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

• TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
  Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Wei-Jer Chang et al. · arXiv · Jul 14, 2026

  Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long ta…

• Robust lightweight facial expression recognition on edge devices: mitigating long-tailed distributions and real-world noises
  Yuchen Song, Yining Yuan, Yufei Guo, Xuerong Zhao et al. · OpenAlex · Jul 13, 2026

  Deploying lightweight facial expression recognition (FER) on resource-constrained edge devices presents challenges beyond mere model compression. This work addresses two critical issues that arise in this context: the exacerbated performanc…

• Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection
  Cláudio Lúcio do Val Lopes, Lucca Machado da Silva · arXiv · Jul 10, 2026

  Financial anomaly detection suffers from extreme class imbalance, causing traditional single-objective algorithms to exhibit ``fraud collapse'', defaulting to the majority class and failing to balance anomaly interdiction with customer fric…

• Balanced Adaptive Logit-Compensated Cross-Entropy and Quadratic Convolutional Network for Intelligent Fault Diagnosis Under Long-Tailed Data Distribution
  Wei Zhang, Zikang Cao, H B Wu, Dewei Guo et al. · Entropy · Jul 10, 2026

  Long-tailed data are very common in industrial scenarios because equipment failures occur with a low probability, resulting in far fewer faulty samples than normal ones. However, when facing long-tailed data distributions, existing deep lea…

• TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios
  Hong Lyu, Mingru Yang, Qianhua He, Yanxiong Li et al. · arXiv · Jul 7, 2026

  There are some datasets of varying scales for audio classification (AC) applied to different tasks. However, annotated data is limited for most scenarios, such as domestic environments. To address this challenge, we propose an $\textbf{A}$u…

• Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving
  Cheng Gong, Haoyang Wang, Chao Lu, Zirui Li et al. · arXiv · Jun 29, 2026

  Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demonstrations …

• QC-SMOTE: Quality-Controlled SMOTE for Imbalanced Classification
  Parth Upman, Shreyank N Gowda · arXiv · Jun 23, 2026

  Class imbalance poses a significant challenge in classification, where existing methods such as SMOTE often generate low-quality synthetic samples in regions with noise or class overlap. We propose QC-SMOTE, a quality-controlled oversamplin…

• Hedgementation = Hedgerow Segmentation: A Remote Sensing Benchmark
  Nathan Senyard, Salem Hamdani, Astrid Zhang, Derek Wang et al. · arXiv · Jun 22, 2026

  We propose Hedgementation: a new benchmark to evaluate machine learning models for hedgerow mapping from remote sensing data at country scale and 10m$^2$ spatial resolution. We combine and harmonize multiple remote sensing data products and…

• Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
  Tianyi Li, Zhiqiang Shen · arXiv · Jun 22, 2026

  Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the interpolation path from only one model endpoint, limiting their …

• Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
  Mengyu Zheng, Kai Han, Boxun Li, Haiyang Xu et al. · arXiv · Jun 10, 2026

  General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and pred…

• DH-OOD: A decoupled hybrid framework for robust skin lesion classification via semantic-structural fusion
  Benyuan He, Lei Yao, Ning Xue, Chunxiu Liu et al. · Journal of X-Ray Science an... · Jun 10, 2026

  Real-world skin lesion classification faces three major challenges: severe class imbalance, high intra-class variability, and the need to reject out-of-distribution (OOD) samples. Conventional monolithic models often struggle to address the…

• OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib
  Abhijoy Sarkar, Aarchi Singh Thakur · arXiv · Jun 9, 2026

  Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computatio…

• Dynamic Fusion Method of Loss Functions for Unbiased Object Detection in Long-tailed Datasets
  Jeonghyeon Kim, Han-Sol Kim, Changeun Lee, Kwangil Lee · The Transactions of The Kor... · Jun 9, 2026

  In this paper, we propose a dynamic fusion method that combines varifocal loss (VFL) and seesaw loss (SSL) to address the class imbalance problem in long-tail datasets for object detection models. The static combination of two loss function…

