Shalin Jain

Hi, my name is Shalin! I am interested in methods for enabling embodied intelligent systems in the real world that exhibit coordinated, adaptable, and collaborative behavior. To this end, my current research centers around reinforcement learning and multi-robot systems.

Papers

• Improving VLA Workspace Randomization Robustness for Industrial Pick-and-Place via Lightweight Residual RL: A Case Study — CVPR Embodied AI Workshop (Oral Spotlight), 2026
• Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video — Preprint, 2026
• JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 Minutes — Conference on Robot Learning (CoRL), 2025
• Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination — Conference on Robot Learning (CoRL), 2025
• Evaluating and Improving Graph-based Explanation Methods for Multi-Agent Coordination — Autonomous Agents and Multi-Agent Systems (AAMAS) - Extended Abstract, 2025
• Learning Flexible Heterogeneous Coordination With Capability-Aware Shared Hypernetworks — Autonomous Agents and Multi-Agent Systems (AAMAS) - Extended Abstract, 2025