Multi-Task Learning

ICLR 2024arXiv:2305.03053

#2

ZipIt! Merging Models from Different Tasks without Training

George Stoica, Daniel Bolya, Jakob Bjorner et al.

167

ICML 2024arXiv:2405.07813

#3

Localizing Task Information for Improved Model Merging and Compression

Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez et al.

model mergingtask arithmetictask vectorsweight space interference+4

92

AAAI 2024arXiv:2312.08636

#4

MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning

Yi Xin, Junlong Du, Qiang Wang et al.

88

AAAI 2024arXiv:2312.08733

#5

VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding

Yi Xin, Junlong Du, Qiang Wang et al.

parameter-efficient transfer learningmulti-task adaptationdense scene understandingvision transformer adapter+2

85

ICML 2024arXiv:2402.00433

#6

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

Anke Tang, Li Shen, Yong Luo et al.

model mergingtask arithmeticmixture of expertsparameter interference+3

84

CVPR 2024arXiv:2311.10707

#7

Multimodal Representation Learning by Alternating Unimodal Adaptation

Xiaohui Zhang, Jaehong Yoon, Mohit Bansal et al.

80

CVPR 2024arXiv:2403.17749

#8

Multi-Task Dense Prediction via Mixture of Low-Rank Experts

Yuqi Yang, Peng-Tao Jiang, Qibin Hou et al.

multi-task dense predictionmixture of expertslow-rank adaptationparameter sharing+3

60

ICLR 2024arXiv:2311.11385

#9

Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts

Ahmed Hendawy, Jan Peters, Carlo D'Eramo

41

AAAI 2024arXiv:2308.13537

#10

STEM: Unleashing the Power of Embeddings for Multi-Task Recommendation

Liangcai Su, Junwei Pan, Ximei Wang et al.

multi-task learningrecommender systemsnegative transfershared embeddings+3

39

CVPR 2024arXiv:2507.13364

#11

OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning

Siddharth Srivastava, Gaurav Sharma

39

ICML 2024arXiv:2312.03801

#12

Generalization to New Sequential Decision Making Tasks with In-Context Learning

Sharath Chandra Raparthy, Eric Hambro, Robert Kirk et al.

in-context learningsequential decision makingoffline datasetstransformers+4

37

CVPR 2024arXiv:2403.02628

#13

Interactive Continual Learning: Fast and Slow Thinking

Biqing Qi, Xinquan Chen, Junqi Gao et al.

continual learningcomplementary learning systemsmultimodal large language modelsvision transformer models+4

36

ICML 2024arXiv:2402.15638

#14

Fair Resource Allocation in Multi-Task Learning

Hao Ban, Kaiyi Ji

multi-task learningconflicting gradientsgradient manipulation methodsfair resource allocation+4

35

ICML 2025arXiv:2502.04959

#15

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces

Daniel Marczak, Simone Magistri, Sebastian Cygert et al.

34

ICLR 2025arXiv:2409.07402

#16

What to align in multimodal contrastive learning?

Benoit Dufumier, Javiera Castillo Navarro, Devis Tuia et al.

multimodal contrastive learningmultimodal self-supervised learningmultimodal representation alignmentmultimodal interactions+3

34

ICLR 2024arXiv:2309.15564

#17

Jointly Training Large Autoregressive Multimodal Models

Emanuele Aiello, Lili Yu, Yixin Nie et al.

34

CVPR 2024arXiv:2404.09263

#18

Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection

Jin Yang, Ping Wei, Huan Li et al.

29

ECCV 2024arXiv:2407.02228

#19

MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders

Baijiong Lin, Weisen Jiang, Pengguang Chen et al.

multi-task dense predictionscene understandingmamba-based architecturelong-range dependency modeling+4

29

ICML 2025arXiv:2501.01230

#20

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

Yongxian Wei, Anke Tang, Li Shen et al.

