Jingcheng Xie — accepted AI-conference papers

2026

Efficient Plug-and-Play Weight Refinement for Sparse Large Models

Jingcheng Xie, Yinda Chen, Xiaoyu Liu, Yinglong Li, Haoyuan Shi, Zhiwei Xiong

AAAI 2026technical

One-shot pruning efficiently compresses Large Language Models but produces coarse sparse weights, causing significant performance degradation. Traditional fine-tuning approaches to refine these weights are prohibitively expensive for large models. This highlights the need for a training-free weight

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

SHERPA: Fine-tuning Segment Anything Models with Task-relevant Guidance

Jingcheng Xie, Yinda Chen, Xiaoyu Liu, Haoyuan Shi, Zhiwei Xiong

ICML 2026poster

Segment Anything Models (SAMs) often struggle with certain specialized tasks. A common approach is to fine-tune models with specific task labels, but this often leads to overfitting, introduces model bias and significantly degrades their generalization ability. To overcome these challenges, we propo…

Cited by 0 Source ↗Scholar ↗