语言大模型 / LLM

A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms

Ruihao Gong, Yifu Ding, Zining Wang, Chengtao Lv, Xingyu Zheng, Jinyang Du, Haotong Qin, Jinyang Guo, Michele Magno, Xianglong Liu

机构 * Beihang University（北京航空航天大学） ； ETH Zurich（苏黎世联邦理工学院） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Comments Ruihao Gong leads the overall organization of the survey, with Yifu Ding and Jinyang Du contributing to Sections 2 and 3. Xingyu Zheng is responsible for authoring Section 4, while Chengtao Lv and Zining Wang collaborate on Section 5. Haotong Qin, Jinyang Guo, Michele Magno, and Xianglong Liu provide guidance during the whole process and assist in refining the final manuscript

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache

Dinghong Song, Yuan Feng, Yiwei Wang, Shangye Chen, Cyril Guyot, Filip Blagojevic, Hyeran Jeon, Pengfei Su, Dong Li

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

Comments 10 pages, 6 figures

Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity

Susav Shrestha, Brad Settlemyer, Nikoli Dryden, Narasimha Reddy

机构 * Texas A&M University（德克萨斯大学） ； NVIDIA（英伟达） ； Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室） 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、cs.LG

Comments NeurIPS 2025, 10 pages, 7 figures

FLAD: Federated Learning for LLM-based Autonomous Driving in Vehicle-Edge-Cloud Networks

Tianao Xiang, Mingjian Zhi, Yuanguo Bi, Lin Cai, Yuhao Chen

机构 * Northeastern University（东北大学） ； University of Victoria（维多利亚大学） 纠错

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

AILINKPREVIEWER: Enhancing Code Reviews with LLM-Powered Link Previews

Panya Trakoolgerntong, Tao Xiao, Masanari Kondo, Chaiyong Ragkhitwetsagul, Morakot Choetkiertikul, Pattaraporn Sangaroonsilp, Yasutaka Kamei

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

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask

Tianzi Wang, Xurong Xie, Zengrui Jin, Mengzhe Geng, Jiajun Deng, Zhaoqing Li, Shoukang Hu, Shujie Hu, Guinan Li, Mingyu Cui, Helen Meng, Xunying Liu

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

Comments Accepted by regular paper in the IEEE Transactions on Audio, Speech and Language Processing (TASLP)

Beyond the Hype: Embeddings vs. Prompting for Multiclass Classification Tasks

Marios Kokkodis, Richard Demsyn-Jones, Vijay Raghavan

机构 * Thumbtack（Thumbtack公司） 纠错

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

AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems

Rohan Kadekodi, Zhan Jin, Keisuke Kamahori, Yile Gu, Sean Khatiri, Noah H. Bayindirli, Sergey Gorbunov, Baris Kasikci

机构 * University of Washington（华盛顿大学） ； Peking University（北京大学） ； University of Waterloo（滑铁卢大学） ； Interop Labs（Interop实验室） 纠错

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

Representing LLMs in Prompt Semantic Task Space

Idan Kashani, Avi Mendelson, Yaniv Nemcovsky

机构 * Technion - Israel Institute of Technology（技术离子-以色列理工学院） 纠错

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

Comments Accepted to Findings of the Association for Computational Linguistics: EMNLP 2025

Ultra-Light Test-Time Adaptation for Vision--Language Models

Byunghyun Kim

机构 * Kyungpook National University（庆尚国立大学） 纠错

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

Comments 7 pages

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning

Huanxuan Liao, Yixing Xu, Shizhu He, Guanchen Li, Xuanwu Yin, Dong Li, Emad Barsoum, Jun Zhao, Kang Liu

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 accepted to AAAI 2026

Mixture-of-Channels: Exploiting Sparse FFNs for Efficient LLMs Pre-Training and Inference

Tong Wu, Yutong He, Bin Wang, Kun Yuan

机构 * Peking University（北京大学） ； Zhejiang University（浙江大学） 纠错

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

Efficient Reasoning via Reward Model

Yuhao Wang, Xiaopeng Li, Cheng Gong, Ziru Liu, Suiyun Zhang, Rui Liu, Xiangyu Zhao

机构 * City University of Hong Kong（香港城市大学） ； Huawei Research（华为研究） 纠错

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

Simpliflow: A Lightweight Open-Source Framework for Rapid Creation and Deployment of Generative Agentic AI Workflows

Deven Panchal

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

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

SPEED-Q: Staged Processing with Enhanced Distillation towards Efficient Low-bit On-device VLM Quantization

Tianyu Guo, Shanwei Zhao, Shiai Zhu, Chenguang Ma

机构 * Tianyu Guo, Shanwei Zhao, Shiai Zhu, Chenguang Ma（作者） 纠错

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

TiDAR: Think in Diffusion, Talk in Autoregression

Jingyu Liu, Xin Dong, Zhifan Ye, Rishabh Mehta, Yonggan Fu, Vartika Singh, Jan Kautz, Ce Zhang, Pavlo Molchanov

机构 * NVIDIA 纠错

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

Comments NVIDIA-Tech Report

BayesQ: Uncertainty-Guided Bayesian Quantization

Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh, Khalid El Makkaoui, Ibrahim Ouahbi

机构 * Multidisciplinary Faculty of Nador, Mohammed Premier University, Oujda 60000, Morocco（摩洛哥奥伊达大学多学科学院） ； Laboratory LaSTI, ENSAK, Sultan Moulay Slimane University, Khouribga 54000, Morocco（摩洛哥库尔希布加大学LaSTI实验室） 纠错

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

Conversational Agents for Building Energy Efficiency -- Advising Housing Cooperatives in Stockholm on Reducing Energy Consumption

Shadaab Ghani, Anne Håkansson, Oleksii Pasichnyi, Hossein Shahrokni

机构 * KTH Royal Institute of Technology（皇家理工学院） 纠错

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

Context-Aware Dynamic Chunking for Streaming Tibetan Speech Recognition

Chao Wang, Yuqing Cai, Renzeng Duojie, Jin Zhang, Yutong Liu, Nyima Tashi

机构 * Qinghai Normal University（青海师范大学） ； University of Electronic Science and Technology of China（电子科技大学） ； Xizang University（西藏大学） ； The State Key Laboratory of Tibetan Intelligence（藏语智能 state key laboratory） 纠错

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

Background Invariance Testing According to Semantic Proximity

Zukang Liao, Min Chen

机构 * University of Oxford（牛津大学） 纠错

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

GRACE: Designing Generative Face Video Codec via Agile Hardware-Centric Workflow

Rui Wan, Qi Zheng, Ruoyu Zhang, Bu Chen, Jiaming Liu, Min Li, Minge Jing, Jinjia Zhou, Yibo Fan

机构 * State Key Laboratory of Integrated Chips and Systems（集成电路与系统集成国家重点实验室） ； Fudan University（复旦大学） ； Department of Electronic Engineering（电子工程系） 纠错

专题命中 效率与部署 ：post-training(abstract)

Efficient and Effective In-context Demonstration Selection with Coreset

Zihua Wang, Jiarui Wang, Haiyang Xu, Ming Yan, Fei Huang, Xu Yang, Xiu-Shen Wei, Siya Mi, Yu Zhang

专题命中 效率与部署 ：language model(abstract)

Comments This paper is accepted by AAAI26