← authors · overview

• R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
  2025
• Stochastic Linear Bandits with Hidden Low Rank Structure
  2019
• Robust Regression for Safe Exploration in Control
  2019
• Learning Causal State Representations of Partially Observable Environments
  2019
• Triply Robust Off-Policy Evaluation
  2019
• Regret Minimization in Partially Observable Linear Quadratic Control
  2020
• Deep Bayesian Quadrature Policy Optimization
  2020
• Pre-Trained Language Models for Interactive Decision-Making
  2022
• Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits
  2022
• Thompson Sampling Achieves O() Regret in Linear Quadratic Control
  2022
• Langevin Monte Carlo for Contextual Bandits
  2022
• LeanAgent: Lifelong Learning for Formal Theorem Proving
  2024