Search papers, labs, and topics across Lattice.
LEMUR 2 introduces a comprehensive framework that integrates generative, evaluative, and deployment processes to explore neural network diversity across various tasks and platforms. By generating over 14,000 architectures and collecting extensive training records, it enables cross-domain analysis and empirical validation of model performance. The framework's innovative use of AST-based code mutation and LLM-guided synthesis significantly enhances the reproducibility and data-driven nature of AI design, paving the way for improved architectural generalization in AutoML applications.
Unlocking over 14,000 unique neural architectures, LEMUR 2 sets a new standard for cross-domain evaluation and deployment in AI design.
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.
