🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal reinforcement le
Shawn
csfufu
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
upvoted
a
paper
5 days ago
Reconstruction Alignment Improves Unified Multimodal Models
upvoted
a
paper
6 days ago
Interleaving Reasoning for Better Text-to-Image Generation
Organizations
