From the 1 of 8 linked papers with an AI index.
8 papers
Soft GRAND under Channel Switching and Drift
Behrooz Razeghi
Under channel switching or drift, the posterior used to order soft GRAND queries can differ from the matched correction posterior, which can increase rank and finite-budget decodin…
Tail-Calibrated Soft-Output GRAND for Finite-Memory Noise-Effect Posteriors
Behrooz Razeghi
In guessing random additive noise decoding (GRAND), memory in the hard-decision noise effect changes the likelihood order of candidate noise effects. In soft-output decoding, the s…
Low-Pathwidth GRAND: Exact Likelihood-Ordered Enumeration for BPSK Transmission over Correlated Gaussian Noise
Behrooz Razeghi
The paper introduces Low-Pathwidth GRAND (LP‑GRAND), an exact maximum‑likelihood decoding method for BPSK transmission over correlated Gaussian noise that exploits the low pathwidt…
ScoreShield: Differentially Private Release of Similarity Scores
Behrooz Razeghi, Parsa Rahimi
A growing number of applications, such as biometrics and retrieval-augmented generation (RAG), rely on cosine similarity scores computed between vector embeddings of text, images,…
Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment
Behrooz Razeghi
AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own ap…
On the Capacity of Distinguishable Synthetic Identity Generation under Face Verification
Behrooz Razeghi
We study how many synthetic identities can be generated so that a face verifier declares same-identity pairs as matches and different-identity pairs as non-matches at a fixed thres…