3 papers
cs.LG2026
Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search
Pranav Somu, Advay Balakrishnan, Stepan Kravtsov +2
Developing effective surrogates (performance predictors) for Neural Architecture Search (NAS) typically requires expensive fine-tuning or the engineering of complex representations…
physics.optics2026
Frequency-domain Event-based Imaging for Selective Surveillance
Megan Birch, James Rick, Adrish Kar +2
Event-based cameras (EBCs) are an attractive sensing modality for surveillance due to their reporting of pixel-level radiance changes with microsecond resolution and high dynamic r…
cs.NE2025
LLM-Guided Evolution: An Autonomous Model Optimization for Object Detection
YiMing Yu, Jason Zutty
In machine learning, Neural Architecture Search (NAS) requires domain knowledge of model design and a large amount of trial-and-error to achieve promising performance. Meanwhile, e…