MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model [CVPR 2026]
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Speculative Forcing for Efficient Autoregressive Video Generation
Omni-Modal LLMs Know More Than They Say
models 40
naver-ai/DroneCATS-Cosmos3-Edge-2B
Image-Text-to-Text • 2B • Updated • 53 • 3
naver-ai/MuCo-2B
Feature Extraction • 2B • Updated • 34 • 1
naver-ai/MuCo-7B
Feature Extraction • 8B • Updated • 19 • 1
naver-ai/tobo_vit_small
Updated
naver-ai/clip_vit_b_32_model_stock
Updated
naver-ai/clip_vit_b_32_model_stock_star
Updated
naver-ai/clip_vit_b_16_model_stock
Updated
naver-ai/clip_vit_b_16_model_stock_star
Updated
naver-ai/USDM-DailyTalk
Audio-to-Audio • 7B • Updated • 11 • 1
naver-ai/USTM
Audio-to-Audio • 7B • Updated • 9