LEMUR 2: Unlocking Neural Network Diversity for AI

• URL: http://arxiv.org/abs/2607.06839v1
• Date: Tue, 07 Jul 2026 22:21:53 GMT
• Title: LEMUR 2: Unlocking Neural Network Diversity for AI
• Abstract summary: LEMUR 2 introduces a large-scale, unifying generative, evaluative, and deployment pipelines to unlock neural-network diversity.<n>It comprises over 14,000 distinct architectures and more than 750,000 structured training records documenting model performance.<n>This dataset defines a new basis for reproducible and data-driven AI design, advancing the emerging paradigm of LLM-driven AutoML.
• Score: 28.96525007010618
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Modeling and Recovering Hierarchical Structural Architectures of ROS 2 Systems from Code and Launch Configurations using LLM-based Agents [3.4923417716883]
  subsystem-level recall drops with repository complexity due to implicit launch semantics.<n>We evaluate the approach on three ROS2 repositories, including an industrial-scale code subset.
  arXiv  Detail & Related papers  (2026-02-20T22:36:47Z)
• Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models [48.83701310501069]
  Large Language Models (LLMs) offer a transformative approach to Neural Architecture Search (NAS)<n>We formulate the search as a sequence of conditional code generation tasks, where an LLM refines architectural specifications based on performance telemetry.<n>We generate a vast corpus of valid, shape-consistent architectures via Abstract Syntax Tree (AST) mutations.<n> Experimental results on CIFAR-100 validate the efficacy of this approach, demonstrating that the model yields statistically significant improvements in accuracy.
  arXiv  Detail & Related papers  (2026-01-13T13:00:30Z)
• Cognitive-YOLO: LLM-Driven Architecture Synthesis from First Principles of Data for Object Detection [3.5554162308775408]
  We propose Cognitive-YOLO, a novel framework for Large Language Models (LLMs)-driven architecture synthesis.<n>Our method consists of three stages: first, an analysis module extracts key meta-features from the target dataset.<n>Second, the LLM reasons upon these features, augmented with state-of-the-art components retrieved via Retrieval-Augmented Generation (RAG), to synthesize the architecture into a structured Neural Architecture Description Language (NADL)<n>Third, a compiler instantiates this description into a deployable model.
  arXiv  Detail & Related papers  (2025-12-13T10:52:54Z)
• A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks [48.83701310501069]
  We introduce NN-RAG, a retrieval-augmented generation system that converts large, heterogeneous PyTorchs into a searchable library of validated neural modules.<n>Applying to 19 major repositories, the pipeline extracted 1,289 candidate blocks, validated 941 (73.0%), and demonstrated that over 80% are structurally unique.
  arXiv  Detail & Related papers  (2025-12-03T23:28:30Z)
• LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding [55.5535016040221]
  LM-Searcher is a novel framework for cross-domain neural architecture optimization.<n>Central to our approach is NCode, a universal numerical string representation for neural architectures.<n>Our dataset, encompassing a wide range of architecture-performance pairs, encourages robust and transferable learning.
  arXiv  Detail & Related papers  (2025-09-06T09:26:39Z)
• LEMUR Neural Network Dataset: Towards Seamless AutoML [35.57280723615144]
  We introduce LEMUR, an open-source dataset and framework that provides a large collection of PyTorch-based neural networks.<n>Each model follows a unified template, with configurations and results stored in a structured database to ensure consistency.<n>LEMUR aims to accelerate AutoML research, enable fair benchmarking, and reduce barriers to large-scale neural network research.
  arXiv  Detail & Related papers  (2025-04-14T09:08:00Z)
• Arch-LLM: Taming LLMs for Neural Architecture Generation via Unsupervised Discrete Representation Learning [2.981775461282335]
  A common approach involves the use of Variational Autoencoders (VAEs) to map discrete architectures onto a continuous representation space.<n>We introduce a Vector Quantized Variational Autoencoder (VQ-VAE) to learn a discrete latent space more naturally aligned with the discrete neural architectures.<n>Compared to VAE-based methods, our approach improves the generation of valid and unique architectures by over 80% on NASBench-101 and over 8% on NASBench-201.
  arXiv  Detail & Related papers  (2025-03-28T00:56:56Z)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models [11.670056503731905]
  We introduce SEKI, a novel large language model (LLM)-based neural architecture search (NAS) method.<n>Inspired by the chain-of-thought (CoT) paradigm in modern LLMs, SEKI operates in two key stages: self-evolution and knowledge distillation.
  arXiv  Detail & Related papers  (2025-02-27T09:17:49Z)
• A Survey of Model Architectures in Information Retrieval [59.61734783818073]
  The period from 2019 to the present has represented one of the biggest paradigm shifts in information retrieval (IR) and natural language processing (NLP)<n>We trace the development from traditional term-based methods to modern neural approaches, particularly highlighting the impact of transformer-based models and subsequent large language models (LLMs)<n>We conclude with a forward-looking discussion of emerging challenges and future directions.
  arXiv  Detail & Related papers  (2025-02-20T18:42:58Z)
• Serving Deep Learning Model in Relational Databases [70.53282490832189]
  Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains. We highlight three pivotal paradigms: The state-of-the-art DL-centric architecture offloads DL computations to dedicated DL frameworks. The potential UDF-centric architecture encapsulates one or more tensor computations into User Defined Functions (UDFs) within the relational database management system (RDBMS)
  arXiv  Detail & Related papers  (2023-10-07T06:01:35Z)
• NAS-Count: Counting-by-Density with Neural Architecture Search [74.92941571724525]
  We automate the design of counting models with Neural Architecture Search (NAS) We introduce an end-to-end searched encoder-decoder architecture, Automatic Multi-Scale Network (AMSNet)
  arXiv  Detail & Related papers  (2020-02-29T09:18:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.