About Me

Hi there, I am a third-year CS PhD student at the University of Notre Dame. I am fortunate to have Professor Xiangliang Zhang as my advisor and grateful for the guidance of Professor Yapeng Tian.

My research broadly focuses on multimodal intelligence, including text, vision, audio, and other modalities, for real-world interaction. My current methodological interests include:

Agentic RL for LLMs and MLLMs
Multimodal perception and reasoning
Multimodal knowledge editing

Organization of Tutorials and Workshops

CVPR 2026 / ICCV 2025, KnowledgeMR: Workshop on Knowledge-Intensive Multimodal Reasoning [Link]
AAAI 2026, AI4Research: Workshop on AI for Scientific Research [Link]
CVPR 2025, Multimodal Mathematical Reasoning Tutorial: Frontiers in Integrating Vision, Language, and Symbolic Representations [Link]

Selected Publications

* indicates equal contribution

Towards Trustworthy Memory Consolidation in Long-Term Memory Agents

Tianyu Yang, Sudipta Paul, Vijay Srinivasan, Vivek Kulkarni, Srinivas Chappidi

in submission 2026

MM-VARA: Understanding-Then-Retrieving for Agentic Multimodal RAG

Tianyu Yang, Simon Shir, Zhenzhen Li, Minhao Cheng, Xiangliang Zhang

in submission 2026

Agentic Multimodal RAG: Roles, Decisions, and Evaluation

Tianyu Yang*, Wenliang Guo*, Xiujin Liu, Shijian Deng, Yilun Zhao, Yapeng Tian, Xiangliang Zhang

in submission 2026

DesignAgent: Interactive 3D Scene Editing via Multimodal Agentic Reasoning

Xiujin Liu*, Tianyu Yang*, Chen Zhao, Yilun Zhao, Xiangliang Zhang

in submission 2026

Multimodal mathematical reasoning teaser

Deconstructing Multimodal Mathematical Reasoning: Towards a Unified Perception-Alignment-Reasoning Paradigm

Tianyu Yang*, Sihong Wu*, Yilun Zhao, Zhenwen Liang, Lisen Dai, Chen Zhao, Minhao Cheng, Arman Cohan, Xiangliang Zhang

ACL 2026

pdf

Quest2DataAgent: Automating End-to-End Scientific Data Collection

Tianyu Yang, Yuhan Liu, Ethan Brown, Sobin Alosious, Jason Rohr, Tengfei Luo, Xiangliang Zhang

EMNLP 2025

pdf

CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP

Tianyu Yang, Lisen Dai, Xiangqi Wang, Minhao Cheng, Yapeng Tian, Xiangliang Zhang

ACL 2025

pdf

SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering

Tianyu Yang, Yiyang Nan, Lisen Dai, Zhenwen Liang, Yapeng Tian, Xiangliang Zhang

EMNLP 2024

pdf

Education

2023.09 - Present, University of Notre Dame, South Bend, IN
PhD in Computer Science

Personal Service

Reviewer: ARR Rolling Review (2023-2025), CVPR, ECCV, ICCV, COLM, ICLR, NeurIPS, ICML, KDD, CIKM, ICDM

Experience

2026.01 - 2026.05, Samsung Research America
Research Intern
2025.05 - 2025.08, Bosch Research
Research Intern
2023.05 - 2023.08, Intel & OpenCV.org
SDE Intern