Haoyi Zhu
9 papers · 2022–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (29) 🌉 Interdisciplinary Bridge · Silver 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 🏆 Keyword Champion (3)
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(64)
Venues
Top co-authors
Research topics
Deep Learning
(9)
Artificial Intelligence
(7)
Core AI
(7)
Learning Types · Deep Learning
(6)
Computer Vision
(5)
Machine Learning
(3)
Reinforcement Learning
(3)
Robotics
(3)
Analysis
(3)
Applications · Reinforcement Learning
(3)
Capabilities
(2)
Domain-Specific
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Applications · Robotics
(1)
Keywords
3d perception
(3)
zero-shot generalization
(2)
reinforcement learning
(2)
robot learning
(2)
video prediction
(1)
self-supervised learning
(1)
vision transformer
(1)
point cloud
(1)
domain generalization
(1)
trajectory prediction
(1)
policy learning
(1)
neural rendering
(1)
autonomous driving
(1)
vector quantization
(1)
reward function
(1)
multi-view learning
(1)
3d object detection
(1)
autonomous agent
(1)
differentiable rendering
(1)
multimodal learning
(1)
Papers
CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning
CVPR 2026
Aether: Geometric-Aware Unified World Modeling
ICCV 2025
SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
ICLR 2025
Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning
CVPR 2025
VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
ICCV 2025
Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
NeurIPS 2024
UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
CVPR 2024
X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360deg Insufficient RGB-D Views
WACV 2023
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
NeurIPS 2022