add alignment verification (ablation)RLPF · CMU test, MuJoCoSuccess rate: 0.90 -> 0.75Hurt
add alignment verification (ablation)RLPF · AMASS test, MuJoCoSuccess rate: 0.99 -> 0.63Hurt
supervised fine-tuning on full dataBase Model · CMU test, IsaacGymSuccess rate: 0.43 -> 0.36Hurt
supervised fine-tuning on tracking-filtered dataBase Model · CMU test, IsaacGymSuccess rate: 0.43 -> 0.57Improved

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