Yunhao Fang 方云浩

Yunaho Fang 

Master candidate,
Department of Computer Science and Engineering,
University of California San Diego
Email: seerkfang [@] gmail [DOT] com
Twitter / Github / LinkedIn


I am looking for a Ph.D. position in fall 2024 and research internship. Please feel free to contact me!

I am currently working on large language model and vision language model for decision making. Email me if you are interested in collaboration!

About me

I am a Master candidate in the Department of Computer Science and Engineering at the University of California San Diego, and I am fortunate to be advised by Prof. Hao Su.

Prior to starting as a Master student, I received my B.Eng. in Electronic Engineering from Zhejiang University. I have also spent time at Shanghai AI Laboratory, as the maintainer of the opensource codebase mmtracking.

My long-term research goal is to build an AGI framework with generalizable perception and beyond-human level decision making capabilities. Specifically, I am interested in Natural Language Processing, Concept Emergence and Reasoning, and Robotics / Embodied AI.

Research interests

My research interests include

  • Perception

    • Senergy of Vision Language Models

    • Generalizable Representation for 2D and 3D

  • Reasoning and Common Sense

    • Emerged Concepts and Common Sense from Data

    • Reasoning over Common Sense and Formal Systems

  • Embodied AI

    • Compositional Low-level Skills

    • General Sequence Modeling

  • Artificial General Intelligence

    • General Decision Making

    • Creative Agents

Publications & Preprints

Papers sorted by years. Representative papers are highlighted.

2023

hierarchical_exploration 

Unleashing the Creative Mind: Language Model as Hierarchical Policy For Improved Exploration on Challenging Problem Solving
Zhan Ling, Yunhao Fang, Xuanlin Li, Tongzhou Mu, Mingu Lee, Mingu Lee, Reza Pourreza, Roland Memisevic, Hao Su
In Submission

verify_cot 

Deductive Verification of Chain-of-Thought Reasoning
Zhan Ling*, Yunhao Fang*, Xuanlin Li, Zhiao Huang, Hao Su
Neural Information Processing Systems (NeurIPS) 2023
[Code]

vlm_distillation 

Distilling Large Vision-Language Model with Out-of-Distribution Generalizability
Xuanlin Li*, Yunhao Fang*, Minghua Liu, Zhan Ling, Zhuowen Tu, Hao Su
International Conference on Computer Vision (ICCV) 2023
[Code]

Awards

  • China National Scholarship, 2022