collaborators

6 papers

cs.CL2026

Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models

Xuan Ding, Pengyu Tong, Ranjie Duan +3

While large language models (LLMs) demonstrate impressive performance across various tasks, their deployment in real-world scenarios is still constrained by high computational dema…

cs.CV2026

ONRW: Optimizing inversion noise for high-quality and robust watermark

Xuan Ding, Xiu Yan, Chuanlong Xie +1

Watermarking methods have always been effective means of protecting intellectual property, yet they face significant challenges. Although existing deep learning-based watermarking…

cs.AI2026

AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning

Suzhong Fu, Jingqi Dong, Xuan Ding +4

Evaluating the clinical correctness and reasoning fidelity of automatically generated medical imaging reports remains a critical yet unresolved challenge. Existing evaluation metho…

cs.CV2025

VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel

Suzhong Fu, Rui Sun, Xuan Ding +8

Accurate vessel segmentation is critical for clinical applications such as disease diagnosis and surgical planning, yet remains challenging due to thin, branching structures and lo…

cs.CV2025

Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs

Xuan Ding, Rui Sun, Yunjian Zhang +7

Depth-wise pruning accelerates LLM inference in resource-constrained scenarios but suffers from performance degradation due to direct removal of entire Transformer layers. This pap…

cs.LG2025

DipSVD: Dual-importance Protected SVD for Efficient LLM Compression

Xuan Ding, Rui Sun, Yunjian Zhang +6

The ever-increasing computational demands and deployment costs of large language models (LLMs) have spurred numerous compressing methods. Compared to quantization and unstructured…