语言大模型 / LLM

LLM-based Multi-Agent Copilot for Quantum Sensor

Rong Sha, Binglin Wang, Jun Yang, Xiaoxiao Ma, Chengkun Wu, Liang Yan, Chao Zhou, Jixun Liu, Guochao Wang, Shuhua Yan, Lingxiao Zhu

机构 * National University of Defense Technology（国防科技大学） 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 13 pages,4 figures

EasySize: Elastic Analog Circuit Sizing via LLM-Guided Heuristic Search

Xinyue Wu, Fan Hu, Shaik Jani Babu, Yi Zhao, Xinfei Guo

机构 * Global College Shanghai Jiao Tong University（上海交通大学全球学院） 纠错

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

Efficient Knowledge Injection in LLMs via Self-Distillation

Kalle Kujanpää, Pekka Marttinen, Harri Valpola, Alexander Ilin

机构 * Aalto University（阿alto大学） ； Finnish Center for Artificial Intelligence (FCAI)（芬兰人工智能中心） ； System 2 AI 纠错

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

Comments Preprint

Enabling On-Device Medical AI Assistants via Input-Driven Saliency Adaptation

Uttej Kallakurik, Edward Humes, Rithvik Jonna, Xiaomin Lin, Tinoosh Mohsenin

机构 * Johns Hopkins Whiting School of Engineering（约翰霍普金斯大学惠蒂工程学院） 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

Comments Accepted for publication in the Proceedings of IEEE BioCAS 2025

DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative Decoding

Hossein Entezari Zarch, Lei Gao, Chaoyi Jiang, Murali Annavaram

机构 * University of Southern California（南加州大学） 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.LG

Scaling Laws For Mixed Quantization

Zeyu Cao, Boyang Gu, Cheng Zhang, Pedro Gimenes, Jianqiao Lu, Jianyi Cheng, Xitong Gao, Yiren Zhao

机构 * Department of Computer Science and Technology, University of Cambridge（计算机科学与技术系，剑桥大学） ； Department of Electrical & Electronic Engineering, Imperial College London（电气与电子工程系，伦敦帝国学院） ； Department of Computer Science, University of Hong Kong（计算机科学系，香港大学） ； School of Informatics, University of Edinburgh（信息学院，爱丁堡大学） 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.LG

Accelerating Conditional Prompt Learning via Masked Image Modeling for Vision-Language Models

Phuoc-Nguyen Bui, Khanh-Binh Nguyen, Hyunseung Choo

机构 * Convergence Research Institute, Sungkyunkwan University（convergence research institute, 首尔大学） ； School of Information Technology, Deakin University（信息科技学院, 德金大学） ； Department of Electrical and Computer Engineering, Sungkyunkwan University（电气与计算机工程系, 首尔大学） 纠错

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

Comments ACMMM-LAVA 2025, 10 pages, camera-ready version

WiFo-CF: Wireless Foundation Model for CSI Feedback

Xuanyu Liu, Shijian Gao, Boxun Liu, Xiang Cheng, Liuqing Yang

专题命中 效率与部署 ：foundation model(title,abstract)

RideAgent: An LLM-Enhanced Optimization Framework for Automated Taxi Fleet Operations

Xinyu Jiang, Haoyu Zhang, Mengyi Sha, Zihao Jiao, Long He, Junbo Zhang, Wei Qi

专题命中 效率与部署 ：LLM(title,abstract)

EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0

Igor Costa, Christopher Baran

机构 * AutoHand AI 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.AI

Comments 15 pages, 3 tables, 1 algorithm. Submitted to ICSE 2025

Toward Low-Latency End-to-End Voice Agents for Telecommunications Using Streaming ASR, Quantized LLMs, and Real-Time TTS

Vignesh Ethiraj, Ashwath David, Sidhanth Menon, Divya Vijay

机构 * NetoAI 纠错

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

Getting out of the Big-Muddy: Escalation of Commitment in LLMs

Emilio Barkett, Olivia Long, Paul Kröger

机构 * Columbia University（哥伦比亚大学） 纠错

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

AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling

Preslav Aleksandrov, Meghdad Kurmanji, Fernando Garcia Redondo, David O'Shea, William Shen, Alex Iacob, Lorenzo Sani, Xinchi Qiu, Nicola Cancedda, Nicholas D. Lane

机构 * University of Cambridge（剑桥大学） ； Meta 纠错

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

Comments 14 pages and 6 figures. Submitted to NeurIPS 2025

Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving

Xiaoxiang Shi, Colin Cai, Junjia Du, Zhihao Jia

机构 * Independent Researcher（独立研究者） ； Nanyang Technological University（南洋理工大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 效率与部署 ：LLM(title)；分类 cs.LG

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Qianli Ma, Yaowei Zheng, Zhelun Shi, Zhongkai Zhao, Bin Jia, Ziyue Huang, Zhiqi Lin, Youjie Li, Jiacheng Yang, Yanghua Peng, Zhi Zhang, Xin Liu