• Long-Tail Learning for Three-Dimensional Pavement Distress Segmentation Using Point Clouds Reconstructed from a Consumer Camera
  Pengjian Cheng, Junyan Yi, Zhongshi 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, Luo Yue · Digital Chinese Medicine · Mar 1, 2026
• EdgeTail: Mitigating Long-Tail Visual Problems in Continual Learning at Edge
  Yuzhong Ouyang, Xiaoning Wu, Menglin Yang, Rui Han et al. · ACM Transactions on Internet of 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, Chuangxin 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
  Yuzhen Zhou, Jiajun Li, Yusheng 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…

• Efficient Long-Tail Learning in Latent Space by sampling Synthetic Data
  Nakul Sharma · arXiv.org · Sep 19, 2025

  Imbalanced classification datasets pose significant challenges in machine learning, often leading to biased models that perform poorly on underrepresented classes. With the rise of foundation models, recent research has focused on the full,…

• Generative Active Learning for Long-Tail Trajectory Prediction via Controllable Diffusion Model
  Daehee Park, Monu Surana, Pranav Desai, A. Mehta et al. · IEEE International Conference on Computer Vision · Jul 30, 2025

  While data-driven trajectory prediction has enhanced the reliability of autonomous driving systems, it still struggles with rarely observed long-tail scenarios. Prior works addressed this by modifying model architectures, such as using hype…

• AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction
  Bin Rao, Haicheng Liao, Yanchen Guan, Chengyue Wang et al. · IEEE International Conference on Computer Vision · Jul 2, 2025

  Accurately predicting the future trajectories of traffic agents is essential in autonomous driving. However, due to the inherent imbalance in trajectory distributions, tail data in natural datasets often represents more complex and hazardou…

• LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
  Huaiyuan Yao, Pengfei Li, Bu Jin, Yupeng Zheng et al. · arXiv.org · May 22, 2025

  Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-driven planners lack adaptability to long-tail scenarios, while knowledge-driven methods offer…

• LIFT+: Lightweight Fine-Tuning for Long-Tail Learning
  Jiang-Xin Shi, Tong Wei, Yu-Feng Li · IEEE Transactions on Pattern Analysis and Machine Intelligence · Apr 17, 2025

  The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models. However, the impact of fine-tuning strategies on long-tail learning performance remains unexplored. In thi…

• Siamese Network with Dual Attention for EEG-Driven Social Learning: Bridging the Human-Robot Gap in Long-Tail Autonomous Driving
  Xiaoshan Zhou, C. Menassa, V. Kamat · Expert systems with applications · Apr 14, 2025

  Robots with wheeled, quadrupedal, or humanoid forms are increasingly integrated into built environments. However, unlike human social learning, they lack a critical pathway for intrinsic cognitive development, namely, learning from human fe…

• Class and Attribute-Aware Logit Adjustment for Generalized Long-Tail Learning
  Xiaoling Zhou, Ou Wu, Nan Yang · AAAI Conference on Artificial Intelligence · Apr 11, 2025

  Compared to conventional long-tail learning, which focuses on addressing class-wise imbalances, generalized long-tail (GLT) learning considers that samples within each class still conform to long-tailed distributions due to varying attribut…

• Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond
  Qiongxiu Li, Xiaoyu Luo, Yiyi Chen, Johannes Bjerva · arXiv.org · Mar 10, 2025

  The role of memorization in machine learning (ML) has garnered significant attention, particularly as modern models are empirically observed to memorize fragments of training data. Previous theoretical analyses, such as Feldman's seminal wo…

• Feature Contrastive Transfer Learning for Few-Shot Long-Tail Sonar Image Classification
  Zhongyu Bai, Hongli Xu, Qichuan Ding, Xiangyue Zhang · IEEE Communications Letters · Mar 1, 2025

  Sonar image classification is challenging due to the limited availability and long-tail distribution of labeled sonar samples. In this work, a Feature Contrastive Transfer Learning (FCTL) framework is proposed for few-shot long-tailed sonar…

• Dynamic Subclass-Balancing Contrastive Learning for Long-Tail Pedestrian Trajectory Prediction With Progressive Refinement
  Biao Yang, Kai Yan, Chuan Hu, Hongyu Hu et al. · IEEE Transactions on Automation Science and Engineering · Jan 1, 2025

  Pedestrian trajectory prediction is critical for understanding human behavior. The prevailing approaches employ neural networks to predict trajectories from large amounts of trajectory data. However, pedestrian trajectory data exhibits a lo…