#Vision Transformers

2 articles with this tag

HYDRA-X: Unifying Image & Video Tokenization
AI Research

HYDRA-X: Unifying Image & Video Tokenization

HYDRA-X, a novel Vision Transformer-based UMM, unifies image and video tokenization, enhancing editing consistency and performance through causal attention and latent-level manipulation.

4 months ago
JACTUS AI Unifies Compression and Adaptation
AI Research

JACTUS AI Unifies Compression and Adaptation

JACTUS AI unifies parameter compression and task adaptation, outperforming sequential methods with fewer retained parameters across vision and language tasks.

5 months ago