语言大模型 / LLM

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs

Landon Butler, Abhineet Agarwal, Justin Singh Kang, Yigit Efe Erginbas, Bin Yu, Kannan Ramchandran

机构 * Department of EECS UC Berkeley（电子工程与计算机科学系，伯克利大学） ； Department of Statistics UC Berkeley（统计学系，伯克利大学） ； Departments of Statistics and EECS UC Berkeley（统计学系和电子工程与计算机科学系，伯克利大学） 纠错

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

Comments Algorithm available at: https://github.com/mmschlk/shapiq

DuoLens: A Framework for Robust Detection of Machine-Generated Multilingual Text and Code

Shriyansh Agrawal, Aidan Lau, Sanyam Shah, Ahan M R, Kevin Zhu, Sunishchal Dev, Vasu Sharma

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

Comments Accepted to 39th Conference on Neural Information Processing Systems (NeurIPS 2025): 4th Workshop on Deep Learning for Code

Journal ref Neural Information Processing Systems (NeurIPS 2025)

Memorization-Compression Cycles Improve Generalization

Fangyuan Yu

机构 * Thoughtworks 纠错

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

Comments 12 pages, 6 figures, NeurIPS2025 NEGEL Workshop

Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures

Pingzhi Li, Morris Yu-Chao Huang, Zhen Tan, Qingquan Song, Jie Peng, Kai Zou, Yu Cheng, Kaidi Xu, Tianlong Chen

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

Comments Code is at https://github.com/unites-lab/shadow-moe

REFRAG: Rethinking RAG based Decoding

Xiaoqiang Lin, Aritra Ghosh, Bryan Kian Hsiang Low, Anshumali Shrivastava, Vijai Mohan

机构 * Meta Superintelligence Labs（Meta超智能实验室） ； National University of Singapore（新加坡国立大学） ； Rice University（Rice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.CL、cs.AI、cs.LG

Comments fix typo perplexity->log perplexity; added recent papers

TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning

Florentin Beck, William Rudman, Carsten Eickhoff

机构 * University of Tübingen, School of Medicine（图宾根大学医学院） ； University of Texas at Austin, Department of Linguistics（德克萨斯大学奥斯汀分校语言学系） 纠错

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

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens

Eugene Kwek, Wenpeng Yin

机构 * Department of Computer Science & Engineering（计算机科学与工程系） 纠错

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

Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings

Shikun Liu, Haoyu Wang, Mufei Li, Pan Li

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

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

Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs

Aneesh Jonelagadda, Christina Hahn, Haoze Zheng, Salvatore Penachio

机构 * Kaliber AI, Research Division（Kaliber AI 研究部门） 纠错

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

Comments 12 pages, 4 figures

LLMs on a Budget? Say HOLA

Zohaib Hasan Siddiqui, Jiechao Gao, Ebad Shabbir, Mohammad Anas Azeez, Rafiq Ali, Gautam Siddharth Kashyap, Usman Naseem

机构 * Jamia Hamdard（贾迈亚哈马达尔大学） ； Center for SDGC, Stanford University（SDGC研究中心，斯坦福大学） ； DSEU-Okhla ； Macquarie University（麦考瑞大学） 纠错

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

Comments Accepted at EMNLP 2025 (Industry Track)

Towards an Efficient, Customizable, and Accessible AI Tutor

Juan Segundo Hevia, Facundo Arredondo, Vishesh Kumar

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；small language model(abstract)；SLM(abstract)

Comments AAAI - iRAISE 2025

SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications

Gabriele Oliaro, Zhihao Jia, Daniel Campos, Aurick Qiao

机构 * Snowflake AI Research（Snowflake AI研究院） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

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

Comments NeurIPS 2025 (Spotlight)

From Compression to Expression: A Layerwise Analysis of In-Context Learning

Jiachen Jiang, Yuxin Dong, Jinxin Zhou, Zhihui Zhu

机构 * The corresponding author.（通讯作者） 纠错

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

Position: Privacy Is Not Just Memorization!

Niloofar Mireshghallah, Tianshi Li

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Northeastern University（东北大学） 纠错

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

Comments 27 pages, 6 figures, 2 tables

Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback

Gen Li, Yuling Yan

机构 * Department of Statistics and Data Science, The Chinese University of Hong Kong（统计与数据科学系，香港中文大学） ； Department of Statistics, University of Wisconsin-Madison（统计系，威斯康星大学麦迪逊分校） 纠错

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

LongCat-Flash Technical Report

Meituan LongCat Team, Bayan, Bei Li, Bingye Lei, Bo Wang, Bolin Rong, Chao Wang, Chao Zhang, Chen Gao, Chen Zhang, Cheng Sun, Chengcheng Han, Chenguang Xi, Chi Zhang, Chong Peng, Chuan Qin, Chuyu Zhang, Cong Chen, Congkui Wang, Dan Ma, Daoru Pan, Defei Bu, Dengchang Zhao, Deyang Kong, Dishan Liu, Feiye Huo, Fengcun Li, Fubao Zhang, Gan Dong, Gang Liu, Gang Xu, Ge Li, Guoqiang Tan, Guoyuan Lin, Haihang Jing, Haomin Fu, Haonan Yan, Haoxing Wen, Haozhe Zhao, Hong Liu, Hongmei Shi, Hongyan Hao, Hongyin Tang, Huantian Lv, Hui Su, Jiacheng Li, Jiahao Liu, Jiahuan Li, Jiajun Yang, Jiaming Wang, Jian Yang, Jianchao Tan, Jiaqi Sun, Jiaqi Zhang, Jiawei Fu, Jiawei Yang, Jiaxi Hu, Jiayu Qin, Jingang Wang, Jiyuan He, Jun Kuang, Junhui Mei, Kai Liang, Ke He, Kefeng Zhang, Keheng Wang, Keqing He, Liang Gao, Liang Shi, Lianhui Ma, Lin Qiu, Lingbin Kong, Lingtong Si, Linkun Lyu, Linsen Guo, Liqi Yang, Lizhi Yan, Mai Xia, Man Gao, Manyuan Zhang, Meng Zhou, Mengxia Shen, Mingxiang Tuo, Mingyang Zhu, Peiguang Li, Peng Pei, Peng Zhao, Pengcheng Jia, Pingwei Sun, Qi Gu, Qianyun Li, Qingyuan Li, Qiong Huang, Qiyuan Duan, Ran Meng, Rongxiang Weng, Ruichen Shao, Rumei Li, Shizhe Wu, Shuai Liang, Shuo Wang, Suogui Dang, Tao Fang, Tao Li, Tefeng Chen, Tianhao Bai, Tianhao Zhou, Tingwen Xie, Wei He, Wei Huang, Wei Liu, Wei Shi, Wei Wang, Wei Wu, Weikang Zhao, Wen Zan, Wenjie Shi, Xi Nan, Xi Su, Xiang Li, Xiang Mei, Xiangyang Ji, Xiangyu Xi, Xiangzhou Huang, Xianpeng Li, Xiao Fu, Xiao Liu, Xiao Wei, Xiaodong Cai, Xiaolong Chen, Xiaoqing Liu, Xiaotong Li, Xiaowei Shi, Xiaoyu Li, Xili Wang, Xin Chen, Xing Hu, Xingyu Miao, Xinyan He, Xuemiao Zhang, Xueyuan Hao, Xuezhi Cao, Xunliang Cai, Xurui Yang, Yan Feng, Yang Bai, Yang Chen, Yang Yang, Yaqi Huo, Yerui Sun, Yifan Lu, Yifan Zhang, Yipeng Zang, Yitao Zhai, Yiyang Li, Yongjing Yin, Yongkang Lv, Yongwei Zhou, Yu Yang, Yuchen Xie, Yueqing Sun, Yuewen Zheng, Yuhuai Wei, Yulei Qian, Yunfan Liang, Yunfang Tai, Yunke Zhao, Zeyang Yu, Zhao Zhang, Zhaohua Yang, Zhenchao Zhang, Zhikang Xia, Zhiye Zou, Zhizhao Zeng, Zhongda Su, Zhuofan Chen, Zijian Zhang, Ziwen Wang, Zixu Jiang, Zizhe Zhao, Zongyu Wang, Zunhai Su

机构 * Meituan LongCat Team（美团LongCat团队） 纠错

专题命中 效率与部署 ：language model(abstract)；foundation model(abstract)；post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs

Santhosh G S, Saurav Prakash, Balaraman Ravindran

机构 * Centre for Responsible AI（负责任人工智能中心） ； Indian Institute of Technology Madras（印度理工学院马德拉斯分校） ； Department of Electrical Engineering（电气工程系） ； Wadhwani School of Data Science and Artificial Intelligence（Wadhwani数据科学与人工智能学院） 纠错

