Neural Architecture Search

Also known as NAS

Neural Architecture Search (NAS) studies how to choose or generate a neural network’s structure so it performs well on a task without relying entirely on manual design. Common approaches include differentiable search such as DARTS, evolutionary and reinforcement-learning methods, weight-sharing supernets, and surrogate or zero-cost predictors that estimate candidate quality cheaply. Increasingly, search also accounts for latency, memory, energy, quantization, and deployment conditions, using hardware measurements or learned cost models alongside accuracy. The central tension is how to make search economical while ensuring that cheap proxies and benchmark results reliably predict performance after full training and on real devices.

Latest papers

130 papers21 papers in the last four weeks, up 75% on the four weeks before. 0.1% of all new papers.

EVOTS: Evolutionary Transformer Search for Time Series Forecasting
Jun 30, 2026AbdElRahman ElSaid, Damir PulatovMultivariate Time Series Forecasting Neural Architecture Search
University of North Carolina Wilmington Wilmington, North Carolina, USA
Morphing into Hybrid Attention Models
Jun 29, 2026Disen Lan, Jianbin Zheng, Yuxi Ren +5Efficient Attention Neural Architecture Search
1Fudan University · 2ByteDance Seed · Work done at ByteDance Seed +1
TacEvo: Self-Evolving Architecture Discovery for Robotic Tactile Perception via LLM-Driven Quality-Diversity Search
Jun 29, 2026Mohammed AbuSadeh, Lan Wei, Dandan ZhangVision-Based Tactile Sensing Large Language Model-Guided NAS
All authors are with the Department of Bioengineering, Imperial-X Initiative, Imperial College London, London, United Kingdom.
Evolutionary Hyperparameter Optimization to Find Lightweight CNN Models for Autonomous Steering
Jun 29, 2026Devson Butani, Ryan Kaddis, Chan-Jin ChungEfficient Neural Network Inference Autonomous Driving
Dept. of Math and Computer Science Lawrence Technological University Southfield, MI, USA
Bilevel Optimization for Neural Architecture Search
Jun 28, 2026Abhishek Shukla, Ankur Sinha, Faiz HamidBilevel Optimization Neural Architecture Search
Department of Management Sciences, IIT Kanpur, India · Krishnamurthy Tandon School of AI, IIM Ahmedabad, India
EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning
Jun 24, 2026Boyun Zhang, Chao Wang, Kai WuLarge Language Model-Guided NAS Neural Architecture Search
Xidian University
Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis
Jun 24, 2026Abrar Alotaibi, Moataz AhmedNeural Architecture Search Generative Adversarial Networks
Department of Information and Computer Science, King Fahd University of Petroleum and Minerals, Dhahran,31261, Saudi Arabia · Computer Science Department, College of Computer Science and Information Technology, Imam Abdulrahman bin Faisal University, Dammam, 31441, Saudi Arabia · SDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum and Minerals, Dhahran, 31261, Saudi Arabia
Neural Architecture Search of Sample Reweighting Networks for Complex Distribution Shift
Jun 22, 2026Keisuke Sugawara, Kento Uchida, Shinichi ShirakawaClass-Imbalanced Learning Instance Reweighting
Yokohama National University, Kanagawa, Japan
Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search
Jun 21, 2026Yashkumar R Lukhi, Harsh Rameshbhai Moradiya, Radu Timofte +1Mixture of Experts Neural Architecture Search
Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany
A3C3: AI Algorithm and Accelerator Co-design, Co-search, and Co-generation
Jun 18, 2026Selin Yildirim, Yingbing Huang, Deming ChenHardware-Aware NAS Hardware-Software Co-Design
Siebel School of Computing and Data Science · Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign
Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity
Jun 18, 2026Shishen Lin, Yixin ChenRL Control Evolutionary Optimization
Department of Statistics, University of Warwick, Coventry, United Kingdom · 2Biozentrum, University of Basel, Basel, Switzerland
InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search
Jun 17, 2026Qinqin Zhou, Fuhai Chen, Jipeng Wu +3Neural Architecture Search Neural Architecture Performance Prediction
School of Computer and Data Science, Fuzhou University · School of Computer and Data Science, Minjiang University · School of Artificial Intelligence, Nanchang University +2
On-Device Neural Architecture Search
Jun 12, 2026Andrea Mattia Garavagno, Edoardo Ragusa, Paolo Gastaldo +2Hardware-Aware NAS Edge ML
Department of Electrical, Electronic, Telecommunication Engineering and Naval Architecture, DITEN University of Genoa, Genoa 16145, Italy · Department of Excellence in Robotics & AI, Scuola Superiore Sant’Anna, Piazza Martiri della Libert`a 33, Pisa 56127, Italy · Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna, Ghezzano, 56010 Pisa, Italy +1
Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains
Jun 9, 2026Zilai Wang, Natarajan Balaji Shankar, Mohan Shi +2Domain Adaptation for ASR Domain Adaptation
University of California, Los Angeles, USA
LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks
Jun 9, 2026Tyler King, Timothee LeleuEnergy-Efficient ML Large Language Model-Guided Optimization
NTT Research · Princeton University · Stanford University
Edge-Constrained UAV Small-Object Detection with P2 Enhancement and Quantum-Inspired Lightweight Structure Search
Jun 8, 2026Wuming Lei, Yanbin Gao, Mingyan Sun +2Small Object Detection Edge Inference
East China Jiaotong University, Nanchang, China.
GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis
Jun 4, 2026Oleeviya Babu Poikarayil, Cédric Schockaert, Abdulrahman Nahhas +3Efficient Neural Network Inference Large Language Model-Guided NAS
Paul Wurth S.A., Luxembourg · Otto-von-Guericke University, Magdeburg, Germany · Technical University of Munich, Germany
Evidence-Guided Neural Architecture Selection under Uncertainty for Subject-Specific Blood Glucose Forecasting
Jun 3, 2026Md Azharul Islam, Dwyer Deighan, Tarunraj Singha +1Time Series Forecasting Blood Glucose Forecasting
Department of Mechanical and Aerospace Engineering, University at Buffalo, Buffalo, NY, USA · Computational and Data-Enabled Sciences, University at Buffalo, Buffalo, NY, USA · University at Buffalo, Buffalo, NY, USA
Seq103: A Unified Neuroevolution Framework for Compact Sequence Architecture Discovery
Jun 3, 2026Wenxiao Li, Yongjian Liu, Qing XieEvolutionary Optimization Time Series Classification
School of Computer Science and Artificial Intelligence, Wuhan University of Technology, No. 122 Luoshi Road, Hongshan District, Wuhan, 430070, Hubei, China
LLM Compression with Jointly Optimizing Architectural and Quantization choices
Jun 2, 2026Hoang-Loc La, Truong-Thanh Le, Amir Taherkordi +1Mixed-Precision Quantization LLM Quantization
UiT The Arctic University of Norway · University of Oslo, Norway
Rethinking Neural Width for Alternating Current Optimal Power Flow Proxies
Jun 2, 2026Dhruvi Khandelwal, Anurag Basistha, Ayushi Jolotia +1Neural Surrogate Modeling Optimal Power Flow
Department of Electrical Engineering, National Institute of Technology Kurukshetra, India. · Indraprastha Institute of Information Technology Delhi, India. · Department of Electrical Engineering, Indian Institute of Technology Roorkee, India.
Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability
May 28, 2026Santosh Premi Adhikari, Radu Timofte, Dmitry IgnatovBlack-Box Optimization Large Language Model-Guided Optimization
Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany
RAISE: RAG Design as an Architecture Search Problem
May 28, 2026Zhen Chen, Yibing Liu, Weihao Xie +3RAG Evaluation Neural Architecture Search
City University of Hong Kong, Hong Kong SAR · Baidu Inc.
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
May 26, 2026Dongyun Zou, Zhuoyang Zhang, Junyu Chen +8Efficient Transformer Inference Vision Foundation Models
MIT · NVIDIA · University of Pennsylvania +1
DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU
May 20, 2026Weizhe Chen, Miao Zhang, Junpeng Jiang +3LLM Inference Efficiency Attention Mechanisms
Harbin Institute of Technology (Shenzhen)
Evolutionary Algorithm for Reservoir Learning and Yielding
May 19, 2026Julien Testu, Pierrick Legrand, Xavier HinautReservoir Computing Neural Architecture Search
UB, Mnemosyne · ENSC, Bordeaux INP · Mnemosyne
Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search
May 19, 2026Yuiko Sakuma, Masakazu Yoshimura, Marcel Gröpl +4Large Language Model-Guided NAS Large Language Model-Guided Optimization
Sony Group Corporation, Tokyo, Japan · ETH Zurich, Switzerland
Hybrid Quantum-Classical Neural Architecture Search
May 18, 2026Alberto Marchisio, Muhammad Kashif, Nouhaila Innan +1Quantum Machine Learning Hybrid Quantum-Classical ML
eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD), Abu Dhabi, United Arab Emirates · Center for Quantum and Topological Systems (CQTS), NYUAD Research Institute, NYUAD, Abu Dhabi, United Arab Emirates
Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
May 15, 2026Alberto Pepe, Chien-Yu Lin, Despoina Magka +6Large Language Model-Guided NAS Large Language Model-Guided Optimization
FAIR at Meta
Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search
May 15, 2026Pranav Somu, Advay Balakrishnan, Stepan Kravtsov +2Neural Surrogate Modeling Representation Learning
Georgia Institute of Technology Atlanta, Georgia, USA · Georgia Tech Research Institute Atlanta, Georgia, USA

