Long-Tail Learning

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 36

All topics

Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution
Oct 8, 2026Haohui Wang, Jiahao Xu, Wangzhi Zhan +9Supervised Fine-Tuning Instruction-Tuning Data Selection
Virginia Tech · Amazon · Meta +2
Unsupervised Long-Tailed Adaptation of Vision-Language Models
Oct 6, 2026Keliang Chen, Yaxin Hou, Hui Liu +1Long-Tail Learning VLM Adaptation
School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · School of Computing and Information Sciences, Saint Francis University, Hong Kong, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China
OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
Sep 29, 2026Shenghan Chen, Yiming Liu, Zhipeng Deng +6Long-Tailed Classification Long-Tail Learning
Westlake University, Hangzhou, China · Shandong University, Jinan, China · Hokkaido University, Sapporo, Japan +1
EHRAdapt: Adapting Pretrained Language Models to Electronic Health Records with Semantic Priors for Rare Clinical Events
Sep 27, 2026Andre R Goncalves, Vincent Liu, Priyadip RayLong-Tail Learning Adapter Tuning
Lawrence Livermore National Laboratory · Kaiser Permanente
When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling
Sep 27, 2026Ping Guo, Zhiqi Huang, Xinran LiImage Segmentation Long-Tail Learning
Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan · School of Software, Dalian University of Technology, Dalian, China · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China
Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge
Sep 20, 2026Shangyue Jia, Jingru Ma, Yangzhuo Li +9Long-Tail Learning Automatic Speech Recognition
School of Intelligence Science and Technology, Nanjing University · Jilin University · Beijing Institute of Technology +3
Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels
Sep 14, 2026Mushir Akhtar, Akarsh J., M. Tanveer +1Class-Imbalanced Learning Long-Tail Learning
Department of Mathematics, Indian Institute of Technology Indore, India · Department of Electrical Engineering, Indian Institute of Technology Indore, India
From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning
Jul 24, 2026Jiaxin Deng, Junbiao PangSharpness-Aware Minimization Long-Tail Learning
School of Information Science and Technology, Beijing University of Technology, Beijing, China
Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning
Jul 15, 2026Shiqi Zhang, Marius Faiß, Ariana Strandburg-Peshkin +1Long-Tail Learning Active Learning
1Audio Research Group, Tampere University, Tampere, Finland · Department for the Ecology of Animal Societies, Max Planck Institute of Animal Behavior · 3International Max Planck Research School for Quantitative Behavior, Ecology and Evolution +1
AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation
Jul 14, 2026Shuai Cui, Chen Wenxuan, Wenjie Du +3Long-Tail Learning Synthetic Data Generation
University of Science and Technology of China · Sun Yat-sen University
Prior-Anchored Debiasing for Long-Tailed Multi-Organ Pathology Report Generation
Jul 1, 2026Feng Yang, Jie Liu, Yubo Pang +5Medical Report Generation Long-Tail Learning
City University of Hong Kong, Hong Kong SAR · University of Nottingham, United Kingdom · University of Massachusetts Boston, United States
Latent-CURE for Breast Cancer Diagnosis
Jun 29, 2026Weiyi Zhao, Xiaoyu Tan, Lu Gan +2Breast Cancer Long-Tail Learning
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China · Tencent YouTu Lab, Shanghai 200232, China · Integrative Clinical Research Ward, Clinical Medicine Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China
Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typing
Jun 25, 2026Mreedul Gupta, Advait Deshmukh, Ashwin Umadi +2Long-Tail Learning
University of Colorado Boulder
Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach
Jun 23, 2026Lianshuai Guo, Zhongzheng Yuan, Xunkai Li +2Graph Structure Learning Long-Tail Learning
Shandong University, School of Airspace Science and Engineering, Weihai 264209, China · Beijing Institute of Technology, School of Computer Science and Technology, Beijing 100081, China
Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition
Jun 21, 2026Prajwal Gatti, Simon Jenni, Fabian Caba Heilbron +1Synthetic Data Augmentation Long-Tail Learning
University of Bristol · 2Adobe Research
Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling
Jun 3, 2026Ting-An Chen, Chin-Yuan Yeh, De-Nian YangLong-Tail Learning Low-Bit Quantization
Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan · Graduate Institute of Communication Engineering, National Taiwan University, Taiwan +1
BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation
Jun 2, 2026Xi Zhou, Famin Wu, Mingming Li +4Sequential Recommendation Long-Tail Learning
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · Beijing Institute for General Artificial Intelligence, Beijing, China
DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning
May 28, 2026Hyuck Lee, Taemin Park, Heeyoung KimClass-Imbalanced Learning Long-Tail Learning
AI Research, Krafton, Teheran-ro 231, Centerfield EAST, Gangnam-gu, Seoul, 06142, Republic of Korea · Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea
Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
May 28, 2026Jing Huang, Daniel Wurgaft, Rachit Bansal +6Long-Tail Learning Language Model Scaling Laws
Stanford University · Kempner Institute at Harvard University · MIT +1
Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors
May 20, 2026Siqi Wei, Hongbin Xu, Feng Xiao +43D Point Cloud Segmentation Long-Tail Learning
South China University of Technology · Bytedance · Tsinghua University +2
When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology
May 19, 2026Wen ZhangNeural Network Generalization Long-Tail Learning
Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization
May 18, 2026Anh B. H. Nguyen, Ba Tho Phan, Viet Cuong TaClass-Imbalanced Learning Long-Tail Learning
VNU University of Engineering and Technology, Hanoi, Vietnam
Flow Matching with Optimized Subclass Priors for Medical Image Augmentation
May 15, 2026Felix Nützel, Mischa Dombrowski, Bernhard KainzFlow Matching Synthetic Data Augmentation
Department of Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91052 Erlangen, Germany · Department of Computing, Imperial College London, London SW7 2AZ, UK
BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring
May 14, 2026Zixuan Shu, Tiancheng Cao, Hen-Wei HuangLong-Tail Learning Communication-Efficient Distributed Training
School of Electrical and Electronic Engineering, Nanyang Technological University, Republic of Singapore · Lee Kong Chian School of Medicine, Nanyang Technological University, Republic of Singapore
Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
May 13, 2026Lilin Zhang, Yimo Guo, Yue Li +2Adversarial Training Class-Imbalanced Learning
1Sichuan University · 2Dongfang Electric (Chengdu) Innovation Research Co., Ltd. · 3Southwest China Research Institute of Electronic Equipment
Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models
May 12, 2026Boyang Guo, Liang Li, Lin Peng +3Long-Tail Learning VLM Adaptation
Hangzhou Dianzi University, Hangzhou, China · Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · The Hong Kong Polytechnic University, Hong Kong, China +2
Dynamic Distillation and Gradient Consistency for Robust Long-Tailed Incremental Learning
May 5, 2026Taigo Sakai, Kazuhiro HottaClass-Incremental Learning Long-Tail Learning
Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan
Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning
May 4, 2026Shihao Hou, Chikai Shang, Zhiheng Yang +5Class-Imbalanced Learning Fine-Tuning
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China · Department of Statistical Science, University College London, London, United Kingdom · School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China
Decision Boundary-aware Generation for Long-tailed Learning
May 2, 2026Jiacheng Yang, Ruichi Zhang, Chikai Shang +5Synthetic Data Augmentation Long-Tailed Classification
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China · College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China · Department of Statistical Science, University College London, London, UK +1
Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training
Apr 30, 2026Mingliang Liang, Zhuoran Liu, Arjen P. de Vries +1Long-Tail Learning Vision-Language Pretraining
Institute for Computing and Information Sciences, Radboud University, Nijmegen, the Netherlands · University of Amsterdam, Amsterdam, the Netherlands · Radboud University

