3 citations · 7 across the 9 of their papers we have counts for
10 papers
Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors
Edward W. Staley, Connor O. Pyles, Rahul Hingorani +5
Vision-Language-Action (VLA) models rely strongly on language for describing task information, despite having multimodal inputs. We hypothesize that other modalities in the state s…
Coupling Language Models with Physics-based Simulation for Synthesis of Inorganic Materials
Edward W. Staley, Tom Arbaugh, Michael Pekala +6
Modern generative machine learning (ML) models can propose novel inorganic crystalline materials with targeted properties; however, synthesis planning of these materials remains di…
A Systematic Review of Poisoning Attacks Against Large Language Models
Neil Fendley, Edward W. Staley, Joshua Carney +3
With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased…
To Burst or Not to Burst: Generating and Quantifying Improbable Text
Kuleen Sasse, Samuel Barham, Efsun Sarioglu Kayi +1
While large language models (LLMs) are extremely capable at text generation, their outputs are still distinguishable from human-authored text. We explore this separation across man…
Clipped-Objective Policy Gradients for Pessimistic Policy Optimization
Jared Markowitz, Edward W. Staley
To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making lar…
Triangular Dropout: Variable Network Width without Retraining
Edward W. Staley, Jared Markowitz
One of the most fundamental design choices in neural networks is layer width: it affects the capacity of what a network can learn and determines the complexity of the solution. Thi…