MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning
Paper
•
2505.24871
•
Published
•
20
Zhewen Hu
larried
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement
Learning
upvoted
a
paper
5 days ago
DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models
Organizations
None yet
larried's activity
upvoted
2
papers
5 days ago