7 citations · 19 across the 34 of their papers we have counts for
6 papers · 1 filter
Understanding the Robustness of Multi-Exit Models under Common Corruptions
Akshay Mehra, Skyler Seto, Navdeep Jaitly +1
Multi-Exit models (MEMs) use an early-exit strategy to improve the accuracy and efficiency of deep neural networks (DNNs) by allowing samples to exit the network before the last la…
Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning
Katherine Metcalf, Miguel Sarabia, Barry-John Theobald
Preference-based reinforcement learning (RL) algorithms help avoid the pitfalls of hand-crafted reward functions by distilling them from human preference feedback, but they remain…
Contrastive Self-Supervised Learning for Skeleton Representations
Nico Lingg, Miguel Sarabia, Luca Zappella +1
Human skeleton point clouds are commonly used to automatically classify and predict the behaviour of others. In this paper, we use a contrastive self-supervised learning method, Si…
Naturalistic Head Motion Generation from Speech
Trisha Mittal, Zakaria Aldeneh, Masha Fedzechkina +2
Synthesizing natural head motion to accompany speech for an embodied conversational agent is necessary for providing a rich interactive experience. Most prior works assess the qual…
On the role of Lip Articulation in Visual Speech Perception
Zakaria Aldeneh, Masha Fedzechkina, Skyler Seto +4
Generating realistic lip motion from audio to simulate speech production is critical for driving natural character animation. Previous research has shown that traditional metrics u…
FedEmbed: Personalized Private Federated Learning
Andrew Silva, Katherine Metcalf, Nicholas Apostoloff +1
Federated learning enables the deployment of machine learning to problems for which centralized data collection is impractical. Adding differential privacy guarantees bounds on pri…