AI Paper Atlas

Research map / Video / Action recognition

Multi-view Consistent Latent Action Learning for World Modeling and Control

Shenghua Wan, Xiaohai Hu, Xunlan Zhou, Lei Yuan, Le Gan, De-Chuan Zhan

ICML 2026 · Video › Action recognition · approach: Action anticipation and latent actions

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-view consistency loss (self-distillation) to latent action learning (ablation)MuCoLA · Multi-view test sets, next-frame reconstructionPSNR: 32.36 -> 37.97Improved
add cross-view consistency loss (ablation)MuCoLA · Action regression on OpenX (test)RMSE: 0.225 -> 0.214Improved
add explicit Gaussian prior (KL weight 0.5) on latent actions (ablation)MuCoLA · Multi-view test sets, next-frame reconstructionPSNR: 37.97 -> 35.42Hurt
add explicit Gaussian prior on latent actions (ablation)MuCoLA · Action regression on OpenX (test)RMSE: 0.214 -> 0.233Hurt
add Gaussian prior or drop consistency loss (ablation)MuCoLA · VP2 visual planning and Meta-World MBRLsuccess rateHurt
use MuCoLA latent actions instead of AdaWorldiVideoGPT world model · Multi-view test sets, next-frame reconstructionLPIPS (%): 14.63 -> 9.42Improved
use MuCoLA instead of AdaWorld for behavior cloningViT-T policy · LIBERO (four suites)success rate (%): Long 55.2 -> 65.4; Goal 76.1 -> 73.8Mixed
increase prototype vocabulary K to 8192 (and shrink below 2048) (ablation)MuCoLA · reconstruction errorreconstruction errorHurt
scale Spatial-Temporal Transformer parameter count (ablation)MuCoLA · next-frame reconstructionLPIPSImproved
scale training data from 1% to 100% (ablation)MuCoLA · next-frame reconstructionLPIPSImproved
increase labeled action samples for grounding (1K to 5K+) (ablation)MuCoLA · LIBEROsuccess rateImproved

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