语言大模型 / LLM

Towards Pareto Optimal Throughput in Small Language Model Serving

Pol G. Recasens, Yue Zhu, Chen Wang, Eun Kyung Lee, Olivier Tardieu, Alaa Youssef, Jordi Torres, Josep Ll. Berral

机构 * Barcelona Supercomputing Center（巴塞罗那超级计算中心） ； IBM Research（IBM研究院） 纠错

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

Comments Revised version of the paper published at EuroMLSys'24, fix figure 6 and 7

Less is More: Selective Reflection for Compatible and Efficient Knowledge Distillation in Large Language Models

Lingyuan Liu, Mengxiang Zhang

机构 * City University of Hong Kong（香港城市大学） ； The University of Hong Kong（香港大学） 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

QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning

Hossein Rajabzadeh, Mojtaba Valipour, Tianshu Zhu, Marzieh Tahaei, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh

机构 * University of Waterloo（滑铁卢大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 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.LG

Comments Best Paper Award AAAI EIW Workshop

Journal ref https://aclanthology.org/2024.emnlp-industry.53.pdf

Integrating large language models and active inference to understand eye movements in reading and dyslexia

Francesco Donnarumma, Mirco Frosolone, Giovanni Pezzulo

机构 * Institute of Cognitive Sciences and Technologies, National Research Council（认知科学与技术研究所，国家研究院） 纠错

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

Comments Main Document - 30 pages, 1 Table, 10 Figures + Supplementary 16 pages, 17 Tables

Contextual Morphogenesis in Large Language Models: A Novel Approach to Self-Organizing Token Representations

Alistair Dombrowski, Beatrix Engelhardt, Dimitri Fairbrother, Henry Evidail

专题命中 效率与部署 ：language model(title,abstract)；large 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Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship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 Embedding Projection for Contextual Large Language Model Inference

Vincent Enoasmo, Cedric Featherstonehaugh, Xavier Konstantinopoulos, Zacharias Huntington

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

Adacc: An Adaptive Framework Unifying Compression and Activation Recomputation for LLM Training

Ping Chen, Zhuohong Deng, Ping Li, Shuibing He, Hongzi Zhu, Yi Zheng, Zhefeng Wang, Baoxing Huai, Minyi Guo

机构 * The State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室） ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院） ； Shanghai Jiao Tong University（上海交通大学） ； Huawei Cloud（华为云） ； Zhejiang Lab（浙江实验室） 纠错

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

Comments 8 pages

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference

Edresson Casanova, Paarth Neekhara, Ryan Langman, Shehzeen Hussain, Subhankar Ghosh, Xuesong Yang, Ante Jukić, Jason Li, Boris Ginsburg

机构 * NVIDIA Corporation（英伟达公司） 纠错

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

Comments Accepted to Interspeech 2025

Contextual Reinforcement in Multimodal Token Compression for Large Language Models

Naderdel Piero, Zacharias Cromwell, Nathaniel Wainwright, Matthias Nethercott

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

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

Can Test-Time Scaling Improve World Foundation Model?

Wenyan Cong, Hanqing Zhu, Peihao Wang, Bangya Liu, Dejia Xu, Kevin Wang, David Z. Pan, Yan Wang, Zhiwen Fan, Zhangyang Wang

机构 * University of Texas at Austin（德克萨斯大学奥斯汀分校） ； NVIDIA（英伟达） ； University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Texas A&M University（德克萨斯阿姆斯特朗大学） 纠错

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

Comments Accepted by COLM2025

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

Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems

Alistair Reid, Simon O'Callaghan, Liam Carroll, Tiberio Caetano

机构 * Gradient Institute Ltd.（梯度研究所有限公司） 纠错

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

DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning

Jucheng Hu, Surong Yang, Lijun Wu, Dongzhan Zhou

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

ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates

Hamidreza Dastmalchi, Aijun An, Ali cheraghian

机构 * York University（约克大学） ； The Australian National University（澳大利亚国立大学） ； Data61-CSIRO 纠错