26

CVPR 2024arXiv:2308.07891

#21

Link-Context Learning for Multimodal LLMs

Yan Tai, Weichen Fan, Zhao Zhang et al.

26

CVPR 2024arXiv:2404.15655

#22

Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering

Jiawei Yao, Qi Qian, Juhua Hu

25

ICML 2024arXiv:2402.02009

#23

Robust Multi-Task Learning with Excess Risks

Yifei He, Shiji Zhou, Guojun Zhang et al.

multi-task learninglabel noise robustnessexcess risk estimationtask balancing methods+3

25

CVPR 2024arXiv:2403.01753

#24

Training-Free Pretrained Model Merging

Zhengqi Xu, Ke Yuan, Huiqiong Wang et al.

model mergingpretrained model fusionweight space alignmentactivation space consistency+4

24

AAAI 2025arXiv:2407.09893

#25

Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

Shengbin Yue, Siyuan Wang, Wei Chen et al.

21

CVPR 2025arXiv:2412.19326

#26

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment

ziang yan, Zhilin Li, Yinan He et al.

multimodal large language modelsvision task alignmenttask preference optimizationdifferentiable task preferences+3

20

AAAI 2024arXiv:2401.06595

#27

Every Node Is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering

Pengfei Zhu, Qian Wang, Yu Wang et al.

attributed graph clusteringself-supervised learningmulti-task learningdynamic task weighting+3

CVPR 2024arXiv:2312.16279

#28

Cloud-Device Collaborative Learning for Multimodal Large Language Models

Guanqun Wang, Jiaming Liu, Chenxuan Li et al.

ICLR 2024arXiv:2311.02684

#29

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE

Zeren Chen, ziqin wang, zhen wang et al.

ECCV 2024arXiv:2407.05363

#30

Multi-branch Collaborative Learning Network for 3D Visual Grounding

Zhipeng Qian, Yiwei Ma, Zhekai Lin et al.

CVPR 2024arXiv:2403.19490

#31

Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment

Alireza Ganjdanesh, Shangqian Gao, Heng Huang

structural model pruningreinforcement learning agentjoint training pruningdynamic reward function+3

17

ICML 2024arXiv:2310.09676

#32

Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning

Jiachen Li, Qiaozi Gao, Michael Johnston et al.

robot manipulationmultimodal promptsvision-language understandinginverse dynamics pretraining+3

17

ICML 2024arXiv:2405.18080

#33

HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning

Shengchao Hu, Ziqing Fan, Li Shen et al.

offline reinforcement learningmulti-task reinforcement learningdecision transformerparameter sharing+4

15

AAAI 2025arXiv:2502.18510

#34

Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition

Chuanguang Yang, XinQiang Yu, Han Yang et al.

15

CVPR 2024arXiv:2403.15389

#35

DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data

Hanrong Ye, Dan Xu

14

AAAI 2025arXiv:2501.06773

#36

Pareto Set Learning for Multi-Objective Reinforcement Learning

Erlong Liu, Yu-Chang Wu, Xiaobin Huang et al.

multi-objective reinforcement learningpareto front learningdecomposition-based methodshypernetwork generation+3

14

ICML 2024arXiv:2402.04005

#37

Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning

Idan Achituve, Idit Diamant, Arnon Netzer et al.

multi-task learninggradient aggregationbayesian uncertaintytask-specific parameters+2

ECCV 2024arXiv:2407.12616

#38

Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models

Taesup Kim, Donggeun Kim

ICCV 2025arXiv:2211.13723

#39

Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective

Hoang Phan, Tung Lam Tran, Quyen Tran et al.

