AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow

Yixiang Chen, Peiyan Li, Yan Huang, Jiabing Yang, Kehan Chen, Liang Wang

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 9 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 goal image prediction auxiliary task (ablation)EC-Flow · Meta-World (9 tasks)average success rate: 0.636 -> 0.720Improved
add point filtering before action calculation (ablation)EC-Flow · Meta-World (9 tasks)average success rate: 0.582 -> 0.720Improved
track full-arm embodiment points instead of only end-effector points (ablation)EC-Flow · Meta-World (9 tasks)average success rate: 0.604 -> 0.720Improved
predict flow end-to-end instead of video prediction plus off-the-shelf tracking (ablation)EC-Flow · Meta-World (9 tasks)average success rate: 0.667 -> 0.720Improved
embodiment-centric flow instead of object-centric flowEC-Flow vs Track2Act · Meta-World (9 tasks)average success rate: 0.556 -> 0.720Improved
embodiment-centric flow instead of object-centric flowEC-Flow vs Track2Act · Real-world manipulation (7 tasks)successful trials out of 70: 21/70 -> 54/70Improved
full-joint optimization instead of end-effector-only regression in action calculation (ablation)EC-Flow · Meta-World and real worldsuccess rate: 66.7% -> 72.0% (sim), 70.0% -> 77.1% (real)Improved
full-joint optimization instead of end-effector-only regression in action calculation (ablation)EC-Flow · Meta-World and real worldinference latency: 0.21 s -> 0.37 sHurt
add 5 human videos to 2 robot demosEC-Flow · Meta-World door-open and door-closesuccess rate: 46% -> 52%Improved
add 50 human videos to 2 robot demosEC-Flow · Meta-World door-open and door-closesuccess rate: 46% -> 70%Improved
human videos alone without robot demosEC-Flow · Meta-World door-open and door-closesuccess rate: 0% vs 46%Hurt
use fewer sampled points N_p (ablation)EC-Flow · Meta-World (9 tasks)average success rateHurt

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