SHERLock: Self-Supervised Hierarchical Event Representation Learning
Temporal event representations are an essential aspect of learning among humans. They allow for succinct encoding of the experiences we …
PDF
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances
Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing …
PDF
Status-quo policy gradient in Multi-Agent Reinforcement Learning
Individual rationality, which involves maximizing expected individual returns, does not always lead to high-utility individual or group …
PDF
Lifi: Towards linguistically informed frame interpolation
Here we explore the problem of speech video interpolation. With close to 70% of web traffic, such content today forms the primary form …
PDF Cite Code DOI
Lifi: Towards linguistically informed frame interpolation
2D to 3D medical image colorization
Colorization involves the synthesis of colors while preserving structural content as well as the semantics of the target image. This is …
PDF Cite Code Project DOI
2D to 3D medical image colorization
DeepABM: Scalable and Efficient Agent-Based Simulations via Graph Convolutional Frameworks - a Case Study for COVID-19 Spread and Interventions
We introduce DeepABM, a computational framework for agent-based modeling that leverages geometric message passing for simulating action …
PDF
LT-GAN: Self-Supervised GAN with Latent Transformation Detection
Generative Adversarial Networks (GANs) coupled with self-supervised tasks have shown promising results in unconditional and …
PDF
Medical Dead-ends and Learning to Identify High-Risk States and Treatments
Machine learning has successfully framed many sequential decision making problems as either supervised prediction, or optimal …
PDF
Robustness of Markov perfect equilibrium to model approximations in general-sum dynamic games
Dynamic games (also called stochastic games or Markov games) are an important class of games for modeling multi-agent interactions. In …
PDF
Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring
Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate’s speaking proficiency in a language. ASS …
PDF