@conference{AdaptViG_WACV_2026,

title = {AdaptViG: Adaptive Vision GNN with Exponential Decay Gating},

author = {Mustafa Munir and Md Mostafijur Rahman and Radu Marculescu},

url = {https://arxiv.org/abs/2511.09942},

year  = {2026},

date = {2026-03-02},

booktitle = {2026 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026)},

keywords = {Deep Learning, Deep Learning Architecture, Efficient AI, Featured, Graph Neural Network},

pubstate = {forthcoming},

tppubtype = {conference}

}

@conference{NeuS-QA,

title = {NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning},

author = {Sahil Shah and S P Sharan and Harsh Goel and Minkyu Choi and Mustafa Munir and Manvik Pasula and Radu Marculescu and Sandeep Chinchali},

url = {https://arxiv.org/abs/2509.18041},

year  = {2026},

date = {2026-01-15},

urldate = {2026-01-15},

booktitle = {AAAI Conference on Artificial Intelligence 2026},

keywords = {Deep Learning, Efficient AI, Featured, Generative AI},

pubstate = {forthcoming},

tppubtype = {conference}

}

@conference{SearchViG_LOG_2025,

title = {SearchViG: Optimal Vision GNNs via Ramanujan Spectral Optimization},

author = {Mustafa Munir and Md Mostafijur Rahman and Xiwen Wei and Yuedong Yang and Radu Marculescu},

url = {https://openreview.net/pdf?id=cmEzgaYIJC},

year  = {2025},

date = {2025-12-15},

booktitle = {The Fourth Learning on Graphs Conference (LOG 2025)},

keywords = {Deep Learning, Deep Learning Architecture, Dynamic networks, Efficient AI, Featured, Graph Neural Network},

pubstate = {forthcoming},

tppubtype = {conference}

}

@conference{VCMamba_ICCV_2025,

title = {VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation},

author = {Mustafa Munir and Alex Zhang and Radu Marculescu},

url = {https://arxiv.org/abs/2509.04669},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {Proceedings of the International Conference on Computer Vision (ICCV 2025) Workshops},

abstract = {Recent advances in Vision Transformers (ViTs) and State Space Models (SSMs) have challenged the dominance of Convolutional Neural Networks (CNNs) in computer vision. ViTs excel at capturing global context, and SSMs like Mamba offer linear complexity for long sequences, yet they do not capture fine-grained local features as effectively as CNNs. Conversely, CNNs possess strong inductive biases for local features but lack the global reasoning capabilities of transformers and Mamba. To bridge this gap, we introduce VCMamba, a novel vision backbone that integrates the strengths of CNNs and multi-directional Mamba SSMs. VCMamba employs a convolutional stem and a hierarchical structure with convolutional blocks in its early stages to extract rich local features. These convolutional blocks are then processed by later stages incorporating multi-directional Mamba blocks designed to efficiently model long-range dependencies and global context. This hybrid design allows for superior feature representation while maintaining linear complexity with respect to image resolution. We demonstrate VCMamba’s effectiveness through extensive experiments on ImageNet-1K classification and ADE20K semantic segmentation. Our VCMamba-B achieves 82.6% top-1 accuracy on ImageNet-1K, surpassing PlainMamba-L3 by 0.3% with 37% fewer parameters, and outperforming Vision GNN-B by 0.3% with 64% fewer parameters. Furthermore, VCMamba-B obtains 47.1 mIoU on ADE20K, exceeding EfficientFormer-L7 by 2.0 mIoU while utilizing 62% fewer parameters. Code is available at https://github.com/Wertyuui345/VCMamba.},

keywords = {Deep Learning Architecture, Efficient AI, Featured, Lightweight Architecture, Model Compression \& Optimization},

pubstate = {published},

tppubtype = {conference}

}

@conference{efficientmednext@rahman,

title = {EfficientMedNeXt: Multi-Receptive Dilated Convolutions for Medical Image Segmentation},

author = {Md Mostafijur Rahman and Mustafa Munir and Radu Marculescu},

url = {https://link.springer.com/chapter/10.1007/978-3-032-04965-0_19},

year  = {2025},

date = {2025-09-23},

urldate = {2025-09-23},

publisher = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},

abstract = {In this work, we introduce EfficientMedNeXt\textemdasha lightweight, high-performance segmentation architecture developed through a two-phase optimization process applied to the MedNeXt architecture. To this end, we first optimize the decoder by reducing the high-resolution redundancy and unifying the decoder channels across stages for enhanced efficiency. Then, we introduce a new Dilated Multi-Receptive Field Block (DMRFB) to capture the multi-scale spatial context efficiently without increasing the kernel sizes and relying on the channel expansion convolutions. Extensive evaluations on BTCV, FeTA, and MSD show that EfficientMedNeXt-L achieves 87.0% DICE score on BTCV (+1.04% over MedNeXt-L) with 96.5% fewer parameters and 77.03% lower FLOPs. In addition, EfficientMedNeXt-S offers comparable DICE score, improved HD95, and 78.1% higher throughput while reducing parameters by 98.5% and FLOPs by 95%. These results demonstrate EfficientMedNeXt’s efficiency and accuracy, making it well-suited for real-world clinical applications. Code will be released upon acceptance.},

keywords = {3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Inference, Featured, Medical Image Segmentation},

