← Back to all news
arXiv Computer Vision By Yuiko Sakuma, Masakazu Yoshimura, Marcel Gr\"opl, Zitang Sun, Junji Otsuka, Atsushi Irie, Takeshi Ohashi

Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search

Read the original on arXiv Computer Vision →

The paper introduces a semi-automated method for structuring neural architecture search (NAS) using large language models (LLMs). It defines a high-level template of architectural attributes, which an LLM populates by analyzing research papers to create a diverse search space. The authors then propose FairNAD, a multi-type mutation strategy that combines fair idea sampling, Pareto-aware mutation, LLM-driven iterative mutation, and a fine-grained feedback loop to efficiently explore this space, achieving significant performance gains on CIFAR-10, CIFAR-100, and ImageNet16-120.

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 Computer Vision.

Related stories

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 →
arXiv Machine Learning
Jul 9

LEMUR 2: Unlocking Neural Network Diversity for AI

arXiv:2607. 06839v1 Announce Type: new Abstract: Existing NAS benchmarks (e.

By Tolgay Atinc Uzun, Waleed Khalid, Saif U Din, Sai Revanth Mulukuledu, Akashdeep Singh, Chandini Vysyaraju, Raghuvir Duvvuri, Avi Goyal, Yashkumar Rajeshbhai Lukhi, Muhammad A. Hussain, Krunal Jesani, Usha Shrestha, Yash Mittal, Roman Kochnev, Pritam Kadam, Mohsin Ikram, Harsh R. Moradiya, Alice Arslanian, Dmitry Ignatov, Radu Timofte
llmsragdiffusionfine-tuningmultimodalbenchmarks
More like this →
arXiv Machine Learning
Oct 3

SyntheticHLS: Building Diverse Synthetic High-Level Synthesis Datasets using LLMs

SyntheticHLS is a framework that uses large language models to create large-scale, diverse synthetic high‑level synthesis (HLS) datasets. It employs an iterative, feedback‑guided mutation loop that transforms seed designs into more complex, scalable ones, guided by quantitative metrics of design complexity and scalability. The resulting datasets outperform manually curated or zero‑shot generated ones in training deep learning models for HLS quality‑of‑results, offering broader coverage of design space and better generalization.

By Stefan Abi-Karam, Miaoyan Zhou, Callie Hao
llmsbenchmarks
More like this →