语言大模型 / LLM

Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models

Wenqi Pei, Hailing Xu, Hengyuan Zhao, Shizheng Hou, Han Chen, Zining Zhang, Pingyi Luo, Bingsheng He

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

Comments DL4C @ ICLR 2025

Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulation

Atsushi Masumori, Takashi Ikegami

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

EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models

Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Shao Tang, Sayan Ghosh, Xuanzhao Dong, Rajat Koner, Yalin Wang

机构 * Arizona State University（亚利桑那州立大学） ； Clemson University（克莱姆森大学） ； LinkedIn Corporation（领英公司） ； Ludwig Maximilian University of Munich（慕尼黑路德维希-马克西米利安大学） 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

Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models

Jinsong Li, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jiaqi Wang, Dahua Lin

机构 * The Chinese University of Hong Kong（香港中文大学） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

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

Comments Code is available at https://github.com/Li-Jinsong/DAEDAL

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models

Ma Teng, Jia Xiaojun, Duan Ranjie, Li Xinfeng, Huang Yihao, Jia Xiaoshuang, Chu Zhixuan, Ren Wenqi

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

Comments ICCV 2025

Understanding LLM-Centric Challenges for Deep Learning Frameworks: An Empirical Analysis

Yanzhou Mu, Rong Wang, Juan Zhai, Chunrong Fang, Xiang Chen, Jiacong Wu, An Guo, Jiawei Shen, Bingzhuo Li, Zhenyu Chen

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

Comments 46 pages, 14 figures

OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference

Seungjun Shin, Jaehoon Oh, Dokwan Oh

机构 * Samsung Advanced Institute of Technology, Korea（三星先进技术研究所，韩国） 纠错

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

Comments ICML 2025 (final version)

Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative Decoding

Jihoon Park, Seungeun Oh, Seong-Lyun Kim

机构 * School of Electrical and Electronic Engineering, Yonsei University（延世大学电子与电气工程学院） 纠错

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

Comments 6 pages, 5 figures

ProtTeX-CC: Activating In-Context Learning in Protein LLM via Two-Stage Instruction Compression

Chuanliu Fan, Zicheng Ma, Jun Gao, Nan Yu, Jun Zhang, Ziqiang Cao, Yi Qin Gao, Guohong Fu

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

Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction

Xinhe Li, Jiajun Liu, Peng Wang

机构 * School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院） ； Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education（新一代人工智能技术及其交叉应用重点实验室（东南大学），教育部） 纠错

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

Comments Accepted by IJCAI2025

Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling

Benjamin Lipkin, Benjamin LeBrun, Jacob Hoover Vigly, João Loula, David R. MacIver, Li Du, Jason Eisner, Ryan Cotterell, Vikash Mansinghka, Timothy J. O'Donnell, Alexander K. Lew, Tim Vieira

机构 * MIT（麻省理工学院） ； ETH Zürich（苏黎世联邦理工学院） ； McGill（麦吉尔大学） ； Canada CIFAR AI Chair（加拿大 CIFAR 人工智能主席） ； Mila（蒙特利尔人工智能研究院） ； Johns Hopkins（约翰霍普金斯大学） ； Yale（耶鲁大学） ； CHI FRO 纠错

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

Comments COLM 2025

D-Attn: Decomposed Attention for Large Vision-and-Language Models

Chia-Wen Kuo, Sijie Zhu, Fan Chen, Xiaohui Shen, Longyin Wen

机构 * ByteDance Intelligent Creation（字节跳动智能创作） 纠错

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

Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling

Tejomay Kishor Padole, Suyash P Awate, Pushpak Bhattacharyya

机构 * Dept. of Computer Science and Engineering, Indian Institute of Technology, Bombay（计算机科学与工程系，印度理工学院，孟买） 纠错

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

Comments Accepted as a main conference submission in the European Conference on Artificial Intelligence (ECAI 2025)

2SSP: A Two-Stage Framework for Structured Pruning of LLMs

Fabrizio Sandri, Elia Cunegatti, Giovanni Iacca

机构 * University of Trento（特伦托大学） 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.AI、cs.LG

Comments Published in Transactions on Machine Learning Research (TMLR)

An LLM Agent-Based Complex Semantic Table Annotation Approach

Yilin Geng, Shujing Wang, Chuan Wang, Keqing He, Yanfei Lv, Ying Wang, Zaiwen Feng, Xiaoying Bai