ICML 2024arXiv:2307.06887

#40

Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks

Liam Collins, Hamed Hassani, Mahdi Soltanolkotabi et al.

multi-task learningrepresentation learningfeature learningtwo-layer neural networks+4

ECCV 2024arXiv:2407.13771

#41

Training-Free Model Merging for Multi-target Domain Adaptation

Wenyi Li, Huan-ang Gao, Mingju Gao et al.

model mergingmulti-target domain adaptationscene understandingnormalization layer statistics+4

12

NEURIPS 2025arXiv:2503.14963

#42

Continual Multimodal Contrastive Learning

Xiaohao Liu, Xiaobo Xia, See-Kiong Ng et al.

AAAI 2024arXiv:2312.14472

#43

Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing

Jinmin He, Kai Li, Yifan Zang et al.

multi-task reinforcement learningdynamic depth routingparameter sharingrouting network+3

AAAI 2024arXiv:2402.08578

#44

FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing

Yongzhe Jia, Xuyun Zhang, Amin Beheshti et al.

federated learningedge computingparameter sharingmodel pruning+4

CVPR 2024arXiv:2406.02996

#45

Quantifying Task Priority for Multi-Task Optimization

Wooseong Jeong, Kuk-Jin Yoon

ICML 2024arXiv:2407.20734

#46

Efficient Pareto Manifold Learning with Low-Rank Structure

Weiyu CHEN, James Kwok

multi-task learningmulti-objective optimizationpareto front approximationlow-rank structure+3

10

ECCV 2024arXiv:2407.10876

#47

RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception

Shen Jianbing, Chunliang Li, Wencheng Han et al.

vector field representationmulti-task 3d perceptionautonomous driving perception3d object detection+3

10

CVPR 2024arXiv:2312.00598

#48

Learning from One Continuous Video Stream

Joao Carreira, Michael King, Viorica Patraucean et al.

online learningcontinuous video streampixel-to-pixel modellingfuture prediction tasks+3

10

AAAI 2025arXiv:2412.15678

#49

Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network

Xiang Fang, Wanlong Fang, Changshuo Wang et al.

NEURIPS 2025arXiv:2505.23150

#50

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners

Michal Nauman, Marek Cygan, Carmelo Sferrazza et al.

value-based reinforcement learningmulti-task learningtemporal difference learningtask interference+4

ICML 2025arXiv:2502.08991

#51

Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?

Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen et al.

ICML 2025arXiv:2410.05603

#52

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition

Zheyang Xiong, Jack Cai, John Cooper et al.

ICLR 2024arXiv:2310.00986

#53

Multi-task Learning with 3D-Aware Regularization

Wei-Hong Li, Steven McDonagh, Ales Leonardis et al.

ICLR 2025arXiv:2503.21200

#54

Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation

Sicong Liu, Yang Shu, Chenjuan Guo et al.

AAAI 2025arXiv:2503.18100

#55

M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving

Xuesong Chen, Shaoshuai Shi, Tao Ma et al.

ICML 2025arXiv:2505.06977

#56

CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging

Wenju Sun, Qingyong Li, Yangliao Geng et al.

AAAI 2025arXiv:2412.12596

#57

OpenViewer: Openness-Aware Multi-View Learning

Shide Du, Zihan Fang, Yanchao Tan et al.

multi-view learningopen-set recognitionpseudo-unknown sample generationdeep unfolding network+3

ICML 2024arXiv:2405.16560

#58

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

Yongxian Wei, Zixuan Hu, Li Shen et al.

data-free meta-learningmodel heterogeneitytask conflict mitigationgradient regularization+4

ICML 2025arXiv:2410.15729

#59

A Two-Stage Learning-to-Defer Approach for Multi-Task Learning

Yannis Montreuil, Shu Heng Yeo, Axel Carlier et al.

ICML 2024arXiv:2410.02068

#60

Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits

Jiabin Lin, Shana Moothedath, Namrata Vaswani

contextual banditsmulti-task learningrepresentation learningalternating projected gradient descent+3

ICLR 2024arXiv:2312.03248

#61

Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning

Haowen Wang, Tao Sun, Congyun Jin et al.