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

Towards Automated Error Discovery: A Study in Conversational AI

Dominic Petrak, Thy Thy Tran, Iryna Gurevych

机构 * Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science and Hessian Center for AI (hessian.AI), Technical University of Darmstadt（德累斯顿技术大学） 纠错

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

Comments Accepted to EMNLP 2025 main conference

Latency and Token-Aware Test-Time Compute

Jenny Y. Huang, Mehul Damani, Yousef El-Kurdi, Ramon Astudillo, Wei Sun

机构 * Department of Electrical Engineering and Computer Science, MIT（麻省理工学院电气工程与计算机科学系） ； IBM Research（IBM研究院） ； MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室） 纠错

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

Rapid Word Learning Through Meta In-Context Learning

Wentao Wang, Guangyuan Jiang, Tal Linzen, Brenden M. Lake

机构 * New York University（纽约大学） ； MIT（麻省理工学院） 纠错

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

Comments EMNLP 2025

Lossless Token Sequence Compression via Meta-Tokens

John Harvill, Ziwei Fan, Hao Wang, Luke Huan, Anoop Deoras, Yizhou Sun, Hao Ding

机构 * AWS AI Labs（AWS人工智能实验室） ； Amazon（亚马逊） ； Rutgers University（罗格斯大学） ； University of California Los Angeles（加州大学洛杉矶分校） 纠错

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

Comments 16 pages, 8 figures

2SSP: A Two-Stage Framework for Structured Pruning of LLMs

Fabrizio Sandri, Elia Cunegatti, Giovanni Iacca

机构 * University of Trento（特伦托大学） 纠错

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

Comments Published in Transactions on Machine Learning Research (TMLR)

Meta-Metrics and Best Practices for System-Level Inference Performance Benchmarking

Shweta Salaria, Zhuoran Liu, Nelson Mimura Gonzalez

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

Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free

Euntae Choi, Sumin Song, Woosang Lim, Sungjoo Yoo

机构 * Seoul National University（首尔国立大学） 纠错

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

Comments 7 pages

Generative Artificial Intelligence Extracts Structure-Function Relationships from Plants for New Materials

Rachel K. Luu, Jingyu Deng, Mohammed Shahrudin Ibrahim, Nam-Joon Cho, Ming Dao, Subra Suresh, Markus J. Buehler

机构 * Department of Materials Science and Engineering（材料科学与工程系） ； Laboratory for Atomistic and Molecular Mechanics (LAMM)（原子分子力学实验室） ； Massachusetts Institute of Technology（麻省理工学院） ； School of Materials Science and Engineering（材料科学与工程学院） ； Centre for Cross Economy Global（跨经济全球中心） ； Nanyang Technological University（南洋理工大学） 纠错

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

Factor Augmented Supervised Learning with Text Embeddings

Zhanye Luo, Yuefeng Han, Xiufan Yu

机构 * University of Chicago（芝加哥大学） ； University of Notre Dame（圣约翰大学） 纠错

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

Transmission With Machine Language Tokens: A Paradigm for Task-Oriented Agent Communication

Zhuoran Xiao, Chenhui Ye, Yijia Feng, Yunbo Hu, Tianyu Jiao, Liyu Cai, Guangyi Liu

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

Comments Accepted by IEEE Globecom 2025

SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs

Patrik Czakó, Gábor Kertész, Sándor Szénási

机构 * Doctoral School of Applied Informatics and Applied Mathematics, Obuda University（应用信息学与应用数学博士学院，奥布达大学） ； John von Neumann Faculty of Informatics, Obuda University（约翰·冯·诺依曼信息学院，奥布达大学） 纠错

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

Comments 6 pages, 3 figures, 5 tables. Accepted to IEEE SMC 2025 conference proceedings

HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs

Dongquan Yang, Yifan Yang, Xiaotian Yu, Xianbiao Qi, Rong Xiao

机构 * Intellifusion Inc.（智融科技公司） 纠错

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

An Efficient Sparse Fine-Tuning with Low Quantization Error via Neural Network Pruning

Cen-Jhih Li, Aditya Bhaskara

机构 * Kahlert School of Computing University of Utah（卡勒特计算学院 乌得勒支大学） 纠错

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