Multi-Task Learning

Follow this topic Ask about this topic

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

391 papers50 papers in the last four weeks, up 16% on the four weeks before. 0.3% of all new papers.

Task-Routed Mixture-of-Experts with Cognitive Appraisal for Implicit Sentiment Analysis
May 20, 2026Yaping Chai, Haoran Xie, Joe S. QinSentiment Analysis Multi-Task Learning
Division of Artificial Intelligence, Lingnan University, Hong Kong
StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels
May 19, 2026Reza M. Asiyabi, Juan Alberto Molina-Valero, The SEOSAW Partnership +2Forest Aboveground Biomass Estimation Multi-Task Learning
School of Geosciences, University of Edinburgh, UK · National Centre for Earth Observation (NCEO), UK · Department of Spatial Sciences, Faculty of Environmental Sciences, Czech University of Life Sciences Prague, Praha, Czech Republic
Lance: Unified Multimodal Modeling by Multi-Task Synergy
May 18, 2026Fengyi Fu, Mengqi Huang, Shaojin Wu +10Unified Multimodal Models Multi-Task Learning
Intelligent Creation Lab, ByteDance
Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning
May 17, 2026Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour +1Multi-Task Learning Object Detection
Univrses AB, Stockholm, Sweden · KTH Royal Institute of Technology, Stockholm, Sweden
Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety
May 16, 2026Seok-Jin KimRobust Regression Multi-Task Learning
Columbia IEOR
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
May 16, 2026Cormac Cureton, Narges ArmanfardTabular Foundation Models Efficient Neural Network Inference
McGill University · Mila - Quebec AI Institute · Montreal, QC, Canada
Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning
May 16, 2026Jan Netík, Patrícia MartinkováTransformer Educational Assessment
Faculty of Education, Charles University, Prague, Czech Republic · Institute of Computer Science of the Czech Academy of Sciences, Prague, Czech Republic
DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation
May 15, 2026Yifan Gao, Lu Zou, Zhangjin Huang +1Object Pose Estimation Gradient Interference
Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, Hubei, China · University of Science and Technology of China, Hefei, Anhui, China · Peking University, Beijing, China
Towards Label-Free Single-Cell Phenotyping Using Multi-Task Learning
May 14, 2026Saqib Nazir, Ardhendu BeheraMulti-Task Learning White Blood Cell Classification
Department of Computer Science, Edge Hill University, UK
CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision
May 13, 2026Xuanhao Luo, Zhizhen Li, Yuchen LiuSelf-Supervised Pre-Training Self-Supervised Time Series Representation Learning
North Carolina State University, USA
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
May 13, 2026Anjir Ahmed Chowdhury, Syed Zawad, Xiaolong Ma +2LLM Fine-Tuning Multi-Task Learning
Department of Computer Science University of Houston · IBM Research · Argonne National Laboratory
Multitask Multimodal Fusion with Tabular Foundation Models for Peak and Durability Prediction of Pertussis Booster Response
May 13, 2026Divya SitaniMulti-Task Learning Clinical Prediction
Berlin, Germany
Multi-Task Representation Learning for Conservative Linear Bandits
May 12, 2026Jiabin Lin, Shana MoothedathMulti-Armed Bandits Multi-Task Learning
Department of Computer Science and Technology, Qingdao University, China · Department of Electrical and Computer Engineering, Iowa State University, USA
MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection
May 11, 2026Xiran Zhao, Jing Jin, Yan Bai +6Multi-View Learning Industrial Anomaly Detection
ShanghaiTech University · Tsinghua University · Meituan Inc. +1
FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
May 10, 2026Xing Han, Shravan Chaudhari, Tanvi Ranade +2Cross-Modal Learning Healthcare
Department of Computer Science Johns Hopkins University · Department of ECE Johns Hopkins University · Department of Computer Science Johns Hopkins University, Bayesian Health
Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions
May 8, 2026Marwane Hariat, Antoine Manzanera, David FilliatOptical Flow Self-Supervised Learning
1U2IS, ENSTA Paris, Institut Polytechnique de Paris, Palaiseau, France · 2INRIA FLOWERS
Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
May 8, 2026Aristotelis Ballas, Christos DiouSharpness-Aware Minimization Multi-Task Learning
Department of Informatics and Telematics Harokopio University of Athens Omirou 9, Athens, Greece
UniV2D: Bridging Visual Restoration and Semantic Perception for Underwater Salient Object Detection
May 8, 2026Laibin Chang, Shaodong Wang, Yunke Wang +4Underwater Image Enhancement Underwater Imaging
School of Computer Science, Wuhan University · School of Computer Science, The University of Sydney · School of Computer Science and Technology, Harbin Institute of Technology
MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text
May 7, 2026Chenjun Li, Cheng Wan, Johannes C. PaetzoldAI-Generated Text Detection Domain Generalization
Cornell University, Ithaca, NY 14853, USA · Weill Cornell Medicine, New York, NY 10021, USA · Cornell Tech, New York, NY 10044, USA
MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors
May 7, 2026Bogdan Alexandru Bercean, Florinel Alin Croitoru, Vlad Hondru +3Medical Image Anomaly Detection Multi-Task Learning
1Rayscape · 3Polytechnic University of Timi¸soara · University of Bucharest +2
$\mathcal{B}^{3}$ -Net: Controlled Posterior Bridge Learning for Multi-Task Dense Prediction
May 7, 2026Meihua Zhou, Li YangMulti-Task Learning Dense Prediction
Wannan Medical University, Wuhu, China · University of Chinese Academy of Sciences, Beijing, China
Morphology-Guided Cross-Task Coupling for Joint Building Height and Footprint Estimation
May 6, 2026Jinzhen Han, JinByeong Lee, Jisung Kim +1Building Footprint Extraction Multi-Task Learning
Department of Civil, Architectural and Environmental System Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon, 16419, Republic of Korea · School of Geography, University of Leeds, Leeds, LS2 9JT, United Kingdom
Beyond Fixed Thresholds and Domain-Specific Benchmarks for Explainable Multi-Task Classification in Autonomous Vehicles
May 5, 2026Maryam Sadat Hosseini Azad, Shahriar Baradaran ShokouhiAutonomous Driving Autonomous Driving Perception
Iran University of Science and Technology, School of Electrical Engineering, Tehran, Iran
Disentangling Shared and Task-Specific Representations from Multi-Modal Clinical Data
May 5, 2026He Lyu, Huolin Zeng, Junren Wang +7Disentangled Representation Learning Representation Learning
Department of Anesthesiology and West China Biomedical Big Data Center West China Hospital, Sichuan University, Chengdu, China · Med-X Center for Informatics, Sichuan University, Chengdu, China · Department of National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China +4
APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music
May 5, 2026Jaavid Aktar Husain, Dorien HerremansMulti-Task Learning Music Information Retrieval
AMAAI Lab, Singapore University of Technology and Design
Active multiple matrix completion with adaptive confidence sets
May 4, 2026Andrea Locatelli, Alexandra Carpentier, Michal ValkoActive Learning Multi-Task Learning
OvGU Magdeburg · SequeL team, Inria Lille
Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality
May 3, 2026Hanxiao Chen, Debarghya MukherjeeSemiparametric Inference Multi-Task Learning
Department of Mathematics and Statistics, Boston University.
CoAction: Cross-task Correlation-aware Pareto Set Learning
May 3, 2026Xinyue Chen, Yingxuan Liang, Yiqin Huang +3Multi-Task Learning Multi-Task Optimization
Guangdong University of Technology, Guangzhou, China · Xiamen University, Xiamen, China
Model Merging: Foundations and Algorithms
May 2, 2026Donato CrisostomiMulti-Task Learning Task Vector Merging
SAPIENZA UNIVERSITY OF ROME · GLADIA research lab · Department of Computer Science +1
Multi-Dataset Cross-Domain Knowledge Distillation for Unified Medical Image Segmentation, Classification, and Detection
May 2, 2026Ceausescu Ciprian-Mihai, Anghelina Ion-Marian, Alexe Dumitru-BogdanMedical Image Object Detection Multi-Task Learning
Faculty of Mathematics and Computer Science, University of Bucharest, Str. Academiei, 14, Bucharest, 010014, Romania · Gheorghe Mihoc-Caius Iacob Institute of Mathematical Statistics and Applied Mathematics of the Romanian Academy, Romania, Calea 13 Septembrie, 13, Bucharest, 050711, Romania

