语言大模型 / LLM

CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

Wenhao Zheng, Yixiao Chen, Weitong Zhang, Souvik Kundu, Yun Li, Zhengzhong Liu, Eric P. Xing, Hongyi Wang, Huaxiu Yao

机构 * The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Intel（英特尔） ； Carnegie Mellon University（卡内基梅隆大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·拉希德人工智能大学） ； Rutgers University（罗格斯大学） 纠错

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

Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning

Wei Huang, Anda Cheng, Yinggui Wang

机构 * Ant Group（蚂蚁集团） 纠错

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

Comments Accepted by emnlp2025

No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models

Flor Miriam Plaza-del-Arco, Paul Röttger, Nino Scherrer, Emanuele Borgonovo, Elmar Plischke, Dirk Hovy

机构 * LIACS, Leiden University（莱顿大学 LIACS） ； Bocconi University（博科尼大学） ； Independent Researcher（独立研究者） ； Boconni University（博科尼大学） ； Helmholtz-Zentrum Dresden-Rossendorf（德累斯顿-罗斯托克亥姆霍兹中心） 纠错

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

LLM-Guided Ansätze Design for Quantum Circuit Born Machines in Financial Generative Modeling

Yaswitha Gujju, Romain Harang, Tetsuo Shibuya

机构 * Computer Science University of Tokyo Tokyo, Japan（计算机科学东京大学东京日本） 纠错

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

Comments Work presented at the 3rd International Workshop on Quantum Machine Learning: From Research to Practice (QML@QCE'25)

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy, Ben Fielding, Tristin Forbus, Harry Grieve, Semih Kara, Jari Kolehmainen, Yihua Lou, Christopher Nies, Edward Phillip Flores Nuño, Diogo Ortega, Shikhar Rastogi, Austin Virts, Matthew J. Wright

机构 * Gensyn AI Team（Gensyn AI团队） 纠错

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

Comments 14 pages, 6 figures

Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation

Chuanqi Cheng, Jian Guan, Wei Wu, Rui Yan

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） 纠错

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

Comments Accepted by ICML 2025

TweakLLM: A Routing Architecture for Dynamic Tailoring of Cached Responses

Muhammad Taha Cheema, Abeer Aamir, Khawaja Gul Muhammad, Naveed Anwar Bhatti, Ihsan Ayyub Qazi, Zafar Ayyub Qazi

机构 * Department of Computer Science（计算机科学系） ； Lahore University of Management Sciences（拉合尔管理科学大学） 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

Comments 13 pages, 9 figures

Privacy Preserving Semantic Communications Using Vision Language Models: A Segmentation and Generation Approach

Haoran Chang, Mingzhe Chen, Huaxia Wang, Qianqian Zhang

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

Comments 6 pages, 6 figures, Accepted at IEEE MILCOM 2025

EvolKV: Evolutionary KV Cache Compression for LLM Inference

Bohan Yu, Yekun Chai

机构 * School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学先进交叉学科学院） ； The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, CAS（复杂系统认知与决策智能重点实验室） ； ETH Zurich（苏黎世联邦理工学院） 纠错

专题命中 效率与部署 ：LLM(title)；分类 cs.CL、cs.LG

Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism

Jiaming Yan, Jianchun Liu, Hongli Xu, Liusheng Huang

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

Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization

Kai Yi

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

Comments PhD Dissertation

Design and Implementation of Code Completion System Based on LLM and CodeBERT Hybrid Subsystem

Bingbing Zhang, Ziyu Lin, Yingxin Su

专题命中 效率与部署 ：LLM(title)

BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion

Sike Xiang, Shuang Chen, Amir Atapour-Abarghouei

机构 * Department of Computer Science, Durham University（计算机科学系，杜伦大学） 纠错

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

Facet: highly efficient E(3)-equivariant networks for interatomic potentials

Nicholas Miklaucic, Lai Wei, Rongzhi Dong, Nihang Fu, Sadman Sadeed Omee, Qingyang Li, Sourin Dey, Victor Fung, Jianjun Hu

机构 * Department of Computer Science and Engineering, University of South Carolina（南卡罗来纳大学计算机科学与工程系） ； Computational Science and Engineering, Georgia Institute of Technology（佐治亚理工学院计算科学与工程系） 纠错

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

MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs

Swati Swati, Arjun Roy, Emmanouil Panagiotou, Eirini Ntoutsi

机构 * University of the Bundeswehr（德国联邦国防军大学） ； Free University Berlin（柏林自由大学） 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.LG

Comments Accepted to be published in the Proceedings of the 34th ACM International Conference on Information and Knowledge Management, November 10--14, 2025, Seoul, Republic of Korea

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism

Zizhao Mo, Jianxiong Liao, Huanle Xu, Zhi Zhou, Chengzhong Xu

专题命中 效率与部署 ：LLM(abstract)

Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse

Jinwoo Hwang, Daeun Kim, Sangyeop Lee, Yoonsung Kim, Guseul Heo, Hojoon Kim, Yunseok Jeong, Tadiwos Meaza, Eunhyeok Park, Jeongseob Ahn, Jongse Park

机构 * Korea University（韩国大学） 纠错

专题命中 效率与部署 ：language model(abstract)

Comments Accepted to 2025 VLDB