Primary
-
Still: Amortized KV Cache Compaction in a Single Forward Pass
— O'Neill, Sandomirsky, Partridge, Jayasekara and Kirkby. arxiv (2026)
-
A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations
— O'Neill, Chalnev, Kirkby, Zhao and Jayasekara. Actionable Interpretability Workshop, ICML (2025)
-
Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
— O'Neill, Jayasekara and Kirkby. arxiv (2025)
-
Guanylate-binding proteins: mechanisms of pattern recognition and antimicrobial functions
— Kirkby et al. Trends in Biochemical Sciences (2023)
-
Streptococcus makes the cut: Gasdermin A-induced pyroptosis
— Zhao, Kirkby and Man. Cell Host & Microbe Immunology (2022)
-
Running to save sight: The effects of exercise on retinal health and function
— Chu-Tan, Kirkby and Natoli. Clinical & Experimental Ophthalmology (2021)
Artefacts
-
Distillation without the dark
— Kirkby and O'Neill. Baseten Research (2026)
-
Dense, on-policy, or both?
— Kirkby and O'Neill. Baseten Research (2026)
-
Practical LoRA Research
— Kirkby and O'Neill. Parsed Research (2025)
-
Training loss predicts evaluation performance, even for non-verifiable tasks
— O'Neill and Kirkby. Parsed Research (2025)
-
Iterative SFT (iSFT): dense reward learning
— O'Neill, Liu, Partridge and Kirkby. Parsed Research (2025)
-
Lumina: building self-improving evaluation through customer-in-the-loop refinement
— O'Neill, Partridge, Kirkby, Liu and Stefanopoulos. Parsed Research (2025)
-
Write small, learn forever: rank-1 LoRA for continual learning
— O'Neill, Liu, Kirkby and Partridge. Parsed Research (2025)
-
Attention-based attribution: what your model is actually looking at
— O'Neill, Liu, Canavan, Kirkby and Jayasekara. Parsed Research (2025)
-
Fine-tuning small open-source LLMs to outperform large closed-source models by 60% on specialized tasks
— O'Neill, Jayasekara and Kirkby. Parsed Research (2025)