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
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
- Learning Visual Feature-Based World Models via Residual Latent Action (NeurIPS 2026 · similarity 0.90)
- DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control (NeurIPS 2026 · similarity 0.89)
- PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning (ICML 2025 · similarity 0.89)
- Latent Action Pretraining from Videos (ICLR 2025 · similarity 0.89)
- World Models as Group Actions (NeurIPS 2026 · similarity 0.89)
- Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training (NeurIPS 2024 · similarity 0.89)
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.
