Molmo 2
SOTA video understanding, pointing, and tracking VLM. Molmo 2, a new suite of state-of-the-art vision-language models with open weights, training data, and training code, can analyze videos and multiple images at once.
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
MolmoAct 2
allenai.orgOpen robotics model that reasons in 3D before acting
Run open-weight OCR
vlmrun.comVLM and vision models behind one API
SmolVLM2
huggingface.coSmallest Video LM Ever from HuggingFace
DeepSeek-VL2
github.comMoE vision-language, now easier to access
V-JEPA 2
ai.meta.comMeta's world model for physical world understanding