3 papers
cs.LG2026
How Do Language Models Choose Between Context and Memory?
Benjamin Shih, John Winnicki, Arianna Cao
When contextual information conflicts with the knowledge stored in model parameters, activation directions can be used to decode and steer which source the model follows. However,…
cs.LG2026
When Does Activation Steering Change What a Model Computes From?
Benjamin Shih, John Winnicki, Eric Darve
Activation steering can reliably change an agent's output by modifying its internal activations. Yet arriving at the same answer need not involve the same computation: behavioral e…
cs.LG2024
Transformers as Neural Operators for Solutions of Differential Equations with Finite Regularity
Benjamin Shih, Ahmad Peyvan, Zhongqiang Zhang +1
Neural operator learning models have emerged as very effective surrogates in data-driven methods for partial differential equations (PDEs) across different applications from comput…