Sudarshan S. Harithas

Robots can now learn complex skills more efficiently, achieving optimal performance even with limited practice time.

Transformer-based SLAM can achieve state-of-the-art accuracy and efficiency by integrating a spatially corrective back-end that restores high-cadence local bundle adjustment.

Training diffusion priors directly in a robot's motion space, using a mixture of human and robot data, unlocks more diverse and robust humanoid skills without manual intervention.