activity
20242026
collaborators

7 papers

cs.RO2026

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman +2

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees…

eess.SY2026

Scalar Federated Learning for Linear Quadratic Regulator

Mohammadreza Rostami, Shahriar Talebi, Solmaz S. Kia

We propose ScalarFedLQR, a communication-efficient federated algorithm for model-free learning of a common policy in linear quadratic regulator (LQR) control of heterogeneous agent…

eess.SY2026

Learning Kalman Policy for Singular Unknown Covariances via Riemannian Regularization

Larsen Bier, Shahriar Talebi

Kalman filtering is a cornerstone of estimation theory, yet learning the optimal filter under unknown and potentially singular noise covariances remains a fundamental challenge. In…

cs.LG2026

Hereditary Geometric Meta-RL: Nonlocal Generalization via Task Symmetries

Paul Nitschke, Shahriar Talebi

Meta-Reinforcement Learning (Meta-RL) commonly generalizes via smoothness in the task encoding. While this enables local generalization around each training task, it requires dense…

math.OC2025

Ergodic-risk Criterion for Stochastically Stabilizing Policy Optimization

Shahriar Talebi, Na Li

This paper introduces ergodic-risk criteria, which capture long-term cumulative risks associated with controlled Markov chains through probabilistic limit theorems--in contrast to…

math.OC2025

Ergodic-Risk Constrained Policy Optimization: The Linear Quadratic Case

Shahriar Talebi, Na Li

Risk-sensitive control balances performance with resilience to unlikely events in uncertain systems. This paper introduces ergodic-risk criteria, which capture long-term cumulative…