语言大模型 / LLM

AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control

Ruosen Li, Ziming Luo, Quan Zhang, Ruochen Li, Ben Zhou, Ali Payani, Xinya Du

机构 * University of Texas at Dallas（德克萨斯大学达拉斯分校） ； Arizona State University（亚利桑那州立大学） ； Cisco Research（思科研究） 纠错

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

Structured Convergence in Large Language Model Representations via Hierarchical Latent Space Folding

Fenella Harcourt, Naderdel Piero, Gilbert Sutherland, Daphne Holloway, Harriet Bracknell, Julian Ormsby

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

Structural Reformation of Large Language Model Neuron Encapsulation for Divergent Information Aggregation

Denis Bakushev, Gideon Boultinghouse, Harriet Oppenheimer, Sebastian Gillingwater, Valentina Ashington, Wilfred Stanborough

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference

Chao Zeng, Songwei Liu, Shu Yang, Fangmin Chen, Lean Fu, Xing Mei

机构 * ByteDance Inc（字节跳动公司） 纠错

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

Comments 14 pages

Large Language Model Guided Self-Debugging Code Generation

Muntasir Adnan, Zhiwei Xu, Carlos C. N. Kuhn

机构 * Open Source Institute, Faculty of Science and Technology, University of Canberra（开源研究院，科学与技术学院，堪培拉大学） 纠错

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

Probabilistic Subspace Manifolds for Contextual Inference in Large Language Models

Christopher Nightingale, Dominic Lavington, Jonathan Thistlethwaite, Sebastian Penhaligon, Thomas Belinski, David Boldo

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

HERA: Hybrid Edge-cloud Resource Allocation for Cost-Efficient AI Agents

Shiyi Liu, Haiying Shen, Shuai Che, Mahdi Ghandi, Mingqin Li

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

Contextual Subspace Manifold Projection for Structural Refinement of Large Language Model Representations

Alistair Wren, Beatrice Loxley, Hamish Cadwallader, Simon Beckwith, Fabian Pargeter, James Blades

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

Latent Convergence Modulation in Large Language Models: A Novel Approach to Iterative Contextual Realignment

Patricia Porretta, Sylvester Pakenham, Huxley Ainsworth, Gregory Chatten, Godfrey Allerton, Simon Hollingsworth, Vance Periwinkle

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

Context-Preserving Gradient Modulation for Large Language Models: A Novel Approach to Semantic Consistency in Long-Form Text Generation

Nirola Kobanov, Edmund Weatherstone, Zachary Vanderpoel, Orlando Wetherby

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models

Ziqin Zhou, Yifan Yang, Yuqing Yang, Tianyu He, Houwen Peng, Kai Qiu, Qi Dai, Lili Qiu, Chong Luo, Lingqiao Liu

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

MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation

Satya Krishna Gorti, Ilan Gofman, Zhaoyan Liu, Jiapeng Wu, Noël Vouitsis, Guangwei Yu, Jesse C. Cresswell, Rasa Hosseinzadeh

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

Comments Published at NAACL 2025

Contextual Compression Encoding for Large Language Models: A Novel Framework for Multi-Layered Parameter Space Pruning

Barnaby Schmitt, Alistair Grosvenor, Matthias Cunningham, Clementine Walsh, Julius Pembrokeshire, Jonathan Teel

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

Structured Context Recomposition for Large Language Models Using Probabilistic Layer Realignment

Jonathan Teel, Jocasta Cumberbatch, Raphael Benington, Quentin Baskerville

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

ChronoLLM: A Framework for Customizing Large Language Model for Digital Twins generalization based on PyChrono

Jingquan Wang, Harry Zhang, Khailanii Slaton, Shu Wang, Radu Serban, Jinlong Wu, Dan Negrut

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

Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment

Jie Li, Yi Liu, Chongyang Liu, Xiaoning Ren, Ling Shi, Weisong Sun, Yinxing Xue

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

Comments The method used in the paper has obvious problems and ambiguities. The security enhancement method we used cannot be considered distillation, but it is described as distillation in the paper, and the experiment lacks comparison and baseline, which has been criticized by many peers. In order to avoid further dissemination, we have decided to withdraw the paper

OneBit: Towards Extremely Low-bit Large Language Models

Yuzhuang Xu, Xu Han, Zonghan Yang, Shuo Wang, Qingfu Zhu, Zhiyuan Liu, Weidong Liu, Wanxiang Che