CVPR 2025arXiv:2410.10604

#62

Multi-modal Vision Pre-training for Medical Image Analysis

Shaohao Rui, Lingzhi Chen, Zhenyu Tang et al.

CVPR 2025arXiv:2504.02264

#63

MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception

Wenzhuo Liu, Wenshuo Wang, Yicheng Qiao et al.

assistive driving perceptionmultimodal learningmulti-task learningdriver behavior recognition+4

ICML 2025arXiv:2505.05279

#64

MTL-UE: Learning to Learn Nothing for Multi-Task Learning

Yi Yu, Song Xia, SIYUAN YANG et al.

ICML 2025arXiv:2506.11672

#65

Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning

Chendi Ge, Xin Wang, Zeyang Zhang et al.

CVPR 2024arXiv:2402.07739

#66

Task-Conditioned Adaptation of Visual Features in Multi-Task Policy Learning

Pierre Marza, Laetitia Matignon, Olivier Simonin et al.

ICLR 2025arXiv:2502.09925

#67

TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types

Jiankang Chen, Tianke Zhang, Changyi Liu et al.

multimodal instruction fine-tuningvision-language modelstask diversity scalingautomated dataset generation+3

NEURIPS 2025arXiv:2409.18893

#68

HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models

Yu Zhou, Xingyu Wu, Jibin Wu et al.

model mergingarchitecture space mergingreinforcement learning optimizationmulti-objective optimization+4

ICML 2025arXiv:2410.05026

#69

Active Fine-Tuning of Multi-Task Policies

Marco Bagatella, Jonas Hübotter, Georg Martius et al.

ICML 2025arXiv:2505.24378

#70

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

Yilun Kong, Guozheng Ma, Qi Zhao et al.

ICLR 2025arXiv:2406.14022

#71

Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning

Xiaolei Wang, Xinyu Tang, Junyi Li et al.

in-context learningtask recognitiontask learningpre-training dynamics+3

ICLR 2025arXiv:2410.14633

#72

Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

Yuxiang Lu, Shengcao Cao, Yu-Xiong Wang

vision foundation modelsmulti-task learningknowledge distillationrepresentation bias+4

few-shot object detectionmulti-task learninggradient balancingknowledge distillation+3

#73

Adaptive Multi-task Learning for Few-shot Object Detection

Yan Ren, Yanling Li, Wai-Kin Adams Kong

ECCV 2024

diffusion modelsmulti-task dense predictionsjoint denoising diffusiontask-integration feature space+2

#74

Multi-Task Dense Predictions via Unleashing the Power of Diffusion

Yuqi Yang, Peng-Tao Jiang, Qibin Hou et al.

ICLR 2025

CVPR 2024arXiv:2404.01976

#75

Joint-Task Regularization for Partially Labeled Multi-Task Learning

Kento Nishi, Junsik Kim, Wanhua Li et al.

ICLR 2025arXiv:2502.11986

#76

Cross-modal Multi-task Learning for Multimedia Event Extraction

Jianwei Cao, Yanli Hu, Zhen Tan et al.

Selective Task Group Updates for Multi-Task Optimization

Wooseong Jeong, Kuk-Jin Yoon

CVPR 2025arXiv:2502.06029

#78

DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations

Krishna Sri Ipsit Mantri, Carola-Bibiane Schönlieb, Bruno Ribeiro et al.

vision transformersmulti-task learningparameter-efficient fine-tuningdiffeomorphic transformations+3

ICLR 2025arXiv:2407.11249

#79

Disentangling Representations through Multi-task Learning

Pantelis Vafidis, Aman Bhargava, Antonio Rangel

disentangled representationsmulti-task learningevidence accumulationcontinuous attractors+4

ICLR 2025arXiv:2302.00671

#80

QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing

Grace Zhang, Ayush Jain, Injune Hwang et al.

multi-task reinforcement learningbehavioral policy sharingoff-policy data collectionq-switch mixture+3

ICCV 2025arXiv:2508.04682

#81

TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction

Zewei Zhou, Zhihao Zhao, Tianhui Cai et al.

multi-agent perceptionmulti-agent predictionmasked reconstruction learninggradient conflict suppression+3

ICML 2025arXiv:2502.14096

#82

Understanding Multi-Task Activities from Single-Task Videos

Yuhan Shen, Ehsan Elhamifar

Aligned Multi Objective Optimization

Yonathan Efroni, Ben Kretzu, Daniel Jiang et al.

