Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models
Xiangyu Yin, Tora Bodin, Rohan Menon +1
Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder layer. We compare five defence c…
cs.AI2023
Hypothesis Network Planned Exploration for Rapid Meta-Reinforcement Learning Adaptation
Maxwell Joseph Jacobson, Rohan Menon, John Zeng +1
Meta-Reinforcement Learning (Meta-RL) learns optimal policies across a series of related tasks. A central challenge in Meta-RL is rapidly identifying which previously learned task…