Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You
Salim Khazem, Ibrahim Mohamed Serouis
Test-time adaptation (TTA) typically assumes that model parameters can be updated at inference time. This assumption is restrictive for inference-only accelerators, frozen or third…
cs.LG2026
Thermodynamic Signatures of Reasoning: Free-Energy and Spectral-Form-Factor Diagnostics for Hallucination Detection in Large Language Models
Salim Khazem
Hallucination detection in large language models (LLMs) is deployment-critical, and recent work shows that the spectrum of attention-derived graph Laplacians carries strong signal…
cs.LG2026
SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbones
Salim Khazem
Early-exit networks reduce inference cost by allowing ``easy'' inputs to stop early, but practical deployment hinges on knowing \emph{when} early exit is safe. We introduce SAFE-KD…