语言大模型 / LLM

TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation

Muhammad Sohail Danish, Muhammad Akhtar Munir, Syed Roshaan Ali Shah, Muhammad Haris Khan, Rao Muhammad Anwer, Jorma Laaksonen, Fahad Shahbaz Khan, Salman Khan

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫扎德·本·扎耶德人工智能大学） ； University College London（伦敦大学学院） ； Aalto University（艾尔沃斯大学） ； Linköping University, Sweden（瑞典林奈大学） ； Australian National University（澳大利亚国立大学） 纠错

专题命中 预训练与数据 ：foundation model(title,abstract)

Active Learning via Vision-Language Model Adaptation with Open Data

Tong Wang, Jiaqi Wang, Shu Kong

机构 * University of Macau（澳门大学） ； Shanghai AI Lab（上海人工智能实验室） ； Institute of Collaborative Innovation project webpage（协同创新项目研究所） 纠错

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

Comments Here is the project webpage: https://leowangtong.github.io/ALOR/

Pretraining Multi-Speaker Identification for Neural Speaker Diarization

Shota Horiguchi, Atsushi Ando, Marc Delcroix, Naohiro Tawara

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments Accepted to Interspeech 2025

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition

Shujie HU, Xurong Xie, Mengzhe Geng, Jiajun Deng, Huimeng Wang, Guinan Li, Chengxi Deng, Tianzi Wang, Mingyu Cui, Helen Meng, Xunying Liu

机构 * The Chinese University of Hong Kong（香港中文大学） ； Chinese Academy of Sciences（中国科学院） ； China National Research Council Canada（中国国家研究委员会加拿大） ； Institute of Software（软件研究所） 纠错

专题命中 预训练与数据 ：foundation model(title,abstract)

Comments Accepted by Interspeech 2025

Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?

Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler, David Acuna

机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） ； NVIDIA（英伟达） ； University of Ottawa（渥太华大学） 纠错

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

Comments Accepted at CVPR 2025. 22 pages, 16 figures

RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval

Haoqin Sun, Jingguang Tian, Jiaming Zhou, Hui Wang, Jiabei He, Shiwan Zhao, Xiangyu Kong, Desheng Hu, Xinkang Xu, Xinhui Hu, Yong Qin

机构 * Nankai University（南开大学） ； TMCC, College of Computer Science（TMCC计算机学院） ； Hithink RoyalFlush AI Research Institute（Hithink RoyalFlush人工智能研究院） ； University of Exeter（埃克塞特大学） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)

Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss

Guang Yang, Yu Zhou, Xiang Chen, Xiangyu Zhang, Terry Yue Zhuo, David Lo, Taolue Chen

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

Comments TOSEM

Can AI automatically analyze public opinion? A LLM agents-based agentic pipeline for timely public opinion analysis

Jing Liu, Xinxing Ren, Yanmeng Xu, Zekun Guo

专题命中 预训练与数据 ：LLM(title,abstract)

Comments 43 pages, 3 figures, 4 tables (1 in appendix), includes appendix. Preprint only

Understanding and Mitigating Toxicity in Image-Text Pretraining Datasets: A Case Study on LLaVA

Karthik Reddy Kanjula, Surya Guthikonda, Nahid Alam, Shayekh Bin Islam

机构 * Cohere for AI Community（Cohere for AI社区） ； Cisco Meraki ； Indiana University Bloomington（印第安纳大学布卢明顿分校） ； Bangladesh University of Engineering and Technology（孟加拉工程与技术大学） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments Accepted at ReGenAI CVPR2025 Workshop as Oral

Transmission Line Defect Detection Based on UAV Patrol Images and Vision-language Pretraining

Ke Zhang, Zhaoye Zheng, Yurong Guo, Jiacun Wang, Jiyuan Yang, Yangjie Xiao

机构 * Department of Electronic and Communication Engineering, North China Electric Power University（电子与通信工程系，华北电力大学） ； Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University（河北省电力物联网技术重点实验室，华北电力大学） ； Computer Science and Software Engineering Department, Monmouth University（计算机科学与软件工程系，蒙特莫恩大学） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)

Foundation Models For Seismic Data Processing: An Extensive Review

Fabian Fuchs, Mario Ruben Fernandez, Norman Ettrich, Janis Keuper

机构 * Fraunhofer-Institut für Techno- und Wirtschaftsmathematik（弗劳恩霍夫技术与经济数学研究所） ； University of Mannheim（曼海姆大学） ； DWS, University of Mannheim（曼海姆大学） ； IMLA, Offenburg University（奥芬堡大学） 纠错

专题命中 预训练与数据 ：foundation model(title,abstract)

Comments In submission to Geophysics

Self-Supervised Pretraining for Fine-Grained Plankton Recognition

Joona Kareinen, Tuomas Eerola, Kaisa Kraft, Lasse Lensu, Sanna Suikkanen, Heikki Kälviäinen

机构 * LUT University, Computer Vision and Pattern Recognition Laboratory（卢霍斯大学） ； Finnish Environment Institute（芬兰环境研究所） ； Brno University of Technology, Faculty of Information Technology（布拉格技术大学） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments CVPR 2025, FGVC12 workshop paper

