• I am a PhD student in Software Institute at Nanjing University. I am fortunate to be advised by Prof. Zhenyu Chen and Prof. Chunrong Fang.
• Research Interests: AI4SE; Responsible AI; LLM Reasoning.

News

• [2025-05] Our research paper “Token-Budget-Aware LLM Reasoning” on LLM Reasoning got accepted by ACL!
• [2025-05] Our research paper “Security of Language Models for Code: A Systematic Literature Review” on LLM Reasoning got accepted by TOSEM!
• [2025-02] Our research paper “Mutual information guided backdoor mitigation for pre-trained encoders” on Responsible AI got accepted by TIFS!
• [2025-02] Our research paper “Towards Imperceptible Backdoor Attack in Self-supervised Learning” on Responsible AI got accepted by CVPR!

Publications

LLM Reasoning

• Token-Budget-Aware LLM Reasoning
  Tingxu Han*, Zhenting Wang*, Chunrong Fang, Shiyu Zhao, Shiqing Ma, Zhenyu Chen (CCF A, ACL 2025 findings, * indicates equal contribution, HuggingFace Daily Paper Top1)

Responsible AI

• Continuous Concepts Removal in Text-to-image Diffusion Models
  Tingxu Han, Weisong Sun, Yanrong Hu, Chunrong Fang, Yonglong Zhang, Shiqing Ma, Tao Zheng, Zhenyu Chen, Zhenting Wang (Preprint)

• Towards Imperceptible Backdoor Attack in Self-supervised Learning
  Hanrong Zhang, Zhenting Wang, Tingxu Han, Mingyu Jin, Chenlu Zhan, Mengnan Du, Hongwei Wang, Shiqing Ma (CCF A, CVPR 2025)

• Mutual information guided backdoor mitigation for pre-trained encoders
  Tingxu_Han, Weisong Sun, Ziqi Ding, Chunrong Fang, Hanwei Qian, Jiaxun Li, Zhenyu Chen, Xiangyu Zhang (CCF A, TIFS 2025)

• On the effectiveness of distillation in mitigating backdoors in pre-trained encoder
  Tingxu Han, Shenghan Huang, Ziqi Ding, Weisong Sun, Yebo Feng, Chunrong Fang, Jun Li, Hanwei Qian, Cong Wu, Quanjun Zhang, Yang Liu, Zhenyu Chen (Preprint)

AI for SE

• Security of Language Models for Code: A Systematic Literature Review
  Yuchen Chen, Weisong Sun, Chunrong Fang, Zhenpeng Chen, Yifei Ge, Tingxu Han, Quanjun Zhang, Yang Liu, Zhenyu Chen, Baowen Xu (CCF A, TOSEM 2025)

• An Extractive-and-Abstractive Framework for Source Code Summarization
  Weisong Sun, Chunrong Fang, Yuchen Chen, Quanjun Zhang, Guanhong Tao, Yudu You, Tingxu Han, Yifei Ge, Yuling Hu, Bin Luo, Zhenyu Chen (CCF A, TOSEM 2024)

• RULER: discriminative and iterative adversarial training for deep neural network fairness
  Guanhong Tao*, Weisong Sun*, Tingxu Han*, Chunrong Fang, Xiangyu Zhang (CCF A, FSE 2022, * indicates equal contribution)

• Code search based on context-aware code translation
  Weisong Sun, Chunrong Fang, Yuchen Chen, Guanhong Tao, Tingxu Han, Quanjun Zhang (CCF A, ICSE 2022)