Latest Long-Tail Learning Research Papers

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

• When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance
  Walter Endrizzi, Flavio Ragni, Raffaele Marchesi, Stefano Bovo et al. · arXiv · Oct 27, 2026

  Background. Selective prediction systems improve the safety of clinical artificial intelligence by deferring ambiguous cases to human experts while automating high-confidence decisions. However, this safety mechanism relies entirely on the …

• Resolving primitive-sharing ambiguity in long-tailed TLS-based industrial MEP point cloud segmentation via spatial context constraints
  Chao Yin, Qing Han, Zhiwei Hou, Yue Liu et al. · Advanced Engineering Inform... · Oct 25, 2026
• 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…

• AFI-ID: adaptive feature intelligence for intrusion detection
  Shritik Raj, M. Madiajagan · Frontiers in Artificial Int... · Oct 19, 2026

  The increasing sophistication of cyber-attacks necessitates intrusion detection systems (IDS) that are both accurate and computationally efficient, particularly in high-dimensional and class-imbalanced environments. Although ensemble-based …

• Hypothalamus and preoptic area in breeding rodent: a review
  Atifa Haseeb Ansari, Durgesh Singh, Alok Mukerjee, Sippy Singh · The Journal of Basic and Ap... · Oct 17, 2026

  Rodent is a diversified group of mammals and characterized by small body, short limb, long tail and incisor teeth. Majority of mammals fall under this category including mice and rats which are commonly used as laboratory animal. Brain of r…

• Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution
  Haohui Wang, Jiahao Xu, Wangzhi Zhan, Tong Zeng et al. · arXiv · Oct 8, 2026

  Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concepts can receive substantially different levels of pretrained support. Frequent concepts are more likely to be well learne…

• Mitigating Popularity Bias in Recommendation with Global Listwise Learning and Progressive Bi-Weighting
  Tianyu Zhu, Jiandong Ding, Yansong Shi, Guoqing Chen et al. · ACM Transactions on Informa... · Oct 8, 2026

  In recommender systems, user feedback typically follows a long-tail distribution, which leads many recommendation algorithms to exacerbate popularity bias by disproportionately favoring popular items. To mitigate this issue, recent studies …

• Modelling Simian malaria disease dynamics in Southern Thailand to inform surveillance strategies for emerging zoonotic diseases.
  Natcha Dankittipong, Pyae Linn Aung, Sirasate Bantuchai, Shri Lak Nanjan Chandran et al. · Wellcome Open Research · Oct 8, 2026

  Background Zoonotic malaria caused by Plasmodium knowlesi poses a growing threat to malaria elimination. In Thailand, Ranong Province reports the highest incidence nationally, yet the role of long-tailed macaques ( Macaca fascicularis ) as …

• 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…

• AI Emulation of Stochastic Sudden Stratospheric Warming with Interpretable Latent Structure
  C. Daniel Boscu, Daniel Hernandez, Fabio Alvarez Ventura, Justin Finkel et al. · arXiv · Oct 1, 2026

  Rare weather regime transitions pose a challenge for data-driven modeling due to class imbalance. In this study, we develop a probabilistic deep learning emulator for a prototypical system with regime transitions, the stochastic Holton--Mas…

• Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis
  Tian Xia, Minghao Liu, Yiqing Liang, Laixi Shi et al. · arXiv · Sep 30, 2026

  Multimodal large language models (MLLMs) are rapidly advancing clinical diagnosis, yet their adaptation pipelines remain anchored to accuracy-based objectives. Clinical data are heavily class-imbalanced: a constant-majority predictor can sc…

• 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…

• TAD: Tail-Aware Diffusion Model for Long-Tailed Medical Image Classification
  Huaqi Zhang, Zhen Zhang · Journal of Imaging Informat... · Sep 22, 2026
• DirPA: Addressing prior shift in imbalanced few-shot crop-type classification
  Joana Reuss, Ekaterina Gikalo, Marco Körner · ISPRS Journal of Photogramm... · Sep 18, 2026

  Real-world agricultural monitoring is often hampered by severe class imbalance and high label acquisition costs, resulting in significant data scarcity. In few-shot learning (FSL) —a framework specifically designed for data-scarce settings—…

• Mamba-based state-space modeling with window attention for explainable multi-class gastrointestinal disease diagnosis in endoscopic images
  Vishesh Tanwar, Bhisham Sharma, Julian Webber, Abolfazl Mehbodniya · Frontiers in Artificial Int... · Sep 17, 2026

