语言大模型 / LLM - arXivDaily 专题

2509.09703 2025-09-15 cs.CL cs.AI 90%

CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor

Zhenhua Xu, Xixiang Zhao, Xubin Yue, Shengwei Tian, Changting Lin, Meng Han

机构 * Zhejiang University（浙江大学）； The Hong Kong Polytechnic University（香港理工大学）

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

Comments Accepted by EMNLP2025 MainConference

2509.10099 2025-09-15 cs.SE cs.AI 87%

Generating Energy-Efficient Code via Large-Language Models -- Where are we now?

Radu Apsan, Vincenzo Stoico, Michel Albonico, Rudra Dhar, Karthik Vaidhyanathan, Ivano Malavolta

机构 * Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）； Federal University of Technology of Paraná (UTFPR)（巴西南里尔联邦技术大学）； IIIT Hyderabad（海得拉巴国家理工学院）

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

2403.02694 2025-09-15 cs.LG cs.AI cs.CL cs.CR cs.DC 87%

MeanCache: User-Centric Semantic Caching for LLM Web Services

Waris Gill, Mohamed Elidrisi, Pallavi Kalapatapu, Ammar Ahmed, Ali Anwar, Muhammad Ali Gulzar

机构 * Virginia Tech（弗吉尼亚理工大学）； Cisco（思科）； University of Minnesota（明尼苏达大学）

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、cs.LG

Comments Accepted at 2025 IEEE 39th International Parallel and Distributed Processing Symposium (IPDPS)

Journal ref 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)

2509.09782 2025-09-15 cs.LG 85%

One Head, Many Models: Cross-Attention Routing for Cost-Aware LLM Selection

Roshini Pulishetty, Mani Kishan Ghantasala, Keerthy Kaushik Dasoju, Niti Mangwani, Vishal Garimella, Aditya Mate, Somya Chatterjee, Yue Kang, Ehi Nosakhare, Sadid Hasan, Soundar Srinivasan

机构 * University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）； Microsoft（微软公司）

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

2509.10372 2025-09-15 cs.AR 85%

MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness

Huizheng Wang, Zichuan Wang, Zhiheng Yue, Yousheng Long, Taiquan Wei, Jianxun Yang, Yang Wang, Chao Li, Shaojun Wei, Yang Hu, Shouyi Yin

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

2509.09801 2025-09-15 cs.CL cs.AI cs.LG 85%

HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning

Brennen Hill

机构 * Department of Computer Science University of Wisconsin-Madison（计算机科学系威斯康星大学麦迪逊分校）

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

2411.02992 2025-09-15 cs.IR cs.CV 85%

Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation

Junchen Fu, Xuri Ge, Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Kaiwen Zheng, Yongxin Ni, Joemon M. Jose

机构 * School of Computing Science, University of Glasgow（格拉斯哥大学计算机科学学院）； Amazon（亚马逊）； Telefonica Scientific Research（Telefonica科学研究院）； University of Science and Technology of China（中国科学技术大学）

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

Comments Accepted by IEEE Transactions on Knowledge and Data Engineering (TKDE)

2508.05084 2025-09-15 cs.CV 82%

AdaFusion: Prompt-Guided Inference with Adaptive Fusion of Pathology Foundation Models

Yuxiang Xiao, Yang Hu, Bin Li, Tianyang Zhang, Zexi Li, Huazhu Fu, Jens Rittscher, Kaixiang Yang

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

Comments 6 Tables, 11 Figures

2412.19087 2025-09-15 cs.CV cs.CL cs.LG 81%

MoPD: Mixture-of-Prompts Distillation for Vision-Language Models

Yang Chen, Shuai Fu, Yu Zhang

机构 * Department of Computer Science and Engineering, Southern University of Science and Technology（计算机科学与工程系，南方科技大学）； School of Mathematical and Computer Sciences, University of Adelaide（数学与计算机科学学院，阿德莱德大学）

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

2509.09864 2025-09-15 cs.LG cs.AI cs.CL 80%

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）

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

2509.09738 2025-09-15 cs.AI q-bio.QM 77%

Human-AI Collaboration Increases Efficiency in Regulatory Writing

Umut Eser, Yael Gozin, L. Jay Stallons, Ari Caroline, Martin Preusse, Brandon Rice, Scott Wright, Andrew Robertson

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

2509.09737 2025-09-15 cs.CV cs.AI cs.LG 73%

World Modeling with Probabilistic Structure Integration

Klemen Kotar, Wanhee Lee, Rahul Venkatesh, Honglin Chen, Daniel Bear, Jared Watrous, Simon Kim, Khai Loong Aw, Lilian Naing Chen, Stefan Stojanov, Kevin Feigelis, Imran Thobani, Alex Durango, Khaled Jedoui, Atlas Kazemian, Dan Yamins