Dual-Domain Masked Image Modeling: A Self-Supervised Pretraining Strategy Using Spatial and Frequency Domain Masking for Hyperspectral Data

Shaheer Mohamed, Tharindu Fernando, Sridha Sridharan, Peyman Moghadam, Clinton Fookes

机构 * Queensland University of Technology（昆士兰技术大学） ； CSIRO Robotics, Data61, CSIRO（CSIRO机器人部、Data61、CSIRO） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments Preprint to appear in IEEE IGARSS 2025

Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining

Weizhen He, Yunfeng Yan, Shixiang Tang, Yiheng Deng, Yangyang Zhong, Pengxin Luo, Donglian Qi

机构 * College of Electrical Engineering, Zhejiang University（浙江大学电气工程学院） ； School of Mechanical Engineering, Zhejiang University（浙江大学机械工程学院） ； Ocean College, Zhejiang University（浙江大学海洋学院） ； Hainan Institute, Zhejiang University（海南研究院） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)

ECG Identity Authentication in Open-set with Multi-model Pretraining and Self-constraint Center & Irrelevant Sample Repulsion Learning

Mingyu Dong, Zhidong Zhao, Hao Wang, Yefei Zhang, Yanjun Deng

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments 10 pages,

MENTOR: Human Perception-Guided Pretraining for Increased Generalization

Colton R. Crum, Adam Czajka

机构 * University of Notre Dame（内布拉斯加大学） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments 10 pages, 3 figures, 5 tables

ViSMaP: Unsupervised Hour-long Video Summarisation by Meta-Prompting

Jian Hu, Dimitrios Korkinof, Shaogang Gong, Mariano Beguerisse-Diaz

机构 * Queen Mary University of London（伦敦玛丽女王大学） ； Spotify 纠错

专题命中 预训练与数据 ：prompting(title,abstract)

CytoFM: The first cytology foundation model

Vedrana Ivezić, Ashwath Radhachandran, Ekaterina Redekop, Shreeram Athreya, Dongwoo Lee, Vivek Sant, Corey Arnold, William Speier

机构 * University of California, Los Angeles, USA（加州大学洛杉矶分校） 纠错

专题命中 预训练与数据 ：foundation model(title,abstract)

ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling

Dongchao Yang, Songxiang Liu, Haohan Guo, Jiankun Zhao, Yuanyuan Wang, Helin Wang, Zeqian Ju, Xubo Liu, Xueyuan Chen, Xu Tan, Xixin Wu, Helen Meng

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

Enhancing Product Search Interfaces with Sketch-Guided Diffusion and Language Agents

Edward Sun

专题命中 预训练与数据 ：language agent(title,abstract)

Comments Companion Proceedings of the ACM Web Conference 2025

Large Scale Supervised Pretraining For Traumatic Brain Injury Segmentation

Constantin Ulrich, Tassilo Wald, Fabian Isensee, Klaus H. Maier-Hein

专题命中 预训练与数据 ：pretraining(title,abstract)

Large Wireless Model (LWM): A Foundation Model for Wireless Channels

Sadjad Alikhani, Gouranga Charan, Ahmed Alkhateeb

专题命中 预训练与数据 ：foundation model(title,abstract)

Comments The LWM model and relevant scripts are available on the LWM website: https://lwm-wireless.net/

F-ViTA: Foundation Model Guided Visible to Thermal Translation

Jay N. Paranjape, Celso de Melo, Vishal M. Patel

专题命中 预训练与数据 ：foundation model(title,abstract)

GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes

Pradyumn Goyal, Dmitry Petrov, Sheldon Andrews, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Evangelos Kalogerakis

专题命中 预训练与数据 ：pretraining(title,abstract)

Leveraging Diffusion Model and Image Foundation Model for Improved Correspondence Matching in Coronary Angiography

Lin Zhao, Xin Yu, Yikang Liu, Xiao Chen, Eric Z. Chen, Terrence Chen, Shanhui Sun

专题命中 预训练与数据 ：foundation model(title,abstract)

SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining

Pei-Kai Huang, Jun-Xiong Chong, Cheng-Hsuan Chiang, Tzu-Hsien Chen, Tyng-Luh Liu, Chiou-Ting Hsu

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments Accepted by AAAI 2025

Role of the Pretraining and the Adaptation data sizes for low-resource real-time MRI video segmentation

Masoud Thajudeen Tholan, Vinayaka Hegde, Chetan Sharma, Prasanta Kumar Ghosh

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments Accepted to ICASSP 2025

Journal ref IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5

Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition

Khanh Nguyen, Ghulam Mubashar Hassan, Ajmal Mian

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments Accepted to CVPR 2025

3D-MVP: 3D Multiview Pretraining for Robotic Manipulation

Shengyi Qian, Kaichun Mo, Valts Blukis, David F. Fouhey, Dieter Fox, Ankit Goyal

专题命中 预训练与数据 ：pretraining(title,abstract)

Comments CVPR 2025

Distilling Monocular Foundation Model for Fine-grained Depth Completion

Yingping Liang, Yutao Hu, Wenqi Shao, Ying Fu

专题命中 预训练与数据 ：foundation model(title,abstract)