Skip to content

Author

Deepti Raghavan

We have 2 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Nov 2026

TIDE: Reclaiming Lost Performance In On-Policy Reinforcement Learning

TIDE is an RL training system that preserves on-policy training semantics while recovering resource utilization, and provides end-to-end speedups of up to 1.36x over colocated systems, outperforming all evaluated on-policy baselines and achieving up to 97% of optimal throughput.

Mathew Jacob, Morgan Borjigin-Wang, Kan Zhu et al. · 0 citations
Book Open access Sep 2026

We Need to Talk About the Actual Guarantees of Rust-based Systems

This paper identifies a common weakness in Rust-based systems: extensions, even those that may be considered “safe,” may fail to uphold the language properties on which these systems rely.

CO Tiffany, Artem Agvanian, Zian Song et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.