0%

All Publications

ICLR 2026

Efficient Test-Time Scaling via Self-Calibration

Chengsong Huang, Langlin Huang, Jixuan Leng, Jiacheng Liu, Jiaxin Huang

International Conference on Learning Representations (ICLR)

PDF Code

TMLR 2025

Reliable and Responsible Foundation Models

Xinyu Yang, Junlin Han, Rishi Bommasani, Jinqi Luo, Wenjie Qu, Wangchunshu Zhou +46 more

Transactions on Machine Learning Research (TMLR)

PDF Paper OpenReview
2025

POSS: Position Specialist Generates Better Draft for Speculative Decoding

Langlin Huang, Chengsong Huang, Jixuan Leng, Di Huang, Jiaxin Huang

Preprint

PDF Paper Code
2025

Semi-structured LLM Reasoners Can Be Rigorously Audited

Jixuan Leng, Cassandra A. Cohen, Zhixian Zhang, Chenyan Xiong, William W. Cohen

Preprint

PDF Paper Code
COLM 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 +1 more

Second Conference on Language Modeling (COLM)

PDF Code Data
ICLR 2025

Taming Overconfidence in LLMs: Reward Calibration in RLHF

Jixuan Leng, Chengsong Huang, Banghua Zhu, Jiaxin Huang

International Conference on Learning Representations (ICLR)

PDF OpenReview Code

NeurIPS 2024

S2FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity

Xinyu Yang, Jixuan Leng, Geyang Guo, Jiawei Zhao, Ryumei Nakada, Linjun Zhang +2 more

Conference on Neural Information Processing Systems (NeurIPS)

PDF OpenReview Code
J.Endourol. 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 +1 more

Journal of Endourology

PDF Website
TMLR 2024

Choosing Wisely and Learning Deeply: Selective Cross-Modality Distillation via CLIP for Domain Generalization

Jixuan Leng, Yijiang Li, Haohan Wang

Transactions on Machine Learning Research (TMLR)

PDF OpenReview Code