moonshotai/Kimi-VL-A3B-Thinking-2506
Image-Text-to-Text
•
16B
•
Updated
•
180k
•
316
ZhimingMa
JimmyMa99
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in
MLLMs
commented on
a paper
about 1 month ago
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in
MLLMs
upvoted
a
paper
about 1 month ago
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and
Training Recipe
Organizations
liked
a
model
4 months ago