语言大模型 / LLM

A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness

Fali Wang, Jihai Chen, Shuhua Yang, Ali Al-Lawati, Linli Tang, Hui Liu, Suhang Wang

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； Michigan State University（密歇根州立大学） 纠错

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

Comments 24 pages, 19 figures-under review; more detailed than v1

Using Multi-modal Large Language Model to Boost Fireworks Algorithm's Ability in Settling Challenging Optimization Tasks

Shipeng Cen, Ying Tan

机构 * School of Intelligence Science ； Technology, Institute for Artificial Intellignce, Peking University, Beijing, China ； Technology, Institute for Artificial Intellignce, National Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China 纠错

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

Inference-Time Reward Hacking in Large Language Models

Hadi Khalaf, Claudio Mayrink Verdun, Alex Oesterling, Himabindu Lakkaraju, Flavio du Pin Calmon

机构 * Harvard University（哈佛大学） 纠错

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

Comments Accepted to NeurIPS 2025 (Spotlight Paper)

LLMComp: A Language Modeling Paradigm for Error-Bounded Scientific Data Compression (Technical Report)

Guozhong Li, Muhannad Alhumaidi, Spiros Skiadopoulos, Panos Kalnis

机构 * KAUST（卡塞姆大学） ； University of Peloponnese（希腊皮洛斯大学） 纠错

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

SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving

Xiangchen Li, Dimitrios Spatharakis, Saeid Ghafouri, Jiakun Fan, Hans Vandierendonck, Deepu John, Bo Ji, Dimitrios Nikolopoulos

机构 * National Technical University of Athens（希腊国家技术大学） ； Queen's University Belfast（贝尔法斯特女王大学） ； University College Dublin（都柏林大学学院） 纠错

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

Comments 8 pages, 8 figures, 2 tables, accepted by SEC 2025: Tenth ACM/IEEE Symposium on Edge Computing

LLM-Driven SAST-Genius: A Hybrid Static Analysis Framework for Comprehensive and Actionable Security

Vaibhav Agrawal, Kiarash Ahi

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

Journal ref IEEE S&P 2025

A Quantized VAE-MLP Botnet Detection Model: A Systematic Evaluation of Quantization-Aware Training and Post-Training Quantization Strategies

Hassan Wasswa, Hussein Abbass, Timothy Lynar

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

From Haystack to Needle: Label Space Reduction for Zero-shot Classification

Nathan Vandemoortele, Bram Steenwinckel, Femke Ongenae, Sofie Van Hoecke

机构 * IDLab, Ghent University - imec（IDLab，根特大学 - imec） 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 Add acknowledgment

FREESH: Fair, Resource- and Energy-Efficient Scheduling for LLM Serving on Heterogeneous GPUs

Xuan He, Zequan Fang, Jinzhao Lian, Danny H. K. Tsang, Baosen Zhang, Yize Chen

专题命中 效率与部署 ：LLM(title,abstract)

Comments In Submission, code available at https://github.com/AndrewFangZequan/LLM_Serving_FREESH

s3: You Don't Need That Much Data to Train a Search Agent via RL

Pengcheng Jiang, Xueqiang Xu, Jiacheng Lin, Jinfeng Xiao, Zifeng Wang, Jimeng Sun, Jiawei Han

机构 * University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Amazon（亚马逊公司） 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

Comments EMNLP 2025 camera-ready

Light over Heavy: Automated Performance Requirements Quantification with Linguistic Inducement

Shihai Wang, Tao Chen

机构 * School of Computer Science and Engineering University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院） ； IDEAS Lab, School of Computer Science University of Birmingham（伯明翰大学计算机科学学院） 纠错

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

Comments accepted by ICSE 2026

Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning

Ruiyi Yang, Hao Xue, Imran Razzak, Shirui Pan, Hakim Hacid, Flora D. Salim

机构 * University of New South Wales（新南威尔士大学） ； Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； Griffith University（格里菲斯大学） ； Technology Innovation Institute（技术创新研究所） 纠错

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

Comments 20 pages, 4 figures

Cache Mechanism for Agent RAG Systems

Shuhang Lin, Zhencan Peng, Lingyao Li, Xiao Lin, Xi Zhu, Yongfeng Zhang

机构 * Rutgers University（新泽西州立大学） ； University of South Florida（佛罗里达州立大学） ； University of Illinois Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Data Dependency-Aware Code Generation from Enhanced UML Sequence Diagrams

Wenxin Mao, Zhitao Wang, Long Wang, Sirong Chen, Cuiyun Gao, Luyang Cao, Ziming Liu, Qiming Zhang, Jun Zhou, Zhi Jin

机构 * WeChat Pay, Tencent Inc（腾讯公司） ； The Chinese University of Hong Kong（香港中文大学） ； Wuhan University（武汉大学） 纠错

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

Traversal Verification for Speculative Tree Decoding

Yepeng Weng, Qiao Hu, Xujie Chen, Li Liu, Dianwen Mei, Huishi Qiu, Jiang Tian, Zhongchao Shi

机构 * Lenovo AI Technology Center, Lenovo（联想人工智能技术中心，联想） ； National Center for Mathematics and Interdisciplinary Sciences (NCMIS), AMSS, CAS（国家数学与交叉科学中心（NCMIS），中国科学院数学研究所） 纠错

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

Comments NeurIPS 2025 poster

Breaking the Encoder Barrier for Seamless Video-Language Understanding

Handong Li, Yiyuan Zhang, Longteng Guo, Xiangyu Yue, Jing Liu

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； MMLab, CUHK（CUHK MMLab） ； Institute of Automation, Chinese Academy of Science（中国科学院自动化研究所） ； Shanghai AI Lab（上海人工智能实验室） 纠错

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

Comments 12 pages

Journal ref Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025, pp. 23167-23176

AURA: Autonomous Upskilling with Retrieval-Augmented Agents

Alvin Zhu, Yusuke Tanaka, Andrew Goldberg, Dennis Hong

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

PerfDojo: Automated ML Library Generation for Heterogeneous Architectures

Andrei Ivanov, Siyuan Shen, Gioele Gottardo, Marcin Chrapek, Afif Boudaoud, Timo Schneider, Luca Benini, Torsten Hoefler

机构 * ETH Zurich（苏黎世联邦理工学院） 纠错

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

Journal ref The International Conference for High Performance Computing, Networking, Storage and Analysis (SC '25), November 16--21, 2025, St Louis, MO, USA

Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction

Yuerong Song, Xiaoran Liu, Ruixiao Li, Zhigeng Liu, Zengfeng Huang, Qipeng Guo, Ziwei He, Xipeng Qiu

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

Comments 12 pages, 7 figures

AgentSLA : Towards a Service Level Agreement for AI Agents

Gwendal Jouneaux, Jordi Cabot

机构 * Luxembourg Institute of Science and Technology（卢森堡科学与技术研究院） 纠错

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

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

Zijian Zhang, Rong Wang, Shiyang Li, Yuebo Luo, Mingyi Hong, Caiwen Ding

机构 * University of Minnesota, Twin Cities（明尼苏达大学，双城分校） 纠错

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

Open Source State-Of-the-Art Solution for Romanian Speech Recognition

Gabriel Pirlogeanu, Alexandru-Lucian Georgescu, Horia Cucu

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

Comments 13th Conference on Speech Technology and Human-Computer Dialogue (SpeD 2025), Cluj-Napoca, Romania

(Approximate) Matrix Multiplication via Convolutions

Yahel Uffenheimer, Omri Weinstein

专题命中 效率与部署 ：LLM(abstract)

CP-AgentNet: Autonomous and Explainable Communication Protocol Design Using Generative Agents

Dae Cheol Kwon, Xinyu Zhang

专题命中 效率与部署 ：LLM(abstract)

Journal ref Proc. IEEE 33rd International Conference on Network Protocols, ICNP 2025, Seoul, South Korea, 22-25 Sept. 2025