SOTAVerified

Preference Mapping

Papers

Showing 111 of 11 papers

TitleStatusHype
Direct Preference Optimization: Your Language Model is Secretly a Reward ModelCode6
ImageReward: Learning and Evaluating Human Preferences for Text-to-Image GenerationCode3
Learning Transferable Visual Models From Natural Language SupervisionCode2
Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image GenerationCode2
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image SynthesisCode2
PAI-BPR: Personalized Outfit Recommendation Scheme with Attribute-wise InterpretabilityCode1
Personalized Language Modeling from Personalized Human FeedbackCode1
PAL: Pluralistic Alignment Framework for Learning from Heterogeneous PreferencesCode1
LAION-5B: An open large-scale dataset for training next generation image-text modelsCode0
Curvature as an Organizing Principle of Mid-level Visual Representation: A Semantic-preference Mapping Approach0
Distributional Domain-Invariant Preference Matching for Cross-Domain Recommendation0
Show:102550

No leaderboard results yet.