Max Torop

PhD student, Northeastern University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

DISCO: Disentangled Communication Steering for Large Language Models

#4001 · Max Torop, Aria Masoomi, Masih Eskandar, Jennifer Dy

We propose, analyze, and validate a method for guiding LLM behavior at inference time by applying steering vectors to query and value representations.