Haoyi Zhu

HaoyiZhu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 10 papers 3 days ago

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

Paper • 2206.08853 • Published Jun 17, 2022 • 1

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time

Paper • 2211.03375 • Published Nov 7, 2022

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

Paper • 2410.08208 • Published Oct 10, 2024

PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

Paper • 2310.08586 • Published Oct 12, 2023

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

Paper • 2507.01016 • Published Jul 1 • 1

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

Paper • 2310.08370 • Published Oct 12, 2023

$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning

Paper • 2507.13347 • Published Jul 17 • 64

DeepVerse: 4D Autoregressive Video Generation as a World Model

Paper • 2506.01103 • Published Jun 1

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

Paper • 2509.05296 • Published 28 days ago • 7

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Paper • 2509.12201 • Published 18 days ago • 103

authored a paper 6 months ago

Aether: Geometric-Aware Unified World Modeling

Paper • 2503.18945 • Published Mar 24 • 28