Wei-Chiu Ma

Cornell University — United States

Computer Science · Physical Sciences

21h-index1.9kcitations76works2.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(29), Advanced Neural Network Applications(16), Robotics and Sensor-Based Localization(16), 3D Shape Modeling and Analysis(16), Human Pose and Action Recognition(15)

Publications76 total

X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
arXiv (Cornell University)·2025Open Access
Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
2025
DRAWER: Digital Reconstruction and Articulation With Environment Realism
2025
Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
2025· 6 cited
X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
arXiv (Cornell University)·2025Open Access
DRAWER: Digital Reconstruction and Articulation With Environment Realism
arXiv (Cornell University)·2025Open Access
From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
arXiv (Cornell University)·2024Open Access
Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
arXiv (Cornell University)·2024Open Access
BLINK: Multimodal Large Language Models Can See but Not Perceive
Lecture notes in computer science·2024· 22 cited
Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
arXiv (Cornell University)·2024· 1 citedOpen Access
ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models
2024
Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video
2024· 8 cited
ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models
arXiv (Cornell University)·2024Open Access
Multilingual Diversity Improves Vision-Language Representations
arXiv (Cornell University)·2024· 2 citedOpen Access
Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video
arXiv (Cornell University)·2024Open Access
Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects
arXiv (Cornell University)·2024Open Access
Multilingual Diversity Improves Vision-Language Representations
2024
From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos
2024· 1 cited
LightSim: Neural Lighting Simulation for Urban Scenes
arXiv (Cornell University)·2023Open Access
UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation
arXiv (Cornell University)·2023· 1 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Raquel Urtasun(31), Shenlong Wang(13), Sivabalan Manivasagam(11), Namdar Homayounfar(8), Yuwen Xiong(8), Justin Liang(7), Antonio Torralba(6), Kris Kitani(6), Ze Yang(6), Rui Hu(5), De-An Huang(5), Sanja Fidler(4), Namhoon Lee(3), Jingkang Wang(3), Anqi Yang(3), Ioan Andrei Bârsan(3), Shrinidhi Kowshika Lakshmikanth(3), Hang Chu(3), Jiayuan Gu(3), Wenyuan Zeng(3)