Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
Paper
•
2506.18898
•
Published
•
33
Tar
[NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
-
-
47
Tar
🚀Unified MLLM with Text-Aligned Representations
-
3
Tar
🚀Unified MLLM with Text-Aligned Representations
-
60
Tar
🚀Unified MLLM with Text-Aligned Representations
-
ByteDance-Seed/Tar-1.5B
Any-to-Any • 3B • Updated • 126 • 20 -
ByteDance-Seed/Tar-7B
Any-to-Any • 9B • Updated • 338 • 38 -
ByteDance-Seed/Tar-TA-Tok
Updated • 6 -
csuhan/Tar-SANA-600M-512px
Text-to-Image • Updated • 2 -
csuhan/Tar-SANA-600M-1024px
Text-to-Image • Updated -
csuhan/Tar-Lumina2
Updated -
csuhan/tar_1.5B_pretrain_demo
3B • Updated • 4 • 1