8 papers
Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models
Omanshu Thapliyal
Safety heads are lightweight classifiers attached to pretrained language models for flagging harmful inputs before generation. Their empirical detection performance has been studie…
SSM Adapters via Hankel Reduced-order Modeling: Injection Site Determines Task Suitability in Long-Context Fine-Tuning
Omanshu Thapliyal
While parameter-efficient fine-tuning (PEFT) typically targets attention projectors, its efficacy for tasks requiring sequential state accumulation remains under-explored. We exami…
A Multi-Head Attention Approach for SLA Compliance Monitoring in Data Centers
Omanshu Thapliyal
Service level agreements (SLAs) in data center colocation contracts define precise thresholds for power, temperature, and humidity, with tiered violation penalties expressed as cre…
Safe Navigation using Neural Radiance Fields via Reachable Sets
Omanshu Thapliyal, Malarvizhi Sankaranarayanasamy, Ravigopal Vennelakanti
Safe navigation in cluttered environments is an important challenge for autonomous systems. Robots navigating through obstacle ridden scenarios need to be able to navigate safely i…
An Algorithm for Distributed Computation of Reachable Sets for Multi-Agent Systems
Omanshu Thapliyal, Shanelle Clarke, Inseok Hwang
In this paper, we consider the problem of distributed reachable set computation for multi-agent systems (MASs) interacting over an undirected, stationary graph. A full state-feedba…
Data-driven Cyberattack Synthesis against Network Control Systems
Omanshu Thapliyal, Inseok Hwang
Network Control Systems (NCSs) pose unique vulnerabilities to cyberattacks due to a heavy reliance on communication channels. These channels can be susceptible to eavesdropping, fa…
Approximating Reachable Sets for Neural Network based Models in Real-Time via Optimal Control
Omanshu Thapliyal, Inseok Hwang
In this paper, we present a data-driven framework for real-time estimation of reachable sets for control systems where the plant is modeled using neural networks (NNs). We utilize…
Direct Data-Driven Discrete-time Bilinear Biquadratic Regulator
Shanelle G. Clarke, Omanshu Thapliyal, Inseok Hwang
We present a novel direct data-driven algorithm that learns an optimal control policy for the Bilinear Biquadratic Regulator (BBR) for an unknown bilinear system. The BBR is diffic…