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

Showing 151200 of 3687 papers

TitleStatusHype
Efficient Diffusion Training via Min-SNR Weighting StrategyCode1
DESCN: Deep Entire Space Cross Networks for Individual Treatment Effect EstimationCode1
DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense PredictionCode1
Detecting 32 Pedestrian Attributes for Autonomous VehiclesCode1
Deep Multi-Task Learning for SSVEP Detection and Visual Response MappingCode1
A Large Scale Search Dataset for Unbiased Learning to RankCode1
A Recurrent Vision-and-Language BERT for NavigationCode1
Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with Multi-task LearningCode1
DeepUnifiedMom: Unified Time-series Momentum Portfolio Construction via Multi-Task Learning with Multi-Gate Mixture of ExpertsCode1
Detection-Correction Structure via General Language Model for Grammatical Error CorrectionCode1
Fair Resource Allocation in Multi-Task LearningCode1
DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients with Advanced Nasopharyngeal Carcinoma using Pretreatment PET/CTCode1
Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement LearningCode1
A Knowledge-Enhanced Pretraining Model for Commonsense Story GenerationCode1
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object TrackingCode1
Denoising Task Routing for Diffusion ModelsCode1
360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse NetworkCode1
DaWin: Training-free Dynamic Weight Interpolation for Robust AdaptationCode1
DeepCVA: Automated Commit-level Vulnerability Assessment with Deep Multi-task LearningCode1
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic TransformationsCode1
ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft PromptsCode1
Dual-Domain Coarse-to-Fine Progressive Estimation Network for Simultaneous Denoising, Limited-View Reconstruction, and Attenuation Correction of Cardiac SPECTCode1
AdaRank: Adaptive Rank Pruning for Enhanced Model MergingCode1
Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-ExpertsCode1
Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep LearningCode1
Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal LearningCode1
Allophant: Cross-lingual Phoneme Recognition with Articulatory AttributesCode1
ELIT: Emory Language and Information ToolkitCode1
AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in RecommendationsCode1
Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulasCode1
End-to-end Emotion-Cause Pair Extraction via Learning to LinkCode1
End-to-End Multi-Task Learning with AttentionCode1
Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous ModalitiesCode1
A Unified Object Motion and Affinity Model for Online Multi-Object TrackingCode1
A Unified Span-Based Approach for Opinion Mining with Syntactic ConstituentsCode1
Cyclic Learning: Bridging Image-level Labels and Nuclei Instance SegmentationCode1
Dataless Knowledge Fusion by Merging Weights of Language ModelsCode1
Explain and Predict, and then Predict AgainCode1
A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation OffloadingCode1
Exploiting Shared Representations for Personalized Federated LearningCode1
AV-RIR: Audio-Visual Room Impulse Response EstimationCode1
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective AdaptationCode1
Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic EnvironmentsCode1
Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender SystemCode1
A Multi-Task Deep Learning Framework for Building Footprint SegmentationCode1
A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment AnalysisCode1
Federated Multi-Task Learning under a Mixture of DistributionsCode1
FedHCA2: Towards Hetero-Client Federated Multi-Task LearningCode1
A Multi-task Framework for Infrared Small Target Detection and SegmentationCode1
Deeper Task-Specificity Improves Joint Entity and Relation ExtractionCode1
Show:102550
← PrevPage 4 of 74Next →

Benchmark Results

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