Jixuan Leng

2026

1. Efficient Test-Time Scaling via Self-Calibration

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

   International Conference on Learning Representations (ICLR) 2026 | [ arXiv Code Preview ]

2025

1. Reliable and Responsible Foundation Models

   Xinyu Yang , Junlin Han , Rishi Bommasani , Jinqi Luo , Wenjie Qu , Wangchunshu Zhou , Adel Bibi , Xiyao Wang

    + 44 more

   Jaehong Yoon , Elias Stengel-Eskin , Shengbang Tong , Lingfeng Shen , Rafael Rafailov , Runjia Li , Zhaoyang Wang , Yiyang Zhou , Chenhang Cui , Yu Wang , Wenhao Zheng , Huichi Zhou , Jindong Gu , Zhaorun Chen , Peng Xia , Tony Lee , Thomas P Zollo , Vikash Sehwag , Jixuan Leng , Jiuhai Chen , Yuxin Wen , Huan Zhang , Zhun Deng , Linjun Zhang , Pavel Izmailov , Pang Wei Koh , Yulia Tsvetkov , Andrew Gordon Wilson , Jiaheng Zhang , James Zou , Cihang Xie , Hao Wang , Philip Torr , Julian McAuley , David Alvarez-Melis , Florian Tramèr , Kaidi Xu , Suman Jana , Chris Callison-Burch , Rene Vidal , Filippos Kokkinos , Mohit Bansal , Beidi Chen , Huaxiu Yao

   (full list hidden)

   Transactions on Machine Learning Research (TMLR) 2025 | [ arXiv OpenReview Preview ]
2. POSS: Position Specialist Generates Better Draft for Speculative Decoding

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

   Preprint 2025 | [ arXiv Code Preview ]
3. Semi-structured LLM Reasoners Can Be Rigorously Audited

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

   Preprint 2025 | [ arXiv Code Preview ]
4. 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 , Jiaxin Huang

   Second Conference on Language Modeling (COLM) 2025 | [ arXiv Code Dataset Preview ]
5. Taming Overconfidence in LLMs: Reward Calibration in RLHF

   Jixuan Leng , Chengsong Huang , Banghua Zhu , Jiaxin Huang

   International Conference on Learning Representations (ICLR) 2025 | [ arXiv Code OpenReview Preview ]

2024

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

   Xinyu Yang , Jixuan Leng , Geyang Guo , Jiawei Zhao , Ryumei Nakada , Linjun Zhang , Huaxiu Yao , Beidi Chen

   Conference on Neural Information Processing Systems (NeurIPS) 2024 | [ arXiv Code OpenReview Preview ]
2. 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 , Rajat Jain

   Journal of Endourology 2024 | [ arXiv Website ]

   Introduction: Chemical composition analysis is important in prevention counseling for kidney stone disease. Advances in laser technology have made dusting techniques more prevalent, but this offers no consistent way to collect enough material to send for chemical analysis, leading many to forgo this test. We developed a novel machine learning (ML) model to effectively assess stone composition based on intraoperative endoscopic video data. Methods: Two endourologists performed ureteroscopy for kidney stones ≥ 10 mm. Representative videos were recorded intraoperatively. Individual frames were extracted from the videos, and the stone was outlined by human tracing. An ML model, UroSAM, was built and trained to automatically identify kidney stones in the images and predict the majority stone composition as follows: calcium oxalate monohydrate (COM), dihydrate (COD), calcium phosphate (CAP), or uric acid (UA). UroSAM was built on top of the publicly available Segment Anything Model (SAM) and incorporated a U-Net convolutional neural network (CNN). Discussion: A total of 78 ureteroscopy videos were collected; 50 were used for the model after exclusions (32 COM, 8 COD, 8 CAP, 2 UA). The ML model segmented the images with 94.77% precision. Dice coefficient (0.9135) and Intersection over Union (0.8496) confirmed good segmentation performance of the ML model. A video-wise evaluation demonstrated 60% correct classification of stone composition. Subgroup analysis showed correct classification in 84.4% of COM videos. A post hoc adaptive threshold technique was used to mitigate biasing of the model toward COM because of data imbalance; this improved the overall correct classification to 62% while improving the classification of COD, CAP, and UA videos. Conclusions: This study demonstrates the effective development of UroSAM, an ML model that precisely identifies kidney stones from natural endoscopic video data. More high-quality video data will improve the performance of the model in classifying the majority stone composition.

3. 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) 2024 | [ arXiv Code OpenReview ]