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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–75 of 3687 papers

Title	Date	Tasks	Status	Hype
MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning	Nov 4, 2023	Multi-Task Learning	CodeCode Available	2
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT	Oct 7, 2023	Audio captioningAutomatic Speech Recognition	CodeCode Available	2
BridgeData V2: A Dataset for Robot Learning at Scale	Aug 24, 2023	Imitation LearningMulti-Task Learning	CodeCode Available	2
TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts	Jul 28, 2023	Long-range modelingMixture-of-Experts	CodeCode Available	2
InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding	Jun 8, 2023	DecoderMulti-Task Learning	CodeCode Available	2
RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning	Apr 9, 2023	BenchmarkingDeep Reinforcement Learning	CodeCode Available	2
Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation	Apr 3, 2023	3D Object DetectionAutonomous Driving	CodeCode Available	2
BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements	Mar 21, 2023	Multi-Task Learning	CodeCode Available	2
Side-channel analysis against ANSSI’s protected AES implementation on ARM: end-to-end attacks with multi-task learning	Mar 10, 2023	Multi-Task LearningSide Channel Analysis	CodeCode Available	2
MAGVIT: Masked Generative Video Transformer	Dec 10, 2022	Multi-Task LearningText-to-Video Generation	CodeCode Available	2
YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception	Aug 24, 2022	Autonomous DrivingDrivable Area Detection	CodeCode Available	2
BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing	Jun 30, 2022	DiversityLanguage Model Evaluation	CodeCode Available	2
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving	May 19, 2022	3D Object DetectionAutonomous Driving	CodeCode Available	2
In-BoXBART: Get Instructions into Biomedical Multi-Task Learning	Apr 15, 2022	Few-Shot LearningMulti-Task Learning	CodeCode Available	2
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark	Mar 21, 2022	3D Lane DetectionAutonomous Driving	CodeCode Available	2
Multi-Task Learning as a Bargaining Game	Feb 2, 2022	Multi-Task Learning	CodeCode Available	2
ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning	Nov 22, 2021	DenoisingMulti-Task Learning	CodeCode Available	2
Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising	May 18, 2021	Multi-Task Learning	CodeCode Available	2
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding	Nov 4, 2020	Multi-Task LearningScene Understanding	CodeCode Available	2
Measuring Massive Multitask Language Understanding	Sep 7, 2020	Elementary MathematicsMulti-task Language Understanding	CodeCode Available	2
AdapterFusion: Non-Destructive Task Composition for Transfer Learning	May 1, 2020	Language ModellingMulti-Task Learning	CodeCode Available	2
A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction	Dec 17, 2019	Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)	CodeCode Available	2
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning	Oct 24, 2019	Meta-LearningMeta Reinforcement Learning	CodeCode Available	2
Towards Real-Time Multi-Object Tracking	Sep 27, 2019	Multi-Object TrackingMultiple Object Tracking	CodeCode Available	2
Multi-Task Learning as Multi-Objective Optimization	Oct 10, 2018	Depth EstimationGeneral Classification	CodeCode Available	2

Show:10 25 50

← PrevPage 3 of 148Next →

All datasets QM9 Cityscapes test NYUv2 OMNIGLOT CelebA UTKFace wireframe dataset

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	PCGrad	∆m%	125.7	—	Unverified
2	CAGrad	∆m%	112.8	—	Unverified
3	IMTL-G	∆m%	77.2	—	Unverified
4	Nash-MTL	∆m%	62	—	Unverified
5	BayesAgg-MTL	∆m%	53.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SwinMTL	mIoU	76.41	—	Unverified
2	Nash-MTL	mIoU	75.41	—	Unverified
3	MultiObjectiveOptimization	mIoU	66.63	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SwinMTL	Mean IoU	58.14	—	Unverified
2	Nash-MTL	Mean IoU	40.13	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Gumbel-Matrix Routing	Average Accuracy	93.52	—	Unverified
2	Mixture-of-Experts	Average Accuracy	92.19	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MGDA-UB	Error	8.25	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BayesAgg-MTL	delta_m	-2.23	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LETR	FH	83.3	—	Unverified