3 citations · 6 across the 5 of their papers we have counts for
6 papers
NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
Hanyu Zhu, Lance Fiondella, Jiawei Yuan +2
Retrieval-Augmented Generation (RAG) empowers Large Language Models (LLMs) to dynamically integrate external knowledge during inference, improving their factual accuracy and adapta…
Temporally Consistent Unsupervised Segmentation for Mobile Robot Perception
Christian Ellis, Maggie Wigness, Craig Lennon +1
Rapid progress in terrain-aware autonomous ground navigation has been driven by advances in supervised semantic segmentation. However, these methods rely on costly data collection…
Predicting Resilience with Neural Networks
Karen da Mata, Priscila Silva, Lance Fiondella
Resilience engineering studies the ability of a system to survive and recover from disruptive events, which finds applications in several domains. Most studies emphasize resilience…
A Mapping of Assurance Techniques for Learning Enabled Autonomous Systems to the Systems Engineering Lifecycle
Christian Ellis, Maggie Wigness, Lance Fiondella
Learning enabled autonomous systems provide increased capabilities compared to traditional systems. However, the complexity of and probabilistic nature in the underlying methods en…
Automating Staged Rollout with Reinforcement Learning
Shadow Pritchard, Vidhyashree Nagaraju, Lance Fiondella
Staged rollout is a strategy of incrementally releasing software updates to portions of the user population in order to accelerate defect discovery without incurring catastrophic o…
Risk Averse Bayesian Reward Learning for Autonomous Navigation from Human Demonstration
Christian Ellis, Maggie Wigness, John G. Rogers +2
Traditional imitation learning provides a set of methods and algorithms to learn a reward function or policy from expert demonstrations. Learning from demonstration has been shown…