mlsanityData to 7 Oct 2026

MT2ST: Adaptive Multi-Task to Single-Task Learning

arXiv 2406.18038 ↗First posted 26 Jun 2024cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Efficient machine learning (ML) has become increasingly important as models grow larger and data volumes expand. In this work, we address the trade-off between generalization in multi-task learning (MTL) and precision in single-task learning (STL) by introducing the Multi-Task to Single-Task (MT2ST) framework. MT2ST is designed to enhance training efficiency and accuracy in multi-modal tasks, showcasing its value as a practical application of efficient ML.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 26 Jun 2024.

Builds on

23 of 41 references.

References · 23

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  4. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  5. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  6. 2017A Survey on Multi-Task Learningcited by 838
  7. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  8. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  9. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  10. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 526
  11. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
  12. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
11 more
  1. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  2. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  3. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  4. 2019Many Task Learning with Task Routingcited by 50
  5. 2022A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methodscited by 42
  6. 2020A Survey on Large-scale Machine Learningcited by 34
  7. 2024Fair Resource Allocation in Multi-Task Learningcited by 34
  8. 2023Embedding in Recommender Systems: A Surveycited by 19
  9. 2021Neural ranking models for document retrievalcited by 16
  10. 2022The Bearable Lightness of Big Data: Towards Massive Public Datasets in Scientific Machine Learningcited by 2
  11. 2017Multi-task Learning with Gradient Guided Policy Specializationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 3.

16 papers.

Sort:

By area:

  1. 2025FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximationcited by 23
  2. 2025Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healingcited by 10
  3. 2025Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMscited by 9
  4. 2025TinyServe: Query-Aware Cache Selection for Efficient LLM Servingcited by 9
  5. 2025Journey into Automation: Image-Derived Pavement Texture Extraction and Evaluationcited by 7
  6. 2025PiKV: KV Cache Management System for Mixture of Expertscited by 5
  7. 2025Regression and Forecasting of U.S. Stock Returns Based on LSTMcited by 4
  8. 2025Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Modelscited by 1
  9. 2025QuickMerge++: Fast Token Merging with Autoregressive Priorcited by 1
  10. 2026Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planningcited by 1
  11. 2026RUBRIC: Realism--Utility Balanced Ranking for Imbalanced Classificationcited by 1
  12. 2025Towards Robust Nonlinear Subspace Clustering: A Kernel Learning Approachcited by 0
4 more
  1. 2025An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learningcited by 0
  2. 2025Leveraging Large Language Model for Intelligent Log Processing and Autonomous Debugging in Cloud AI Platformscited by 0
  3. 2025Cognitive Load Traces as Symbolic and Visual Accounts of Deep Model Cognitioncited by 0
  4. 2026OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletonscited by 0