Publications

Jingqi Zhou, Sheng Wang

Co-Corresponding Author

, Dezhao Deng, Junwen Lu, Qintong Li, Jiahui Gao, Junwei Su, Hao Wu, Jiyue Jiang, Lingpeng Kong, Chuan Wu

Co-Corresponding Author

(2026). ToolSelf: Runtime Self-Reconfiguration for Robust Long-Horizon Agentic Tasks. ICML 2026 Submission.

Fangrui Huang, Souhad Chbeir, Arpandeep Khatua, Sheng Wang, Sijun Tan, Kenan Ye, Lillian Annabelle Bailey, Merryn Daniel, Ryan Louie, Sanmi Koyejo, Ehsan Adeli (2026). TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots. ICML 2026 Submission.

Jiyue Jiang, Alfred Kar Yin Truong, Yanyu Chen, Qinghang Bao, Sheng Wang, Pengan Chen, Jiuming Wang, Lingpeng Kong, Yu Li, Chuan Wu (2025). Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models. In EMNLP 2025 Findings.

Boyang Xue, Fei Mi, Qi Zhu, Hongru Wang, Rui Wang, Sheng Wang, Erxin Yu, Xuming Hu, Kam-Fai Wong (2025). UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models. In ACL 2025 Main.

Boyang Xue, Hongru Wang, Rui Wang, Sheng Wang, Zezhong Wang, Yiming Du, Bin Liang, Wenxuan Zhang, Kam-Fai Wong (2025). MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models. In ACL 2025 Findings.

Equal contribution

Equal contribution

Equal contribution

, Qintong Li, Jingwei Dong, Jiahui Gao, Boyang Xue, Jiyue Jiang, Lingpeng Kong, Chuan Wu (2025). TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning. In NeurIPS 2025 Spotlight.

Preprint Preprint

Equal contribution

Equal contribution

Equal contribution

, Lingpeng Kong, Chuan Wu (2025). QSpec: Speculative decoding with complementary quantization schemes. In EMNLP 2025 Main.

Preprint Preprint

Jingqi Zhou, Sheng Wang

Co-Corresponding Author

, Jingwei Dong, Lei Li, Jiahui Gao, Lingpeng Kong, Chuan Wu

Co-Corresponding Author

(2025). ProReason: Multi-modal proactive reasoning with decoupled eyesight and wisdom. In EMNLP 2025 Main.

Preprint Preprint

Equal contribution

, Liheng Chen, Pengan Chen, Jingwei Dong, Boyang Xue, Jiyue Jiang, Lingpeng Kong, Chuan Wu (2025). MoS: Unleashing parameter efficiency of low-rank adaptation with mixture of shards. In ICLR 2025.

Jiyue Jiang, Pengan Chen, Liheng Chen, Sheng Wang, Qinghang Bao, Lingpeng Kong, Yu Li, Chuan Wu (2025). How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models. In NAACL 2025 Findings.

Preprint Preprint