Research map / Video / Action recognition
Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer
Hao Luo, Zongqing Lu
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.
Proposes a joint embedding predictive transformer to learn video-conditioned policies from unlabelled (action-free) demonstration videos.
Problem
Training video-conditioned policies requires abundant demonstrations with action labels, but in some tasks expert rollouts exist only as videos, and annotating actions is costly and time-consuming.
Approach
Uses a joint embedding predictive transformer to learn from unlabelled videos without action labels, as stated in the abstract; the specific mechanism is not described in the provided text.
Closest papers by meaning
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations (ICML 2025 · similarity 0.90)
- Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training (NeurIPS 2024 · similarity 0.89)
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations (NeurIPS 2025 · similarity 0.88)
- PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning (ICML 2025 · similarity 0.87)
- Learning to Act from Actionless Videos through Dense Correspondences (ICLR 2024 · similarity 0.87)
- Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos (ICLR 2025 · similarity 0.87)
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.
