5 stories
Vision foundation models such as DINOv2, SigLIP2, and MASt3R develop complementary capabilities from different pretraining objectives, yet their knowledge remains distributed across separate, specialized models.
Vision-language models such as CLIP exhibit strong semantic generalization, but remain limited in fine-grained visual perception. A recent work named KUEA presents a natural remedy by finetuning the image encoder under the supervision of the vision-centric DINOv2 to align their kernel matrices…
Representation alignment (REPA) accelerates diffusion transformer training, but its alignment targets are almost exclusively semantic encoders such as DINOv2 and CLIP.
AI image models have become extremely good at producing something that looks like stone, ceramic, brushed metal, leather, or concrete, but these images are not readily usable in a traditional CGI workflow - they have baked-in specular highlights, occlusion, perspective distortions, and any number…
Meta set a goal to reach net zero emissions by 2030. We are developing technology to mitigate our carbon footprint and making these openly available.
Showing 5 of 5 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
