2 papers
cs.LG2026
Online Adaptive Kernel Mixing for Gaussian Process Decision Making
Kavin Aravindan, Mani Tej Sriram, Gautam Dasarathy +1
Gaussian Processes (GPs) are widely used as surrogates for black-box functions in sequential decision-making problems such as Bayesian optimization (BO), level set estimation (LSE)…
cs.LG2026
OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization
Kavin Aravindan, Arihant Rastogi, Krishak Aneja +4
Activation steering provides a lightweight mechanism for controlling large language models at inference time, but steering vectors can have unintended externalities: utility vector…