3 papers
cs.CV2025
Rejoining fragmented ancient bamboo slips with physics-driven deep learning
Jinchi Zhu, Zhou Zhao, Hailong Lei +8
Bamboo slips are a crucial medium for recording ancient civilizations in East Asia, and offers invaluable archaeological insights for reconstructing the Silk Road, studying materia…
cs.LG2025
Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient
Yuan Gao, Zujing Liu, Weizhong Zhang +2
Recent Large-Language Models (LLMs) pruning methods typically operate at the post-training phase without the expensive weight finetuning, however, their pruning criteria often rely…
cs.CL2025
Model Hemorrhage and the Robustness Limits of Large Language Models
Ziyang Ma, Zuchao Li, Lefei Zhang +4
Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment t…