Latest Neural Architecture Search Research Papers
The newest Neural Architecture Search papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Neural Architecture Search so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Neural Architecture Search papers in your inbox — free →Recent papers
- Conservative Meta-Agent Search: Architecture Adaptation under Non-StationarityAli Atiah Alzahrani · arXiv · Oct 22, 2026
Automated agentic-system design is typically evaluated on static task suites with immediate scalar rewards. Deployed systems face persistent shift, delayed dependent feedback, correlated component failures, and costly architecture changes. …
- Kronecker Delta Rule for Long Context Linear AttentionAnamaria-Roberta Hartl, Levente Zólyomi, Michael List, Günter Klambauer et al. · arXiv · Oct 19, 2026
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associati…
- Decoupling Exploration from Optimization in RLVRSaif Punjwani, Micah Goldblum · arXiv · Oct 7, 2026
Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas abs…
- Measurement-Efficient Differentiable Quantum Architecture Search for Combinatorial OptimizationLukas Theißinger, Thore Gerlach, Christian Bauckhage · arXiv · Oct 7, 2026
Differentiable quantum architecture search (DQAS) is a promising framework for the automated design of quantum circuits, particularly for variational quantum optimization algorithms. However, its practical deployment on quantum hardware is …
- IdeaLens: Detecting AI Ideas in Long-form WritingRishanth Rajendhran, Minjoon Choi, Jenna Russell, Ramya Namuduri et al. · arXiv · Oct 5, 2026
While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce IdeaLens, a detector that identifies whether a document's ideas came fr…
- TabFM: A Zero-Shot Foundation Model for Tabular DataWeihao Kong, Erez Louidor Ilan, Shuxin Nie, Taman Narayan et al. · arXiv · Sep 29, 2026
Tabular machine learning typically relies on per-dataset workflows, fitting tree ensembles or running AutoML searches from scratch for every task. We present TabFM, a 400M-parameter tabular foundation model that formulates supervised tabula…
- CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture SearchYifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li et al. · arXiv · Sep 10, 2026
Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve r…
- LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style UpdatesDmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026
Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…
- Microcontroller neural architecture search: An automated framework for developing a fall detection systemSeyed Mojtaba Mohasel, John W. Sheppard, Lindsey K. Molina, Richard R. Neptune et al. · Engineering Applications of... · Sep 2, 2026
- ArtNAS-Style: Style-Prior-Guided Differentiable Architecture Search for Artwork RecognitionChunhu Shi, Shu Gong, He Jiye · Electronics · Sep 2, 2026
Recognizing visual artworks is difficult because images of art combine large within-class diversity, ambiguous boundaries, and non-photographic textures with intertwined cues related to the artist, genre, style, and historical period. Stand…
- Agentic Neural Architecture SearchSeokhoon Jeong, Mijung Kim, Taehwan Kim · ICML 2026 Workshop DL4C Poster · Jun 16, 2026
Neural architecture search (NAS) methods have grown increasingly efficient, yet they remain bounded by manually engineered search spaces that require substantial domain expertise and must be rebuilt for every new task. Large language models…
- pTNAS: Progressive Neural Architecture Search for Tabular DataNaili Xing, Shaofeng Cai, Lingze Zeng, Jiaqi Zhu et al. · ICML 2026 regular · Apr 30, 2026
Recent advances have shifted the paradigm of tabular learning toward tabular foundation models, yet their accuracy relies on a heavy inference cost that scales poorly with context size. Deep neural networks remain a highly competitive and m…
- An Evolutionary Multiobjective Neural Architecture Search Approach to Advancing Cognitive Diagnosis in Intelligent EducationShang-Shang Yang, Hai-Ping Ma, Ying Bi, Ye Tian et al. · IEEE Transactions on Evolutionary Computation · Dec 1, 2025
As a pivotal technique in intelligent education systems, cognitive diagnosis (CD) serves to reveal students’ knowledge proficiency for better tackling subsequent tasks. Unfortunately, due to pursuing high model interpretability, existing ma…
- RF-DETR: Neural Architecture Search for Real-Time Detection TransformersIsaac Robinson, Peter Robicheaux, Matvei Popov, D. Ramanan et al. · arXiv.org · Nov 12, 2025
Open-vocabulary detectors achieve impressive performance on COCO, but often fail to generalize to real-world datasets with out-of-distribution classes not typically found in their pre-training. Rather than simply fine-tuning a heavy-weight …
- Optimizing deep learning models for on-orbit deployment through neural architecture searchRoberto del Prete, Parampuneet Kaur Thind, A. Mazzeo, Matthew Whitley et al. · Scientific Reports · Oct 29, 2025
Advancements in spaceborne edge computing have facilitated the incorporation of Artificial Intelligence (AI)-powered chips into CubeSats, enabling intelligent data handling and enhanced analytical capabilities with greater operational auton…
- Neural Architecture Search with Progressive Evaluation and Subpopulation PreservationYu Xue, Jiajie Zha, Danilo Pelusi, Peng Chen et al. · IEEE Transactions on Evolutionary Computation · Oct 1, 2025
