Multi-dimensional Preference Alignment by Conditioning Reward Itself
- 2 October 2026
- book chapter
- Published by Springer Nature
- p. 639-655
Abstract
No abstract availableKeywords
All Related Versions
This publication has 13 references indexed in Scilit:
- ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models Using Pareto High-Quality DataProceedings of the AAAI Conference on Artificial Intelligence, 2026
- Calibrated Multi-Preference Optimization for Aligning Diffusion Models2025
- Sequential Preference Optimization: Multi-Dimensional Preference Alignment with Implicit Reward ModelingProceedings of the AAAI Conference on Artificial Intelligence, 2025
- Diffusion Model Alignment Using Direct Preference Optimization2024
- Learning Multi-Dimensional Human Preference for Text-to-Image Generation2024
- Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning2024
- ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Training Language Models to Follow Instructions with Human Feedback2022
- RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNSBiometrika, 1952