mlsanityData to 7 Oct 2026

RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions

arXiv 2601.10921 ↗First posted 16 Jan 2026cs.CV cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Robust Multi-Task Learning (MTL) is crucial for autonomous systems operating in real-world environments, where adverse weather conditions can severely degrade model performance and reliability. In this paper, we introduce RobuMTL, a novel architecture designed to adaptively address visual degradation by dynamically selecting task-specific hierarchical Low-Rank Adaptation (LoRA) modules and a LoRA expert squad based on input perturbations in a mixture-of-experts fashion. Our framework enables adaptive specialization based on input characteristics, improving robustness across diverse real-world conditions. To validate our approach, we evaluated it on the PASCAL and NYUD-v2 datasets and compared it against single-task models, standard MTL baselines, and state-of-the-art methods. On the PASCAL benchmark, RobuMTL delivers a +2.8% average relative improvement under single perturbations and up to +44.4% under mixed weather conditions compared to the MTL baseline. On NYUD-v2, RobuMTL achieves a +9.7% average relative improvement across tasks. The code is available at GitHub.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 16 Jan 2026.

Builds on

29 of 46 references.

References · 29

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  4. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
  5. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  6. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  7. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  8. 2022Multi-Task Learning as a Bargaining Gamecited by 209
  9. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  10. 2019Attentive Single-Tasking of Multiple Taskscited by 148
  11. 2024MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Expertscited by 144
  12. 2023When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applicationscited by 110
17 more
  1. 2023Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuningcited by 106
  2. 2024Higher Layers Need More LoRA Expertscited by 101
  3. 2022M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designcited by 97
  4. 2024MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learningcited by 63
  5. 2024Multi-Task Dense Prediction via Mixture of Low-Rank Expertscited by 58
  6. 2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 54
  7. 2022JPEG Artifact Correction using Denoising Diffusion Restoration Modelscited by 45
  8. 2021Adversarial Robustness in Multi-Task Learning: Promises and Illusionscited by 17
  9. 2022Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learnerscited by 15
  10. 2024MeteoRA: Multiple-tasks Embedded LoRA for Large Language Modelscited by 14
  11. 2019A CNN-RNN Architecture for Multi-Label Weather Recognitioncited by 13
  12. 2023WeatherProof: A Paired-Dataset Approach to Semantic Segmentation in Adverse Weathercited by 9
  13. 2022Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approachcited by 7
  14. 2020Robust Semantic Segmentation in Adverse Weather Conditions by means of Fast Video-Sequence Segmentationcited by 4
  15. 2023Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditionscited by 4
  16. 2024UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank Adaptationcited by 3
  17. 2024D-YOLO a robust framework for object detection in adverse weather conditionscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
  2. 2024MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning
  3. 2026RoboHarness: A Memory-Augmented Policy Harness for Vision-Language-Action Model Robustness via In-Context Adaptation
  4. 2025JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration
  5. 2025Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning
  6. 2024MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
  7. 2025RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models
  8. 2026ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models