Collecting large-scale, diverse, and high-quality post-training datasets for autoregressive language models is challenging. Consequently, Supervised Fine-Tuning (SFT) is typically applied to datasets significantly smaller than those used for pre-training, which leads to overfitting and the catastrophic forgetting of th...
G. Daras, M. Papachristou, A. Klivans et al.· 0 citations
We introduce RefineMix, a framework for training discrete diffusion models under severe data scarcity, a common constraint in scientific applications. RefineMix uses out-of-distribution data at selected diffusion times to improve generalization without biasing the sampling distribution. Although this strategy has been...
Julian Kleutgens, M. Tec, Claudio Battiloro et al.· 0 citations
PoEM, a framework to predict the outputs of RL on a new reward function using a set of models already post-trained on other rewards, is introduced by introducing PoEM, a framework to predict the outputs of RL on a new reward function using a set of models already post-trained on other rewards.
K. Hamidieh, G. Daras, Antonio Torralba· arXiv.org· 0 citations
Ambient Dataloops is an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution, and a dataset-model co-evolution process; at each iteration of the method, the dataset becomes progressively higher quality, and the model improves accordingly.
Adrián Rodríguez-Muñoz, William Daspit, Adam Klivans et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.