May 20, 2026J/K move · Enter open · S save

Task-Routed Mixture-of-Experts with Cognitive Appraisal for Implicit Sentiment Analysis

Yaping Chai, Haoran Xie, Joe S. Qin

Division of Artificial Intelligence, Lingnan University, Hong Kong

Sentiment Analysis Multi-Task Learning Aspect-Based Sentiment Analysis Mixture-of-Experts Models

Open paper AskPDF arXiv

Implicit sentiment analysis is challenging because sentiment toward an aspect is often inferred from events rather than expressed through explicit opinion words. Existing models typically learn from the final polarity label, which provides limited guidance for reasoning about sentiment from the context. Motivated by cognitive appraisal theory, we propose an appraisal-aware multi-task learning (MTL) framework for implicit sentiment analysis that provides polarity prediction with two complementary auxiliary tasks: implicit sentiment detection and cognitive rationale generation. However, training several objectives with different targets and sharing a single backbone across tasks in MTL limits flexibility and can lead to task interference. To reduce interference among these related but distinct objectives, we adopt task-level mixture-of-experts models in which all tasks share a common set of experts, and task identity controls the sparse combination of these experts. Our method builds on an encoder-decoder architecture and replaces a subset of encoder and decoder blocks with these sparse mixtures. We use a task-conditioned router to select sparse expert mixtures for each task, and a task-separated routing objective to encourage different tasks to learn distinct expert-selection patterns. Experimental results show that our model outperforms recently proposed approaches, with strong gains on the implicit sentiment subset. Our code is available at https://github.com/yaping166/TRMoE-ISA.