-
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
Paper • 2407.04842 • Published • 53 -
yichaodu/DiffusionDPO-alignment-gemini-1.5
Text-to-Image • Updated • 2 -
yichaodu/DiffusionDPO-safety-internvl-1.5
Text-to-Image • Updated • 2 -
yichaodu/DiffusionDPO-alignment-gpt-4o
Text-to-Image • Updated • 4
yichaodu
yichaodu
AI & ML interests
None yet
Organizations
Collections
1
Papers
1
models
18
yichaodu/DiffusionDPO-bias-internvl-1.5
Text-to-Image
•
Updated
•
3
yichaodu/DiffusionDPO-bias-hps-2.1
Text-to-Image
•
Updated
•
2
yichaodu/DiffusionDPO-bias-gpt-4v
Text-to-Image
•
Updated
•
5
yichaodu/DiffusionDPO-bias-gpt-4o
Text-to-Image
•
Updated
•
6
yichaodu/DiffusionDPO-bias-gemini-1.5
Text-to-Image
•
Updated
•
4
•
1
yichaodu/DiffusionDPO-bias-claude3-opus
Text-to-Image
•
Updated
•
5
yichaodu/DiffusionDPO-safety-internvl-1.5
Text-to-Image
•
Updated
•
2
yichaodu/DiffusionDPO-safety-hps-2.1
Text-to-Image
•
Updated
•
8
yichaodu/DiffusionDPO-safety-gpt-4v
Text-to-Image
•
Updated
•
16
yichaodu/DiffusionDPO-safety-gpt-4o
Text-to-Image
•
Updated
•
4
datasets
None public yet