CVPR 2025arXiv:2411.15099

#84

Context-Aware Multimodal Pretraining

Karsten Roth, Zeynep Akata, Dima Damen et al.

multimodal representation learningcontrastive learningvision-language modelsfew-shot adaptation+2

NEURIPS 2025arXiv:2506.02935

#85

MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver

yuepeng zheng, Fu Luo, Zhenkun Wang et al.

ICML 2025arXiv:2506.13406

#86

CALM: Consensus-Aware Localized Merging for Multi-Task Learning

Kunda Yan, Min Zhang, Sen Cui et al.

ICLR 2025arXiv:2410.05454

#87

Meta-Dynamical State Space Models for Integrative Neural Data Analysis

Ayesha Vermani, Josue Nassar, Hyungju Jeon et al.

latent dynamics learningneural data analysismeta-learningdynamical systems+4

ICLR 2024arXiv:2403.01400

#88

Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks

Tianyu Fan, Lirong Wu, Yufei Huang et al.

AAAI 2025arXiv:2501.13985

#89

Pilot: Building the Federated Multimodal Instruction Tuning Framework

Baochen Xiong, Xiaoshan Yang, Yaguang Song et al.

federated instruction tuningmultimodal large language modelsadapter on adaptercross-task mixture-of-adapters+4

NEURIPS 2025arXiv:2502.17821

#90

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems

Rui Liu, Yu Shen, Peng Gao et al.

CVPR 2025arXiv:2410.06664

#91

Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters

Xiaohan Qin, Xiaoxing Wang, Junchi Yan

Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning

Qianli Ma, Xuefei Ning, Dongrui Liu et al.

diffusion modelsmulti-task learningparameter mergingdenoising tasks+4

ICML 2024arXiv:2406.05993

#93

Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning

Takayuki Osa, Tatsuya Harada

offline reinforcement learningmultiple solution learningbehavioral diversityfew-shot adaptation+1

NEURIPS 2025arXiv:2502.06244

#94

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts

Zeman Li, Yuan Deng, Peilin Zhong et al.

NEURIPS 2025arXiv:2505.23859

#95

Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration

Wenju Sun, Qingyong Li, Wen Wang et al.

model mergingfeature drift minimizationlayer-wise optimizationtask vector fusion+3

ICML 2024arXiv:2407.05082

#96

DMTG: One-Shot Differentiable Multi-Task Grouping

Yuan Gao, Shuguo Jiang, Moran Li et al.

multi-task learningtask groupingdifferentiable pruningadaptive network architecture+4

ICML 2025arXiv:2503.01885

#97

Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks

Luise Ge, Michael Lanier, Anindya Sarkar et al.

ICLR 2024arXiv:2403.01636

#98

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

Ziping Xu, Zifan Xu, Runxuan Jiang et al.

multitask reinforcement learningmyopic explorationsample efficiencydiverse tasks+4

ECCV 2024arXiv:2407.13122

#99

MO-EMT-NAS: Multi-Objective Continuous Transfer of Architectural Knowledge Between Tasks from Different Datasets

Peng Liao, Xilu Wang, Yaochu Jin et al.

neural architecture searchmulti-objective optimizationknowledge transfermodel efficiency+3

#100

Test-Time Fine-Tuning of Image Compression Models for Multi-Task Adaptability

Unki Park, Seongmoon Jeong, Jang Youngchan et al.

CVPR 2025