3 papers
cs.LG2026
Does Text Steer Neural PDE Surrogates? A Controlled Diagnostic with OperatorCLIP
Aadi Dash, Lennon J. Shikhman, Michael Galarnyk
Lower error from a text-conditioned neural surrogate does not, by itself, show that the model uses the meaning of the text. We examine this attribution problem with OperatorCLIP, c…
cs.AI2026
Synchronized Logit Steering: Real-world Steganography
Andrew Rufail, Aadi Dash, Onir Narahari +5
Steganography in large language models offers a way to embed hidden messages within natural-sounding text. Existing token and logit-level methods typically require the sender and r…
cs.LG2026
Inverse Learning of Latent Risk-Neutral Densities from Irregular Option Quotes
Lennon J. Shikhman, Michael Galarnyk, Aadi Dash +1
Accurate option prices do not imply accurate recovery of the latent risk-neutral density. We study this distinction with two complementary benchmarks. A controlled benchmark expose…