no code implementations • 25 Nov 2023 • Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Mohanty Das, Chirag Shah, John P Dickerson, Jeff Bilmes
In this work, we demonstrate that the efficacy of CleanCLIP in mitigating backdoors is highly dependent on the particular objective used during model pre-training.
no code implementations • CVPR 2022 • Sai Rajeswar, Pau Rodriguez, Soumye Singhal, David Vazquez, Aaron Courville
We also show that MILe is effective reducing label noise, achieving state-of-the-art performance on real-world large-scale noisy data such as WebVision.
Ranked #6 on Image Classification on WebVision-1000
no code implementations • 29 Sep 2021 • Sai Rajeswar Mudumba, Pau Rodriguez, Soumye Singhal, David Vazquez, Aaron Courville
This ambiguity biases models towards a single prediction, which could result in the suppression of classes that tend to co-occur in the data.
no code implementations • EMNLP 2020 • Yuchen Lu, Soumye Singhal, Florian Strub, Olivier Pietquin, Aaron Courville
Language drift has been one of the major obstacles to train language models through interaction.
no code implementations • ICML 2020 • Yuchen Lu, Soumye Singhal, Florian Strub, Olivier Pietquin, Aaron Courville
At each time step, the teacher is created by copying the student agent, before being finetuned to maximize task completion.
no code implementations • 17 Dec 2019 • Yatin Dandi, Aniket Das, Soumye Singhal, Vinay P. Namboodiri, Piyush Rai
The proposed model allows minor variations in content across frames while maintaining the temporal dependence through latent vectors encoding the pose or motion features.
no code implementations • ICLR 2019 • Anirudh Goyal, Philemon Brakel, William Fedus, Soumye Singhal, Timothy Lillicrap, Sergey Levine, Hugo Larochelle, Yoshua Bengio
In many environments only a tiny subset of all states yield high reward.