mlsanityData to 7 Oct 2026

Parameter Aware Mamba Model for Multi-task Dense Prediction

arXiv 2511.14503 ↗First posted 18 Nov 2025cs.CVcited by 0

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

Understanding the inter-relations and interactions between tasks is crucial for multi-task dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this work, we introduce a novel decoder-based framework, Parameter Aware Mamba Model (PAMM), specifically designed for dense prediction in multi-task learning setting. Distinct from approaches that employ Transformers to model holistic task relationships, PAMM leverages the rich, scalable parameters of state space models to enhance task interconnectivity. It features dual state space parameter experts that integrate and set task-specific parameter priors, capturing the intrinsic properties of each task. This approach not only facilitates precise multi-task interactions but also allows for the global integration of task priors through the structured state space sequence model (S4). Furthermore, we employ the Multi-Directional Hilbert Scanning method to construct multi-angle feature sequences, thereby enhancing the sequence model's perceptual capabilities for 2D data. Extensive experiments on the NYUD-v2 and PASCAL-Context benchmarks demonstrate the effectiveness of our proposed method. Our code is available at https://github.com/CQC-gogopro/PAMM.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 55 of its 88 references that are in the map. First posted on arXiv 18 Nov 2025.

Builds on

55 of 88 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition26 Mar
  2. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan14 Mar
  3. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model17 Jan

Other references · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  7. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  10. 2024VMamba: Visual State Space Modelcited by 955
  11. 2017A Survey on Multi-Task Learningcited by 838
  12. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
38 more
  1. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 495
  2. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  3. 2024Jamba: A Hybrid Transformer-Mamba Language Modelcited by 390
  4. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  5. 2019Attention Augmented Convolutional Networkscited by 363
  6. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  7. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 230
  8. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  9. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  10. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  11. 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
  12. 2017Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learningcited by 125
  13. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 106
  14. 2022M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designcited by 97
  15. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  16. 2024MedMamba: Vision Mamba for Medical Image Classificationcited by 86
  17. 2021Multi-Task Self-Training for Learning General Representationscited by 85
  18. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  19. 2024MoE-Mamba: Efficient Selective State Space Models with Mixture of Expertscited by 60
  20. 2024Multi-Task Dense Prediction via Mixture of Low-Rank Expertscited by 58
  21. 2014Rigid-Motion Scattering for Texture Classificationcited by 52
  22. 2024Vivim: a Video Vision Mamba for Medical Video Segmentationcited by 51
  23. 2019Many Task Learning with Task Routingcited by 50
  24. 2023TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Expertscited by 45
  25. 2024MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learningcited by 44
  26. 2024BlackMamba: Mixture of Experts for State-Space Modelscited by 37
  27. 2022Multi-Task Learning with Multi-Query Transformer for Dense Predictioncited by 34
  28. 2019Learning Sparse Sharing Architectures for Multiple Taskscited by 31
  29. 2023DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Predictioncited by 27
  30. 2023InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understandingcited by 22
  31. 2024DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Datacited by 18
  32. 2019DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detectioncited by 17
  33. 2025AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentationcited by 15
  34. 2023BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictionscited by 12
  35. 2024Efficient Multitask Dense Predictor via Binarizationcited by 7
  36. 2024SAM-Mamba: Mamba Guided SAM Architecture for Generalized Zero-Shot Polyp Segmentationcited by 7
  37. 2025Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentationcited by 7
  38. 2024Joint-Task Regularization for Partially Labeled Multi-Task Learningcited by 6

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction
  2. 2024MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders
  3. 2024MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders
  4. 2024The Hidden Attention of Mamba Models
  5. 2025Mamba-Adaptor: State Space Model Adaptor for Visual Recognition
  6. 2024Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
  7. 2026B3-Net: Controlled Posterior Bridge Learning for Multi-Task Dense Prediction
  8. 2024A Survey of Mamba