Yunhao Fang
Scholar

Yunhao Fang

Google Scholar ID: vrYHLMgAAAAJ
Research Scientist @ ByteDance
PerceptionDecision Making
Citations & Impact
All-time
Citations
693
 
H-index
9
 
i10-index
9
 
Publications
12
 
Co-authors
2
list available
Resume (English only)
Academic Achievements
  • Selected Publications & Preprints: VILA^2: VLM Augmented VLM with Self-Improvement (In Submission); Deductive Verification of Chain-of-Thought Reasoning (NeurIPS 2023); Distilling Large Vision-Language Model with Out-of-Distribution Generalizability (ICCV 2023); Conference Reviewer: ECCV 2024, ICLR 2024, CVPR 2024; China National Scholarship, 2022.
Research Experience
  • Research Scientist Intern at Nvidia, advised by Dr. Jason Lu and Prof. Song Han; Maintainer of the opensource codebase mmtracking at Shanghai AI Laboratory; Teaching Assistant for CSE 275: Deep Learning for 3D Data at UC San Diego, Fall 2023.
Education
  • Master's degree, Department of Computer Science and Engineering, University of California San Diego, advised by Prof. Hao Su; B.Eng. in Electronic Engineering, Zhejiang University.
Background
  • Research interests include Perception, Generalized Representation, Synergy between Understanding and Generation, Reasoning and Common Sense, Concept Emergence and Common Sense, Advanced Reasoning for Scientific Discoveries, Generative Modeling, Efficient World Model, Learning from (Human or AI) Feedback. Long-term research goal is to advance multimodal intelligence by developing automated learning systems that integrate closed-loop data pipelines, efficient algorithms, and robust evaluation tools.
Miscellany
  • Contact: Email: seerkfang [@] gmail [DOT] com; Social: Twitter / Github / LinkedIn