Hao Su

12

Papers

368

Total Citations

Papers (12)

TD-MPC2: Scalable, Robust World Models for Continuous Control

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Hierarchical World Models as Visual Whole-Body Humanoid Controllers

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D

DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks

When Should We Prefer State-to-Visual DAgger over Visual Reinforcement Learning?

Reward-free World Models for Online Imitation Learning

De^2Gaze: Deformable and Decoupled Representation Learning for 3D Gaze Estimation

CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation

One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion

PartField: Learning 3D Feature Fields for Part Segmentation and Beyond

Chain-of-Thought Predictive Control