About Me - Xiang Huang - 黄祥
Currently, I am a researcher in the Qwen Character Team. I received my Ph.D. degree in 2025, at Nanjing University Websoft Research Group under the supervision of Prof. Yuzhong Qu. Before that, I received my B.Sc. degree from Chongqing University in June 2020.
Feel free to reach out to me if you’re interested in my research~
Research Interest
- Character Model.
- Test time training and Continual Learning.
- Complex Reasoning over Structural Environments (Agent).
Publication
First Author
[ACL’25 Findings] Reverse Preference Optimization for Complex Instruction Following
Keyword: Instruction following, Alignment
Xiang Huang, Ting-En Lin, Feiteng Fang, Yuchuan Wu, Hangyu Li, Yuzhong Qu, Fei Huang, Yongbin Li
paper | code[ACL’25] TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data
Keyword: Synthetic data, ICL-based KBQA, Generalization, Zero-shot QA
Xiang Huang, Jiayu Shen, Shanshan Huang, Sitao Cheng, Xiaxia Wang, Yuzhong Qu
paper | code[ACL’24 Oral] QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction
Keyword: Agent, Self-correction, Neural-Symbolic Reasoning, Tool learning
Xiang Huang, Sitao Cheng, Shanshan Huang, Jiayu Shen, Yong Xu, Chaoyun Zhang, Yuzhong Qu
paper | code[EMNLP’23] MarkQA: A large scale KBQA dataset with numerical reasoning
Keyword: Numerical reasoning, Code/Program-aided reasoning(PAL, PoT)
Xiang Huang, Sitao Cheng, Yuheng Bao, Shanshan Huang, Yuzhong Qu
paper | code[AAAI’23 Oral] Question Decomposition Tree for Answering Complex Questions over Knowledge Bases
Keyword: Question decomposition, Semantic parsing-based KBQA
Xiang Huang, Sitao Cheng, Yiheng Shu, Yuheng Bao, Yuzhong Qu
paper | code
Participants
[AAAI’26 Oral] Reality vs Counterfactual: Multi-World Contrastive Reinforcement Learning for Enhancing MLLM’s Theory of Mind in Egocentric Videos
Keyword:Egocentric videos, Contrastive Reinforcement Learning, Theory of Mind
Guiyang Hou, Yihui Fu, Chen Wu, Xiang Huang, Zhe Zheng, Wenqi Zhang, Yongliang Shen, Weiming Lu(arxiv) TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs’ Social Intelligence
Keyword: Social Intelligence, R1
Guiyang Hou, Gao Xing, Yuchuan Wu, Xiang Huang, Zhe Zheng, Yongliang Shen, Wenqi Zhang, Jialu Du, Fei Huang, Yongbin Li, Weiming Lu(arxiv) Beyond Pairwise Preferences: Modeling Subjective Rewards with Act Adaptive Margins
Keyword:Character Model, Reward Model
Feiteng Fang, Dingwei Chen, Xiang Huang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Jing Ye, Ziqiang Liu, Haonan Zhang, Liang Zhu, Hamid Alinejad-Rokny, Min Yang, Fei Huang, Yongbin Li[ACL’24 Findings] Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
Keyword: Information retrieval-based KBQA, Self-correction
Sitao Cheng, Ziyuan Zhuang, Yong Xu, Fangkai Yang, Chaoyun Zhang, Xiaoting Qin, Xiang Huang, Ling Chen, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
paper | code[ISWC’21] EDG-Based Question Decomposition for Complex Question Answering over Knowledge Bases
Keyword: Question decomposition, Semantic parsing-based KBQA
Xixin Hu, Yiheng Shu, Xiang Huang & Yuzhong Qu
paper | code[UIC’19] Cnnloc: Deep-learning based indoor localization with wifi fingerprinting
Keyword: Question decomposition, Semantic parsing-based KBQA
Xudong Song, Xiaochen Fan, Xiangjian He, Chaocan Xiang, Qianwen Ye, Xiang Huang, Gengfa Fang, Liming Luke Chen, Jing Qin, Zumin Wang
paper | code
Awards & Honors
- Scholarship for Doctoral Excellence, Nanjing University
- Outstanding Graduate Students, Nanjing University
- First-Class Scholarship (Top 2%), Chongqing University
- National Inspiration Scholarship, Chongqing University
- Advanced Individuals in Innovation and Entrepreneurship (Top 10 in university), Chongqing University
Education
- 2020.09 - Now Nanjing University - Computer science (Ph.D.)
- 2016.09 - 2020.06 Chongqing University - Computer science and technology (Bachelor)
Intership
- 2024.07 - 2025.09 Tongyi Laboratory, Alibaba Group
Teaching Assistant
Discrete Mathematics (2021-2025)
Academic Services
Reviewer
