preference learning
An area of machine learning that focuses on predicting user preferences, typically based on pairwise comparisons of items or actions. It is essential for recommendation systems and personalized content delivery.
- A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
- Aligning Text-to-Image Diffusion Models to Human Preference by Classification
- CPO: Condition Preference Optimization for Controllable Image Generation
- Can DPO Learn Diverse Human Values? A Theoretical Scaling Law
- DeepHalo: A Neural Choice Model with Controllable Context Effects
- Generalizing while preserving monotonicity in comparison-based preference learning models
- Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
- Preference Learning with Lie Detectors can Induce Honesty or Evasion
- Preference Learning with Response Time: Robust Losses and Guarantees
- RePO: Understanding Preference Learning Through ReLU-Based Optimization
- Self-Refining Language Model Anonymizers via Adversarial Distillation