Multi-Task Learning

Ask about this topic

Overview

Multi-task learning studies how one model can learn several related predictions at once, using shared information to improve accuracy, data efficiency, or deployment cost. Common designs combine a shared encoder with task-specific heads, adapters, or routed experts; other methods balance losses, adjust conflicting gradients, or group tasks by affinity. Applications range from dense vision benchmarks such as NYUv2 and Cityscapes to language, medical prediction, recommendation, and scientific modeling. The central tension is positive versus negative transfer: sharing can help when tasks have useful common structure, but differences in data, objectives, or capacity can cause gains for some tasks and losses for others.

Latest papers

CardsList

387 papers61 papers in the last four weeks, up 61% on the four weeks before. 0.3% of all new papers.

  1. Interactive image diagnosis using test-time backpropagation from the auxiliary task

    Oct 23, 2026Takuro ShimayaMulti-Task LearningMedical Image Classification

    Biometrics Research Laboratories, NEC Corporation, Kawasaki, Japan

  2. Sparsity-driven emergence of functional modularity in multitask neural networks

    Oct 23, 2026Bowen Shi, Qi Ouyang, Long QianModular Neural NetworksMulti-Task Learning

    Institute for Advanced Study in Physics, Zhejiang University, Hangzhou 310058, China · Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China · ZJU–Hangzhou Global Scientific and Technological Innovation Center, Hangzhou 311200, China +1

  3. Rethinking Multi-View Fusion for Urban Representation Learning

    Oct 22, 2026Sean Bin Yang, Zongyi Xu, Jilin Hu +5Urban Representation LearningMulti-View Feature Fusion

    Aalborg University, Denmark · Chongqing University of Posts and Telecommunications, China · East China Normal University, China

  4. Optimal Multitask Representations Under a Rate Constraint: An Information Bottleneck Analysis

    Oct 21, 2026Nicholas Stiles, Gregory W. WornellRepresentation LearningInformation Bottleneck

    Massachusetts Institute of Technology

  5. Exploring Recurrent-Depth Language Models for Multitask Clinical Text Processing

    Oct 20, 2026Xi Yang, Guodong Liu, Cheng Peng +7Recurrent Language ModelsClinical NLP

    Advanced Intelligence and Research Eli Lilly and Company Indianapolis, IN, USA · Dept. of Health Outcomes and Biomedical Informatics University of Florida Gainesville, FL, USA · Higher Education and Research NVIDIA Santa Clara, CA, USA +2

  6. Preference-Aware Pareto Steering for Multi-Task Speech LLMs

    Oct 19, 2026Liuyuan Jiang, Vishal Sunder, Samuel Thomas +4Multi-Task LearningSpeech Language Models

    Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA · IBM Research, Thomas J. Watson Research Center, Yorktown Heights, NY, USA

  7. Learning to Be Different: Component Specialization for Compositional Diffusion Policies

    Oct 19, 2026Alec Laprevotte, Haonan Chen, Xiaoshen Han +1Diffusion PolicyMulti-Task Learning

    Harvard University

  8. Motor compound fault diagnosis using an attention-based cross-talk architecture

    Oct 19, 2026Wonjun Yi, Wonho Jung, Junho Kim +2Fault DiagnosisIndustrial Fault Diagnosis

    Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea

  9. Deep Auxiliary Learning via Bilevel Feature Optimization for Label-Efficient Medical Image Segmentation

    Oct 18, 2026Fuping Wu, Xi Jia, Le Zhang +4Medical Image SegmentationMulti-Task Learning

    Big Data Institute, Nuffield Department of Population Health, University of Oxford · Imperial College London · Nuffield Department of Population Health, University of Oxford +2

  10. Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition

    Oct 16, 2026Juho Jung, Seongjae Kang, Jinyoung HanActive LearningMulti-Task Learning

    Sungkyunkwan University · KAIST

  11. ReVision: Reprogramming Image Generators for Dense Visual Perception

    Oct 16, 2026Yitong Yang, Yinglin Wang, Xuexin Liu +6Multi-Task LearningHypernetworks

    Tencent Hy · Shanghai University of Finance and Economics

  12. Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models

    Oct 15, 2026Yuqi Xiong, Chunyi Peng, Zhipeng Xu +5VLM DistillationRL for VLMs

    School of Computer Science and Engineering, Northeastern University, Shenyang, China · Alibaba Group, Hangzhou, China

  13. Hierarchical Interpretable Multitask Audio Representation Learning: An Analysis of Event-Scene Relationships through the Information Bottleneck

    Oct 15, 2026Claudia Montero-Ramírez, Alba Martínez-Serrano, Carmen Peláez-MorenoAudio ClassificationMulti-Task Learning

  14. Learning to Forecast on Multiple Spatiotemporal Hierarchies

    Oct 15, 2026Valentina Moretti, Cesare Alippi, Andrea CiniTime Series ForecastingSpatiotemporal Forecasting

    IDSIA USI-SUPSI, Universit`a della Svizzera italiana · Politecnico di Milano · EPFL

  15. IMU-Bench: Benchmarking Wrist IMU Representations Across Kinematic, Semantic and Clinical Tasks

    Oct 14, 2026Yiquan Li, Aidan Bradshaw, Chenfeng Gao +1Wearable SensingMulti-Task Learning

    Northwestern University

  16. Recalibrating Many Questions with Few Labels: Minimax Rates and Identification Limits

    Oct 13, 2026Xiaoyu Li, Chiwun YangProbability CalibrationMinimax Estimation

    University of New South Wales. · City University of Hong Kong.