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

Comments Accepted by NeurIPS 2024

Video-to-Text Pedestrian Monitoring (VTPM): Leveraging Computer Vision and Large Language Models for Privacy-Preserve Pedestrian Activity Monitoring at Intersections

Ahmed S. Abdelrahman, Mohamed Abdel-Aty, Dongdong Wang

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

Optimization of Armv9 architecture general large language model inference performance based on Llama.cpp

Longhao Chen, Yina Zhao, Qiangjun Xie, Qinghua Sheng

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

Semantic Membership Inference Attack against Large Language Models

Hamid Mozaffari, Virendra J. Marathe

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

Exploring and Unleashing the Power of Large Language Models in Automated Code Translation

Zhen Yang, Fang Liu, Zhongxing Yu, Jacky Wai Keung, Jia Li, Shuo Liu, Yifan Hong, Xiaoxue Ma, Zhi Jin, Ge Li

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

Comments 23 pages, 7 figures, accepted by FSE'24 (2024 ACM International Conference on the Foundations of Software Engineering)

Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modeling

Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li, Jindong Li, Kang Sun, Yi Zeng

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

Scaling Studies for Efficient Parameter Search and Parallelism for Large Language Model Pre-training

Michael Benington, Leo Phan, Chris Pierre Paul, Evan Shoemaker, Priyanka Ranade, Torstein Collett, Grant Hodgson Perez, Christopher Krieger

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

Journal ref Supercomputing 2023 (SC23) Student Research Poster Track

Prompting Visual-Language Models for Efficient Video Understanding

Chen Ju, Tengda Han, Kunhao Zheng, Ya Zhang, Weidi Xie

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

Comments ECCV 2022. Project page: https://ju-chen.github.io/efficient-prompt/

AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models

Dongkuan Xu, Subhabrata Mukherjee, Xiaodong Liu, Debadeepta Dey, Wenhui Wang, Xiang Zhang, Ahmed Hassan Awadallah, Jianfeng Gao

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

Comments 15 pages, 4 figures, 10 tables

Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs

Raghavv Goel, Mukul Gagrani, Wonseok Jeon, Junyoung Park, Mingu Lee, Christopher Lott

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

Comments 8 pages, 3 figures, Published at the ICLR 2024 Workshop on Understanding of Foundation Models (ME-FoMo)

The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models

隐形编辑层：形式化部署语言模型中未公开的推理时调控、概率置放与归因问题

Augusto Camargo

机构 * Bluecore Consulting（蓝芯咨询） 纠错

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

AI总结 本文针对部署语言模型提出隐形编辑层概念，形式化推理归因问题、概率置放等核心概念，探讨其与相关监管框架的关联，揭示未公开推理调控的潜在影响。

AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models

AgentWeave：在工具丰富的语言模型中实现高效函数调用的推理前路由

Saurav Singla, Aarav Singla, Advik Gupta, Parnika Gupta

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

AI总结 本研究提出AgentWeave，一种推理前确定性路由层，可缩小工具丰富语言模型的函数调用候选集，在BFCL V4多函数任务上实现12.5%的原生BFCL成功，同时减少工具数量、输入token和延迟。

Comments 12 pages, 2 figures, 6 tables. Open-source implementation and reproducibility artifacts available in the AgentWeave repository

HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models

HiViS: 为视觉语言模型中的推测解码隐藏视觉标记

Zhinan Xie, Peisong Wang, Shuang Qiu, Jian Cheng

机构 * C 2 DL, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； AIRIA ； City University of Hong Kong（香港城市大学） 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

AI总结 HiViS通过隐藏视觉标记，提升视觉语言模型在推测解码中的生成效率和速度。

Comments CVPR 2026 Findings

Target-Aware Calibration Data Selection for Preserving Uncertainty in Quantized Language Models

面向量化语言模型不确定性保留的目标感知校准数据选择

Zhen Yang, Sizai Hou, Kaiwen Zheng, Yaofang Liu, Liang He, Yixuan Chen, Kangning Cui

机构 * The Hong Kong University of Science and Technology（香港科技大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； City University of Hong Kong（香港城市大学） ； Shanghai Institute of Optics and Fine Mechanics（上海光学精密机械研究所） ； University of Oxford（牛津大学） ； Yale University（耶鲁大学） 纠错

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

AI总结 本文针对量化语言模型的不确定性保留问题，提出DPQ方案，通过选择与目标对齐的校准数据，在多模型多基准实验中验证其能根据部署需求保留不同类型的不确定性行为。

Comments 20 pages, 5 figures. Accepted to EMNLP Findings 2026