Tar
🚀
49
Unified MLLM with Text-Aligned Representations
Tar
[NeurIPS 2025] Unifying Visual Understanding and Generation via Text-Aligned Representations
-
-
ByteDance-Seed/Tar-1.5B
Any-to-Any • 3B • Updated • 74 • 23 -
ByteDance-Seed/Tar-7B
Any-to-Any • 9B • Updated • 86 • 40 -
ByteDance-Seed/Tar-TA-Tok
Updated • 7 -
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
Paper • 2506.18898 • Published • 35