CIFAR-10

CIFAR-10 is a benchmark dataset containing 60,000 32x32 color images across 10 classes, used to evaluate the performance of machine learning models, particularly in image classification tasks.

Papers using CIFAR-10 (4)

LLM-Driven Neural Network Generation with Same-Family Architecture Guidance: Disentangling Transfer and Adaptation2026From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures2026Large Language Models Implicitly Learn to See and Hear Just By Reading2025ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs2025