Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
–Neural Information Processing Systems
Project lead, main contributor, correspondence to alexandre.rame@isir.upmc.fr. Equal experimental contribution, order determined at random. Further information and resources related to this project can be found on this website.
Neural Information Processing Systems
Feb-17-2026, 14:16:58 GMT
- Country:
- Africa > Malawi (0.05)
- Europe > France
- Île-de-France > Paris > Paris (0.04)
- North America > United States (0.14)
- Genre:
- Research Report > New Finding (0.92)
- Industry:
- Media (0.93)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (1.00)
- Reinforcement Learning (1.00)
- Statistical Learning (0.92)
- Natural Language
- Chatbot (0.92)
- Large Language Model (1.00)
- Representation & Reasoning > Optimization (0.67)
- Vision (1.00)
- Machine Learning
- Communications (0.93)
- Game Theory (0.82)
- Artificial Intelligence
- Information Technology