6 papers
HyperCertificates: Verification of Discrete-time Dynamical Systems against HyperLTL Specifications
Vishnu Murali, Amin Falah, Ashutosh Trivedi +1
We introduce a functional inductive framework to verify discrete-time dynamical systems against hyperproperties specified as Hyperlinear temporal logic formulae via a notion of Hyp…
Monotonicity as an Architectural Bias for Robust Language Models
Patrick Cooper, Alireza Nadali, Ashutosh Trivedi +1
Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility r…
Monotone Neural Barrier Certificates
Saber Jafarpour, Alireza Nadali, Ashutosh Trivedi +1
This report presents a neurosymbolic framework for safety verification and control synthesis in high-dimensional monotone dynamical systems without relying on explicit models or co…
Co-Buchi Barrier Certificates for Discrete-time Dynamical Systems
Vishnu Murali, Ashutosh Trivedi, Majid Zamani
Barrier certificates provide functional overapproximations for the reachable set of dynamical systems and provide inductive guarantees on the safe evolution of the system. In autom…
Physics-Informed Reward Machines
Daniel Ajeleye, Ashutosh Trivedi, Majid Zamani
Reward machines (RMs) provide a structured way to specify non-Markovian rewards in reinforcement learning (RL), thereby improving both expressiveness and programmability. Viewed mo…
Transfer Learning for Control Systems via Neural Simulation Relations
Alireza Nadali, Bingzhuo Zhong, Ashutosh Trivedi +1
Transfer learning is an umbrella term for machine learning approaches that leverage knowledge gained from solving one problem (the source domain) to improve speed, efficiency, and…