  Introduction This paper introduces a new hybrid deep learning architecture, which is named GINet, to accurately and efficiently classify gastrointestinal (GI) diseases using endoscopic images. Automated diagnosis is not an easy task due to …

• LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models
  Xucong Wang, Pengkun Wang, Zhe Zhao, Liheng Yu et al. · International Journal of Co... · Sep 17, 2026
• Mechanical fault diagnosis under long-tailed data: an improved federated learning method integrating attention, asymmetric convolution, and margin calibration
  Zhaoqi Liu, Ang Cai, Zhen Xu · Scientific Reports · Sep 16, 2026

  Abstract Due to the inability to collect sufficient fault samples for specific types of gear and bearing faults, the data presents a long-tailed distribution, which hinders the effective construction of neural network diagnostic models. Fur…

• FedLTLib: A Comprehensive Benchmark for Federated Long-Tail Learning
  Chang-Kun Lin, Junxiao Wang · Semantic Scholar · Sep 14, 2026

  Driven by the escalating demand for privacy-preserving computing, Federated Learning (FL) has witnessed remarkable progress, becoming a cornerstone technology for bridging distributed data silos in mobile edge networks. However, in real-wor…

• Breaking the dilemma of trajectory imbalance and sample scarcity: A Multi-Behavior Prototype Siamese Network for vessel type recognition
  Ze Cai, Quan Qian · Ocean Engineering · Sep 13, 2026

  Vessel type recognition is at the core of intelligent maritime monitoring. Real-world AIS datasets follow a long-tailed distribution, giving rise to two coupled challenges: class imbalance and sample scarcity in minority vessel categories. …

• 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…

• Turing–Entropic Tail Classification: A Nonparametric Approach to Tail Inference
  Jialin Zhang, Zhiyi Zhang · Methodology And Computing I... · Sep 1, 2026
• Long-Tail Learning for Three-Dimensional Pavement Distress Segmentation Using Point Clouds Reconstructed from a Consumer Camera
  Pengjian Cheng, Junyan Yi, Zhong-Shi Pei, Zengxin Liu et al. · Remote Sensing · Mar 27, 2026

  The application of 3D data in pavement inspection represents an emerging trend. Acquiring and measuring the 3D information of pavement distress enables a more comprehensive assessment of severity, thereby allowing for accurate monitoring an…

• Knowledge graph-enhanced long-tail learning approach for traditional Chinese medicine syndrome differentiation
  Weikang Kong, Chuanbiao Wen, Yue Luo · Digital Chinese Medicine · Mar 1, 2026
• EdgeTail: Mitigating Long-Tail Visual Problems in Continual Learning at Edge
  Yuzhong Ouyang, Xiaoning Wu, Meng-Lin Yang, Rui Han et al. · ACM Trans. Internet Things · Dec 25, 2025

  Large vision and language models deployed at edge encounter continuously evolving input distributions, including not only new tasks but also highly unbalanced long-tail classes. For example, smart-surveillance cameras frequently capture com…

• Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learning
  Canran Xiao, Chuang-Xin Zhao, Zong Ke, Fei Shen · arXiv.org · Oct 20, 2025

  Long-tail imbalance is endemic to multi-label learning: a few head labels dominate the gradient signal, while the many rare labels that matter in practice are silently ignored. We tackle this problem by casting the task as a cooperative pot…

• APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
  Yu-Zhe Zhou, Jiajun Li, Yu-Sheng Su, Gowtham Ramesh et al. · arXiv.org · Sep 23, 2025

  Reinforcement learning (RL) has become a cornerstone in advancing large-scale pre-trained language models (LLMs). Successive generations, including GPT-o series, DeepSeek-R1, Kimi-K1.5, Grok 4, and GLM-4.5, have relied on large-scale RL tra…

• Interpretable Preference Elicitation: Aligning User Intent with Controllable Long-tailed Learning
  HaiBin Wen, Shuangwang, Xucong Wang, YuHeng Yang et al. · ICLR 2026 Conference Withdrawn Submission · Sep 20, 2025

  Long-tailed recognition remains a significant challenge, where models often struggle with tail class performance and adaptability to diverse user preferences. While recent controllable paradigms leveraging hypernetworks allow numerical spec…

• Class-Adaptive Rectification with Experts for Robust Long-Tailed Noisy Label Learning
  Mengke Li, Haiquan Ling, Lihao Chen, Yang Lu et al. · Submitted to ICLR 2026 · Sep 19, 2025

  Real-world datasets frequently exhibit long-tailed class distributions alongside noisy labels, posing compounded challenges for robust learning. While recent methods have made progress, they often neglect the uneven impact of label noise ac…