Abhishek Gupta

This work presents RebarSim, a visual sim-to-real system trained entirely in simulation, a privileged state-based teacher is trained with reinforcement learning over procedurally generated rebar geometries, then distilled into a multi-view student that maps raw RGB and proprioception directly to actions under extensive domain randomization.

Recoverable eviction can drastically reduce missed attention and improve information retention in long-context decoding, outperforming traditional methods.

By combining simulation-trained priors with real-world adaptation, SPARR achieves near-perfect success in robotic assembly without human supervision, outperforming both sim-to-real and real-world RL baselines.