PPaperPicks

Hao Su

University of California San Diego, CA, USA

28 papers at tracked venues · 21 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation
  2. Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenes
  3. Hierarchical World Models as Visual Whole-Body Humanoid Controllers
  4. Learning Adaptive Dexterous Grasping from Single Demonstrations
  5. ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks
  6. Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
  7. MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic Humans
  8. NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support
  9. Point-SAM: Promptable 3D Segmentation Model for Point Clouds
  10. Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
  11. Reward-free World Models for Online Imitation Learning
  12. When Should We Prefer State-to-Visual DAgger over Visual Reinforcement Learning?
  13. BeyondVision: An EMG-driven Micro Hand Gesture Recognition Based on Dynamic Segmentation
  14. CONDENSE: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images
  15. Chain-of-Thought Predictive Control
  16. CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
  17. Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-rank Decomposition
  18. DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
  19. Estimating before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning
  20. Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
  21. MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model
  22. MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field
  23. One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion
  24. Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration
  25. RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
  26. Reverse Forward Curriculum Learning for Extreme Sample and Demo Efficiency
  27. SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views
  28. TD-MPC2: Scalable, Robust World Models for Continuous Control