pith. sign in

arxiv: 2504.10552 · v4 · pith:4KHD5D4Fnew · submitted 2025-04-14 · 💻 cs.LG · cs.AI· cs.CV· cs.DL

LEMUR Neural Network Dataset: Towards Seamless AutoML

Arash Torabi Goodarzi , Roman Kochnev , Waleed Khalid , Hojjat Torabi Goudarzi , Furui Qin , Tolgay Atinc Uzun , Yashkumar Sanjaybhai Dhameliya , Yash Kanubhai Kathiriya
show 3 more authors
Zofia Antonina Bentyn Dmitry Ignatov Radu Timofte
This is my paper
classification 💻 cs.LG cs.AIcs.CVcs.DL
keywords lemurneuralabrain-onegithubhttpsautomldatasetdatasets
0
0 comments X
read the original abstract

Neural networks are the backbone of modern artificial intelligence, but designing, evaluating, and comparing them remains labor-intensive. While numerous datasets exist for training, there are few standardized collections of the models themselves. We introduce LEMUR, an open-source dataset and framework that provides a large collection of PyTorch-based neural networks across tasks such as classification, segmentation, detection, and natural language processing. Each model follows a unified template, with configurations and results stored in a structured database to ensure consistency and reproducibility. LEMUR integrates automated hyperparameter optimization via Optuna, includes statistical analysis and visualization tools, and offers an API for seamless access to performance data. The framework is extensible, allowing researchers to add new models, datasets, or metrics without breaking compatibility. By standardizing implementations and unifying evaluation, LEMUR aims to accelerate AutoML research, enable fair benchmarking, and reduce barriers to large-scale neural network experimentation. To support adoption and collaboration, LEMUR and its plugins are released under the MIT license at: https://github.com/ABrain-One/nn-dataset https://github.com/ABrain-One/nn-plots https://github.com/ABrain-One/nn-vr

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs

    cs.LG 2026-05 unverdicted novelty 7.0

    Fine-tuned 7B LLMs generating unified diffs for neural architecture refinement achieve 66-75% valid rates and 64-66% mean first-epoch accuracy, outperforming full-generation baselines by large margins while cutting ou...

  2. From Code to Prediction: Fine-Tuning LLMs for Neural Network Performance Classification in NNGPT

    cs.LG 2026-05 unverdicted novelty 6.0

    Fine-tuned LLMs classify neural network architectures by cross-dataset performance suitability, achieving 80% accuracy from code alone versus 70% from metadata.

  3. Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models

    cs.CV 2026-01 unverdicted novelty 6.0

    Closed-loop LLM search with AST-generated examples discovers non-standard channel widths that improve vision model performance over initial architectures on CIFAR-100.

  4. Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design

    cs.CV 2025-12 conditional novelty 6.0

    Three-example few-shot prompting optimizes LLM-generated vision architectures while a whitespace-normalized hash provides 100x faster duplicate detection than AST parsing across seven benchmarks.

  5. A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks

    cs.CV 2025-12 unverdicted novelty 6.0

    NN-RAG extracts 1,289 candidate neural modules from 19 PyTorch repositories, validates 941 of them, and supplies roughly 72% of the novel structures in the LEMUR dataset while enabling cross-repository migration.

  6. From Code to Prediction: Fine-Tuning LLMs for Neural Network Performance Classification in NNGPT

    cs.LG 2026-05 unverdicted novelty 5.0

    Fine-tuned LLMs reach 80% accuracy predicting which dataset a neural network code performs better on, outperforming metadata prompts at 70%.

  7. Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs

    cs.CV 2026-05 unverdicted novelty 5.0

    A 1.96M-parameter LiteDenoiseNet student model achieves 37.58 dB PSNR on full-resolution real image denoising benchmarks while running in 34-46 ms on mobile NPUs by leveraging NPU-compatible primitives and high-alpha ...

  8. Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis

    cs.LG 2025-11 unverdicted novelty 4.0

    FractalNet automatically generates and tests over 1,200 CNN architectures based on recursive fractal templates, achieving up to 80.18% accuracy on CIFAR-10 after five training epochs.

  9. MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment

    cs.CV 2026-04 unverdicted novelty 3.0

    MobileAgeNet uses a MobileNetV3-Large backbone with a regression head to achieve 4.65 years mean absolute error in age estimation and 14.4 ms on-device latency with 3.23 million parameters.

  10. Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis

    cs.LG 2025-11 unverdicted novelty 3.0

    Fractal templates enable systematic creation of more than 1,200 neural network variants that show strong performance and computational efficiency when trained on CIFAR-10 for five epochs.