语言大模型 / LLM - arXivDaily 专题

2505.09372 2025-05-15 cs.CV 85%

MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment

Siyuan Yan, Xieji Li, Ming Hu, Yiwen Jiang, Zhen Yu, Zongyuan Ge

机构 * Faculty of Engineering, Monash University, Melbourne, Australia（墨尔本大学工程学院）； AIM for Health Lab, Monash University, Victoria, Australia（墨尔本大学健康人工智能实验室）

专题命中预训练与数据：pretraining(title,abstract)；large language model(abstract)；language model(abstract)

Comments MICCAI2025 early acceptance; First two authors contribute equally

2403.06869 2025-05-06 cs.LG cs.AI cs.CL cs.CV 85%

Impact of Noisy Supervision in Foundation Model Learning

Hao Chen, Zihan Wang, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj, Jindong Wang

专题命中预训练与数据：foundation model(title,abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 18 pages, 10 figures, 6 tables, preprint. arXiv admin note: substantial text overlap with arXiv:2309.17002

2504.20414 2025-04-30 cs.CR 85%

Enhancing Leakage Attacks on Searchable Symmetric Encryption Using LLM-Based Synthetic Data Generation

Joshua Chiu, Partha Protim Paul, Zahin Wahab

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)

2504.14666 2025-04-22 cs.CV 85%

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

Kaihang Pan, Wang Lin, Zhongqi Yue, Tenglong Ao, Liyu Jia, Wei Zhao, Juncheng Li, Siliang Tang, Hanwang Zhang

机构 * Zhejiang University（浙江大学）； Nanyang Technological University（新加坡国立大学）； Peking University（北京大学）； Huawei Singapore Research Center（华为新加坡研究中心）

专题命中预训练与数据：pretraining(title)；LLM(abstract)；large language model(abstract)；language model(abstract)

Comments Accepted by CVPR 2025 (Oral)

2412.04332 2025-04-14 cs.CV 85%

Liquid: Language Models are Scalable and Unified Multi-modal Generators

Junfeng Wu, Yi Jiang, Chuofan Ma, Yuliang Liu, Hengshuang Zhao, Zehuan Yuan, Song Bai, Xiang Bai

专题命中预训练与数据：language model(title,abstract)；LLM(abstract)；large language model(abstract)

Comments Technical report. Project page: https://foundationvision.github.io/Liquid/

2504.01890 2025-04-08 cs.CV 85%

Is Temporal Prompting All We Need For Limited Labeled Action Recognition?

Shreyank N Gowda, Boyan Gao, Xiao Gu, Xiaobo Jin

专题命中预训练与数据：prompting(title,abstract)；language model(abstract)；pretraining(abstract)

Comments Accepted in CVPR-W 2025

2410.07093 2025-03-11 cs.CV 85%

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

Zhe Li, Weihao Yuan, Yisheng He, Lingteng Qiu, Shenhao Zhu, Xiaodong Gu, Weichao Shen, Yuan Dong, Zilong Dong, Laurence T. Yang

专题命中预训练与数据：pretraining(title,abstract)；large language model(abstract)；language model(abstract)

2502.17328 2025-02-25 cs.CL cs.AI cs.LG 85%

Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization

Yen-Ju Lu, Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari, Jen-Hao Rick Chang, Yin Xia, Xiang Kong, Qi Zhu, Simon Wang, Oncel Tuzel, Raviteja Vemulapalli

专题命中预训练与数据：LLM(title,abstract)；preference optimization(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NAACL 2025 Findings

2405.17719 2025-02-21 cs.CV 85%

Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?

Boshen Xu, Ziheng Wang, Yang Du, Zhinan Song, Sipeng Zheng, Qin Jin

专题命中预训练与数据：language model(title,abstract)；large language model(abstract)；pretraining(abstract)

Comments Accepted by ICLR 2025. Code: https://github.com/xuboshen/EgoNCEpp

2501.10322 2025-01-22 cs.CL cs.AI cs.LG 85%

Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models

Pit Neitemeier, Björn Deiseroth, Constantin Eichenberg, Lukas Balles

专题命中预训练与数据：language model(title,abstract)；pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

