AI for Disability Collection A collection of datasets, models, spaces and papers that uses AI to address a disability-related topic. • 3 items • Updated 6 days ago • 3
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated 12 days ago • 197
Multimodal Chaptering for Long-Form TV Newscast Video Paper • 2406.17590 • Published Mar 20, 2024 • 2
Building and better understanding vision-language models: insights and future directions Paper • 2408.12637 • Published Aug 22, 2024 • 124
Goldfish: Vision-Language Understanding of Arbitrarily Long Videos Paper • 2407.12679 • Published Jul 17, 2024 • 7
Towards Retrieval Augmented Generation over Large Video Libraries Paper • 2406.14938 • Published Jun 21, 2024 • 19
Inserting Faces inside Captions: Image Captioning with Attention Guided Merging Paper • 2405.02305 • Published Mar 20, 2024 • 2