ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
Paper • 2607.27924 • Published • 15
Haoyi Niu
DRLearner
AI & ML interests
Cross-Embodiment Learning, Reinforcement Learning, Robot Learning
Recent Activity
authored a paper 6 days ago
ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow authored a paper 6 days ago
Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models authored a paper 6 days ago
Efficient Robotic Policy Learning via Latent Space Backward PlanningOrganizations
None yet
authored 6
papers 6 days ago
Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models
Paper • 2607.14635 • Published
Efficient Robotic Policy Learning via Latent Space Backward Planning
Paper • 2505.06861 • Published
PhysiAgent: An Embodied Agent Framework in Physical World
Paper • 2509.24524 • Published
Skill Expansion and Composition in Parameter Space
Paper • 2502.05932 • Published • 4
When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning
Paper • 2206.13464 • Published • 1
upvoted a paper 8 days ago