2501.08365 2025-01-16 cs.CY cs.AI cs.CL cs.LG 85%

Towards Best Practices for Open Datasets for LLM Training

Stefan Baack, Stella Biderman, Kasia Odrozek, Aviya Skowron, Ayah Bdeir, Jillian Bommarito, Jennifer Ding, Maximilian Gahntz, Paul Keller, Pierre-Carl Langlais, Greg Lindahl, Sebastian Majstorovic, Nik Marda, Guilherme Penedo, Maarten Van Segbroeck, Jennifer Wang, Leandro von Werra, Mitchell Baker, Julie Belião, Kasia Chmielinski, Marzieh Fadaee, Lisa Gutermuth, Hynek Kydlíček, Greg Leppert, EM Lewis-Jong, Solana Larsen, Shayne Longpre, Angela Oduor Lungati, Cullen Miller, Victor Miller, Max Ryabinin, Kathleen Siminyu, Andrew Strait, Mark Surman, Anna Tumadóttir, Maurice Weber, Rebecca Weiss, Lee White, Thomas Wolf

专题命中预训练与数据：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2409.00698 2025-01-08 cs.CV 85%

Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification

Karim El Khoury, Maxime Zanella, Benoît Gérin, Tiffanie Godelaine, Benoît Macq, Saïd Mahmoudi, Christophe De Vleeschouwer, Ismail Ben Ayed

专题命中预训练与数据：language model(title,abstract)；pretraining(abstract)；prompting(abstract)

Comments Accepted at ICASSP 2025

2501.02045 2025-01-07 q-bio.GN cs.AI cs.CL cs.LG 85%

METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring

Ollie Liu, Sami Jaghouar, Johannes Hagemann, Shangshang Wang, Jason Wiemels, Jeff Kaufman, Willie Neiswanger

专题命中预训练与数据：foundation model(title,abstract)；pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

2412.13233 2024-12-24 cs.SE 85%

Creating an LLM-based AI-agent: A high-level methodology towards enhancing LLMs with APIs

Ioannis Tzachristas

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments in Greek language. This Master's Thesis was supervised by Prof. Nikolaos Papaspyrou (National Technical University of Athens) and Dr. Aifen Sui (Huawei Munich Research Center). English version: pages 57-104. Original submission link: http://artemis.cslab.ece.ntua.gr:8080/jspui/handle/123456789/19180

2402.10532 2024-12-18 cs.CL cs.AI cs.CY cs.HC cs.LG 85%

Properties and Challenges of LLM-Generated Explanations

Jenny Kunz, Marco Kuhlmann

专题命中预训练与数据：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2412.10372 2024-12-16 cs.CV 85%

UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities

Muhammad Uzair Khattak, Shahina Kunhimon, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan

专题命中预训练与数据：pretraining(title,abstract)；large language model(abstract)；language model(abstract)

Comments Code, models and demo available at https://github.com/mbzuai-oryx/UniMed-CLIP

2412.02816 2024-12-05 cs.CR 85%

Unleashing GHOST: An LLM-Powered Framework for Automated Hardware Trojan Design

Md Omar Faruque, Peter Jamieson, Ahmad Patooghy, Abdel-Hameed A. Badawy

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)

2411.18908 2024-12-04 cs.HC 85%

DuetML: Human-LLM Collaborative Machine Learning Framework for Non-Expert Users

Wataru Kawabe, Yusuke Sugano

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments 22 pages, 10 figures

2411.10683 2024-11-19 cs.CR 85%

I'm Spartacus, No, I'm Spartacus: Measuring and Understanding LLM Identity Confusion

Kun Li, Shichao Zhuang, Yue Zhang, Minghui Xu, Ruoxi Wang, Kaidi Xu, Xinwen Fu, Xiuzhen Cheng

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments 16 pages, 8 figure, 6 tables

2411.04704 2024-11-08 cs.SE 85%

Distinguishing LLM-generated from Human-written Code by Contrastive Learning

Xiaodan Xu, Chao Ni, Xinrong Guo, Shaoxuan Liu, Xiaoya Wang, Kui Liu, Xiaohu Yang

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments 30 pages, 6 figures, Accepted by TOSEM'24

2410.24034 2024-11-01 cs.CV 85%

Handwriting Recognition in Historical Documents with Multimodal LLM

Lucian Li

专题命中预训练与数据：LLM(title,abstract)；language model(abstract)；prompting(abstract)

