SOTAVerified

Multi-Task Learning

Multi-task learning aims to learn multiple different tasks simultaneously while maximizing performance on one or all of the tasks.

( Image credit: Cross-stitch Networks for Multi-task Learning )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 3687 papers

TitleStatusHype
A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and ApplicationsCode9
Arcee's MergeKit: A Toolkit for Merging Large Language ModelsCode9
Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and BeyondCode7
VITA: Towards Open-Source Interactive Omni Multimodal LLMCode7
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningCode7
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task LearningCode5
MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter ExpertsCode5
YOLOR-Based Multi-Task LearningCode5
CoBa: Convergence Balancer for Multitask Finetuning of Large Language ModelsCode4
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and OpportunitiesCode4
DocRes: A Generalist Model Toward Unifying Document Image Restoration TasksCode4
InternLM-Math: Open Math Large Language Models Toward Verifiable ReasoningCode4
Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language TasksCode4
Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization PerspectiveCode3
DARWIN 1.5: Large Language Models as Materials Science Adapted LearnersCode3
YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem AugmentationCode3
MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-ExpertsCode3
MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsCode3
UCF: Uncovering Common Features for Generalizable Deepfake DetectionCode3
Relational Multi-Task Learning: Modeling Relations between Data and TasksCode3
Zero-shot Entity Linking with Less DataCode3
PETRv2: A Unified Framework for 3D Perception from Multi-Camera ImagesCode3
Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextCode3
Language Models are Few-Shot LearnersCode3
Ludwig: a type-based declarative deep learning toolboxCode3
ERNIE 2.0: A Continual Pre-training Framework for Language UnderstandingCode3
SonicVerse: Multi-Task Learning for Music Feature-Informed CaptioningCode2
Fast and Accurate Blind Flexible DockingCode2
Joint Perception and Prediction for Autonomous Driving: A SurveyCode2
Diffusion-based Visual Anagram as Multi-task LearningCode2
GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual GroundingCode2
radarODE-MTL: A Multi-Task Learning Framework with Eccentric Gradient Alignment for Robust Radar-Based ECG ReconstructionCode2
Tissue Concepts: supervised foundation models in computational pathologyCode2
LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorchCode2
NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG SignalsCode2
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning BenchmarksCode2
RouteFinder: Towards Foundation Models for Vehicle Routing ProblemsCode2
Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-TuningCode2
Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale AttentionCode2
Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model ErasCode2
OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest SearchCode2
EGTR: Extracting Graph from Transformer for Scene Graph GenerationCode2
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task LearningCode2
Volumetric Environment Representation for Vision-Language NavigationCode2
Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-ExpertsCode2
One Train for Two Tasks: An Encrypted Traffic Classification Framework Using Supervised Contrastive LearningCode2
Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm PerspectivesCode2
LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake DetectionCode2
MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task LearningCode2
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style PluginCode2
Show:102550
← PrevPage 1 of 74Next →
All datasetsQM9Cityscapes testNYUv2OMNIGLOTCelebAUTKFacewireframe dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PCGrad∆m%125.7—Unverified
2CAGrad∆m%112.8—Unverified
3IMTL-G∆m%77.2—Unverified
4Nash-MTL∆m%62—Unverified
5BayesAgg-MTL∆m%53.7—Unverified
#ModelMetricClaimedVerifiedStatus
1SwinMTLmIoU76.41—Unverified
2Nash-MTLmIoU75.41—Unverified
3MultiObjectiveOptimizationmIoU66.63—Unverified
#ModelMetricClaimedVerifiedStatus
1SwinMTLMean IoU58.14—Unverified
2Nash-MTLMean IoU40.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Gumbel-Matrix RoutingAverage Accuracy93.52—Unverified
2Mixture-of-ExpertsAverage Accuracy92.19—Unverified
#ModelMetricClaimedVerifiedStatus
1MGDA-UBError8.25—Unverified
#ModelMetricClaimedVerifiedStatus
1BayesAgg-MTLdelta_m-2.23—Unverified
#ModelMetricClaimedVerifiedStatus
1LETRFH83.3—Unverified