About Me

I am a Ph.D. student at The Hong Kong University of Science and Technology (Guangzhou), starting in 2024, advised by Prof. Jing Tang and Prof. Yiwei Wang. I have also been fortunate to collaborate with Prof. Yujun Cai, whose guidance and support have been invaluable to my research.

Before joining HKUST (GZ), I received my Bachelor degree from the School of Mathematics, South China University of Technology in 2024.

My research interests focus on large language models (LLMs) and multimodal large language models, with particular emphasis on reasoning and post-training techniques (e.g., alignment, reinforcement learning, and optimization after pretraining).

I am actively seeking research internship opportunities in industry. If you’re interested in collaborating or exploring potential research opportunities, please don’t hesitate to reach out.

Education

2024/09 — Present: Ph.D. in Data Science and Analytics, The Hong Kong University of Science and Technology (Guangzhou)
2020/09 — 2024/06: B.Eng. in Information Management and Information System, South China University of Technology

Publication

ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning
Xingjian Tao, Yiwei Wang, Yujun Cai, Yifan Song, Jing Tang
ECCV 2026
[Paper]

Mitigating Coordinate Prediction Bias from Positional Encoding Failures
Xingjian Tao, Yiwei Wang, Yujun Cai, Yihong Luo, Kai Han, Jing Tang
Findings of ACL 2026
[Paper]

Are LLMs Really Not Knowledgable? Mining the Submerged Knowledge in LLMs' Memory
Xingjian Tao, Yiwei Wang, Yujun Cai, Zhicheng Yang, Jing Tang
ICLR 2026
[Paper]

Understanding GUI Agent Localization Biases through Logit Sharpness
Xingjian Tao, Yiwei Wang, Yujun Cai, Zhicheng Yang, Jing Tang
Findings of EMNLP 2025
[Paper]

EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval
Yifan Song, Xingjian Tao, Zhicheng Yang, Yihong Luo, Jing Tang
Findings of ACL 2026
[Paper]

Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation
Yifan Song, Fenglin Yu, Yihong Luo, Xingjian Tao, Siya Qiu, Kai Han, Jing Tang
SIGIR 2026
[Paper]

Energy-calibrated vae with test time free lunch
Yihong Luo, Siya Qiu, Xingjian Tao, Yujun Cai, Jing Tang
ECCV 2024
[Paper]

Experience

Research Intern, Tencent
Research Assistant, Hong Kong University of Science and Technology (Guangzhou)