语言大模型 / LLM - arXivDaily 专题

2510.15304 2025-10-20 cs.CV cs.LG 89%

Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation

Fei Wang, Li Shen, Liang Ding, Chao Xue, Ye Liu, Changxing Ding

机构 * South China University of Technology（华南理工大学）； JD Explore Academy（JD探索学院）； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）； University of Sydney（悉尼大学）； Pazhou Lab（琶洲实验室）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；post-training(abstract)；分类 cs.LG

2507.03308 2025-10-20 cs.AR 89%

Hummingbird: A Smaller and Faster Large Language Model Accelerator on Embedded FPGA

Jindong Li, Tenglong Li, Ruiqi Chen, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng

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

Comments Accepted by ICCAD2025

2509.23809 2025-10-20 cs.LG cs.AI 88%

Tequila: Trapping-free Ternary Quantization for Large Language Models

Hong Huang, Decheng Wu, Rui Cen, Guanghua Yu, Zonghang Li, Kai Liu, Jianchen Zhu, Peng Chen, Xue Liu, Dapeng Wu

机构 * City University of Hong Kong（香港城市大学）； Tencent（腾讯）； MBZUAI ； McGill University（麦吉尔大学）

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

2503.01933 2025-10-20 cs.LG cs.AR cs.CL cs.CV 88%

Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective

Rakshit Aralimatti, Syed Abdul Gaffar Shakhadri, Kruthika KR, Kartik Basavaraj Angadi

机构 * SandLogic Technologies Pvt Ltd（SandLogic技术有限公司）

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

2503.00059 2025-10-20 cs.CV cs.LG 88%

Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models

Rui Hu, Delai Qiu, Shuyu Wei, Jiaming Zhang, Yining Wang, Shengping Liu, Jitao Sang

机构 * Beijing Key Lab of Traffic Data Analysis and Mining（北京交通数据挖掘重点实验室）； Beijing Jiaotong University（北京交通大学）； Unisound AI Technology Co., Ltd.（Unisound人工智能技术有限公司）； Peng Cheng Lab（鹏城实验室）

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

Comments Accepted to ACL 2025 Findings

Journal ref Findings of the Association for Computational Linguistics: ACL 2025

2408.01890 2025-10-20 cs.CL 88%

Cross-layer Attention Sharing for Pre-trained Large Language Models

Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu

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

Comments A version accepted by TACL, prior to its publication by MIT Press

2510.15330 2025-10-20 cs.DC cs.AI cs.CL cs.NI 86%

BeLLMan: Controlling LLM Congestion

Tella Rajashekhar Reddy, Atharva Deshmukh, Karan Tandon, Rohan Gandhi, Anjaly Parayil, Debopam Bhattacherjee

机构 * Microsoft（微软）

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

Comments To be presented at FAISYS 2025

2510.15283 2025-10-20 cs.CL cs.AI 86%

Exemplar-Guided Planing: Enhanced LLM Agent for KGQA

Jingao Xu, Shuoyoucheng Ma, Xin Song, Rong Jiang, Hongkui Tu, Bin Zhou

机构 * College of Computer Science and Technology, National University of Defense Technology, Changsha, China（计算机科学与技术学院，国防科技大学，长沙，中国）

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

2505.23052 2025-10-20 cs.CL 85%

RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models

Jiarui Zhang, Xiangyu Liu, Yong Hu, Chaoyue Niu, Fan Wu, Guihai Chen

机构 * Shanghai Jiao Tong University（上海交通大学）； WeChat, Tencent Inc（微信、腾讯公司）

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

2510.09607 2025-10-20 cs.CV 82%

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation

Shaoqi Dong, Chaoyou Fu, Haihan Gao, Yi-Fan Zhang, Chi Yan, Chu Wu, Xiaoyu Liu, Yunhang Shen, Jing Huo, Deqiang Jiang, Haoyu Cao, Yang Gao, Xing Sun, Ran He, Caifeng Shan