Oct 8, 2026, cs.AIJ/K move · Enter open · S save

Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution

Haohui Wang, Jiahao Xu, Wangzhi Zhan, Tong Zeng+8

Virginia Tech · Amazon · Meta+2

Supervised Fine-Tuning Instruction-Tuning Data Selection Long-Tail Learning

Open paper AskPDF arXiv

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 learned, whereas rare concepts may remain weakly represented. We introduce a novel notion named prior barrier to quantify how strongly the pretrained model supports competing concepts over the target concept. We observe that prior barriers follow a long-tail distribution, placing head and tail concepts at different starting points for SFT: head concepts face lower prior barriers, whereas tail concepts require additional instructions to overcome their higher prior barriers. Our theoretical analysis further derives a predictive risk bound for SFT under long-tail prior barriers, explicitly characterizing how the prior barrier and accumulated SFT evidence jointly determine predictive performance. Motivated by this prior barrier-dependent demand, we propose PASS, an adaptive SFT instruction selection method that constructs reference-derived concepts and estimates the distinguishing evidence provided by each instruction, and adaptively allocates the selection budget toward concepts that remain insufficiently covered under the current selection. In this way, PASS jointly considers which instructions can provide useful evidence and where additional supervision is needed under a limited budget. Experiments show that our method consistently outperforms seven state-of-the-art instruction selection methods on four backbone-budget settings. An ablation study further shows that PASS's adaptive allocation consistently improves over uniform allocation.

Momentum

Related topics

Latest papers 36