Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
Paper
•
2506.18898
•
Published
•
32
Tar
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
-
-
44
Tar
🚀Unified MLLM with Text-Aligned Representations
-
2
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 • 318 • 16 -
ByteDance-Seed/Tar-7B
Any-to-Any • 9B • Updated • 148 • 30 -
ByteDance-Seed/Tar-TA-Tok
Updated • 5 -
csuhan/tar_1.5B_pretrain_demo
3B • Updated • 3