works on

From the 1 of 25 linked papers with an AI index.

collaborators

25 papers

cs.CV2026

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…

cs.CV2026

Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis

Anujaya Vijayakumar, Radu Timofte, Dmitry Ignatov

The paper proposes a MinHash‑based curriculum that gradually presents neural‑architecture code of increasing diversity to a large language model, fine‑tuning it with LoRA adapters…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

LLM-Driven Neural Network Generation with Same-Family Architecture Guidance: Disentangling Transfer and Adaptation

Kabir Dev Paul Baghel, Radu Timofte, Dmitry Ignatov

Large language models (LLMs) can generate neural-network modifications, but unrestricted generation is often invalid or harmful. This paper studies a narrower setting: improving a…