Scholar
Zhuoyang Zhang
Google Scholar ID: Q1csT-8AAAAJ
Massachusetts Institute of Technology
Citations & Impact
Citations
1,156
H-index
8
i10-index
8
Publications
11
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- Publications: VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation (ICLR 2025); EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss (CVPR 2024 ELVM Workshop); One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion (CVPR 2024); Complete-to-partial 4D distillation for self-supervised point cloud sequence representation learning (CVPR 2023); CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (CVPR 2025); NVILA: Efficient Frontier Visual Language Models (CVPR 2025); HART: Efficient Visual Generation with Hybrid Autoregressive Transformer (ICLR 2025); Sparse Refinement for Efficient High-resolution Semantic Segmentation (ECCV 2024); Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model (Technical Report).
Research Experience
- During undergraduate studies, worked with Prof. Li Yi and Prof. Hao Su on 3D computer vision.
Education
- Ph.D. Student at MIT EECS, advised by Prof. Song Han; Bachelor's Degree in Computer Science from Yao Class, Tsinghua University.
Background
- Research Interests: Vision-centric efficient machine learning, especially for foundation models. Bachelor's degree from Yao Class, Tsinghua University.
Miscellany
- Academic Service: Conference reviewer for ICLR, ICML, NeurIPS, CVPR, ICCV, ECCV, etc.
