OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models Paper β’ 2502.01061 β’ Published Feb 3, 2025 β’ 222
view article Article SmolVLM Grows Smaller β Introducing the 256M & 500M Models! +1 Jan 23, 2025 β’ 189
Qwen2.5-VL Collection Vision-language model series based on Qwen2.5 β’ 11 items β’ Updated 3 days ago β’ 549
PixMo Collection A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog β’ 10 items β’ Updated 10 days ago β’ 85