{"ID":6138901,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-10T22:16:18.90904708Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06839","arxiv_id":"2607.06839","title":"LEMUR 2: Unlocking Neural Network Diversity for AI","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 NN-VR and 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 and coupling diverse architectural origins with large-scale, cross-platform empirical validation. This dataset defines a new basis for reproducible and data-driven AI design, advancing the emerging paradigm of LLM-driven AutoML and architectural generalization across modalities and hardware.","short_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...","url_abs":"https://arxiv.org/abs/2607.06839","url_pdf":"https://arxiv.org/pdf/2607.06839v1","authors":"[\"Tolgay Atinc Uzun\",\"Waleed Khalid\",\"Saif U Din\",\"Sai Revanth Mulukuledu\",\"Akashdeep Singh\",\"Chandini Vysyaraju\",\"Raghuvir Duvvuri\",\"Avi Goyal\",\"Yashkumar Rajeshbhai Lukhi\",\"Muhammad A. Hussain\",\"Krunal Jesani\",\"Usha Shrestha\",\"Yash Mittal\",\"Roman Kochnev\",\"Pritam Kadam\",\"Mohsin Ikram\",\"Harsh R. Moradiya\",\"Alice Arslanian\",\"Dmitry Ignatov\",\"Radu Timofte\"]","published":"2026-07-07T22:21:53Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}