3 citations · 3 across the 5 of their papers we have counts for
6 papers
Rate or Fate? RLVR: Reinforcement Learning with Verifiable Noisy Rewards
Ali Rad, Khashayar Filom, Darioush Keivan +2
Reinforcement learning with verifiable rewards (RLVR) is a simple but powerful paradigm for training LLMs: sample a completion, verify it, and update. In practice, however, the ver…
Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs
Xingang Guo, Yaxin Li, Xiangyi Kong +62
Modern engineering, spanning electrical, mechanical, aerospace, civil, and computer disciplines, stands as a cornerstone of human civilization and the foundation of our society. Ho…
ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise
Xingang Guo, Darioush Keivan, Usman Syed +5
Control system design is a crucial aspect of modern engineering with far-reaching applications across diverse sectors including aerospace, automotive systems, power grids, and robo…
Model-Free -Synthesis: A Nonsmooth Optimization Perspective
Darioush Keivan, Xingang Guo, Peter Seiler +2
In this paper, we revisit model-free policy search on an important robust control benchmark, namely -synthesis. In the general output-feedback setting, there do not exist convex…
Revisiting PGD Attacks for Stability Analysis of Large-Scale Nonlinear Systems and Perception-Based Control
Aaron Havens, Darioush Keivan, Peter Seiler +2
Many existing region-of-attraction (ROA) analysis tools find difficulty in addressing feedback systems with large-scale neural network (NN) policies and/or high-dimensional sensing…
Model-Free Synthesis via Adversarial Reinforcement Learning
Darioush Keivan, Aaron Havens, Peter Seiler +2
Motivated by the recent empirical success of policy-based reinforcement learning (RL), there has been a research trend studying the performance of policy-based RL methods on standa…