  17. Omni-RS: Unifying Multi-Task Understanding and Generation in Remote Sensing

    Oct 13, 2026Pan Yin, Shuai Yang, Yuanhao Liu +7Image GenerationUnified Multimodal Models

    Xi’an Jiaotong University

  18. A Multi-Task Deep Learning Framework for Pose-Invariant Face Recognition and Facial Landmark Localization

    Oct 12, 2026Ali Ashkeyev, Zukhra AbdiakhmetovaFace RecognitionMulti-Task Learning

    Faculty of Information Technology, Kazakh-British Technical University, Almaty, Kazakhstan · Faculty of Information Technology and Artificial Intelligence, Abai Kazakh National Pedagogical University, Almaty, Kazakhstan

  19. The Bell Boundary of Shared Representations

    Oct 12, 2026Yang Wu, Hanyu Zhao, Yazhou Zhang +1Shared Representation LearningTask Interference

    Tianjin University, China

  20. How Shared Representations Become Specialized: Formation, Maintenance, and Latent Susceptibility

    Oct 11, 2026Toru TakahashiMulti-Task Learning

    Human Informatics and Systems Lab, Doshisha University · Linked Open Data Initiative, NPO · Keio Research Institute at SFC +1

  21. PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging

    Oct 10, 2026Muqing Liu, Chongjie Si, Zhuoya Liu +1Language Model MergingLow-Rank Adaptation

    Chien-Shiung Wu College, Southeast University · MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science, Shanghai Jiao Tong University · School of Computer Science and Engineering, Southeast University +1

  22. Studying the Effects of Task Diversity Using Small Mathematical Worlds

    Oct 9, 2026Emily Xia Meng, Xuanyu Yang, Junaid Hasan +2Multi-Task LearningLLM Training

    University of Washington, Seattle · University of Washington Pacific Northwest National Laboratory

  23. JMT-YOLO: Multi-task Domain Adaptation via Segmentation-Guided Consistency Learning

    Oct 9, 2026Zhenhua Yu, Jiahao Zhang, Wenchao Zhang +2Object DetectionUnsupervised Domain Adaptation

    Institute of Systems Security and Control, College of Artificial Intelligence and Computer Science, Xi’an University of Science and Technology, Xi’an 710054, China

  24. Leakage-Controlled Multimodal Learning for Diagnosis and Progression Prediction in Alzheimer's Disease Research

    Oct 7, 2026Akeem Temitope Otapo, Ghazaleh Khodabandelou, Zuheng Ming +1Alzheimer's Disease Progression PredictionAlzheimer's Disease Classification

  25. TTNet: Multi-Task Deep Learning for Table Tennis Player Analysis with Smart Racket

    Oct 6, 2026Ko-Hsun Chen, Xiang-Wei Ke, Hsien-Cheng Huang +1Multi-Task Learning

    Department of Computer Science and Engineering, Yuan Ze University, Taoyuan, Taiwan

  26. SkillFormer: Skill-Decomposed Adaptation for Audio Language Models

    Oct 6, 2026Lee Seung-woo, Bowen Qi, Kim Min-jun +1Multi-Task LearningAudio Understanding

    Pusan National University · Shanghai Jiao Tong University · Hanyang University

  27. To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks

    Oct 5, 2026Louis Tichelman, Xingyue Huang, Jinwoo Kim +1Multi-Task LearningGraph Transfer Learning

    TU Wien · AITHYRA · University of Oxford +1

  28. Multitask Conditional Generative Adversarial Network Enables Automatic Whole Knee Cartilage and Menisci Segmentation and Reliable T1ρT_{1ρ} and T2T_2 Quantification Without High-Resolution Morphological Images

    Oct 5, 2026Ahmed Tahseen Minhaz, Richard Lartey, Zhiyuan Zhang +8Multi-Task LearningMagnetic Resonance Imaging

    Program of Advanced Musculoskeletal Imaging (PAMI), Cleveland Clinic · Department of Biomedical Engineering, Cleveland Clinic Research, Cleveland Clinic · Department of Mathematics, Case Western Reserve University +1

  29. Multi-Task Partially Supervised Learning for Super-Resolution and Semantic Segmentation on Earth Observation data

    Oct 5, 2026Hoàng-Ân Lê, Minh-Tan Pham, Solange Lemai-Chenevier +1Remote Sensing Image SegmentationRemote Sensing Image Super-Resolution

    Universit´e Bretagne Sud, IRISA, UMR 6074, Vannes, France · Centre National d’Etudes Spatiales (CNES), Toulouse, France

  30. Wiring Matters: Injection Topology and Initialization of Affordance Heads in Vision-Language-Action Policies

    Oct 5, 2026Zijian An, Linhan Wang, Jiayan Wang +4Multi-Task LearningVision-Language-Action Models

    Drexel University, Philadelphia, PA 19104, USA · Virginia Tech, Virginia Seafood Agricultural Research and Extension Center, Hampton, VA 23669, USA · TODO: Jiayan Wang’s affiliation and email +1