2410.23676 2024-11-01 cs.CV 85%

Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach

Mathilde Caron, Alireza Fathi, Cordelia Schmid, Ahmet Iscen

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments NeurIPS 2024

2312.17120 2024-10-30 cs.CL cs.AI cs.LG 85%

MathPile: A Billion-Token-Scale Pretraining Corpus for Math

Zengzhi Wang, Xuefeng Li, Rui Xia, Pengfei Liu

专题命中预训练与数据：pretraining(title)；language model(abstract)；foundation model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 43 pages. Accepted by NeurIPS 2024. https://github.com/GAIR-NLP/MathPile/

2410.09687 2024-10-15 cs.LG cs.AI cs.CL 85%

MoIN: Mixture of Introvert Experts to Upcycle an LLM

Ajinkya Tejankar, KL Navaneet, Ujjawal Panchal, Kossar Pourahmadi, Hamed Pirsiavash

专题命中预训练与数据：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2408.03617 2024-10-10 cs.CL cs.AI cs.LG 85%

Is Child-Directed Speech Effective Training Data for Language Models?

Steven Y. Feng, Noah D. Goodman, Michael C. Frank

专题命中预训练与数据：language model(title,abstract)；pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2024. Code and data at https://github.com/styfeng/TinyDialogues

2409.07431 2024-10-04 cs.LG cs.AI cs.CL stat.ML 85%

Synthetic continued pretraining

Zitong Yang, Neil Band, Shuangping Li, Emmanuel Candès, Tatsunori Hashimoto

专题命中预训练与数据：pretraining(title,abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Updated organization of experimental results and methods introduction. Released the dataset and model weights artifact

2405.10938 2024-10-03 cs.LG cs.AI cs.CL stat.ML 85%

Observational Scaling Laws and the Predictability of Language Model Performance

Yangjun Ruan, Chris J. Maddison, Tatsunori Hashimoto

专题命中预训练与数据：language model(title,abstract)；post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at NeurIPS 2024 as a spotlight

2406.11176 2024-09-26 cs.CL cs.AI cs.LG 85%

Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement

Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, Sujian Li

专题命中预训练与数据：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to EMNLP 2024 (Main Conference)

2409.15678 2024-09-25 q-bio.QM q-bio.GN 85%

Objectively Evaluating the Reliability of Cell Type Annotation Using LLM-Based Strategies

Wenjin Ye, Yuanchen Ma, Junkai Xiang, Hongjie Liang, Tao Wang, Qiuling Xiang, Andy Peng Xiang, Wu Song, Weiqiang Li, Weijun Huang

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)

2308.04029 2024-09-17 cs.RO 85%

ChatSim: Underwater Simulation with Natural Language Prompting

Aadi Palnitkar, Rashmi Kapu, Xiaomin Lin, Cheng Liu, Nare Karapetyan, Yiannis Aloimonos

专题命中预训练与数据：prompting(title)；LLM(abstract)；large language model(abstract)；language model(abstract)

Journal ref OCEANS 2023 - MTS/IEEE U.S. Gulf Coast

1. 预训练与数据 12393 篇

MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment

Impact of Noisy Supervision in Foundation Model Learning

Enhancing Leakage Attacks on Searchable Symmetric Encryption Using LLM-Based Synthetic Data Generation

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

Liquid: Language Models are Scalable and Unified Multi-modal Generators

Is Temporal Prompting All We Need For Limited Labeled Action Recognition?

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization

Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?

Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models

Towards Best Practices for Open Datasets for LLM Training

Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification

METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring

Creating an LLM-based AI-agent: A high-level methodology towards enhancing LLMs with APIs

Properties and Challenges of LLM-Generated Explanations

UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities

Unleashing GHOST: An LLM-Powered Framework for Automated Hardware Trojan Design

DuetML: Human-LLM Collaborative Machine Learning Framework for Non-Expert Users

I'm Spartacus, No, I'm Spartacus: Measuring and Understanding LLM Identity Confusion

Distinguishing LLM-generated from Human-written Code by Contrastive Learning

Handwriting Recognition in Historical Documents with Multimodal LLM

Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach

MathPile: A Billion-Token-Scale Pretraining Corpus for Math

MoIN: Mixture of Introvert Experts to Upcycle an LLM

Is Child-Directed Speech Effective Training Data for Language Models?

Synthetic continued pretraining

Observational Scaling Laws and the Predictability of Language Model Performance

Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement

Objectively Evaluating the Reliability of Cell Type Annotation Using LLM-Based Strategies

ChatSim: Underwater Simulation with Natural Language Prompting