MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Paper
•
2510.08540
•
Published
•
108
kevin726
kevin726hy
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
VideoScore2: Think before You Score in Generative Video Evaluation
upvoted
a
paper
about 1 month ago
Critique-Coder: Enhancing Coder Models by Critique Reinforcement
Learning
Organizations
None yet
upvoted
a
paper
20 days ago