2 papers
cs.LG2026
Targeted Neuron Modulation via Contrastive Pair Search
Sam Herring, Jake Naviasky, Karan Malhotra
Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering methods operate on the resi…
cs.AI2025
Hermes 4 Technical Report
Ryan Teknium, Roger Jin, Jai Suphavadeeprasit +6
We present Hermes 4, a family of hybrid reasoning models that combine structured, multi-turn reasoning with broad instruction-following ability. We describe the challenges encounte…