-
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
Paper • 2407.04842 • Published • 55 -
yichaodu/DiffusionDPO-alignment-gemini-1.5
Text-to-Image • 0.9B • Updated • 17 • 1 -
yichaodu/DiffusionDPO-safety-internvl-1.5
Text-to-Image • 0.9B • Updated • 6 -
yichaodu/DiffusionDPO-alignment-gpt-4o
Text-to-Image • 0.9B • Updated • 6
Yichao Du
yichaodu
AI & ML interests
None yet
Recent Activity
authored a paper about 4 hours ago
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models authored a paper 2 days ago
PhysBrain 1.5: From Vision-Language Models to Physical Foundation ModelsOrganizations
-
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
Paper • 2407.04842 • Published • 55 -
yichaodu/DiffusionDPO-alignment-gemini-1.5
Text-to-Image • 0.9B • Updated • 17 • 1 -
yichaodu/DiffusionDPO-safety-internvl-1.5
Text-to-Image • 0.9B • Updated • 6 -
yichaodu/DiffusionDPO-alignment-gpt-4o
Text-to-Image • 0.9B • Updated • 6