no code implementations • 28 Dec 2023 • Jyothir S V, Siddhartha Jalagam, Yann Lecun, Vlad Sobal
The enduring challenge in the field of artificial intelligence has been the control of systems to achieve desired behaviours.
1 code implementation • 8 Sep 2023 • Saksham Bassi, Giulio Duregon, Siddhartha Jalagam, David Roth
In light of recent successes in large scale audio pretraining, we revisit the performance comparison between two-stage and end-to-end model and find that audio based language models pretrained using weak self-supervised objectives match or exceed the performance of similarly trained two-stage models, and further, that the choice of pretraining objective substantially effects a model's ability to be adapted to the disfluency removal task.
1 code implementation • 20 Nov 2022 • Vlad Sobal, Jyothir S V, Siddhartha Jalagam, Nicolas Carion, Kyunghyun Cho, Yann Lecun
Many common methods for learning a world model for pixel-based environments use generative architectures trained with pixel-level reconstruction objectives.