1 code implementation • 16 Nov 2023 • Alex Wilf, Sihyun Shawn Lee, Paul Pu Liang, Louis-Philippe Morency
Human interactions are deeply rooted in the interplay of thoughts, beliefs, and desires made possible by Theory of Mind (ToM): our cognitive ability to understand the mental states of ourselves and others.
1 code implementation • 3 Nov 2023 • Alex Wilf, Alex Tianyi Xu, Paul Pu Liang, Alexander Obolenskiy, Daniel Fried, Louis-Philippe Morency
We observe that prevalent KD techniques and state of the art data augmentation strategies fall short in this constrained setting.
1 code implementation • 7 Jun 2023 • Paul Pu Liang, Chun Kai Ling, Yun Cheng, Alex Obolenskiy, Yudong Liu, Rohan Pandey, Alex Wilf, Louis-Philippe Morency, Ruslan Salakhutdinov
We propose two lower bounds based on the amount of shared information between modalities and the disagreement between separately trained unimodal classifiers, and derive an upper bound through connections to approximate algorithms for min-entropy couplings.
1 code implementation • 23 May 2023 • Alex Wilf, Syeda Nahida Akter, Leena Mathur, Paul Pu Liang, Sheryl Mathew, Mengrou Shou, Eric Nyberg, Louis-Philippe Morency
The self-supervised objective of masking-and-predicting has led to promising performance gains on a variety of downstream tasks.
no code implementations • 29 Jul 2022 • Alex Wilf, Martin Q. Ma, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
Creating artificial social intelligence - algorithms that can understand the nuances of multi-person interactions - is an exciting and emerging challenge in processing facial expressions and gestures from multimodal videos.
no code implementations • 21 Oct 2020 • Alex Wilf, Emily Mower Provost
Robustness to environmental noise is important to creating automatic speech emotion recognition systems that are deployable in the real world.