Search Results - "Sontakke, Sumedh A"

Model2Detector: Widening the Information Bottleneck for Out-of-Distribution Detection using a Handful of Gradient Steps by Sontakke, Sumedh A, Ramanan, Buvaneswari, Itti, Laurent, Woo, Thomas

“…Out-of-distribution detection is an important capability that has long eluded vanilla neural networks. Deep Neural networks (DNNs) tend to generate…”
Get full text

RoboCLIP: One Demonstration is Enough to Learn Robot Policies by Sontakke, Sumedh A, Zhang, Jesse, Arnold, Sébastien M. R, Pertsch, Karl, Bıyık, Erdem, Sadigh, Dorsa, Finn, Chelsea, Itti, Laurent

“…Reward specification is a notoriously difficult problem in reinforcement learning, requiring extensive expert supervision to design robust reward functions…”
Get full text

Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning by Sontakke, Sumedh A, Mehrjou, Arash, Itti, Laurent, Schölkopf, Bernhard

“…Animals exhibit an innate ability to learn regularities of the world through interaction. By performing experiments in their environment, they are able to…”
Get full text

GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL by Sontakke, Sumedh A, Iota, Stephen, Hu, Zizhao, Mehrjou, Arash, Itti, Laurent, Schölkopf, Bernhard

“…Out-of-distribution (OOD) detection is a well-studied topic in supervised learning. Extending the successes in supervised learning methods to the reinforcement…”
Get full text

Video2Skill: Adapting Events in Demonstration Videos to Skills in an Environment using Cyclic MDP Homomorphisms by Sontakke, Sumedh A, Roychowdhury, Sumegh, Sarkar, Mausoom, Puri, Nikaash, Krishnamurthy, Balaji, Itti, Laurent

“…Humans excel at learning long-horizon tasks from demonstrations augmented with textual commentary, as evidenced by the burgeoning popularity of tutorial videos…”
Get full text

SHERLock: Self-Supervised Hierarchical Event Representation Learning by Roychowdhury, Sumegh, Sontakke, Sumedh A, Puri, Nikaash, Sarkar, Mausoom, Aggarwal, Milan, Badjatiya, Pinkesh, Krishnamurthy, Balaji, Itti, Laurent

“…Temporal event representations are an essential aspect of learning among humans. They allow for succinct encoding of the experiences we have through a variety…”
Get full text