机构 * Stanford NeuroAI Lab（斯坦福神经人工智能实验室）

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

2509.10377 2025-09-15 cs.CL 70%

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs

Yixiao Zhou, Ziyu Zhao, Dongzhou Cheng, zhiliang wu, Jie Gui, Yi Yang, Fei Wu, Yu Cheng, Hehe Fan

机构 * Zhejiang University（浙江大学）； Shanghai Innovation Institute（上海创新研究院）； Southeast University（东南大学）； Shanghai AI Laboratory（上海人工智能实验室）； The Chinese University of Hong Kong（香港中文大学）

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

Comments Accepted to EMNLP2025

2509.09550 2025-09-15 cs.SD cs.LG 70%

Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates

Harry Julian, Rachel Beeson, Lohith Konathala, Johanna Ulin, Jiameng Gao

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

2505.19634 2025-09-15 cs.CL 70%

Faster and Better LLMs via Latency-Aware Test-Time Scaling

Zili Wang, Tianyu Zhang, Haoli Bai, Lu Hou, Xianzhi Yu, Wulong Liu, Shiming Xiang, Lei Zhu

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）； MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS）； Huawei Noah’s Ark Lab（华为诺亚实验室）

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

2505.13204 2025-09-15 cs.CL 70%

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification

Jikai Wang, Zhenxu Tian, Juntao Li, Qingrong Xia, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Min Zhang

机构 * Soochow University（苏州大学）； Key Laboratory of Data Intelligence and Advanced Computing, Soochow University（数据智能与先进计算关键实验室）； Huawei Cloud（华为云）

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

Comments Accepted at EMNLP 2025 Main

2505.07531 2025-09-15 cs.AI eess.SP 57%

QuantX: A Framework for Hardware-Aware Quantization of Generative AI Workloads

Muhammad Ahmad, Khurram Mazher, Saqib Akram, Ahmad Tameem, Saad Bin Nasir

机构 * xEngineers Inc.（10xEngineers公司）

专题命中效率与部署：LLM(abstract)；分类 cs.AI

2509.09952 2025-09-15 cs.GR cs.CV 50%

Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Images

Zhi Ying, Boxiang Rong, Jingyu Wang, Maoyuan Xu

机构 * ETH Zürich（苏黎世联邦理工学院）

专题命中效率与部署：foundation model(abstract)

Comments Accepted to SIGGRAPH Asia 2025. Project page: https://ubisoft-laforge.github.io/world/chord

2507.05674 2025-09-15 cs.RO 50%

Integrating Diffusion-based Multi-task Learning with Online Reinforcement Learning for Robust Quadruped Robot Control

Xinyao Qin, Xiaoteng Ma, Yang Qi, Qihan Liu, Chuanyi Xue, Ning Gui, Qinyu Dong, Jun Yang, Bin Liang

机构 * Department of Automation, Tsinghua University（自动化系，清华大学）

专题命中效率与部署：pretraining(abstract)

2503.08336 2025-09-15 cs.CV 50%

Talk2PC: Enhancing 3D Visual Grounding through LiDAR and Radar Point Clouds Fusion for Autonomous Driving

Runwei Guan, Jianan Liu, Ningwei Ouyang, Shaofeng Liang, Daizong Liu, Xiaolou Sun, Lianqing Zheng, Ming Xu, Yutao Yue, Guoqiang Mao, Hui Xiong

机构 * Thrust of Artificial Intelligence, Hong Kong University of Science and Technology (Guangzhou), China（香港理工大学（广州）人工智能研究所）； Mononai AI, Sweden（蒙诺人工智能）； College of Computer Science and Technology, China University of Petroleum (East China)（中国石油大学（华东）计算机科学与技术学院）； School of Advanced Technology, Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学先进科技学院）； Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）； School of Automation, Southeast University（东南大学自动化学院）； College of Science and Engineering, James Cook University（詹姆斯库克大学科学与工程学院）； School of Transportation, Southeast University（东南大学交通运输学院）

专题命中效率与部署：language model(abstract)

Comments 13 pages, 12 figures

1. 效率与部署 20 篇

CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor

Generating Energy-Efficient Code via Large-Language Models -- Where are we now?

MeanCache: User-Centric Semantic Caching for LLM Web Services

One Head, Many Models: Cross-Attention Routing for Cost-Aware LLM Selection

MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness

HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning

Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation

AdaFusion: Prompt-Guided Inference with Adaptive Fusion of Pathology Foundation Models

MoPD: Mixture-of-Prompts Distillation for Vision-Language Models

Latency and Token-Aware Test-Time Compute

Human-AI Collaboration Increases Efficiency in Regulatory Writing

World Modeling with Probabilistic Structure Integration

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs

Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates

Faster and Better LLMs via Latency-Aware Test-Time Scaling

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification

QuantX: A Framework for Hardware-Aware Quantization of Generative AI Workloads

Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Images

Integrating Diffusion-based Multi-task Learning with Online Reinforcement Learning for Robust Quadruped Robot Control

Talk2PC: Enhancing 3D Visual Grounding through LiDAR and Radar Point Clouds Fusion for Autonomous Driving