语言大模型 / LLM

KnowDR-REC: A Benchmark for Referring Expression Comprehension with Real-World Knowledge

Guanghao Jin, Jingpei Wu, Tianpei Guo, Yiyi Niu, Weidong Zhou, Guoyang Liu

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)；分类 cs.LG

JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics

Simindokht Jahangard, Mehrzad Mohammadi, Yi Shen, Zhixi Cai, Hamid Rezatofighi

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)

Reinforcement Learning to Rank Using Coarse-grained Rewards

Yiteng Tu, Zhichao Xu, Tao Yang, Weihang Su, Yujia Zhou, Yiqun Liu, Fen Lin, Qin Liu, Qingyao Ai

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)

MetaWild: A Multimodal Dataset for Animal Re-Identification with Environmental Metadata

Yuzhuo Li, Di Zhao, Tingrui Qiao, Yihao Wu, Bo Pang, Yun Sing Koh

机构 * University of Auckland（奥克兰大学） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.LG

Comments 7 pages, 6 figures

Benchmarking Sociolinguistic Diversity in Swahili NLP: A Taxonomy-Guided Approach

Kezia Oketch, John P. Lalor, Ahmed Abbasi

机构 * Department of IT, Analytics, and Operations University of Notre Dame（信息科技、分析与运营系 纽约大学） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.CL

From Image Captioning to Visual Storytelling

Admitos Passadakis, Yingjin Song, Albert Gatt

机构 * TUDelft（代尔夫特理工大学） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.CL

Comments 16 pages (including references), 5 figures and 6 tables

Investigating Transcription Normalization in the Faetar ASR Benchmark

Leo Peckham, Michael Ong, Naomi Nagy, Ewan Dunbar

机构 * Department of Linguistics（语言学系） ； Department of Computer Science（计算机科学系） ； Department of French（法语系） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.CL

Benchmarking graph construction by large language models for coherence-driven inference

Steve Huntsman, Jewell Thomas

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

The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget

Dangfeng Pan, Zhensu Sun, Cenyuan Zhang, David Lo, Xiaoning Du

机构 * Monash University（墨尔本大学） ； Singapore Management University（新加坡管理学院） 纠错

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

Comments Accepted by ICSE'26 (First Cycle)

CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection

Jiaming Hu, Haoyu Wang, Debarghya Mukherjee, Ioannis Ch. Paschalidis

机构 * Department. of Math & Statistics, Boston University（数学与统计学系，波士顿大学） ； Department. of Computer Science, University at Albany（计算机科学系，阿尔巴尼大学） ； Department. of ECE & Systems Eng., Department. of Biomedical Eng., Faculty of Computing & Data Sciences, Boston University（电子工程与系统工程系，生物医学工程系，计算与数据科学学院，波士顿大学） 纠错

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

Comments 11 pages, 1 figure

An automatic patent literature retrieval system based on LLM-RAG

Yao Ding, Yuqing Wu, Ziyang Ding

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

Impact of Clinical Image Quality on Efficient Foundation Model Finetuning

Yucheng Tang, Pawel Rajwa, Alexander Ng, Yipei Wang, Wen Yan, Natasha Thorley, Aqua Asif, Clare Allen, Louise Dickinson, Francesco Giganti, Shonit Punwani, Daniel C. Alexander, Veeru Kasivisvanathan, Yipeng Hu

机构 * UCL Hawkes Insitute, University College London Dept. of Medical Physics \& Biomedical Engineering, University College London Division of Surgery \& Interventional Science, University College London Centre of Medical Imaging, University College London Department of Radiology, UCLH NHS Foundation Trust Department of Urology, UCLH NHS Foundation Trust Department of Computer Science, University College London 纠错

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

Comments This paper was accepted to the 1st MICCAI Workshop on Efficient Medical AI (EMA4MICCAI2025) and selected for oral presentation

Cross-Modality Controlled Molecule Generation with Diffusion Language Model

Yunzhe Zhang, Yifei Wang, Khanh Vinh Nguyen, Pengyu Hong

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

Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference

Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban

机构 * Texas A\&M University, College Station, TX., USA（德克萨斯大学） ； Hamad Bin Khalifa University, Doha, Qatar（哈马德·本·卡伊夫大学） 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

Comments Under review

Action Engine: Automatic Workflow Generation in FaaS

Akiharu Esashi, Pawissanutt Lertpongrujikorn, Shinji Kato, Mohsen Amini Salehi

机构 * University of North Texas (UNT)（北卡罗来纳州立大学） 纠错

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

Comments Published in the Future Generation Computer Systems (FGCS) journal; Source code is available at: https://github.com/hpcclab/action_engine

EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition

Hugo Thimonier, Antony Perzo, Renaud Seguier

机构 * Emobot ； CentraleSupélec ； IETR (UMR CNRS 6164)（IETR） 纠错

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

UpANNS: Enhancing Billion-Scale ANNS Efficiency with Real-World PIM Architecture

Sitian Chen, Amelie Chi Zhou, Yucheng Shi, Yusen Li, Xin Yao

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

Comments Accepted by SC 25

Coupling without Communication and Drafter-Invariant Speculative Decoding

Majid Daliri, Christopher Musco, Ananda Theertha Suresh

机构 * New York University（纽约大学） ； Google Research, NY（谷歌研究） 纠错

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

Comments 18 pages

Multiscale Video Transformers for Class Agnostic Segmentation in Autonomous Driving

Leila Cheshmi, Mennatullah Siam

机构 * Ontariotechu（安大略理工学院） 纠错

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

Comments 6 pages, 2 figures, 1 table

GOGS: High-Fidelity Geometry and Relighting for Glossy Objects via Gaussian Surfels

Xingyuan Yang, Min Wei

机构 * Chengdu University of Information Technology（成都信息科技大学） 纠错

专题命中 效率与部署 ：foundation model(abstract)

Comments 13 pages, 13 figures

The invisible hand as an emergent property: a gradient flow approach

Giorgio Fabbri, Davide Fiaschi, Cristiano Ricci

专题命中 效率与部署 ：prompting(abstract)

BEVANet: Bilateral Efficient Visual Attention Network for Real-Time Semantic Segmentation

Ping-Mao Huang, I-Tien Chao, Ping-Chia Huang, Jia-Wei Liao, Yung-Yu Chuang

机构 * Graduate Institute of Networking and Multimedia, National Taiwan University（网络与多媒体研究所，国立台湾大学） ； Department of Computer Science and Information Engineering, National Taiwan University（计算机科学与信息工程系，国立台湾大学） 纠错

专题命中 效率与部署 ：pretraining(abstract)

Comments Copyright 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Journal ref IEEE International Conference on Image Processing (ICIP) 2025 Spotlight

Multi-Rationale Explainable Object Recognition via Contrastive Conditional Inference

Ali Rasekh, Sepehr Kazemi Ranjbar, Simon Gottschalk

机构 * Leibniz University Hannover（汉诺威莱布尼茨大学） ； L3S Research Center（L3S研究中心） 纠错

专题命中 效率与部署 ：language model(abstract)

A Distributed Learned Hash Table

Shengze Wang, Yi Liu, Xiaoxue Zhang, Liting Hu, Chen Qian

专题命中 效率与部署 ：LLM(abstract)

3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation

Nikolaos Gkanatsios, Jiahe Xu, Matthew Bronars, Arsalan Mousavian, Tsung-Wei Ke, Katerina Fragkiadaki

机构 * Carnegie Mellon University（卡内基梅隆大学） ； NVIDIA（英伟达） ； National Taiwan University（国立台湾大学） 纠错

专题命中 效率与部署 ：pretraining(abstract)

Comments Project page: https://3d-flowmatch-actor.github.io/

Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual Tuning

Yutian Liu, Zhengyi Yang, Jiancan Wu, Xiang Wang

机构 * University of Science and Technology of China（科学技术大学） 纠错

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models

Anindya Bijoy Das, Shibbir Ahmed, Shahnewaz Karim Sakib

机构 * The University of Akron, OH, USA（俄亥俄州阿克伦大学） ； Texas State University, TX, USA（德克萨斯州立大学） ； University of Tennessee at Chattanooga, TN, USA（田纳西大学查塔努加分校） 纠错

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

PathGPT: Reframing Path Recommendation as a Natural Language Generation Task with Retrieval-Augmented Language Models

Steeve Cuthbert Marcelyn, Yucen Gao, Yuzhe Zhang, Xiaofeng Gao

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 领域大模型 ：language model(title,abstract)；LLM(abstract)；large language model(abstract)；分类 cs.AI、cs.LG

RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition

Pengcheng Wang, Sheng Li, Takahiro Shinozaki

机构 * School of Engineering（工程学院） 纠错

专题命中 领域大模型 ：LLM(title,abstract)；SLM(abstract,comments)；分类 cs.CL

Comments accepted at Interspeech2025 MLC-SLM Challenge workshop (task I system description)

Students' Perceptions to a Large Language Model's Generated Feedback and Scores of Argumentation Essays

Winter Allen, Anand Shanker, N. Sanjay Rebello

专题命中 领域大模型 ：large language model(title)；language model(title)

Comments 7 pages, 4 figures, Physics Education Research Conference 2025