Jun 30, 2026J/K move · Enter open · S save

EVOTS: Evolutionary Transformer Search for Time Series Forecasting

AbdElRahman ElSaid, Damir Pulatov

University of North Carolina Wilmington Wilmington, North Carolina, USA

Multivariate Time Series Forecasting Neural Architecture Search Time Series Transformers

Open paper AskPDF arXiv

Evolutionary neural architecture design for multivariate time-series forecasting remains underexplored, with most approaches relying on fixed Transformer architectures despite substantial variation across tasks and forecasting settings. This paper introduces an evolutionary neural architecture search framework for discovering task-adaptive Transformer-like models for time-series forecasting (EVOTS). Architectures are encoded using a modular genome representation that enables flexible composition of attention, feed-forward, and projection components, while a repair mechanism enforces structural validity throughout the evolutionary process. This formulation allows effective exploration of a diverse architecture space without relying on hand-crafted design rules. The proposed approach is evaluated on four benchmark datasets from the ETT family (ETTh1, ETTh2, ETTm1, and ETTm2) under multiple forecasting settings, including univariate-to-univariate, multivariate-to-univariate, and multivariate-to-multivariate prediction, with horizons of 96, 192, 336, and 720. In the multivariate-to-multivariate setting, the evolved architectures achieve competitive and, in several cases, improved mean squared error relative to a strong Transformer-based baseline. Additional analyses examine performance differences across forecasting settings and report wall-clock training time to provide a coarse indication of computational cost. Overall, the results demonstrate that evolutionary search can effectively discover flexible and high-performing Transformer-like architectures for multivariate time-series forecasting within practical runtime constraints.