Multi--Task Learning

Follow this topic Ask about this topic

Recent momentum

-62%

11 papers in the last 28 days · 0.3% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Multi--Task Learning.

Period ending 2026-09-07

6 new papers

A weekly snapshot of new work published in Multi--Task Learning.

215 papers

Latest in Multi--Task Learning

Open your feed →

Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation
May 1, 2026Shihong Ding, Fangyu Du, Cong FangMulti--Task Learning Compact Matrix Factorization
A Proof-of-Concept Study of Multitask Learning for Cranial Synthetic CT Generation Across Heterogeneous MRI Field Strengths
Apr 30, 2026Zhuoyao Xin, Yiren Zhang, Christopher Wu +6Magnetic Resonance Imaging Computed Tomography
Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
Apr 30, 2026Junqi Gao, Dazhi Zhang, Zhichang Guo +3Continual Model Merging Convolutional Neural Network Compression
FiLMMeD: Feature-wise Linear Modulation for Cross-Problem Multi-Depot Vehicle Routing
Apr 30, 2026Arthur Corrêa, Paulo Nascimento, Samuel MonizVehicle Routing Problem Multi--Task Learning
Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation
Apr 28, 2026Sicheng Dai, Kai Chen, Hongwang Xiao +2Electroencephalogram Brain-Computer Interface
Conflict-Aware Harmonized Rotational Gradient for Multiscale Kinetic Regimes
Apr 27, 2026Zhangyong LiangMultiscale Dynamics Multiscale
WISE-FM:Operation-Aware, Engineering-Informed Foundation Model for Multi-Task Well Design
Apr 26, 2026Carine de Menezes Rebello, Anderson Rapello dos Santos, Idelfonso B. R. NogueiraDrilling Data Fluid Dynamics
Multi-Task Optimization over Networks of Tasks
Apr 23, 2026Julian Hatzky, Thomas Bartz-Beielstein, A. E. Eiben +1Multi--Task Learning
Enhancing Science Classroom Discourse Analysis through Joint Multi-Task Learning for Reasoning-Component Classification
Apr 22, 2026Jiho Noh, Mukhesh Raghava Katragadda, Raymond Carl +1Discourse Education
Opportunistic Bone-Loss Screening from Routine Knee Radiographs Using a Multi-Task Deep Learning Framework with Sensitivity-Constrained Threshold Optimization
Apr 22, 2026Zhaochen Li, Xinghao Yan, Runni Zhou +8Knee Osteoarthritis Xray-Visual
SMART: A Spectral Transfer Approach to Multi-Task Learning
Apr 22, 2026Boxin Zhao, Mladen Kolar, Jinchi LvMulti--Task Learning Transfer Learning
VLA Foundry: A Unified Framework for Training Vision-Language-Action Models
Apr 21, 2026Jean Mercat, Sedrick Keh, Kushal Arora +5Vision-Language-Action Reinforcement Fine-Tuning
SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning
Apr 21, 2026Boyan Shi, Wei Chen, Shuyuan Zhao +4Low-Rank Adaptation Experts Multi--Task Learning
Multi-Domain Learning with Global Expert Mapping
Apr 20, 2026Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou +3Multi--Task Learning Experts
From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
Apr 20, 2026Qidong Wang, Junjie Hu, Ming JiangRecent Vision-Language Models Multi--Task Learning
Evolutionary Negative Module Pruning for Better LoRA Merging
Apr 20, 2026Anda Cao, Zhuo Gou, Yi Wang +5Continual Model Merging Magnitude-Based Pruning
MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Textures
Apr 19, 2026Vasileios Toulatzis, Sofia Theodoridou, Ioannis FudosImage Restoration Preservation
Unified Ultrasound Intelligence Toward an End-to-End Agentic System
Apr 18, 2026Chen Ma, Yunshu Li, Junhu Fu +3Ultrasound Multimodal Clinical Data
Crowded in B-Space: Calibrating Shared Directions for LoRA Merging
Apr 18, 2026Yixuan Tang, Yi YangAdapters Multi--Task Learning
Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects
Mar 5, 2026Ayed M. Alrashdi, Oussama Dhifallah, Houssem SifaouMulti--Task Learning Asymptotics
