# Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras

arXiv: https://arxiv.org/abs/2404.18961 · HTML: https://mlsanity.com/paper/2404.18961/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2024.

## Built on by (most cited first, 26 of 26)

- [Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond](https://mlsanity.com/paper/2501.10945/) (2025)
- [Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning](https://mlsanity.com/paper/2410.14633/) (2024)
- [From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning](https://mlsanity.com/paper/2501.19067/) (2025)
- [FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization](https://mlsanity.com/paper/2503.12649/) (2025)
- [HM3: Heterogeneous Multi-Class Model Merging](https://mlsanity.com/paper/2409.19173/) (2024)
- [Parameter-Efficient Interventions for Enhanced Model Merging](https://mlsanity.com/paper/2412.17023/) (2024)
- [Mitigating Domain Drift in Multi Species Segmentation with DINOv2: A Cross-Domain Evaluation in Herbicide Research Trials](https://mlsanity.com/paper/2508.07514/) (2025)
- [One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning](https://mlsanity.com/paper/2509.07945/) (2025)
- [Generalizable and Efficient Automated Scoring with a Knowledge-Distilled Multi-Task Mixture-of-Experts](https://mlsanity.com/paper/2511.17601/) (2025)
- [Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences](https://mlsanity.com/paper/2409.07268/) (2024)
- [Exploring Model Kinship for Merging Large Language Models](https://mlsanity.com/paper/2410.12613/) (2024)
- [3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding](https://mlsanity.com/paper/2511.20646/) (2025)
- [Stealthy Multi-Task Adversarial Attacks](https://mlsanity.com/paper/2411.17936/) (2024)
- [Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling](https://mlsanity.com/paper/2505.24185/) (2025)
- [SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation](https://mlsanity.com/paper/2507.07883/) (2025)
- [Surgical Video Understanding with Label Interpolation](https://mlsanity.com/paper/2509.18802/) (2025)
- [Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation](https://mlsanity.com/paper/2509.19602/) (2025)
- [EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence](https://mlsanity.com/paper/2511.10834/) (2025)
- [FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning](https://mlsanity.com/paper/2605.09355/) (2026)
- [ColNet: Collaborative Optimization in Decentralized Federated Multi-task Learning Systems](https://mlsanity.com/paper/2501.10347/) (2025)
- [Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution](https://mlsanity.com/paper/2501.19316/) (2025)
- [Cascaded Transfer: Learning Many Tasks under Budget Constraints](https://mlsanity.com/paper/2601.21513/) (2026)
- [Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Auxiliary Graphs](https://mlsanity.com/paper/2602.06700/) (2026)
- [Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent](https://mlsanity.com/paper/2602.19837/) (2026)
- [PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization](https://mlsanity.com/paper/2606.03444/) (2026)
- [Gradient Surgery for Physics-Informed Neural Networks](https://mlsanity.com/paper/2609.30966/) (2026)

## Abstract (arXiv)

MTL is a learning paradigm that effectively leverages both task-specific and shared information to address multiple related tasks simultaneously. In contrast to STL, MTL offers a suite of benefits that enhance both the training process and the inference efficiency. MTL's key advantages encompass streamlined model architecture, performance enhancement, and cross-domain generalizability. Over the past twenty years, MTL has become widely recognized as a flexible and effective approach in various fields, including CV, NLP, recommendation systems, disease prognosis and diagnosis, and robotics. This survey provides a comprehensive overview of the evolution of MTL, encompassing the technical aspects of cutting-edge methods from traditional approaches to deep learning and the latest trend of pretrained foundation models. Our survey methodically categorizes MTL techniques into five key areas: regularization, relationship learning, feature propagation, optimization, and pre-training. This categorization not only chronologically outlines the development of MTL but also dives into various specialized strategies within each category. Furthermore, the survey reveals how the MTL evolves from handling a fixed set of tasks to embracing a more flexible approach free from task or modality constraints. It explores the concepts of task-promptable and -agnostic training, along with the capacity for ZSL, which unleashes the untapped potential of this historically coveted learning paradigm. Overall, we hope this survey provides the research community with a comprehensive overview of the advancements in MTL from its inception in 1997 to the present in 2023. We address present challenges and look ahead to future possibilities, shedding light on the opportunities and potential avenues for MTL research in a broad manner. This project is publicly available at https://github.com/junfish/Awesome-Multitask-Learning.