Showing 2026Show all
2 papers · 1 filter
cs.LG2026
LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models
Luzhe Huang, Lei Chu, Jingyi Liang +1
Compact JEPA world models enable efficient latent-space planning, but low-dimensional representation trained under reward-free self-supervision must encode both action-conditioned…
cs.CV2026
Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Prediction
Lei Chu, Yuhuan Zhao
Deepgenerative models havebecomeapromisingapproach for human motion prediction due to their ability to capture multimodal distributions and represent diverse human be haviors. Howe…