#image understanding

Salesforce has released BLIP3-o, an open-source multimodal model that unifies image understanding and generation using CLIP embeddings and Flow Matching, achieving state-of-the-art results.

NVIDIA unveiled Eagle 2.5, a compact 8B parameter vision-language model that achieves state-of-the-art performance on long-context video tasks, rivaling much larger models like GPT-4o through innovative training and data strategies.