Shankar Sastry
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Graph-as-Policy (GaP), a multi-agent coding harness for Variational Automation tasks that generates directed computation graphs and improves success rates and throughput through internal simulation.
RPG framework improves robot execution systems without updating model weights by identifying manipulation capabilities, constructing practice tasks, and revising system prompts.
This paper explores generative modeling of humanoid control networks through their weights, enabling the creation of deployable networks for various motions.
Papers
Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion
This paper explores generative modeling of humanoid control networks through their weights, enabling the creation of deployable networks for various motions.