AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction

Jung Min Lee, Dohyeok Lee, Seokhun Ju, Taehyun Cho, Jin Woo Koo, Li Zhao, Sangwoo Hong, Jungwoo Lee

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 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 cross-viewpoint reconstruction loss (ablation)MVP-LAM · Bridge V2 latent actionMI (KSG): 0.27 -> 1.10Improved
add cross-viewpoint reconstruction loss (ablation)MVP-LAM · Bridge V2 latent actionlinear probe NMSE: 0.96 -> 0.73Improved
add human multi-view videos to training (ablation)MVP-LAM · Bridge V2 latent actionMI (KSG): 0.50 -> 1.10Improved
add human multi-view videos to training (ablation)MVP-LAM · Bridge V2 latent actionlinear probe NMSE: 0.91 -> 0.73Improved
increase synchronization lag from 0 to 4 frames (ablation)MVP-LAM · Bridge V2 latent action (sync lag)MI (KSG): 1.02 -> 1.02No clear effect
increase synchronization lag from 0 to 4 frames (ablation)MVP-LAM · Bridge V2 latent action (sync lag)linear probe NMSE: 0.78 -> 0.80No clear effect
replace UniVLA latent actions with MVP-LAMVLA pretraining · SIMPLER (WidowX) AVGsuccess rate (%): 39.6 -> 60.4Improved
replace UniVLA latent actions with MVP-LAMVLA pretraining · LIBERO AVG (Bridge V2 pretrain)success rate (%): 92.5 -> 94.1Improved
replace UniVLA latent actions with MVP-LAMVLA pretraining · LIBERO-Object (Bridge V2 pretrain)success rate (%): 95.4 -> 94.6Hurt
replace UniVLA latent actions with MVP-LAMVLA pretraining · LIBERO-Long (Bridge V2 pretrain)success rate (%): 87.5 -> 90.8Improved
replace UniVLA latent actions with MVP-LAMlatent action model · Bridge V2 inverse probeNMSE: 0.875 -> 0.792Improved
replace UniVLA latent actions with MVP-LAMlatent action model · LIBERO-Goal inverse probeNMSE: 0.587 -> 0.643Hurt

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