1 citations · 1 across the 25 of their papers we have counts for
25 papers
Curating Same-Family Neural Networks for LLM-Guided Model Improvement: A Controlled Case Study
Kabir Dev Paul Baghel, Radu Timofte, Dmitry Ignatov
Neural-network repositories contain executable models, recipes, input transformations, and measured accuracies. We study whether one same-family experiment can be curated as prompt…
Device-First Feedback: Toward Mobile-Native LLM-Driven Neural Architecture Search
Saif U Din, Muhammad Ahsan Hussain, Radu Timofte +1
Deploying convolutional neural networks generated by large language models (LLMs) on real mobile hardware requires more than GPU validation accuracy: INT8 TensorFlow Lite export, d…
Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis
Anujaya Vijayakumar, Radu Timofte, Dmitry Ignatov
Introduce a MinHash-based similarity scheduling framework that constructs a progressive curriculum over neural architecture code for LLM-based neural architecture search (NAS). Usi…
Systematic Evaluation of Learning Rate Scheduling Strategies Across Heterogeneous Architectures
Hafsa Mateen, Radu Timofte, Dmitry Ignatov
Choosing a learning rate scheduling strategy is critical to neural network training, but manual selection is costly and rarely exhaustive. While classical AutoML approaches often t…
Scaling Closed-Loop Feature Channel Configuration with LLMs
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 executabl…
LEMUR 2: Unlocking Neural Network Diversity for AI
Tolgay Atinc Uzun, Waleed Khalid, Saif U Din +17
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 evaluatio…
Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search
Yashkumar R Lukhi, Harsh Rameshbhai Moradiya, Radu Timofte +1
We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Building o…
Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study
Anton Abramochkin, Radu Timofte, Dmitry Ignatov
The choice of loss function and optimizer is an important decision, that shapes further model training. Yet automated architecture search pipelines (AutoML) benefits significantly…
Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability
Santosh Premi Adhikari, Radu Timofte, Dmitry Ignatov
Large language models (LLMs) are increasingly used as generators in iterative neural architecture search (NAS), yet no formal convergence theory exists for this class of algorithms…
Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs
Santosh Premi Adhikari, Radu Timofte, Dmitry Ignatov
Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationall…
From Code to Prediction: Fine-Tuning LLMs for Neural Network Performance Classification in NNGPT
Mahmoud Hanouneh, Radu Timofte, Dmitry Ignatov
Automated Machine Learning (AutoML) frameworks increasingly leverage Large Language Models (LLMs) for tasks such as hyperparameter optimization and neural architecture code generat…
Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs
Faraz Kayani, Sarmad Kayani, Asad Ahmed +2
While deep-learning-based image restoration has achieved unprecedented fidelity, deployment on mobile Neural Processing Units (NPUs) remains bottlenecked by operator incompatibilit…
MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment
Arun Kumar, Aswathy Baiju, Radu Timofte +1
Mobile deployment of facial age estimation requires models that balance predictive accuracy with low latency and compact size. In this work, we present MobileAgeNet, a lightweight…
Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models
Tolgay Atinc Uzun, Dmitry Ignatov, Radu Timofte
Channel-configuration search, the optimization of layer specifications such as channel widths in deep neural networks, presents a combinatorial challenge constrained by tensor-shap…
From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs
Usha Shrestha, Dmitry Ignatov, Radu Timofte
Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handled via heuristic design or brute-…
From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures
Waleed Khalid, Dmitry Ignatov, Radu Timofte
Large language models (LLMs) excel in program synthesis, yet their capacity for neural architecture design -- balancing syntactic reliability, performance, and structural novelty -…
LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts
Krunal Jesani, Dmitry Ignatov, Radu Timofte
Neural architecture search (NAS) traditionally requires significant human expertise or automated trial-and-error to design deep learning models. We present NN-Caption, an LLM-guide…
Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design
Raghuvir Duvvuri, Chandini Vysyaraju, Avi Goyal +2
Automated neural network architecture design remains a significant challenge in computer vision. Task diversity and computational constraints require both effective architectures a…
A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks
Waleed Khalid, Dmitry Ignatov, Radu Timofte
Reusing existing neural-network components is central to research efficiency, yet discovering, extracting, and validating such modules across thousands of open-source repositories…
NNGPT: Rethinking AutoML with Large Language Models
Roman Kochnev, Waleed Khalid, Tolgay Atinc Uzun +8
Building self-improving AI systems remains a fundamental challenge in the AI domain. We present NNGPT, an open-source framework that turns a large language model (LLM) into a self-…
Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis
Yash Mittal, Dmitry Ignatov, Radu Timofte
This paper proposes FractalNet, a framework based on fractal design principles that automatically generates and evaluates convolutional neural network (CNN) architectures using rec…
AugmentGest: Can Random Data Cropping Augmentation Boost Gesture Recognition Performance?
Nada Aboudeshish, Dmitry Ignatov, Radu Timofte
Data augmentation is a crucial technique in deep learning, particularly for tasks with limited dataset diversity, such as skeleton-based datasets. This paper proposes a comprehensi…
VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?
Mohamed Gado, Towhid Taliee, Muhammad Memon +2
Visual storytelling is an interdisciplinary field combining computer vision and natural language processing to generate cohesive narratives from sequences of images. This paper pre…
LEMUR Neural Network Dataset: Towards Seamless AutoML
Arash Torabi Goodarzi, Roman Kochnev, Waleed Khalid +8
Neural networks are the backbone of modern artificial intelligence, but designing, evaluating, and comparing them remains labor-intensive. While numerous datasets exist for trainin…