AI Paper of the Day Collection A collection of papers that I think are interesting, one added each day • 249 items • Updated 3 days ago • 30
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations Paper • 2412.08580 • Published 14 days ago • 44
Learning Flow Fields in Attention for Controllable Person Image Generation Paper • 2412.08486 • Published 14 days ago • 32
MarDini: Masked Autoregressive Diffusion for Video Generation at Scale Paper • 2410.20280 • Published Oct 26 • 23
view article Article Breaking resolution curse of vision-language models By visheratin • Feb 24 • 11
Playground v2 Collection Collection of Playground v2 models • 4 items • Updated Dec 6, 2023 • 7
OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models Paper • 2407.11213 • Published Jul 15 • 3
OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person Paper • 2407.16224 • Published Jul 23 • 27
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions Paper • 2406.04325 • Published Jun 6 • 72
Large Model driven Radiology Report Generation with Clinical Quality Reinforcement Learning Paper • 2403.06728 • Published Mar 11 • 2
Boximator: Generating Rich and Controllable Motions for Video Synthesis Paper • 2402.01566 • Published Feb 2 • 26
VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation Paper • 2311.16492 • Published Nov 27, 2023 • 2
Text Promptable Surgical Instrument Segmentation with Vision-Language Models Paper • 2306.09244 • Published Jun 15, 2023 • 2
HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation Paper • 2303.15994 • Published Mar 28, 2023 • 2