Geodesic Multi-Modal Mixup for Robust Fine-Tuning Neurips 2023 Changdae Oh, Junhyuk So, Hoyoon Byun, YongTaek Lim, Minchul Shin, Jong-June Jeon, Kyungwoo Song University of Seoul, POSTECH, KAIS...
TWhat to Align in Multimodal Contrastive Learning ICLR 2025 Benoit Dufumier, aviera Castillo Navarro, Devis Tuia, Dong Wang, Jean-Philippe Thiran EPFL, NeuroSpin-CFA, CEDRIC-CNAM, Radiology Depa...
Train Once, Deploy Anywhere: Matryoshka Representation Learning for Multimodal Recommendation EMNLP findinds 2024 Yueqi Wang, Zhenrui Yue, Huimin Zeng, Dong Wang, Julian McAuley University of Ca...
Matryoshka Representation Learning Neurips 2022 Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham Kakade, Prateek Jain, Ali Fa...
DrVideo: Document Retrieval Based Long Video Understanding CVPR 2025 Ziyu Ma, Chenhui Gou, Hengcan Shi, Bin Sun, Shutao Li, Hamid Rezatofighi, Jianfei Cai College of Electrical and Information E...
Discovering Clone Negatives via Adaptive Contrastive Learning for Image-Text Matching ICLR 2025 Renjie Pan, Jihao Dong, Hua Yang Institute of Image Communication and Network Engineering, Shanghai...
Effective post-training embedding compression via temperature control in contrastive training ICLR 2025 spotlight Georgiana Dinu, Corey Barrett, Yi Xiang, Miguel Romero Calvo, Anna Currey, Xing N...
VkD : Improving Knowledge Distillation using Orthogonal Projections CVPR 2024 Roy Miles, Ismail Elezi, Jiankang Deng Huawei Noah’s Ark Lab [paper] 1. Abstract & Introduction 기존 연구 문제점 ...
Weighted Point Cloud Embedding for Multi-modal Contrastive Learning Toward Optimal Similarity Metric ICLR 2025 spotlight Toshimitsu Uesaka, aiji Suzuki, Yuhta Takida, Chieh-Hsin Lai, Naoki Murata...
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models ICLR 2025 oral Simon Schrodi, David T. Hoffmann, Max Argus, Volker Fisch...