Showing 2026Show all
2 papers · 1 filter
cs.CR2026
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
Minoo Kim, Vasileios Lampos, George Drayson
Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted behaviour when a trigger appears in the input. Existing backdoor defences for LL…
cs.CL2026
Jupiter-N Technical Report
George Drayson
We present Jupiter-N, a hybrid reasoning model post-trained from Nemotron 3 Super, a fully open-source 120 billion parameter LLM. We target three objectives: (1) agentic capability…