OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
Paper
•
2510.15870
•
Published
•
89
chinoll
chinoll
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 months ago
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding
LLM
new activity
3 months ago
chinoll/chatsakura-3b-int8:Adding `safetensors` variant of this model
upvoted
a
paper
5 months ago
Trainable Dynamic Mask Sparse Attention
Organizations
