Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Wilf, Alex"'
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. Although ToM may come naturally to us, emula
Externí odkaz:
http://arxiv.org/abs/2311.10227
Autor:
Wilf, Alex, Xu, Alex Tianyi, Liang, Paul Pu, Obolenskiy, Alexander, Fried, Daniel, Morency, Louis-Philippe
In the era of large scale pretrained models, Knowledge Distillation (KD) serves an important role in transferring the wisdom of computationally heavy teacher models to lightweight, efficient student models while preserving performance. Traditional KD
Externí odkaz:
http://arxiv.org/abs/2311.02253
Autor:
Liang, Paul Pu, Ling, Chun Kai, Cheng, Yun, Obolenskiy, Alex, Liu, Yudong, Pandey, Rohan, Wilf, Alex, Morency, Louis-Philippe, Salakhutdinov, Ruslan
In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: how modalities combine to provide new task-relevant information that was not present in eit
Externí odkaz:
http://arxiv.org/abs/2306.04539
Autor:
Wilf, Alex, Akter, Syeda Nahida, Mathur, Leena, Liang, Paul Pu, Mathew, Sheryl, Shou, Mengrou, Nyberg, Eric, Morency, Louis-Philippe
The self-supervised objective of masking-and-predicting has led to promising performance gains on a variety of downstream tasks. However, while most approaches randomly mask tokens, there is strong intuition that deciding what to mask can substantial
Externí odkaz:
http://arxiv.org/abs/2305.14577
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. Recent multimodal methods
Externí odkaz:
http://arxiv.org/abs/2208.01036
Autor:
Wilf, Alex, Provost, Emily Mower
Robustness to environmental noise is important to creating automatic speech emotion recognition systems that are deployable in the real world. Prior work on noise robustness has assumed that systems would not make use of sample-by-sample training noi
Externí odkaz:
http://arxiv.org/abs/2010.11226