pubstate = {published},

tppubtype = {conference}

}

@conference{prime@rahman,

title = {Training-Free Dataset Pruning for Polyp Segmentation via Community Detection in Similarity Networks},

author = {Md Mostafijur Rahman and Radu Marculescu},

url = {https://openreview.net/pdf?id=VQX4B2A2Y0},

year  = {2025},

date = {2025-07-09},

urldate = {2025-07-09},

publisher = {Medical Imaging with Deep Learning (MIDL) },

abstract = {Recent advances in deep learning have been driven by the availability of larger datasets and more complex models; however, this progress comes at the expense of substantial computational and annotation costs. To address these issues, we introduce a novel, training-free dataset pruning method,PRIME, targeting polyp segmentation in medical imaging. To this end, PRIME constructs a similarity network among the images in the target dataset and then applies community detection to retain a much smaller, yet representative subset of images from the original dataset. Unlike existing methods that require model training for dataset pruning, our PRIME completely avoids model training, thus significantly reducing computational demands. The reduction in the training dataset cuts 56.2% data annotation costs and enables 2.3× faster training of polyp segmentation models, with only a 0.5% drop in the DICE score. Consequently, our PRIME enables efficient training, fine-tuning, and domain adaptation across medical centers, thus offering a cost-effective solution for deep learning in polyp segmentation.},

keywords = {Community Detection, Dataset Pruning, Featured, Medical Image Segmentation, Polyp segmentation, Training-free},

pubstate = {published},

tppubtype = {conference}

}

@conference{effidec3d@rahman,

title = {EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation},

author = {Md Mostafijur Rahman and Radu Marculescu},

url = {https://openaccess.thecvf.com/content/CVPR2025/html/Rahman_EffiDec3D_An_Optimized_Decoder_for_High-Performance_and_Efficient_3D_Medical_CVPR_2025_paper.html},

year  = {2025},

date = {2025-06-10},

urldate = {2025-06-10},

publisher = {Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)},

abstract = {Recent 3D deep networks such as SwinUNETR, SwinUNETRv2, and 3D UX-Net have shown promising performance by leveraging self-attention and large-kernel convolutions to capture the volumetric context. However, their substantial computational requirements limit their use in real-time and resource-constrained environments. The high #FLOPs and #Params in these networks stem largely from complex decoder designs with high-resolution layers and

excessive channel counts. In this paper, we propose EffiDec3D, an optimized 3D decoder that employs a channel reduction strategy across all decoder stages, which sets the number of channels to the minimum needed for accurate feature representation. Additionally, EffiDec3D removes the high-resolution layers when their contribution

to segmentation quality is minimal. Our optimized EffiDec3D decoder achieves a 96.4% reduction in #Params and a 93.0% reduction in #FLOPs compared to the decoder of original 3D UX-Net. Similarly, for SwinUNETR and SwinUNETRv2 (which share an identical decoder), we observe reductions of 94.9% in #Params and 86.2% in #FLOPs. Our extensive experiments on 12 different medical imaging tasks confirm that EffiDec3D not only significantly reduces the computational demands, but also maintains a performance level comparable to original models, thus establishing a new standard for efficient 3D medical image segmentation. Our implementation is available at https://github.com/SLDGroup/EffiDec3D.},

keywords = {3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Decoder, Featured, Medical Image Segmentation},

pubstate = {published},

tppubtype = {conference}

}

@conference{RapidNet_WACV_2025,

title = {RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone},

author = {Mustafa Munir and Md Mostafijur Rahman and Radu Marculescu},

url = {https://ieeexplore.ieee.org/document/10943953},

year  = {2025},

date = {2025-03-03},

urldate = {2025-03-03},

booktitle = {2025 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)},

journal = {2025 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)},

keywords = {Deep Learning Architecture, Edge AI, Efficient Inference, Featured, Model Compression \& Optimization},

pubstate = {published},

tppubtype = {conference}

}

@conference{tips_icml2023,

title = {TIPS: Topologically Important Path Sampling for Anytime Neural Networks},

author = {Li, Guihong and Bhardwaj, Kartikeya and Yang, Yuedong and Marculescu, Radu},

url = {https://arxiv.org/abs/2305.08021},

year  = {2023},

date = {2023-07-15},

urldate = {2023-07-15},

booktitle = {International Conference on Machine Learning (ICML)},

keywords = {Dynamic networks, Edge AI, Featured, Internet of Things, Model Compression \& Optimization, Neural Architecture Search},

pubstate = {published},

tppubtype = {conference}

}

@conference{iclr2023,

title = {ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients},

author = {Guihong Li and Yuedong Yang and Kartikeya Bhardwaj and Radu Marculescu },

url = {https://arxiv.org/pdf/2301.11300.pdf},

year  = {2023},

date = {2023-01-26},

urldate = {2023-01-26},

booktitle = {International Conference on Learning Representations (ICLR)},

keywords = {Edge AI, Featured, Neural Architecture Search},

pubstate = {published},

tppubtype = {conference}

}

@conference{cvpr2021,

title = {How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?},

author = {Bhardwaj, Kartikeya. and Li, Guihong. and Marculescu, Radu. },

url = {https://arxiv.org/pdf/1910.00780.pdf},

year  = {2021},

date = {2021-06-12},

urldate = {2021-06-12},

booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

pages = {13498-13507},

keywords = {Featured, Model Compression \& Optimization, Neural Architecture Search},

pubstate = {published},

tppubtype = {conference}

}