🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal reinforcement.
Shawn
csfufu
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
about 16 hours ago
ARES
upvoted
a
paper
about 1 month ago
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
upvoted
a
paper
about 1 month ago
Reconstruction Alignment Improves Unified Multimodal Models
Organizations
