Koushil Sreenath

MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning

CHyLL: Learning Continuous Neural Representations of Hybrid Systems

LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction

Robust Adversarial Policy Optimization Under Dynamics Uncertainty

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations