Latest Meta-Learning Research Papers

The newest Meta-Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Meta-Learning 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.

Recent papers

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly Detection
  Bernardo Perrone Ribeiro, Erkut Akdag, Egor Bondarev · arXiv · Oct 23, 2026

  Few-shot industrial anomaly detection requires modeling category-specific normality from only a handful of defect-free images. Common approaches tie inference to stored exemplars, impose rigid linear structure, or risk reproducing anomalous…

• SCDM: Scalable Causal Discovery in Nonlinear Temporal Systems with Meta-Learning
  Jingbo Wang, Kegeng Tang, Zihao Wang, Shaogang Ren · arXiv · Oct 21, 2026

  Causal discovery from nonlinear multivariate time series is challenging in high-dimensional systems, where the number of candidate directed relations grows quadratically with the number of variables. Existing methods are often limited by ta…

• Newton-Based Methods for Bilevel Optimization Beyond Lower-Level Strong Convexity
  Youran Dong, Junfeng Yang, Wei Yao, Jin Zhang · arXiv · Oct 19, 2026

  Bilevel optimization provides a framework for machine learning tasks such as hyperparameter optimization, data reweighting, and meta-learning. Existing Newton-based bilevel methods typically rely on the classical hypergradient formula, whic…

• Kronecker Delta Rule for Long Context Linear Attention
  Anamaria-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 RLVR
  Saif 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…

• IdeaLens: Detecting AI Ideas in Long-form Writing
  Rishanth 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…

• Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)
  Zilin Du, Bowen Yang, Boyang Albert Li · arXiv · Oct 1, 2026

  Data selection is critical for training large language models on massive and heterogeneous corpora. Meta-learning for Training-data Selection offers a principled alternative to heuristic scoring by learning data weights from a target valida…

• hyperbolix: Hyperbolic Deep Learning in JAX
  Timo Klein, Thomas Lang, Yllka Velaj, Sebastian Tschiatschek · arXiv · Sep 23, 2026

  We present hyperbolix, an open-source library for hyperbolic deep learning in JAX, built on Flax NNX. To our knowledge, it is the first comprehensive, general-purpose hyperbolic deep learning library in JAX. It includes six manifolds with a…

• Neural Cellular Automata Learn General Features in their Hidden Channels
  Etienne Guichard, Stefano Nichele · arXiv · Sep 18, 2026

  Modern deep learning models achieve impressive generalization through over-parameterization, but this paradigm often struggles with overfitting and memorization in few-shot regimes. Neural Cellular Automata (NCAs) offer a highly parameter-e…

• LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening
  Muhammad Ashad Kabir, Sirajam Munira · arXiv · Sep 3, 2026

  Early screening of chronic kidney disease (CKD) is critical for timely intervention, yet most machine learning (ML) and deep learning (DL) approaches require labeled data and model training, limiting their use in real-world screening settin…

• LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates
  Dmitrii 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…

• Federated Meta-Learning Based Computation Offloading Approach With Energy-Delay Tradeoffs in UAV-Assisted VEC
  Chun-Lin Li, Chao Deng, Yong Zhang, Shao-Hua Wan · IEEE Transactions on Mobile Computing · Oct 1, 2025

  Federated learning (FL) provides an applicable solution for computation offloading in Unmanned Aerial Vehicle(UAV)-assisted Vehicular Edge Computing (VEC) by preserving privacy. However, the heterogeneity of clients brings challenges to the…

• Federated active meta-learning with blockchain for zero-day attack detection in industrial IoT
  Kapil Kumar, Manju Khari · Peer-to-Peer Networking and Applications · Jun 5, 2025
• Meta-XPFL: An Explainable and Personalized Federated Meta-Learning Framework for Privacy-Aware IoMT
  M. Serhani, A. Tariq, Tariq Qayyum, Ikbal Taleb et al. · IEEE Internet of Things Journal · May 15, 2025

  In the Internet of Medical Things (IoMT), specifically in the field of medical image classification—particularly for skin cancer detection—traditional methods face challenges related to data privacy, heterogeneity, and the need for personal…

• System Prompt Optimization with Meta-Learning
  Yumin Choi, Jinheon Baek, Sung Ju Hwang · Neural Information Processing Systems · May 14, 2025

  Large Language Models (LLMs) have shown remarkable capabilities, with optimizing their input prompts playing a pivotal role in maximizing their performance. However, while LLM prompts consist of both the task-agnostic system prompts and tas…

• Optimized Intrusion Detection Approach for Cyber‐Physical System Using Meta‐Learning With Stacked Generalization: An Ensemble Learning Inspired Approach
  Ram Ji, Neerendra Kumar, Devanand Padha · Security and Privacy · Apr 27, 2025

  Cyber‐physical systems (CPSs) are crucial in providing vital infrastructure like smart grids, smart cities, smart automobiles, smart healthcare systems, and so forth, for many nations. CPSs are vulnerable to various attacks due to their lar…

• A framework reforming personalized Internet of Things by federated meta-learning
  Linlin You, Zihan Guo, Chau Yuen, C. Chen et al. · Nature Communications · Apr 20, 2025

  Advances in Artificial Intelligence envision a promising future, where the personalized Internet of Things can be revolutionized with the ability to continuously improve system efficiency and service quality. However, with the introduction …

• An Adaptive Framework for Intrusion Detection in IoT Security Using MAML (Model-Agnostic Meta-Learning)
  Fatma S. Alrayes, Syed Umar Amin, N. Hakami · Italian National Conference on Sensors · Apr 1, 2025

  With the rapid emergence of the Internet of Things (IoT) devices, there were new vectors for attacking cyber, so there was a need for approachable intrusion detection systems (IDSs) with more innovative custom tactics. The traditional IDS m…

• Metalinguist: enhancing hate speech detection with cross-lingual meta-learning
  Ehtesham Hashmi, Sule YAYILGAN YILDIRIM, Mohamed Abomhara · Complex & Intelligent Systems · Feb 27, 2025

  The rise of social media has led to an increase in hate speech. Hate speech is generally described as a deliberate act of aggression aimed at a particular group, intended to harm or marginalize them based on specific attributes of their ide…

• A Hybrid Model for Few-Shot Text Classification Using Transfer and Meta-Learning
  Jia Gao, Shuangquan Lyu, Guiran Liu, Binrong Zhu et al. · 2025 8th International Conference on Advanced Algorithms and Control Engineering (ICAACE) · Feb 13, 2025

  With the continuous development of natural language processing (NLP) technology, text classification tasks have been widely used in multiple application fields. However, obtaining labeled data is often expensive and difficult, especially in…

• Improving landslide susceptibility prediction through ensemble recursive feature elimination and meta-learning framework
  K. Halder, A. Srivastava, Anitabha Ghosh, Subhabrata Das et al. · Scientific Reports · Feb 12, 2025

  Landslides pose significant threats to ecosystems, lives, and economies, particularly in the geologically fragile Sub-Himalayan region of West Bengal, India. This study enhances landslide susceptibility prediction by developing an ensemble …

• Learning to Imbalanced Open Set Generalize: A Meta-Learning Framework for Enhanced Mechanical Diagnosis
  Changdong Wang, Zhou Shu, Jing-Li Yang, Zhenyu Zhao et al. · IEEE Transactions on Cybernetics · Feb 5, 2025

  To alleviate data distribution under different operating conditions, domain generalization (DG) has been applied in mechanical diagnosis. Still, its effectiveness is limited when unknown fault states appear in the target domain. Consequentl…

• A Meta-Learning Method for Few-Shot Multidomain State-of-Health Estimation of Lithium-Ion Batteries
  Xiaoyu Zhao, Zuo-Lu Wang, Te Han, Wen-Xian Yang et al. · IEEE Transactions on Transportation Electrification · Feb 1, 2025

  Diverse electrochemical characteristics and complex operational conditions of the lithium-ion battery cause multidomain discrepancies in practical applications, which poses huge challenges to the robust state-of-health (SOH) estimation base…

• Evaluation-free Time-series Forecasting Model Selection via Meta-learning
  Mustafa Abdallah, R. Rossi, K. Mahadik, Sungchul Kim et al. · ACM Transactions on Knowledge Discovery from Data · Jan 24, 2025

  Time-series forecasting models are invariably used in a variety of domains for crucial decision-making. Traditionally these models are constructed by experts with considerable manual effort. Unfortunately, this approach has poor scalability…

• Short-term Load Forecasting of Distribution Transformer Supply Zones Based on Federated Model-Agnostic Meta Learning
  Changsen Feng, Liang Shao, Jia-Ying Wang, You-Bing Zhang et al. · IEEE Transactions on Power Systems · Jan 1, 2025

  With the increasing data privacy concerns raised by not only organizations but also individuals in distribution systems, traditional centralized data-driven forecasting approaches for short-term load forecasting (STLF) in distribution trans…

• Meta Learning Strategies for Comparative and Efficient Adaptation to Financial Datasets
  Kubra Noor, Ubaida Fatima · IEEE Access · Jan 1, 2025

  This research proposes a Meta learning framework for financial time series forecasting, designed to rapidly adapt to novel market conditions with minimal retraining. The framework operates in two stages: 1) pretraining on a diverse set of f…

• Meta-Learning Enhanced Model Predictive Contouring Control for Agile and Precise Quadrotor Flight
  Mingxin Wei, Lanxiang Zheng, Ying Wu, Ruidong Mei et al. · IEEE Transactions on robotics · Jan 1, 2025

  In agile quadrotor flight, accurately modeling the varying aerodynamic drag forces encountered at different speeds is critical. These drag forces significantly impact the performance and maneuverability of the quadrotor, especially during h…

• Global or Local Adaptation? Client-Sampled Federated Meta-Learning for Personalized IoT Intrusion Detection
  Haorui Yan, Xi Lin, Shenghong Li, Hao Peng et al. · IEEE Transactions on Information Forensics and Security · Jan 1, 2025

  With the increasing size of Internet of Things (IoT) devices, cyber threats to IoT systems have increased. Federated learning (FL) has been implemented in an anomaly-based intrusion detection system (NIDS) to detect malicious traffic in IoT…

• MAML-KalmanNet: A Neural Network-Assisted Kalman Filter Based on Model-Agnostic Meta-Learning
  Shanli Chen, Yun-Fei Zheng, Dong-Yuan Lin, Peng Cai et al. · IEEE Transactions on Signal Processing · Jan 1, 2025

  Neural network-assisted (NNA) Kalman filters provide an effective solution to addressing the filtering issues involving partially unknown system information by incorporating neural networks to compute the intermediate values influenced by u…