Corentin Dancette

Fishr: Invariant Gradient Variances for Out-of-Distribution\n Generalization

2021 · arXiv (Cornell University)

Learning robust models that generalize well under changes in the data\ndistribution is critical for real-world applications. To this end, there has\nbeen a growing surge of interest to learn simultaneously from multiple training\ndomains - while enforcing …

Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

2023 · arXiv (Cornell University)

Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further align the network with the intended usage. Yet the imperfections in …