OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models Paper • 2502.01061 • Published Feb 3 • 218
view article Article SmolVLM Grows Smaller – Introducing the 250M & 500M Models! By andito and 2 others • Jan 23 • 181
Qwen2.5-VL Collection Vision-language model series based on Qwen2.5 • 11 items • Updated Apr 28 • 490
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 • 10 items • Updated Apr 30 • 73
view article Article Open-R1: a fully open reproduction of DeepSeek-R1 By eliebak and 2 others • Jan 28 • 868