Publications (6)
Recommending More Efficient Workflows to Software Developers
Dylan Bates
Existing recommendation systems can help developers improve their software development abilities by recommending new programming tools, such as a refactoring tool or a program navi…
Can Editing 1 Neuron Fix Repetition Loops in LLMs?
Aristotelis Lazaridis, Aman Sharma, Dylan Bates +3
Yes. Can it cure doom loops? Probably not. The Gemma 4 instruction-tuned models share a reproducible failure: on long factual enumeration prompts, such as listing every episode of…
EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation
Aristotelis Lazaridis, Dylan Bates, Aman Sharma +3
On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution d…
EdgeRunner 20B: Military Task Parity with GPT-5 while Running on the Edge
Jack FitzGerald, Aristotelis Lazaridis, Dylan Bates +17
We present EdgeRunner 20B, a fine-tuned version of gpt-oss-20b optimized for military tasks. EdgeRunner 20B was trained on 1.6M high-quality records curated from military documenta…
Measuring and Eliminating Refusals in Military Large Language Models
Jack FitzGerald, Dylan Bates, Aristotelis Lazaridis +17
Military Large Language Models (LLMs) must provide accurate information to the warfighter in time-critical and dangerous situations. However, today's LLMs are imbued with safety be…
A Hybrid Approach for Reinforcement Learning Using Virtual Policy Gradient for Balancing an Inverted Pendulum
Dylan Bates
Using the policy gradient algorithm, we train a single-hidden-layer neural network to balance a physically accurate simulation of a single inverted pendulum. The trained weights an…