Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

Add code
Oct 02, 2025
Figure 1 for Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
Figure 2 for Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
Figure 3 for Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
Figure 4 for Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: