HuskyDoge

Benhao Huang

MAITRIX
TRAIS
SJTU-XAI
Shanghai, China

About Me

Hello! Husky Here! I'm a senior student at Shanghai Jiao Tong University(SJTU), majoring in Computer Science. I'm currently working with with Professor Zhiting Hu on World Model Projects. Before this, I've been working with my amazing supervisor Jiaqi W. Ma on dataset curations using LLM Agents, at TRAIS Lab. I also had a wonderful research experience regarding AI Interpretability at Professor Quanshi Zhang's XAI Lab.

I'm now busy preparing my MS/PhD applications for Fall 2025, wish all the best!

Education

Sept 2021 - Current
B.S.E. in Computer Science
Shanghai Jiao Tong University
Sept 2018 - June 2021
High School
Zhejiang Ruian High School

Interests

World Model, Reasoning and Planning
Data-centric AI, AI Automation
Interpretable AI

Awards & Scholarships

National Scholarship (Top 0.2% nationwide)
2024
Rui Yuan Hong Shan Scholarship (Top 2%, SJTU)
2023
Shao Qiu Scholarship (Top 4%, SJTU)
2022
Meritorious Winner of MCM/ICM
2022

Research Projects

PAN: Towards General World Model with Natural Language Actions and Video States
Benhao Huang (co-lead), 
Pandora Team, 
Zhiting Hu, 
Eric P. Xing
#World Model
#Image to Video
#Diffusion

A step towards a General World Model (GWM) that can simulate complex video scenarios with natural language actions.

paper (in progress)
report-v1
code
DCA-Bench: A Benchmark for Dataset Curation Agents
Benhao Huang, 
Yingzhuo Yu, 
Jin Huang, 
Xingjian Zhang, 
Jiaqi W. Ma
#LLM Agent
#Benchmark

A benchmark exploring the performance of LLM Agents on detecting issues in datasets hosted on popular platforms. (Under Review)

paper
code
Defining and extracting generalizable interaction primitives from DNNs
Lu Chen, 
Siyu Lou, 
Benhao Huang, 
Quanshi Zhang
ICLR-2024
#LLM
#Explainablity

Given different DNNs trained for the same task, developed a new method to extract interactions that are shared by these DNNs. Experiments show that the extracted interactions can better reflect common knowledge shared by different DNNs.

paper
GitHub
Contrasting Adversarial Perturbations: The Space of Harmless Perturbations
Lu Chen, 
Shaofeng Li, 
Benhao Huang, 
Fan Yang, 
Zheng Li, 
Jie Li, 
Luo Yuan
AAAI 2025
#Adversarial Perturbations
#security

paper