Preference-based Reinforcement Learning - Groups

Direct Preference Optimization With Unobserved Preference Heterogeneity

The dataset used in the paper is a binary preference dataset from heterogeneous annotators.
- Dataset
- JSON
Subject-driven Text-to-Image Generation via Preference-based Reinforcement Le...

Text-to-image generative models have recently attracted considerable interest, enabling the synthesis of high-quality images from textual prompts. However, these models often...
- Dataset
- JSON

2 datasets found