Haoyi Zhu

6

Papers

98

Total Citations

Papers (6)

Aether: Geometric-Aware Unified World Modeling

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers

Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge