12 citations · 25 across the 16 of their papers we have counts for
16 papers
Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching
William English, Hao Zheng, Rickard Ewetz
Vision-Language-Action (VLA) models have demonstrated promising generalization capabilities across robotic manipulation tasks, yet their real-world deployment remains limited by th…
Characterizing the Impact of NVFP4 Quantization for Low-Power Edge AI Deployment
Ovishake Sen, Venkata Nithin Kamineni, Daniel Lobo +3
Energy-efficient neural-network inference at the edge requires reducing arithmetic cost, memory traffic, computation energy, and storage overhead while maintaining acceptable accur…
Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs
William English, Dominic Simon, Sumit Kumar Jha +1
Translating natural language (NL) into a formal language such as temporal logic (TL) is integral for human communication with robots and autonomous systems. State-of-the-art approa…
GinSign: Grounding Natural Language Into System Signatures for Temporal Logic Translation
William English, Chase Walker, Dominic Simon +1
Natural language (NL) to temporal logic (TL) translation enables engineers to specify, verify, and enforce system behaviors without manually crafting formal specifications-an essen…
Explaining the Reasoning of Large Language Models Using Attribution Graphs
Chase Walker, Rickard Ewetz
Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to inp…
Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis
Dominic Simon, Rickard Ewetz
Large Language Models (LLMs) require lightweight avenues of updating stored information that has fallen out of date. Knowledge Editing (KE) approaches have been successful in updat…
Verifiable Natural Language to Linear Temporal Logic Translation: A Benchmark Dataset and Evaluation Suite
William H English, Chase Walker, Dominic Simon +2
Empirical evaluation of state-of-the-art natural-language (NL) to temporal-logic (TL) translation systems reveals near-perfect performance on existing benchmarks. However, current…
NSP: A Neuro-Symbolic Natural Language Navigational Planner
William English, Dominic Simon, Sumit Jha +1
Path planners that can interpret free-form natural language instructions hold promise to automate a wide range of robotics applications. These planners simplify user interactions a…
Data Augmentation for Image Classification using Generative AI
Fazle Rahat, M Shifat Hossain, Md Rubel Ahmed +2
Scaling laws dictate that the performance of AI models is proportional to the amount of available data. Data augmentation is a promising solution to expanding the dataset size. Tra…
Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving
Sumit Kumar Jha, Susmit Jha, Patrick Lincoln +4
Generative large language models (LLMs) with instruct training such as GPT-4 can follow human-provided instruction prompts and generate human-like responses to these prompts. Apart…
Neural Stochastic Differential Equations for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions
Sumit Kumar Jha, Susmit Jha, Rickard Ewetz +1
We present a comprehensive evaluation of the robustness and explainability of ResNet-like models in the context of Unintended Radiated Emission (URE) classification and suggest a n…
Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision
Chase Walker, Sumit Jha, Kenny Chen +1
Attribution algorithms are frequently employed to explain the decisions of neural network models. Integrated Gradients (IG) is an influential attribution method due to its strong a…
On the Robustness of AlphaFold: A COVID-19 Case Study
Ismail Alkhouri, Sumit Jha, Andre Beckus +5
Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks…
Protein Folding Neural Networks Are Not Robust
Sumit Kumar Jha, Arvind Ramanathan, Rickard Ewetz +2
Deep neural networks such as AlphaFold and RoseTTAFold predict remarkably accurate structures of proteins compared to other algorithmic approaches. It is known that biologically sm…
An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks
Sumit Kumar Jha, Susmit Jha, Rickard Ewetz +4
Deep neural networks have been shown to be vulnerable to membership inference attacks wherein the attacker aims to detect whether specific input data were used to train the model.…
Representable Matrices: Enabling High Accuracy Analog Computation for Inference of DNNs using Memristors
Baogang Zhang, Necati Uysal, Deliang Fan +1
Analog computing based on memristor technology is a promising solution to accelerating the inference phase of deep neural networks (DNNs). A fundamental problem is to map an arbitr…