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

Comments BMVC2025

Principle-Guided Verilog Optimization: IP-Safe Knowledge Transfer via Local-Cloud Collaboration

Jing Wang, Zheng Li, Lei Li, Fan He, Liyu Lin, Yao Lai, Yan Li, Xiaoyang Zeng, Yufeng Guo

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

Comments Our code and dataset are available at https://github.com/friyawang/VeriOptim

OpenCodeReasoning: Advancing Data Distillation for Competitive Coding

Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, Aleksander Ficek, Siddhartha Jain, Jocelyn Huang, Vahid Noroozi, Boris Ginsburg

机构 * NVIDIA Santa Clara, CA 95051, USA（NVIDIA圣克拉拉分校） 纠错

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

Comments Published at COLM 2025

Llasa+: Free Lunch for Accelerated and Streaming Llama-Based Speech Synthesis

Wenjie Tian, Xinfa Zhu, Hanke Xie, Zhen Ye, Wei Xue, Lei Xie

机构 * Northwestern Polytechnical University（西北工业大学） ； Hong Kong University of Science（香港科技大学） 纠错

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

The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More)

Jeffrey Uhlmann

机构 * Dept. of Electrical Engineering and Computer Science University of Missouri - Columbia（电气工程与计算机科学系 密苏里大学-哥伦比亚） 纠错

专题命中 效率与部署 ：LLM(title)；分类 cs.LG

Neural Contextual Reinforcement Framework for Logical Structure Language Generation

Marcus Irvin, William Cooper, Edward Hughes, Jessica Morgan, Christopher Hamilton

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

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

A Framework for Inherently Safer AGI through Language-Mediated Active Inference

Bo Wen

机构 * IBM T.J. Watson Research Center（IBM T.J. Watson研究院） 纠错

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

Scaling Personality Control in LLMs with Big Five Scaler Prompts

Gunhee Cho, Yun-Gyung Cheong

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

What Builds Effective In-Context Examples for Code Generation?

Dongze Li, Songqiang Chen, Jialun Cao, Shing-Chi Cheung

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

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation

Zhiyou Xiao, Qinhan Yu, Binghui Li, Geng Chen, Chong Chen, Wentao Zhang

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

KV Cache Compression for Inference Efficiency in LLMs: A Review

Yanyu Liu, Jingying Fu, Sixiang Liu, Yitian Zou, You Fu, Jiehan Zhou, Shouhua Zhang

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

Comments 12 pages

Training Plug-n-Play Knowledge Modules with Deep Context Distillation

Lucas Caccia, Alan Ansell, Edoardo Ponti, Ivan Vulić, Alessandro Sordoni

机构 * Microsoft Research Montréal（微软研究院蒙特利尔分部） ； University of Cambridge（剑桥大学） ； University of Edinburgh（爱丁堡大学） 纠错

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

Comments Accepted at the CONFERENCE ON LANGUAGE MODELING (COLM) 2025

Prosocial Behavior Detection in Player Game Chat: From Aligning Human-AI Definitions to Efficient Annotation at Scale

Rafal Kocielnik, Min Kim, Penphob, Boonyarungsrit, Fereshteh Soltani, Deshawn Sambrano, Animashree Anandkumar, R. Michael Alvarez

机构 * California Institute of Technology（加利福尼亚理工学院） ； Activision Publishing, Inc.（暴雪娱乐公司） 纠错

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

Comments 9 pages, 4 figures, 4 tables

Hierarchical Pattern Decryption Methodology for Ransomware Detection Using Probabilistic Cryptographic Footprints

Kevin Pekepok, Persephone Kirkwood, Esme Christopolous, Florence Braithwaite, Oliver Nightingale

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

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

Enhancing Construction Site Analysis and Understanding with 3D Segmentation

Sri Ramana Saketh Vasanthawada, Pengkun Liu, Pingbo Tang

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