Publications
Also on Google Scholar.
-
arXiv 2026Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads
* Equal contribution
- AdaptFM @ ICML 2026LOCUS: Low-Dimensional Model Embeddings for Efficient Model Exploration, Comparison, and Selection
-
arXiv 2026Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
* Equal contribution
- AISTATS 2026ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers
- IEEE SPCOM 2024An Asymptotic CVaR Measure of Risk for Markov Chains
- ICLR 2024f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization