AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search

Qinqin Zhou, Fuhai Chen, Jipeng Wu, Zhiwei Chen, Zhikai Hu, Weiwei Cai

CVPR 2026 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add gradient health to participation-ratio score (multiplicative) (ablation)InTrain · NAS-Bench-201 (CIFAR-10)Kendall tau: 0.61 -> 0.67Improved
add participation-ratio capacity to gradient-health score (multiplicative) (ablation)InTrain · NAS-Bench-201 (CIFAR-10)Kendall tau: 0.63 -> 0.67Improved
couple components multiplicatively instead of additively (ablation)InTrain · NAS-Bench-201 (CIFAR-10)Kendall tau: 0.59 -> 0.67Improved
combine components additively instead of using one alone (ablation)InTrain · NAS-Bench-201 (CIFAR-10)Kendall tau: 0.63 -> 0.59Hurt
couple components multiplicatively instead of additively (ablation)InTrain · NAS-Bench-201 (CIFAR-10)Spearman rho: 0.80 -> 0.86Improved
use Gaussian instead of uniform synthetic inputs (ablation)InTrain · NAS-Bench-201 (CIFAR-10)Kendall tauImproved
use constant all-ones inputs (ablation)InTrain · NAS-Bench-201 (CIFAR-10)Kendall tauHurt
vary input resolution 32 to 128 (ablation)InTrain · NAS-Bench-201 (CIFAR-10)Kendall tauNo clear effect
use InTrain-NAS instead of AZ-NASInTrain · ImageNet MobileNetV2 450Mtop-1 accuracy (%): 78.6 -> 78.9Improved
use InTrain-NAS instead of AZ-NASInTrain · ImageNet MobileNetV2 1000Mtop-1 accuracy (%): 81.1 -> 81.3Improved
use InTrain-NAS instead of AZ-NASInTrain · ImageNet MobileNetV2 600Mtop-1 accuracy (%): 79.9 -> 79.9No clear effect
use InTrain instead of ensemble AZ-NASInTrain · NAS-Bench-201 CIFAR-10Kendall tau: 0.712 -> 0.669Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy