语言大模型 / LLM

EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint

Zhenhua Xu, Meng Han, Wenpeng Xing

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments Accepted by EMNLP2025 Main

SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention

Qianchao Zhu, Jiangfei Duan, Chang Chen, Siran Liu, Guanyu Feng, Xin Lv, Xiao Chuanfu, Dahua Lin, Chao Yang

专题命中 效率与部署 ：LLM(title)；large language model(abstract)；language model(abstract)；pretraining(abstract)

sam-llm: interpretable lane change trajectoryprediction via parametric finetuning

Zhuo Cao, Yunxiao Shi, Min Xu

机构 * University of Queensland, School of Civil Engineering（昆士兰大学土木工程学院） ； University of Technology Sydney, Faculty of Engineering（悉尼科技大学工程学院） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 5 pages

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

Yueke Zhang, Yifan Zhang, Kevin Leach, Yu Huang

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments 6 Pages

Evaluating Efficiency and Novelty of LLM-Generated Code for Graph Analysis

Atieh Barati Nia, Mohammad Dindoost, David A. Bader

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments 7 pages, v2: minor revision to match final paper published in the The 29th Annual IEEE High Performance Extreme Computing Conference (HPEC), Virtual, September 15-19, 2025. Outstanding Student Paper Award

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling

Jiahao Qiu, Yifu Lu, Yifan Zeng, Jiacheng Guo, Jiayi Geng, Chenhao Zhu, Xinzhe Juan, Ling Yang, Huazheng Wang, Kaixuan Huang, Yue Wu, Mengdi Wang

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；RLHF(abstract)；preference optimization(abstract)

Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training

Yangtao Deng, Lei Zhang, Qinlong Wang, Xiaoyun Zhi, Xinlei Zhang, Zhuo Jiang, Haohan Xu, Lei Wang, Zuquan Song, Gaohong Liu, Yang Bai, Shuguang Wang, Wencong Xiao, Jianxi Ye, Minlan Yu, Hong Xu

机构 * The Chinese University of Hong Kong（香港中文大学） ； ByteDance（字节跳动） ； ByteDance Seed（字节跳动种子） ； Harvard University（哈佛大学） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；分类 cs.LG

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Ruoyu Qin, Zheming Li, Weiran He, Mingxing Zhang, Yongwei Wu, Weimin Zheng, Xinran Xu

机构 * Moonshot AI ； Tsinghua University（清华大学） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；分类 cs.AI

Comments 23 pages, 13 figures

HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization

Gabor Petnehazi, Bernadett Aradi

机构 * University of Debrecen（德布勒恩大学） 纠错

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs

Haijun Zhang, Jinxiang Wang, Zhenhua Yu, Yanyong Zhang, Xuejie Ji, Kaining Mao, Jun Zhang, Yaqing Zhang, Ting Wu, Fei Jie, Xiemin Huang, Zhifang Cai, Junhua Cheng, Shuwei Wang, Wei Li, Xiaoming Bao, Hua Xu, Shixiong Zhao, Jun Li, Hongwei Sun, Ziyang Zhang, Yi Xiong, Chunsheng Li

机构 * iFLYTEK AI Engineering Institute（iFLYTEK人工智能工程研究院） ； University of Science and Technology of China（中国科学技术大学） ； Huawei Technologies Co., Ltd（华为技术有限公司） 纠错

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation

Abdullah Alabdullah, Lifeng Han, Chenghua Lin

机构 * University of Manchester（曼彻斯特大学） ； School of Informatics, University of Edinburgh（爱丁堡大学信息学院） ； Leiden University（莱顿大学） ； LIACS ； LUMC 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

Efficiently Editing Mixture-of-Experts Models with Compressed Experts

Yifei He, Yang Liu, Chen Liang, Hany Hassan Awadalla

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Microsoft（微软公司） 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments EMNLP 2025 Findings

Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs

Yao Fu, Runchao Li, Xianxuan Long, Haotian Yu, Xiaotian Han, Yu Yin, Pan Li

机构 * Case Western Reserve University（凯斯西储大学） ； Hangzhou Dianzi University（杭州电子科技大学） 纠错

专题命中 效率与部署 ：LLM(abstract)；prompting(abstract)；分类 cs.CL、cs.LG

Comments Accepted to EMNLP2025 findings (poster)

Adaptive KV-Cache Compression without Manually Setting Budget

Chenxia Tang, Jianchun Liu, Hongli Xu, Liusheng Huang

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.AI

Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems

Peter J. Bentley, Soo Ling Lim, Fuyuki Ishikawa

专题命中 效率与部署 ：LLM(abstract)；分类 cs.CL、cs.AI

Comments 9 pages

Journal ref 7th International Workshop on Agent-Based Modelling of Human Behaviour (ABMHuB'25), ALife 2025

Deep Self-knowledge Distillation: A hierarchical supervised learning for coronary artery segmentation

Mingfeng Lin

机构 * Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学深圳学院） ； Xiamen University, Xiamen, China（厦门大学） 纠错

专题命中 效率与部署 ：prompting(abstract)；分类 cs.LG

LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference

Krishna Teja Chitty-Venkata, Sandeep Madireddy, Murali Emani, Venkatram Vishwanath

机构 * Argonne National Laboratory（阿贡国家实验室） 纠错

专题命中 效率与部署 ：post-training(abstract)；分类 cs.LG

Comments Preprint

SOPSeg: Prompt-based Small Object Instance Segmentation in Remote Sensing Imagery

Chenhao Wang, Yingrui Ji, Yu Meng, Yunjian Zhang, Yao Zhu

专题命中 效率与部署 ：prompting(abstract)

Breaking the HBM Bit Cost Barrier: Domain-Specific ECC for AI Inference Infrastructure

Rui Xie, Asad Ul Haq, Yunhua Fang, Linsen Ma, Sanchari Sen, Swagath Venkataramani, Liu Liu, Tong Zhang

专题命中 效率与部署 ：LLM(abstract)