机构 * Nanjing University（南京大学）； Tencent Youtu Lab（腾讯优图实验室）； CASIA（中国科学院自动化研究所）

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

Comments Homepage: https://ltbai.github.io/VITA-VLA/

2502.17092 2025-10-20 cs.CV cs.CL 79%

Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI

Syed Abdul Gaffar Shakhadri, Kruthika KR, Kartik Basavaraj Angadi

机构 * SandLogic Technologies Pvt Ltd（沙德逻辑技术 Pvt Ltd）

专题命中效率与部署：language model(title,abstract)；分类 cs.CL

2509.02444 2025-10-20 cs.AI cs.CL cs.CV cs.HC 79%

AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent

Jingru Fan, Yufan Dang, Jingyao Wu, Huatao Li, Runde Yang, Xiyuan Yang, Yuheng Wang, Chen Qian

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

Comments Project at https://github.com/OpenBMB/AppCopilot

2510.15152 2025-10-20 eess.SY cs.SY 78%

Tail-Optimized Caching for LLM Inference

Wenxin Zhang, Yueying Li, Ciamac C. Moallemi, Tianyi Peng

专题命中效率与部署：LLM(title,abstract)

2411.14398 2025-10-20 cs.CL 77%

Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings

Aaron Zheng, Mansi Rana, Andreas Stolcke

机构 * Uniphore & UC Berkeley（Uniphore与伯克利大学）

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

Comments To appear in Proceedings of COLING 2025

Journal ref Proc. 31st Intl. Conf. Computational Linguistics: Industry Track, COLING 2025, pp. 689-696

2502.06438 2025-10-20 cs.LG cs.AI 76%

FEMBA: Efficient and Scalable EEG Analysis with a Bidirectional Mamba Foundation Model

Anna Tegon, Thorir Mar Ingolfsson, Xiaying Wang, Luca Benini, Yawei Li

机构 * Integrated Systems Laboratory, ETH Zürich（瑞士苏黎世联邦理工学院集成系统实验室）； DEI, University of Bologna（博洛尼亚大学DEI）

专题命中效率与部署：foundation model(title)；分类 cs.AI、cs.LG

Comments 7 pages, 3 figures, 5 tables, Camera-ready version, EMBC 2025

2506.21603 2025-10-20 cs.CL cs.CY cs.LG 73%

Operationalizing Automated Essay Scoring: A Human-Aware Approach

Yenisel Plasencia-Calaña

机构 * Brigthlands Institute for a Smart Society（智能社会研究院）

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

2412.10543 2025-10-20 cs.LG cs.CL cs.IR 73%

METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation

Siddhant Ray, Rui Pan, Zhuohan Gu, Kuntai Du, Shaoting Feng, Ganesh Ananthanarayanan, Ravi Netravali, Junchen Jiang

机构 * University of Chicago（芝加哥大学）； Princeton University（普林斯顿大学）； University of Chicago / TensorMesh（芝加哥大学 / TensorMesh）； Microsoft（微软公司）

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

Comments 17 pages, 18 figures

2510.15517 2025-10-20 cs.CL 70%

From Characters to Tokens: Dynamic Grouping with Hierarchical BPE

Rares Dolga, Lucas Maystre, Tudor Berariu, David Barber

机构 * University College London（伦敦大学学院）； UiPath

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

2505.11483 2025-10-20 cs.LG cs.PF 70%

msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML

Zhaolan Huang, Emmanuel Baccelli

机构 * Freie Universität Berlin（柏林自由大学）； Einstein Center Digital Future Inria, France（数字未来埃因斯坦中心，Inria，法国）

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

Comments NeurIPS 2025 (poster)

2505.11432 2025-10-20 cs.LG cs.DC 70%

MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production

Chao Jin, Ziheng Jiang, Zhihao Bai, Zheng Zhong, Juncai Liu, Xiang Li, Ningxin Zheng, Xi Wang, Cong Xie, Qi Huang, Wen Heng, Yiyuan Ma, Wenlei Bao, Size Zheng, Yanghua Peng, Haibin Lin, Xuanzhe Liu, Xin Jin, Xin Liu

