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 51–100 of 3687 papers

TitleStatusHype
MFTCoder: Boosting Code LLMs with Multitask Fine-TuningCode2
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPTCode2
BridgeData V2: A Dataset for Robot Learning at ScaleCode2
TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-ExpertsCode2
InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene UnderstandingCode2
RoboPianist: Dexterous Piano Playing with Deep Reinforcement LearningCode2
Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth EstimationCode2
BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological MeasurementsCode2
Side-channel analysis against ANSSI’s protected AES implementation on ARM: end-to-end attacks with multi-task learningCode2
MAGVIT: Masked Generative Video TransformerCode2
YOLOPv2: Better, Faster, Stronger for Panoptic Driving PerceptionCode2
BigBIO: A Framework for Data-Centric Biomedical Natural Language ProcessingCode2
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous DrivingCode2
In-BoXBART: Get Instructions into Biomedical Multi-Task LearningCode2
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane BenchmarkCode2
Multi-Task Learning as a Bargaining GameCode2
ExT5: Towards Extreme Multi-Task Scaling for Transfer LearningCode2
Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display AdvertisingCode2
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingCode2
Measuring Massive Multitask Language UnderstandingCode2
AdapterFusion: Non-Destructive Task Composition for Transfer LearningCode2
A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term ExtractionCode2
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement LearningCode2
Towards Real-Time Multi-Object TrackingCode2
Multi-Task Learning as Multi-Objective OptimizationCode2
Non-Contact Health Monitoring During Daily Personal Care RoutinesCode1
StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic DatasetsCode1
CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi SensingCode1
Prot2Token: A Unified Framework for Protein Modeling via Next-Token PredictionCode1
Hierarchical Document Refinement for Long-context Retrieval-augmented GenerationCode1
MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving PerceptionCode1
AdaRank: Adaptive Rank Pruning for Enhanced Model MergingCode1
VADMamba: Exploring State Space Models for Fast Video Anomaly DetectionCode1
PAVE: Patching and Adapting Video Large Language ModelsCode1
M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous DrivingCode1
REF-VLM: Triplet-Based Referring Paradigm for Unified Visual DecodingCode1
Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech RepresentationsCode1
UnPuzzle: A Unified Framework for Pathology Image AnalysisCode1
R-LoRA: Random Initialization of Multi-Head LoRA for Multi-Task LearningCode1
LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy ControlCode1
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic TransformationsCode1
A Multi-Task Learning Approach to Linear Multivariate ForecastingCode1
Combinatorial Optimization Perspective based Framework for Multi-behavior RecommendationCode1
Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential RecommendationCode1
Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech RepresentationCode1
TimberVision: A Multi-Task Dataset and Framework for Log-Component Segmentation and Tracking in Autonomous Forestry OperationsCode1
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous LearningCode1
Modeling Multi-Task Model Merging as Adaptive Projective Gradient DescentCode1
STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy LearningCode1
Revisiting Weight Averaging for Model MergingCode1
Show:102550
← PrevPage 2 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