← Back to all news
arXiv AI By Tyler King, Timothee Leleu

LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks

Read the original on arXiv AI →

arXiv:2606. 10294v1 Announce Type: cross Abstract: Deploying neural networks on unconventional hardware demands architectures that co-optimize task accuracy and platform-specific constraints such as energy cost, physical non-idealities, and numerical precision.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jun 5

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

arXiv:2605. 16138v2 Announce Type: replace Abstract: Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost.

By Jason Weitz, Dmitri Demler, Benjamin Hawks, Aaron Wang, Nhan Tran, Javier Duarte
agentsfine-tuningefficiency
More like this →
arXiv AI
Jun 26

A3C3: AI Algorithm and Accelerator Co-design, Co-search, and Co-generation

arXiv:2606. 20869v2 Announce Type: replace-cross Abstract: We present a holistic methodology for artificial intelligence algorithm and accelerator co-design, co-search, and co-generation (A3C3), which jointly optimizes neural network architectures and their hardware implementations to address the inefficiencies of traditional top-down AI system design flows.

By Selin Yildirim, Yingbing Huang, Deming Chen
efficiency
More like this →
arXiv Machine Learning
Jul 31

SNAC-Pack 2.0: Scaled-Out Surrogate Neural Architecture Codesign

arXiv:2605. 16138v3 Announce Type: replace Abstract: Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost.

By Jason Weitz, Dmitri Demler, Benjamin Hawks, Aaron Wang, Nhan Tran, Javier Duarte
agentsfine-tuningefficiency
More like this →
arXiv AI
6d ago

ENAS: An Efficient Hardware-Aware Neural Architecture Search Framework for TinyML on Resource-Constrained Microcontrollers

ENAS is a hardware‑aware neural architecture search framework tailored for TinyML on microcontrollers. It uses a static feasibility check, a cell‑based search space with various block types and skip connections, and a three‑stage hybrid search strategy (random → top‑K → mutation) with cross‑run caching. The framework runs efficiently without GPUs, achieving significant search‑time speedups and competitive accuracy on Visual Wake Words and Melanoma Cancer benchmarks across a range of microcontrollers.

By Mohd Moin Khan, Naman Srivastava, Pandarasamy Arjunan
benchmarks
More like this →
arXiv Machine Learning
Aug 27

ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures

ONNX-Net introduces a universal representation for neural architectures using natural language descriptions, enabling instant performance prediction across diverse search spaces. The authors present ONNX-Bench, a benchmark of over 600k architecture–accuracy pairs compiled from open‑source NAS‑bench networks in ONNX format. Experiments demonstrate strong zero‑shot predictive performance with minimal pretraining, overcoming the limitations of cell‑based, graph‑encoded approaches.

By Shiwen Qin, Alexander Auras, Shay B. Cohen, Elliot J. Crowley, Michael Moeller, Linus Ericsson, Jovita Lukasik
efficiencybenchmarks
More like this →