LEMUR 2: Unlocking Neural Network Diversity for AI

Tolgay Atinc Uzun, Waleed Khalid, Saif U Din, Sai Revanth Mulukuledu, Akashdeep Singh, Chandini Vysyaraju, Raghuvir Duvvuri, Avi Goyal, YASHKUMAR R LUKHI, Muhammad Ahsan Hussain, Krunal Jesani, Usha Shrestha, Yash Mittal, Roman Kochnev, Pritam Kadam, Mohsin ikram, Harsh Rameshbhai Moradiya, Alice Arslanian, Dmitry Ignatov, Radu Timofte

Keywords: dataset construction, neural architecture search, automl, computer vision

TL;DR: The paper builds a large scale dataset consisting of neural network architectures and their statistics.

Abstract: Existing NAS benchmarks (e.g., NAS-Bench, NATS-Bench) cover only narrow, task-specific regions of the architectural design space and lack cross-domain or deployment-aware evaluation. LEMUR 2 introduces a large-scale, extensible framework unifying generative, evaluative, and deployment pipelines to unlock neural-network diversity. It comprises over 14{,}000 distinct architectures and more than 750{,}000 structured training records documenting model performance, hyperparameters, and task outcomes. These models were produced through AST-based code mutation, genetic and reinforcement-learning evolution, generation of fractal architectures, and synthesis guided by a Large Language Model (LLM). This includes deep models generated with the retrieval-augmented system NN-RAG, which derived and used architectural motifs from over 900 PyTorch modules extracted from public repositories. LEMUR 2 further employs $\text{NN-VR}$ and $\text{NN-Lite}$ pipelines for automated deployment and latency benchmarking on heterogeneous mobile and Unity-based VR platforms, providing real-device performance metadata. It spans multimodal tasks—image captioning, text-to-image synthesis, and language modeling—supporting cross-domain analysis of architectural transferability. By linking diverse architectures, tasks, and deployment data, LEMUR 2 provides the data foundation for LLM fine-tuning, coupling diverse architectural origins with large-scale, cross-platform empirical validation. This dataset supports reproducible, data-driven AI design, advancing LLM-driven AutoML and cross-modal, hardware-aware architectural generalization.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 15