Jiannan Huang

jiannan.jpeg

Hi, I am Jiannan Huang, a first-year graduate student majoring in Computer Science at Georgia Institute of Technology, where I am fortunate to be advised by Prof. Humphery Shi. Prior to joining Georgia Tech, I hold a B.S. in Computer Science from Beijing Jiaotong University. During my undergradute, I had the privilege of being supervisied by Prof. Yunchao Wei.

Human intelligence and reasoning are not limited to text, but arise from coordinated multimodal thinking. My long-term goal is to build robust, high-performing multimodal reasoning systems that enable stronger intelligence and content generation. My research interest lies in data synthesis, evaluation, model/agentic system design, and training for such multimodal system.

I am open to any collaboration on topics with which I am familiar. If you would like to collaborate with me or just chat, feel free to send me an email.

Email: jiannan2003 at gmail dot com

CV

News

Dec. 2025

We release the tech report for PAI-Bench, the first comprehensive benchmark for Physical AI! Check it out here. 🚀

Sep. 2025

We release Physical AI Bench (PAI-Bench), a comprehensive benchmark for Physical AI generation, check our code and data!

Aug. 2025

I begin my journey at Gatech as a graduate student, hello Atlanta!

Apr. 2025

Our paper about Generalized Neighborhood Attention(GNA) is out!

Feb. 2025

Our paper AdGPT is accepted to TOMM!

Education

Graduate Student in Computer Science

School of Interactive Computing
Georgia Institute of Technology Aug. 2025 - Present

B.S., Computer Science & Technology

School of Computer Science & Technology
Beijing Jiaotong University Sept. 2021 - June 2025

Experiences

Researcher

Mentor: Humphrey Shi
SHI Labs, Interactive Computing @ Georgia Tech Jun. 2024 - Present

Visiting Student

Mentor: Jiazheng Xu, Jie Tang
Knowledge Engineering Group(KEG), Tsinghua University May. 2023 - Sept. 2023

Undergraduate Researcher

Mentor: Yunchao Wei
WEI Lab, Beijing Jiaotong University Apr. 2022 - Jul. 2025

Publications

  1. physical-ai-bench-logo.png
    Physical AI Bench: A Comprehensive Benchmark for Physical AI Generation and Understanding
    Fengzhe Zhou*, Jiannan Huang*, Jialuo Li*, Deva Ramanan, and Humphrey Shi
    Arxiv, 2025
    arXiv Code Leaderboard PAI-Bench-G PAI-Bench-C PAI-Bench-U
  2. gna_preview.png
    Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light
    Ali Hassani, Fengzhe Zhou, Aditya Kane, Jiannan Huang, Chieh-Yun Chen, Min Shi, 
    Steven Walton, Markus Hoehnerbach, Vijay Thakkar, Michael Isaev, Qinsheng Zhang, Bing Xu, 
    Haicheng Wu, Wen-mei Hwu, Ming-Yu Liu, and Humphrey Shi
    Arxiv, 2025
    arXiv PDF Code
  3. sage.png
    SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing
    Hongguang Zhu, Yunchao Wei, Mengyu Wang, Siyu Jiao, Yan Fang, Jiannan Huang, 
    and Yao Zhao
    Arxiv, 2025
    arXiv PDF
  4. classdiffusion_preview.png
    ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance
    Jiannan Huang, Jun Hao Liew, Hanshu Yan, Yuyang Yin, Yao Zhao, Humphrey Shi, 
    and Yunchao Wei
    International Conference on Learning Representations(ICLR), 2025
    arXiv PDF Code Website
  5. collaborative.png
    Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation
    Siyu Jiao*, Hongguang Zhu*, Jiannan Huang, Yao Zhao, Yunchao Wei, and Humphrey Shi
    European Conference on Computer Vision(ECCV)(Oral) , 2024
    arXiv PDF Code
  6. adgpt_preview.png
    AdGPT: Explore Meaningful Advertising with ChatGPT
    Jiannan Huang, Mengxue Qu, Longfei Li, and Yunchao Wei
    Transactions on Multimedia Computing Communications and Applications(TOMM), 2025
    HTML PDF Code

Service

Reviewer: ICLR2025/2026, ICCV2025