机构 * ByteDance（字节跳动） 纠错

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

The Missing Reward: Active Inference in the Era of Experience

Bo Wen

机构 * IBM T.J. Watson Research Center（IBM TJ沃森研究中心） 纠错

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

MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

Xiaodong Chen, Mingming Ha, Zhenzhong Lan, Jing Zhang, Jianguo Li

机构 * Renmin University of China（中国人民大学） ； Westlake University（西湖大学） 纠错

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

When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails

Manish Nagireddy, Inkit Padhi, Soumya Ghosh, Prasanna Sattigeri

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

Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models

Mason Nakamura, Saaduddin Mahmud, Kyle H. Wray, Hamed Zamani, Shlomo Zilberstein

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

Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks

Nirjhor Datta, Swakkhar Shatabda, M Sohel Rahman

机构 * Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology（孟加拉工程与技术大学计算机科学与工程系） ； Department of Computer Science and Engineering, BRAC University（布拉克大学计算机科学与工程系） 纠错

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

Textual Inversion for Efficient Adaptation of Open-Vocabulary Object Detectors Without Forgetting

Frank Ruis, Gertjan Burghouts, Hugo Kuijf

机构 * TNO（荷兰技术院） ； Intelligent Imaging（智能成像） 纠错

专题命中 效率与部署 ：language model(abstract)

Dual-Stream Attention with Multi-Modal Queries for Object Detection in Transportation Applications

Noreen Anwar, Guillaume-Alexandre Bilodeau, Wassim Bouachir

机构 * LITIV, Polytechnique Montréal（Polytechnique Montréal 的 LITIV） ； Data Science Laboratory, Université du Québec (TELUQ)（Université du Québec (TELUQ) 的 Data Science Laboratory） 纠错

专题命中 效率与部署 ：language model(abstract)

Comments 10 pages

Analyzing zero-inflated clustered longitudinal ordinal outcomes using GEE-type models with an application to dental fluorosis studies

Shoumi Sarkar, Anish Mukherjee, Jeremy T. Gaskins, Steven Levy, Peihua Qiu, Somnath Datta

专题命中 效率与部署 ：prompting(abstract)

Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)

Iyiola E. Olatunji, Franziska Boenisch, Jing Xu, Adam Dziedzic

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Iterative Learning of Computable Phenotypes for Treatment Resistant Hypertension using Large Language Models

Guilherme Seidyo Imai Aldeia, Daniel S. Herman, William G. La Cava

机构 * Federal University of ABC（亚巴西联邦大学） ； Department of Pathology and Laboratory Medicine, University of Pennsylvania（宾夕法尼亚大学病理学与实验室医学系） ； Computational Health Informatics Program, Boston Children’s Hospital, Harvard Medical School（哈佛医学院波士顿儿童医院计算健康信息学项目） 纠错

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments To appear in PMLR, Volume 298, Machine Learning for Healthcare, 2025

MoMA: A Mixture-of-Multimodal-Agents Architecture for Enhancing Clinical Prediction Modelling

Jifan Gao, Mahmudur Rahman, John Caskey, Madeline Oguss, Ann O'Rourke, Randy Brown, Anne Stey, Anoop Mayampurath, Matthew M. Churpek, Guanhua Chen, Majid Afshar

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Northwestern University（西北大学） 纠错

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

DSBC : Data Science task Benchmarking with Context engineering

Ram Mohan Rao Kadiyala, Siddhant Gupta, Jebish Purbey, Giulio Martini, Ali Shafique, Suman Debnath, Hamza Farooq

机构 * Cohere Labs Community ； IIT Roorkee（印度理工学院罗尔基分校） ； Amazon（亚马逊） ； UCLA（加州大学洛杉矶分校） 纠错

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments 32 pages

The Homework Wars: Exploring Emotions, Behaviours, and Conflicts in Parent-Child Homework Interactions

Nan Gao, Yibin Liu, Xin Tang, Yanyan Liu, Chun Yu, Yun Huang, Yuntao Wang, Flora D. Salim, Xuhai Orson Xu, Jun Wei, Yuanchun Shi

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)

Comments This paper was accepted by Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)

Explainable Recommendation with Simulated Human Feedback

Jiakai Tang, Jingsen Zhang, Zihang Tian, Xueyang Feng, Lei Wang, Xu Chen

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学agate人工智能学院） 纠错

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Journal ref ACM Transactions on Information Systems, Vol. 1, No. 1, Article 1 (January 2025)

"Set It Up": Functional Object Arrangement with Compositional Generative Models (Journal Version)

Yiqing Xu, Jiayuan Mao, Linfeng Li, Yilun Du, Tomas Lozáno-Pérez, Leslie Pack Kaelbling, David Hsu

机构 * School of Computing, National University of Singapore（新加坡国立大学计算机学院） ； CSAIL, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室） 纠错

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)

Comments This is the journal version accepted to the International Journal of Robotics Research (IJRR). It extends our prior work presented at Robotics: Science and Systems (RSS) 2024, with a new compositional program induction pipeline from natural language, and expanded evaluations on personalized bookshelf and bedroom furniture layout tasks