机构 * School of Computer Science, Peking University（北京大学计算机学院）

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

2510.15110 2025-10-20 cs.LG cs.AI cs.CL 67%

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

Shih-Yang Liu, Xin Dong, Ximing Lu, Shizhe Diao, Mingjie Liu, Min-Hung Chen, Hongxu Yin, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Yejin Choi, Jan Kautz, Pavlo Molchanov

机构 * NVIDIA

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

Comments NVIDIA-Tech Report

2505.22981 2025-10-20 cs.HC 67%

Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies

Siyang Liu, Sahand Sabour, Xiaoyang Wang, Rada Mihalcea

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

2412.09585 2025-10-20 cs.CV 67%

Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation

Jitesh Jain, Zhengyuan Yang, Humphrey Shi, Jianfeng Gao, Jianwei Yang

机构 * Microsoft Research, Redmond（微软研究院（红mond））； Meta Superintelligence Labs（Meta超智能实验室）

专题命中效率与部署：LLM(abstract)；pretraining(abstract)

Comments Project Page: https://praeclarumjj3.github.io/visper_lm/

2503.10679 2025-10-20 cs.CL cs.AI 62%

LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss

Pau Rodriguez, Michal Klein, Eleonora Gualdoni, Valentino Maiorca, Arno Blaas, Luca Zappella, Marco Cuturi, Xavier Suau

机构 * Apple（苹果公司）； Sapienza（拉维尼恩大学）

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

Comments NeurIPS 2025

2502.17460 2025-10-20 eess.SP cs.AI cs.LG 62%

Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation

Bálint Tóth, Dominik Senti, Thorir Mar Ingolfsson, Jeffrey Zweidler, Alexandre Elsig, Luca Benini, Yawei Li

机构 * ETH Zürich（苏黎世联邦理工学院）； University of Bologna（博洛尼亚大学）

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

Comments 7 pages, 1 figure, 5 tables, Camera-ready, EMBC 2025

2510.15653 2025-10-20 cs.LG 57%

Fast and Compact Tsetlin Machine Inference on CPUs Using Instruction-Level Optimization

Yefan Zeng, Shengyu Duan, Rishad Shafik, Alex Yakovlev

机构 * thanks: Yefan Zeng, Shengyu Duan, Rishad Shafik, Alex Yakovlev（致谢）

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

2507.08867 2025-10-20 physics.data-an cs.LG hep-ex stat.ML 57%

Mind the Gap: Navigating Inference with Optimal Transport Maps

Malte Algren, Tobias Golling, Francesco Armando Di Bello, Christopher Pollard

机构 * University of Geneva（日内瓦大学）； University of Pisa（比萨大学）； University of Warwick（沃里克大学）

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

Comments 31 pages, 13 figures

2409.12682 2025-10-20 cs.SE cs.AI 57%

Retrieval-Augmented Test Generation: How Far Are We?

Jiho Shin, Nima Shiri Harzevili, Reem Aleithan, Hadi Hemmati, Song Wang

机构 * York University（约克大学）

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

Comments 11 pages + reference. Accepted as Research Track Paper at ICSE'26

2510.15026 2025-10-20 cs.CV 50%

MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning

Mattia Segu, Marta Tintore Gazulla, Yongqin Xian, Luc Van Gool, Federico Tombari

机构 * Google（谷歌）； ETH Zurich（苏黎世联邦理工学院）； INSAIT, Sofia University, St. Kliment Ohridski（INSAIT，索菲亚大学，圣克莱孟·奥赫里茨基）

专题命中效率与部署：foundation model(abstract)

Comments ICCV 2025

2503.07465 2025-10-20 cs.CV 50%

YOLOE: Real-Time Seeing Anything

Ao Wang, Lihao Liu, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding

机构 * School of Software, Tsinghua University（清华大学软件学院）； BNRist, Tsinghua University（清华大学BNRist）； Department of Automation, Tsinghua University（清华大学自动化系）

专题命中效率与部署：language model(abstract)

Comments ICCV 2025 Camera-ready Version

1. 效率与部署 31 篇