I am a first-year Ph.D. student in Computer Science at the University of California, Santa Barbara, advised by Prof. Xin (Eric) Wang. I received my M.S. in Computer Science from the University of Southern California, where I was honored with the Best Computer Science Research Award. Prior to that, I earned my B.E. in Software Engineering from Tsinghua University and graduated with the distinction of Outstanding Undergraduate.
At USC, I was fortunate to be advised by Prof. Jieyu Zhao and Prof. Kuan-Hao Huang.
My research interests primarily lie in multimodal learning and AI agents. Recently, I have been particularly interested in improving the fine-grained reasoning capabilities of multimodal models and in developing open-ended self-improving agents.
😊 Collaboration
I’m always excited to collaborate on research projects. If you are a PhD student or researcher and think our interests align, feel free to reach out via email!
I’m also happy to mentor undergraduate and master’s students interested in research. If you are interested in working together, please don’t hesitate to contact me by email.
🔥 News
- 2026.02: 🎉🎉 I’ll be joining Amazon this summer as an Applied Scientist Intern, working on self-improving AI and agents. Excited for the opportunity and looking forward to the summer!
- 2026.01: 🎉🎉 one paper accepted at EACL 2026 as an Oral Presentation! Check What’s Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning for more details!
- 2025.09: Started my Ph.D. in Computer Science at UCSB.
- 2024.05: 🎉🎉 Honored to receive the Best Computer Science Research Award at USC.
📝 Selected Publications
-
Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing
Zhaotian Weng, Antonis Antoniades, Deepak Nathani, Zhen Zhang, Sophia Xiao Pu, Xin (Eric) Wang.
Under review for a top-tier conference. -
What’s Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning
Zhaotian Weng, Haoxuan Li, Xin (Eric) Wang, Kuan-Hao Huang, Jieyu Zhao.
EACL 2026. -
Evaluating and Improving Context-aware Privacy Protection in Vision-Language Models
Zhaotian Weng, Haoxuan Li, Jieyu Zhao.
NeurIPS 2025 Workshop on Efficient Reasoning. -
Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Models from a Causal Mediation Perspective
Zhaotian Weng, Zijun Gao, Jerone Andrews, Jieyu Zhao.
EMNLP 2024. -
BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents
Haoxuan Li, Mingyu Derek Ma, Jen-tse Huang, Zhaotian Weng, Wei Wang, Jieyu Zhao.
arXiv preprint. -
LLM Self-contradictory Hallucination Mitigation via Retrieval-Based Post-Processing
Zhaotian Weng, Xingjian Dong, Liyan Huang, Jingwen Qi.
SoCal NLP Symposium 2024.
🎖 Honors and Awards
- Best Computer Science Research Award, University of Southern California
- Outstanding Undergraduate Graduate Honor, Tsinghua University
- Scholarships: Academic Excellence; Scientific Research Excellence; Sports Excellence (Tsinghua University)
- Competitions: 1st prize, National College Students Physics Competition (2020); Honorable Mention, MCM (2022); 1st prize, Tsinghua University Software Development Competition
🎓 Education
-
University of California, Santa Barbara
Ph.D. in Computer Science, Sep. 2025 – Present
Advisor: Prof. Xin (Eric) Wang -
University of Southern California
M.S. in Computer Science, Aug. 2023 – May. 2025
Advisors: Prof. Jieyu Zhao, Prof. Kuan-Hao Huang
Honor: Best Computer Science Research Award -
Tsinghua University
B.Eng. in Software Engineering, Sep. 2019 – Jun. 2023
Honor: Outstanding Undergraduate Graduate Honor
📘 Teaching
-
Teaching Assistant, CS 16: Problem Solving (C++)
University of California, Santa Barbara, Winter 2026 -
Course Producer, CSCI 585: Database Systems
University of Southern California, Fall 2024
🧑⚖️ Service
- Conference Reviewer: EMNLP 2024, ARR 2024 (August, October, December), ACL 2025, EMNLP 2025, ARR 2025 October.
- Conference Volunteer: EMNLP 2024
💻 Internships
- Machine Learning Engineer, MockAI
Los Angeles, CA · Feb. 2024 – May. 2024