Resolving Predictive Multiplicity for the Rashomon Set
Jan 14, 2026Parian Haghighat, Hadis Anahideh, Cynthia RudinMulti--Task Learning Dense Prediction
Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
Dec 1, 2025Kuangpu Guo, Aijing Yu, Jian Liang +4Continual Model Merging Multi--Task Learning
Graph Coloring for Multi-Task Learning
Sep 21, 2025Santosh Patapati, Ian NoronhaMulti--Task Learning Graph Learning
Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning
Aug 20, 2025Xudong Wang, Guoming Tang, Junyu Xue +3Energy Based Models Multi--Task Learning
From Isolation to Alignment: Unified LoRA for Efficient Multi-Task Learning
Aug 7, 2025Jinda Liu, Yi Chang, Yuan WuParameter-Efficient Fine-Tuning Methods Multi--Task Learning
Calibrating Biophysical Models for Grape Phenology Prediction via Multi-Task Learning
Aug 5, 2025William Solow, Sandhya SaisubramanianUsda Cropland Data Layer Multi--Task Learning
Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
Jun 12, 2025Hongyu Yao, Zijin Hong, Hao Chen +6Multi--Task Learning Recommender Systems
( $θ_l, θ_u$ )-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces(θ_l, θ_u)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces
Mar 11, 2025Tingyang Wei, Jiao Liu, Abhishek Gupta +2Multi--Task Learning Gradient-Based Trajectory Optimization
Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
Feb 3, 2025Siqi Zeng, Yifei He, Meitong Liu +5Model and Context Compression Data-Efficient
Variational Model Merging for Pareto Front Estimation in Multitask Finetuning
Dec 11, 2024Hugo Monzón Maldonado, Nico Daheim, Thomas Möllenhoff +2Continual Model Merging Pareto Frontier
Stealthy Multi-Task Adversarial Attacks
Nov 26, 2024Jiacheng Guo, Tianyun Zhang, Lei Li +3Black-Box Adversarial Attacks Multi--Task Learning
Uni-HOI:A Unified framework for Learning the Joint distribution of Text and Human-Object Interaction
Date pendingMengfei Zhang, Jinlu Zhang, Zhigang TuHuman-Object Interactions Human Motion Prediction
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
Date pendingQuanhao Li, Junqiu Yu, Kaixun Jiang +7Diffusion Policies On-Policy Distillation
Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks
Date pendingRachel Longjohn, Giri Gopalan, Emily CasletonModel Evaluation Multi--Task Learning
UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures
Date pendingHoma Esfahanizadeh, Matin Mortaheb, Adeel Mahmood +2Image Compression Multi--Task Learning

May 1, 2026 · cs.LGJ/K move · Enter open · S save

Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation

Shihong Ding, Fangyu Du, Cong Fang

Multi-task learning (MTL) has emerged as a pivotal paradigm in machine learning by leveraging shared structures across multiple related tasks. Despite its empirical success, the development of likelihood-based efficiently solvable algorithms--even for shared linear representations--remains largely underdeveloped, primarily due to the non-convex structure intrinsic to matrix factorization. This paper introduces a first-order algorithm that jointly learns a shared representation and task-specific parameters, with guaranteed efficiency. Notably, it converges in

\widetilde{\mathcal{O}}(1)

iterations and attains a \emph{near-optimal} estimation error of

\widetilde{\mathcal{O}}(dk/(TN))

, \emph{improving} over existing likelihood-based methods by a factor of

k

, where

d

k

T

N

denote input dimension, representation dimension, task count, and samples per task, respectively. Our results justify that likelihood-based first-order methods can efficiently solve the MTL problem.

Multi--Task Learning Compact Matrix Factorization Representation Learning Representation Space Optimal

Open paper Ask about it PDF