Fine-Grained Self-Rewarding for Unified Multimodal Models
Weiyang Jin
Wayne-King
AI & ML interests
CV
Recent Activity
upvoted
a
paper
about 10 hours ago
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
upvoted
a
paper
4 days ago
GENIUS: Generative Fluid Intelligence Evaluation Suite
authored
a paper
about 2 months ago
Next-Embedding Prediction Makes Strong Vision Learners
Organizations
