Paper Trail
Search
Search
Dark mode
Light mode
Explorer
Tag: stanford
6 items with this tag.
Mar 25, 2026
Diffusion Model Alignment Using Direct Preference Optimization
paper
image-generation-posttrain
stanford
salesforce
modality/image
modality/text
Mar 18, 2026
Diffusion Model Alignment Using Direct Preference Optimization
paper
image-generation-posttrain
salesforce
stanford
modality/image
modality/text
Mar 18, 2026
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
paper
reward-model
stanford
modality/text
Mar 18, 2026
KTO: Model Alignment as Prospect Theoretic Optimization
paper
reward-model
stanford
contextual-ai
modality/text
Mar 18, 2026
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
paper
reward-model
unc-chapel-hill
uchicago
stanford
modality/image
modality/text
Mar 18, 2026
R3: Robust Rubric-Agnostic Reward Models
paper
reward-model
stanford
allen-ai
modality/text