ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
Paper • 2504.01934 • Published • 22 •
4
huangrh9
huangrh9
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation authored a paper 1 day ago
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable RewardOrganizations
commented 2
papers over 1 year ago