Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Adhikari, Santosh Premi, Timofte, Radu, Ignatov, Dmitry
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability
by: Adhikari, Santosh Premi, et al.
Published: (2026)

From Code to Prediction: Fine-Tuning LLMs for Neural Network Performance Classification in NNGPT
by: Hanouneh, Mahmoud, et al.
Published: (2026)

LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts
by: Jesani, Krunal, et al.
Published: (2025)

From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures
by: Khalid, Waleed, et al.
Published: (2026)

Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design
by: Duvvuri, Raghuvir, et al.
Published: (2025)

Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis
by: Mittal, Yash, et al.
Published: (2025)

Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation?
by: Ignatov, Dmitry, et al.
Published: (2024)

VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?
by: Gado, Mohamed, et al.
Published: (2025)

Learning Transformer-based World Models with Contrastive Predictive Coding
by: Burchi, Maxime, et al.
Published: (2025)

From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs
by: Shrestha, Usha, et al.
Published: (2026)

Resource-Efficient Iterative LLM-Based NAS with Feedback Memory
by: Gu, Xiaojie, et al.
Published: (2026)

Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives
by: Premi, Santosh
Published: (2026)

MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment
by: Kumar, Arun, et al.
Published: (2026)

Accurate and Efficient World Modeling with Masked Latent Transformers
by: Burchi, Maxime, et al.
Published: (2025)

LLM as a Tool, Not an Agent: Code-Mined Tree Transformations for Neural Architecture Search
by: Yoshimura, Masakazu, et al.
Published: (2026)

Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs
by: Kayani, Faraz, et al.
Published: (2026)

LEMUR Neural Network Dataset: Towards Seamless AutoML
by: Goodarzi, Arash Torabi, et al.
Published: (2025)

Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models
by: Uzun, Tolgay Atinc, et al.
Published: (2026)

CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search
by: Li, Zhe, et al.
Published: (2025)

A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks
by: Khalid, Waleed, et al.
Published: (2025)

einspace: Searching for Neural Architectures from Fundamental Operations
by: Ericsson, Linus, et al.
Published: (2024)

Loss Functions for Predictor-based Neural Architecture Search
by: Ji, Han, et al.
Published: (2025)

Fine-Tuning is Fine, if Calibrated
by: Mai, Zheda, et al.
Published: (2024)

Zero-Shot Neural Architecture Search with Weighted Response Correlation
by: Jing, Kun, et al.
Published: (2025)

Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning?
by: Kochnev, Roman, et al.
Published: (2025)

AugmentGest: Can Random Data Cropping Augmentation Boost Gesture Recognition Performance?
by: Aboudeshish, Nada, et al.
Published: (2025)

Insights from the Use of Previously Unseen Neural Architecture Search Datasets
by: Geada, Rob, et al.
Published: (2024)

A Lightweight Neural Architecture Search Model for Medical Image Classification
by: Xie, Lunchen, et al.
Published: (2024)

NASH: Neural Architecture Search for Hardware-Optimized Machine Learning Models
by: Ji, Mengfei, et al.
Published: (2024)

FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution Robustness
by: Gambella, Matteo, et al.
Published: (2024)

Integrating Large Language Models into a Tri-Modal Architecture for Automated Depression Classification on the DAIC-WOZ
by: Patapati, Santosh V.
Published: (2024)

Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches
by: Bai, Haoyue
Published: (2024)

SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation
by: Termritthikun, Chakkrit, et al.
Published: (2024)

Curriculum Multi-Task Self-Supervision Improves Lightweight Architectures for Onboard Satellite Hyperspectral Image Segmentation
by: Carlesso, Hugo, et al.
Published: (2025)

Domain-Aware Fine-Tuning of Foundation Models
by: Kaplan, Ugur Ali, et al.
Published: (2024)

SiamNAS: Siamese Surrogate Model for Dominance Relation Prediction in Multi-objective Neural Architecture Search
by: Zhou, Yuyang, et al.
Published: (2025)

STeP-Diff: Spatio-Temporal Physics-Informed Diffusion Models for Mobile Fine-Grained Pollution Forecasting
by: Zhou, Nan, et al.
Published: (2025)

MuDreamer: Learning Predictive World Models without Reconstruction
by: Burchi, Maxime, et al.
Published: (2024)

Learned Lightweight Smartphone ISP with Unpaired Data
by: Arhire, Andrei, et al.
Published: (2025)

Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning
by: Elmimouni, Zakarya, et al.
Published: (2026)