DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 โข 15 items โข Updated 13 days ago โข 549
Learning Flow Fields in Attention for Controllable Person Image Generation Paper โข 2412.08486 โข Published Dec 11, 2024 โข 36