Neural architecture search (NAS) is an effective approach for automating the design of deep neural networks. Evolutionary computation (EC) is commonly used in NAS due to its global optimization capability. However, the evaluation phase of a…
- Distilling SNN Students from ANN Teachers via Spiking Neural Architecture SearchXiaotian Song, Yanan Sun · Submitted to ICLR 2026 · Sep 19, 2025
Bridging the performance gap between Spiking Neural Networks (SNNs) and Artificial Neural Networks (ANNs) under low timesteps remains a critical challenge in the SNN community. Recent work uses either ANN-supervised training or automated ar…
- RDNAS: Robust Dual-Branch Neural Architecture SearchSongbai Liu, GuanHeng Huang · ICLR 2026 Conference Withdrawn Submission · Sep 19, 2025
Deep neural networks have achieved remarkable success but remain highly vulnerable to adversarial perturbations, posing serious challenges in safety-critical applications. We propose **RDNAS**, a robust dual-branch neural architecture searc…
- PEL-NAS: Search Space Partitioned Architecture Prompt Co-evolutionary LLM-driven Hardware-Aware Neural Architecture SearchHengyi Zhu, Grace Li Zhang, Shaoyi Huang · ICLR 2026 Conference Withdrawn Submission · Sep 17, 2025
Hardware-Aware Neural Architecture Search (HW-NAS) requires joint optimization of accuracy and latency under device constraints. Traditional supernet-based methods require multiple GPU days per dataset. Large Language Model (LLM)-driven ap…
- Jet-Nemotron: Efficient Language Model with Post Neural Architecture SearchYu-Xian Gu, Qing-Hao Hu, Hao-Cheng Xi, Jun-Yu Chen et al. · Neural Information Processing Systems · Aug 21, 2025
We present Jet-Nemotron, a new family of hybrid-architecture language models, which matches or exceeds the accuracy of leading full-attention models while significantly improving generation throughput. Jet-Nemotron is developed using Post N…
- Causal-aware Graph Neural Architecture Search under Distribution ShiftsPeiwen Li, Xin Wang, Zeyang Zhang, Zi-Wei Zhang et al. · Knowledge Discovery and Data Mining · Aug 3, 2025
Graph neural architecture search (NAS) has emerged as a promising approach for autonomously designing graph neural network architectures by leveraging correlations between graphs and architectures. However, existing methods merely rely on c…
- GA-OMTL: Genetic algorithm optimization for multi-task neural architecture search in NIR spectroscopyYu Yang, Siqi Wang, Gan Zhang, Qifu Wang et al. · Expert systems with applications · Jun 1, 2025
- DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image ClassificationMatt Poyser, T. Breckon · Pattern Recognition · Jun 1, 2025
In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilizing an autoencoder that enforces an image simil…
- Defying Multi-Model Forgetting in One-Shot Neural Architecture Search Using Orthogonal Gradient LearningLianbo Ma, Yuee Zhou, Ye Ma, Guo Yu et al. · IEEE transactions on computers · May 1, 2025
One-shot neural architecture search (NAS) trains an over-parameterized network (termed as supernet) that assembles all the architectures as its subnets by using weight sharing for computational budget reduction. However, there is an issue o…
- MicroNAS for memory and latency constrained hardware aware neural architecture search in time series classification on microcontrollersTobias King, Ye-Xu Zhou, Tobias Röddiger, Michael Beigl · Scientific Reports · Mar 4, 2025
The use and research of neural networks on very small processor systems are currently still limited. One of the main reasons is that the design of microcontroller-architecture-aware ML models that take into account user-defined constraints …
- Multi-objective Differentiable Neural Architecture SearchRhea Sanjay Sukthanker, Arber Zela, Benedikt Staffler, Samuel Dooley et al. · ICLR 2025 Poster · Jan 22, 2025
Pareto front profiling in multi-objective optimization (MOO), i.e., finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives that require training a neural network. Typically, in MOO for neural…
- Systematic review on neural architecture searchSasan Salmani Pour Avval, Nathan Eskue, Roger M. Groves, Vahid Yaghoubi · Artificial Intelligence Review · Jan 6, 2025
Machine Learning (ML) has revolutionized various fields, enabling the development of intelligent systems capable of solving complex problems. However, the process of manually designing and optimizing ML models is often time-consuming, labor…
- A Novel Centralized Federated Deep Fuzzy Neural Network with Multi-objectives Neural Architecture Search for Epistatic DetectionXiang Wu, Yongting Zhang, K. Lai, Ming-Zhao Yang et al. · IEEE transactions on fuzzy systems · Jan 1, 2025
Epistasis detection (ED) was widely used for identifying potential risk disease variants in the human genome. A statistically meaningful ED typically requires a more extensive dataset to detect complex disease-associated single nucleotide p…
- RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost StrategyZipeng Ji, Guanghui Zhu, C. Yuan, Y. Huang · International Conference on Machine Learning · Jan 1, 2025
- Beyond Performance: Designing a Super-Resolution Architecture Search Space and a Hybrid Multi-Objective Approach for Neural Architecture OptimizationJ. L. L. García, Raúl Monroy, Víctor Adrián Sosa Hernández, Kalyanmoy Deb · IEEE Access · Jan 1, 2025
Multi-objective neural architecture search (NAS) for super-resolution image restoration (SRIR) targets models that simultaneously deliver high-fidelity reconstructions and respect strict computational budgets—requirements that single-object…