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 251300 of 3687 papers

TitleStatusHype
Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with Multi-task LearningCode1
Improved Feature Distillation via Projector EnsembleCode1
Analyzing Multi-Task Learning for Abstractive Text SummarizationCode1
M^3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designCode1
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic ApproachCode1
Continued Pretraining for Better Zero- and Few-Shot PromptabilityCode1
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task modelsCode1
PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in FinanceCode1
Task Compass: Scaling Multi-task Pre-training with Task PrefixCode1
Instruction Tuning for Few-Shot Aspect-Based Sentiment AnalysisCode1
Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based ApproachCode1
GRANITE: A Graph Neural Network Model for Basic Block Throughput EstimationCode1
Causal Inference for Chatting HandoffCode1
Option-Aware Adversarial Inverse Reinforcement Learning for Robotic ControlCode1
CERBERUS: Simple and Effective All-In-One Automotive Perception Model with Multi Task LearningCode1
Neural Graphical ModelsCode1
Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge BasesCode1
MLink: Linking Black-Box Models from Multiple Domains for Collaborative InferenceCode1
Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue SummarizationCode1
Retinal Structure Detection in OCTA Image via Voting-based Multi-task LearningCode1
KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed VideosCode1
Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose EstimationCode1
UFO: Unified Feature OptimizationCode1
Multi-Task Learning for Depression Detection in DialogsCode1
GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source LearningCode1
DESCN: Deep Entire Space Cross Networks for Individual Treatment Effect EstimationCode1
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving ScenesCode1
Learning to Estimate External Forces of Human Motion in VideoCode1
A Large Scale Search Dataset for Unbiased Learning to RankCode1
DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot LearningCode1
Saliency-Regularized Deep Multi-Task LearningCode1
DenseMTL: Cross-task Attention Mechanism for Dense Multi-task LearningCode1
On Privacy and Personalization in Cross-Silo Federated LearningCode1
Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep LearningCode1
A Multi-task Framework for Infrared Small Target Detection and SegmentationCode1
Human Mobility Prediction with Causal and Spatial-constrained Multi-task NetworkCode1
Learning Ego 3D Representation as Ray TracingCode1
RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event ExtractionCode1
PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence UnderstandingCode1
Stochastic Multiple Target Sampling Gradient DescentCode1
FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear ModulationCode1
Multi-Task Learning with Multi-Query Transformer for Dense PredictionCode1
Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming ChallengesCode1
Cascading Residual Graph Convolutional Network for Multi-Behavior RecommendationCode1
ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft PromptsCode1
uGLAD: Sparse graph recovery by optimizing deep unrolled networksCode1
On Measuring Social Biases in Prompt-Based Multi-Task LearningCode1
Wojood: Nested Arabic Named Entity Corpus and Recognition using BERTCode1
Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation AssessmentCode1
UniTE: Unified Translation EvaluationCode1
Show:102550
← PrevPage 6 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