Alexandre Ramé
Home
Publications
Talks/Posts
Teaching
Books
Page not found
Perhaps you were looking for one of these?
Publications
WARM: On the Benefits of Weight Averaged Reward Models
Diverse and Efficient Ensembling of Deep Networks
Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
UnIVAL: Unified Model for Image, Video, Audio and Language Tasks
Cite
×