arXiv preprint 2026 First authorShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy DistillationQingyu Zhang, Qianhao Yuan, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun, Xiang Li, Ming Xu, Jiarui Li, Xiuyin ZhaoPDF Cite
AAAI 2026 First authorAI-Salesman: Towards Reliable Large Language Model Driven TelemarketingQingyu Zhang, Chunlei Xin, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Qing Ye, Qianlong Xie, Xingxing WangPDF Cite
ACL Demo 2025AutoAlign: Automated Alignment for Large Language ModelsXinyu Lu, Dong Xu, Chunkang Zhang, Xinyan Guan, Junxiang Wang, Qingyu Zhang, Pengbo Wang, Yingzhi Mao, Hao Xiang, Xueru Wen, Zichao Li, Yaojie Lu, Hongyu Lin, Le Sun, Xianpei HanPDF Cite Code
ICCV 2025ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective LayersQianhao Yuan, Qingyu Zhang, Yanjiang Liu, Jiawei Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le SunPDF Cite
ACL Findings 2025 Co-first authorShortGPT: Layers in Large Language Models are More Redundant Than You ExpectXin Men*, Mingyu Xu*, Qingyu Zhang*, Qianhao Yuan*, Bingning Wang†, Hongyu Lin, Yaojie Lu, Xianpei Han, Weipeng ChenPDF Cite
NeurIPS 2024Base of RoPE Bounds Context LengthXin Men*, Mingyu Xu*, Bingning Wang†, Qingyu Zhang, Hongyu Lin, Xianpei Han, Weipeng ChenPDF Cite
