# RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions

arXiv: https://arxiv.org/abs/2601.10921 · HTML: https://mlsanity.com/paper/2601.10921/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 29 of 29)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions](https://mlsanity.com/paper/2111.14813/) (2021)
- [PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing](https://mlsanity.com/paper/1805.04409/) (2018)
- [Multi-Task Learning as a Bargaining Game](https://mlsanity.com/paper/2202.01017/) (2022)
- [MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning](https://mlsanity.com/paper/2001.06902/) (2020)
- [Attentive Single-Tasking of Multiple Tasks](https://mlsanity.com/paper/1904.08918/) (2019)
- [MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts](https://mlsanity.com/paper/2404.15159/) (2024)
- [When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications](https://mlsanity.com/paper/2310.18339/) (2023)
- [Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning](https://mlsanity.com/paper/2312.12379/) (2023)
- [Higher Layers Need More LoRA Experts](https://mlsanity.com/paper/2402.08562/) (2024)
- [M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design](https://mlsanity.com/paper/2210.14793/) (2022)
- [MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning](https://mlsanity.com/paper/2402.11260/) (2024)
- [Multi-Task Dense Prediction via Mixture of Low-Rank Experts](https://mlsanity.com/paper/2403.17749/) (2024)
- [TAPE: Task-Agnostic Prior Embedding for Image Restoration](https://mlsanity.com/paper/2203.06074/) (2022)
- [JPEG Artifact Correction using Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2209.11888/) (2022)
- [Adversarial Robustness in Multi-Task Learning: Promises and Illusions](https://mlsanity.com/paper/2110.15053/) (2021)
- [MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models](https://mlsanity.com/paper/2405.13053/) (2024)
- [Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners](https://mlsanity.com/paper/2212.08066/) (2022)
- [A CNN-RNN Architecture for Multi-Label Weather Recognition](https://mlsanity.com/paper/1904.10709/) (2019)
- [WeatherProof: A Paired-Dataset Approach to Semantic Segmentation in Adverse Weather](https://mlsanity.com/paper/2312.09534/) (2023)
- [Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approach](https://mlsanity.com/paper/2210.05626/) (2022)
- [Robust Semantic Segmentation in Adverse Weather Conditions by means of Fast Video-Sequence Segmentation](https://mlsanity.com/paper/2007.00290/) (2020)
- [Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions](https://mlsanity.com/paper/2303.14115/) (2023)
- [UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank Adaptation](https://mlsanity.com/paper/2409.20197/) (2024)
- [D-YOLO a robust framework for object detection in adverse weather conditions](https://mlsanity.com/paper/2403.09233/) (2024)

## Built on by (most cited first, 1 of 1)

- [DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identification](https://mlsanity.com/paper/2607.16644/) (2026)

## 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.