语言大模型 / LLM

DACTYL: Diverse Adversarial Corpus of Texts Yielded from Large Language Models

Shantanu Thorat, Andrew Caines

机构 * Department of Computer Science & Technology University of Cambridge（计算机科学与技术系剑桥大学） 纠错

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

Comments MPhil in Advanced Computer Science thesis for University of Cambridge

Meta CLIP 2: A Worldwide Scaling Recipe

Yung-Sung Chuang, Yang Li, Dong Wang, Ching-Feng Yeh, Kehan Lyu, Ramya Raghavendra, James Glass, Lifei Huang, Jason Weston, Luke Zettlemoyer, Xinlei Chen, Zhuang Liu, Saining Xie, Wen-tau Yih, Shang-Wen Li, Hu Xu

机构 * FAIR, Meta（FAIR与Meta公司） ； MIT（麻省理工学院） ； Princeton University（普林斯顿大学） ； New York University（纽约大学） 纠错

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

Comments 10 pages

Robust Classification under Noisy Labels: A Geometry-Aware Reliability Framework for Foundation Models

Ecem Bozkurt, Antonio Ortega

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

Comments 5 pages, 2 figures, under review at CAMSAP 2025

LLaVA-Video: Video Instruction Tuning With Synthetic Data

Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun Ma, Ziwei Liu, Chunyuan Li

机构 * S-Lab, Nanyang Technological University（南洋理工大学S实验室） ； BUPT（北京邮电大学） ； ByteDance（字节跳动） 纠错

专题命中 预训练与数据 ：instruction tuning(title,abstract)；分类 cs.CL

Comments Project page: https://llava-vl.github.io/blog/2024-09-30-llava-video/; Accepted at TMLR

Out-of-Context Abduction: LLMs Make Inferences About Procedural Data Leveraging Declarative Facts in Earlier Training Data

Sohaib Imran, Rob Lamb, Peter M. Atkinson

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

SA-GCS: Semantic-Aware Gaussian Curriculum Scheduling for UAV Vision-Language Navigation

Hengxing Cai, Jinhan Dong, Yijie Rao, Jingcheng Deng, Jingjun Tan, Qien Chen, Haidong Wang, Zhen Wang, Shiyu Huang, Agachai Sumalee, Renxin Zhong

专题命中 预训练与数据 ：language model(abstract)；post-training(abstract)；分类 cs.CL

Reducing the gap between general purpose data and aerial images in concentrated solar power plants

M. A. Pérez-Cutiño, J. Valverde, J. Capitán, J. M. Díaz-Báñez

机构 * organization= Department of Applied Mathematics II, University of Seville , city= Seville , country= Spain ； organization= Multi-robot \& Control Systems group, University of Seville , city= Seville , country= Spain 纠错

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI

H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation

Hongzhe Bi, Lingxuan Wu, Tianwei Lin, Hengkai Tan, Zhizhong Su, Hang Su, Jun Zhu

专题命中 预训练与数据 ：foundation model(abstract)；分类 cs.LG

BERTtime Stories: Investigating the Role of Synthetic Story Data in Language Pre-training

Nikitas Theodoropoulos, Giorgos Filandrianos, Vassilis Lyberatos, Maria Lymperaiou, Giorgos Stamou

机构 * First Author Affiliation（第一作者单位） ； Second Author Affiliation（第二作者单位） 纠错

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL

Journal ref The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning, pages 308-323, Miami, FL, USA. Association for Computational Linguistics, 2024

$\texttt{BATCLIP}$: Bimodal Online Test-Time Adaptation for CLIP

Sarthak Kumar Maharana, Baoming Zhang, Leonid Karlinsky, Rogerio Feris, Yunhui Guo

机构 * The University of Texas at Dallas（德克萨斯大学达拉斯分校） ； MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室） 纠错

专题命中 预训练与数据 ：pretraining(abstract)

Comments ICCV 2025

Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data

Sagi Eppel, Jolina Li, Manuel Drehwald, Alan Aspuru-Guzik

机构 * Vector institute（向量研究所） ； University of Toronto（多伦多大学） 纠错

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

Journal ref Advances in Neural Information Processing Systems, vol. 37, pp. 60237-60259, 2024