Browse State-of-the-Art › Neural Architecture Search

Neural Architecture Search

859 papers with code · 26 benchmarks · 27 datasets archive 2025-07-28

Methodology

Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.

Image Credit : NAS with Reinforcement Learning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

26 leaderboard tables shown for this task, 26 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 26 until expanded.

Syntology 5 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): ImageNet (2 judged, 0 placed), CIFAR-10 (2 judged, 0 placed), CIFAR-10 Image Classification (1 judged, 0 placed), NATS-Bench Topology, ImageNet16-120 (1 judged, 0 placed), NATS-Bench Topology, CIFAR-10 (1 judged, 0 placed), NATS-Bench Topology, CIFAR-100 (1 judged, 0 placed), DTD (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
ImageNet (135 rows) DeepMAD-50M DeepMAD: Mathematical Architecture Design for Deep Convolutional... code — Compare
NAS-Bench-201, ImageNet-16-120 (49 rows) CR-LSO CR-LSO: Convex Neural Architecture Optimization in the Latent... code — Compare
CIFAR-10 (41 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
NAS-Bench-201, CIFAR-100 (40 rows) DiNAS Multi-conditioned Graph Diffusion for Neural Architecture Search code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
NAS-Bench-201, CIFAR-10 (37 rows) DiNAS Multi-conditioned Graph Diffusion for Neural Architecture Search code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
CIFAR-10 Image Classification (19 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
CIFAR-100 (13 rows) DNA-c Blockwisely Supervised Neural Architecture Search with Knowledge... code — Compare
NATS-Bench Topology, ImageNet16-120 (11 rows) LayerNAS LayerNAS: Neural Architecture Search in Polynomial Complexity — — Compare
NATS-Bench Topology, CIFAR-10 (11 rows) LayerNAS LayerNAS: Neural Architecture Search in Polynomial Complexity — — Compare
NATS-Bench Topology, CIFAR-100 (11 rows) LayerNAS LayerNAS: Neural Architecture Search in Polynomial Complexity — — Compare
Food-101 (5 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
NAS-Bench-101 (5 rows) DiNAS Multi-conditioned Graph Diffusion for Neural Architecture Search code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
NATS-Bench Size, CIFAR-10 (5 rows) GreenMachine-3 GreenMachine: Automatic Design of Zero-Cost Proxies for... code — Compare
NATS-Bench Size, CIFAR-100 (5 rows) GreenMachine-2 GreenMachine: Automatic Design of Zero-Cost Proxies for... code — Compare
CINIC-10 (4 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
DTD (4 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
FGVC Aircraft (4 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
NATS-Bench Size, ImageNet16-120 (4 rows) GreenMachine-2 GreenMachine: Automatic Design of Zero-Cost Proxies for... code — Compare
Oxford 102 Flowers (4 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
Oxford-IIIT Pet Dataset (4 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
Stanford Cars (4 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
STL-10 (4 rows) NAT-M4 Neural Architecture Transfer code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
NAS-Bench-201 (2 rows) Improved FireFly Algorithme Improving Neural Architecture Search by Mixing a FireFly algorithm... code — Compare
LIDC-IDRI (1 row) NASLung (ours) Learning Efficient, Explainable and Discriminative Representations... code — Compare
MNIST (1 row) Sparse Neural Network Structural Analysis of Sparse Neural Networks — — Compare
NAS-Bench-301 (1 row) DiNAS Multi-conditioned Graph Diffusion for Neural Architecture Search code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

27 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 1,915 · with a code link: 859 · where Syntology ran a sample: 243 (204 with a run with no instrument failure, 39 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (243 of 1,915 tagged: 204 with a run with no instrument failure, 39 where every run was a failure of Syntology's instrument)

Page 1 of 20: papers 1 to 100 of 1,915, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 54 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections