Tolgay Atinc Uzun

Tolgay Atinc Uzun, Waleed Khalid, Saif U Din et al.

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.

Tolgay Atinc Uzun, Dmitry Ignatov, Radu Timofte

Channel configuration search the optimization of layer specifications such as layer widths in deep neural networks presents a complex combinatorial challenge constrained by tensor shape compatibility and computational budgets. We posit that Large Language Models (LLMs) offer a transformative approach to Neural Architecture Search (NAS), capable of reasoning about architectural code structure in ways that traditional heuristics cannot. In this paper, we investigate the application of an LLM-driven NAS framework to the problem of channel configuration. We formulate the search as a sequence of conditional code generation tasks, where an LLM refines architectural specifications based on performance telemetry. Crucially, we address the data scarcity problem by generating a vast corpus of valid, shape-consistent architectures via Abstract Syntax Tree (AST) mutations. While these mutated networks are not necessarily high-performing, they provide the critical volume of structural data required for the LLM to learn the latent relationship between channel configurations and model performance. This allows the LLM to internalize complex design patterns and apply them to optimize feature extraction strategies. Experimental results on CIFAR-100 validate the efficacy of this approach, demonstrating that the model yields statistically significant improvements in accuracy. Our analysis confirms that the LLM successfully acquires domain-specific architectural priors, distinguishing this method from random search and highlighting the immense potential of language-driven design in deep learning.

Arash Torabi Goodarzi, Roman Kochnev, Waleed Khalid et al.

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

Tolgay Atinc Uzun, Radu Timofte, Dmitry Ignatov

Promising initial results in closed-loop large-language-model-based channel-configuration search demonstrated that neural-network widths can be optimized directly through executable code generation and accuracy feedback. However, those results were obtained from a relatively sparse set of valid evaluations, leaving open whether the observed optimization behavior transfers to a denser sampling regime and whether additional architectural regularities emerge when more generated networks are evaluated. To test this, the same search setting is scaled to 250 candidate networks per fine-tuning cycle. The analysis covers 2000 generated candidates from 8 complete cycles, yielding 462 verified CIFAR-100 evaluations after task and metadata filtering. Per-cycle mean accuracy exhibits a positive linear trend with slope 9.87e-4 (p=0.043), while the high-performing frontier improves more strongly: the best observed accuracy increases from 0.3144 to 0.3676, and both the top-5 and top-10 cycle-level means exhibit positive trends. The scaled run also reveals improved parameter efficiency. The best model reaches 0.3676 with 11.8M parameters, compared with an early high-performing model at 0.3144 with 166.5M parameters. Beyond accuracy, the larger sample exposes architectural regularities that were difficult to assess from sparse observations. Non-power-of-two channel widths occur in 41.8% of verified candidates, and the strongest models share structured channel-allocation patterns characterized by moderate early widths and expanded middle or later blocks. These findings indicate that the channel-search signal observed in the initial study transfers