Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC Paper • 2203.15565 • Published Mar 28, 2022 • 1
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm Paper • 2502.12513 • Published 11 days ago • 15
Unicom: Universal and Compact Representation Learning for Image Retrieval Paper • 2304.05884 • Published Apr 12, 2023 • 2
Multi-label Cluster Discrimination for Visual Representation Learning Paper • 2407.17331 • Published Jul 24, 2024 • 2
Qwen2-VL Collection Vision-language model series based on Qwen2 • 16 items • Updated Dec 6, 2024 • 207
AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model Paper • 2309.16058 • Published Sep 27, 2023 • 55