Full Publications Browse every paper with quick PDF previews. Use the year strip to jump between cohorts. Please use Menu to go back. Updated Feb 2026 ☰ Menu All 2026 2025 2024 2026 2026 Efficient Test-Time Scaling via Self-Calibration Chengsong Huang , Langlin Huang , Jixuan Leng , Jiacheng Liu , Jiaxin Huang ICLR International Conference on Learning Representations (ICLR) PDF Code 2025 2025 Reliable and Responsible Foundation Models Xinyu Yang , Junlin Han , Rishi Bommasani , Jinqi Luo , Wenjie Qu , Wangchunshu Zhou … (full author list hidden) Transactions on Machine Learning Research (TMLR) PDF 2025 POSS: Position Specialist Generates Better Draft for Speculative Decoding Langlin Huang , Chengsong Huang , Jixuan Leng , Di Huang , Jiaxin Huang Preprint (2025) PDF Code 2025 Semi-structured LLM Reasoners Can Be Rigorously Audited Jixuan Leng , Cassandra A. Cohen , Zhixian Zhang , Chenyan Xiong , William W. Cohen Preprint (2025) PDF Code 2025 CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation Jixuan Leng , Chengsong Huang , Langlin Huang , Bill Yuchen Lin , William W. Cohen , Haohan Wang … (full author list hidden) COLM Second Conference on Language Modeling (COLM) PDF Code Data 2025 Taming Overconfidence in LLMs: Reward Calibration in RLHF Jixuan Leng , Chengsong Huang , Banghua Zhu , Jiaxin Huang ICLR International Conference on Learning Representations (ICLR) PDF Code 2024 2024 S²FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity Xinyu Yang , Jixuan Leng , Geyang Guo , Jiawei Zhao , Ryumei Nakada , Linjun Zhang … (full author list hidden) NeurIPS Conference on Neural Information Processing Systems (NeurIPS) PDF Code 2024 Development of UroSAM: A Machine Learning Model to Automatically Identify Kidney Stone Composition from Endoscopic Video Jixuan Leng , Junfei Liu , Galen Cheng , Haohan Wang , Scott Quarrier , Jiebo Luo … (full author list hidden) J.Endourol. Journal of Endourology PDF 2024 Choosing Wisely and Learning Deeply: Selective Cross-Modality Distillation via CLIP for Domain Generalization Jixuan Leng , Yijiang Li , Haohan Wang TMLR Transactions on Machine Learning Research (TMLR) PDF Code