AI Paper Atlas

Research map / Video / Action recognition

Generalizing Action-Conditioned Latent World Models with Video Model Rewards

Haichao Zhang, Yijiang Li, Shwai He, Van T Le, Nuno Vasconcelos, Yun Fu

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

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

The paper targets generalization of action-conditioned JEPA-style latent world models beyond narrow embodied training data, using video model rewards; only the abstract was available, so most fields are left unknown.

Problem

Action-conditioned latent world models (JEPA-style) are usually trained on single or narrowly scoped embodied datasets with limited task, object, embodiment, and action-space coverage, so they fail to generalize beyond those settings.

Approach

Uses video model rewards to train or guide action-conditioned latent predictors so they generalize beyond narrow embodied datasets; the precise mechanism is not stated in the abstract provided.

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