机构 * College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China, 430070（华中农业大学信息学院） ； Military Science Information Research Center, Academy of Military Sciences, Beijing, 100080（军事科学信息研究中心） ； School of Computer, Wuhan University, Wuhan, Hubei, China, 430072（武汉大学计算机学院） ； Hubei Key Laboratory of Agricultural Bioinformatics（湖北省农业生物信息学重点实验室） ； Engineering Research Center of Agricultural Intelligent Technology, Ministry of Education（农业智能技术工程研究中心） 纠错

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

Optimizing Language Models for Inference Time Objectives using Reinforcement Learning

Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve, Rémi Munos

机构 * Meta GenAI（Meta 生成式人工智能） ； Meta FAIR 纠错

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

Comments Published as a conference paper at ICML 2025

WeChat-YATT: A Scalable, Simple, Efficient, and Production Ready Training Library

Junyu Wu, Weiming Chang, Xiaotao Liu, Guanyou He, Tingfeng Xian, Haoqiang Hong, Boqi Chen, Hongtao Tian, Tao Yang, Yunsheng Shi, Feng Lin, Ting Yao, Jiatao Xu

机构 * Tencent（腾讯） 纠错

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

Comments arXiv admin note: substantial text overlap with arXiv:2507.22789

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias

Yuanzhe Hu, Kinshuk Goel, Vlad Killiakov, Yaoqing Yang

机构 * dartmouth（达特茅斯学院） ； ucsd（加州大学圣迭戈分校） ； srm（SRM科学与技术学院） ； ucb（加州大学伯克利分校） 纠错

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

Comments 29 pages, 14 figures, ICML 2025

FedSODA: Federated Fine-tuning of LLMs via Similarity Group Pruning and Orchestrated Distillation Alignment

Manning Zhu, Songtao Guo, Pengzhan Zhou, Yansong Ning, Chang Han, Dewen Qiao

机构 * Chongqing University（重庆大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Third Military Medical University（第三军医大学） 纠错

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

Concealment of Intent: A Game-Theoretic Analysis

Xinbo Wu, Abhishek Umrawal, Lav R. Varshney

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

iFairy: the First 2-bit Complex LLM with All Parameters in $\{\pm1, \pm i\}$

Feiyu Wang, Guoan Wang, Yihao Zhang, Shengfan Wang, Weitao Li, Bokai Huang, Shimao Chen, Zihan Jiang, Rui Xu, Tong Yang

专题命中 效率与部署 ：LLM(title)；分类 cs.CL、cs.LG

Comments 15 pages, 9 figures

AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up

Sakhinana Sagar Srinivas, Shivam Gupta, Venkataramana Runkana

机构 * Tata Research Development（塔塔研究发展） ； Design Center, Bangalore（设计中心，班加罗尔） 纠错

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

From Teacher to Student: Tracking Memorization Through Model Distillation

Simardeep Singh

机构 * Indian Institute of Technology, Roorkee（印度理工学院拉胡尔学院） 纠错

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

Comments 5 pages, in-proceedings L2M2 @ ACL 2025

ZigzagAttention: Efficient Long-Context Inference with Exclusive Retrieval and Streaming Heads

Zhuorui Liu, Chen Zhang, Dawei Song

机构 * Beijing Institute of Technology（北京理工大学） 纠错

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

Comments 5 pages, 4 figures

Choosing the Right Engine in the Virtual Reality Landscape

Santiago Berrezueta-Guzman, Stefan Wagner

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

Comments Pre-print

MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies

Weiwei Qi, Shuo Shao, Wei Gu, Tianhang Zheng, Puning Zhao, Zhan Qin, Kui Ren

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

Comments 7 pages, 3 figures

WebGeoInfer: A Structure-Free and Multi-Stage Framework for Geolocation Inference of Devices Exposing Information

Huipeng Yang, Li Yang, Lichuan Ma, Lu Zhou, Junbo Jia, Anyuan Sang, Xinyue Wang

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

SpectR: Dynamically Composing LM Experts with Spectral Routing

William Fleshman, Benjamin Van Durme

机构 * Johns Hopkins University（约翰霍普金斯大学） 纠错

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

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models

Xun Su, Jianming Huang, Yang Yusen, Zhongxi Fang, Hiroyuki Kasai

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

Visual Perception Engine: Fast and Flexible Multi-Head Inference for Robotic Vision Tasks

Jakub Łucki, Jonathan Becktor, Georgios Georgakis, Rob Royce, Shehryar Khattak

机构 * Jet Propulsion Laboratory, California Institute of Technology（喷气推进实验室，加州理工学院） ； Swiss Federal Institute of Technology (ETH Zürich)（瑞士联邦理工学院（ETH Zurich）） 纠错

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

Comments 8 pages, 6 figures, 2 tables