Publications

@inproceedings{agiagenticintelligencean2027,
  title     = {AGI: Agentic Intelligence and Latent Lookahead for Robust Manipulation},
  author    = {Md Selim Sarowar, Taeung Kang, Soon Kwon, and Sungho Kim},
  booktitle = {IEEE International Conference on Robotics and Automation},
  year      = {2027}
  % TODO: verify entry type, add volume/pages/doi
}

@inproceedings{learningmanipulationsuff2027,
  title     = {Learning Manipulation-Sufficient Representations via Outcome Bottlenecks},
  author    = {Md Selim Sarowar and Sungho Kim},
  booktitle = {IEEE International Conference on Robotics and Automation},
  year      = {2027}
  % TODO: verify entry type, add volume/pages/doi
}

@inproceedings{Sarowar_2026_BMVC,
author    = {Md Selim Sarowar and Md Tanvir Islam and Sungho Kim and Sangtae Ahn},
title     = {GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model},
booktitle = {37th British Machine Vision Conference 2026, {BMVC} 2026, Lancaster, UK, November 23-26, 2026},
publisher = {BMVA},
year      = {2026},
url       = {https://bmva-archive.org.uk/bmvc/2026/assets/papers/Paper_121/paper.pdf}
}

@inproceedings{Ashikuzzaman_2026_BMVC,
author    = {Ashikuzzaman and Md Selim Sarowar and Md Tanvir Islam and Sangtae Ahn and Khan Muhammad},
title     = {HNH40K: A Robust Dataset and Risk-Weighted Learning for Hand Filtering},
booktitle = {37th British Machine Vision Conference 2026, {BMVC} 2026, Lancaster, UK, November 23-26, 2026},
publisher = {BMVA},
year      = {2026},
url       = {https://bmva-archive.org.uk/bmvc/2026/assets/papers/Paper_652/paper.pdf}
}

@article{202606.1149,
	doi = {10.20944/preprints202606.1149.v1},
	url = {https://doi.org/10.20944/preprints202606.1149.v1},
	year = 2026,
	month = {June},
	publisher = {Preprints},
	author = {Md Selim Sarowar},
	title = {What Matters: Datasets or Robust Frameworks in Modern Robot Learning?},
	journal = {Preprints}
}

@inproceedings{
sarowar2026gstvla,
title={{GSTVLA}: Structured Gaussian Spatial Tokens for 3D Depth-Aware Vision-Language-Action Models},
author={Md Selim Sarowar and Sungho Kim},
booktitle={The 6th Muslims in ML (MusIML) Workshop at ICML 2026},
year={2026},
url={https://openreview.net/forum?id=J57nR3hyAd}
}

@ARTICLE{11400555,
  author={Sarowar, Md Selim and Alnaasan, Manar and Kim, Sungho},
  journal={IEEE Access}, 
  title={C3G-VM6D: Data-Efficient C3G Vision Model Aided 6D Pose Estimation Based on RGB-D Data}, 
  year={2026},
  volume={14},
  number={},
  pages={34223-34238},
  keywords={Pose estimation;Transformers;Point cloud compression;Three-dimensional displays;Probabilistic logic;Training;Visualization;Uncertainty;Foundation models;Feature extraction;Vision foundation model;cross-modal fusion;compact 3D Gaussian (C3G);vision transformer (ViT);6D object pose estimation;3D point cloud},
  doi={10.1109/ACCESS.2026.3666439}}

@article{alnaasan2026fusionvlmgait,
  title={Fusion VLM-Gait: RGB-D fusion in vision-language models for explainable multi-task Parkinsonian gait analysis},
  author={Alnaasan, Manar and Sarowar, Md Selim and Kim, Sungho},
  journal={Scientific Reports},
  year={2026},
  publisher={Nature Publishing Group},
  doi={10.1038/s41598-026-67440-x},
  url={https://www.nature.com/articles/s41598-026-67440-x}
}

@article{visionlanguageactionandv2026,
  title     = {Vision-Language-Action and Vision Language Models for Robot Manipulation: A Comprehensive Review Towards Real-World Applications},
  author    = {Md Selim Sarowar and Sungho Kim},
  journal = {Artificial Intelligence Review},
  year      = {2026}
  % TODO: verify entry type, add volume/pages/doi
}

@INPROCEEDINGS{11632566,
  author={Sarowar, Md Selim and Islam, Md Tanvir and Nuruzzaman, Md. and Islam Mozumder, Md Ariful},
  booktitle={2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET)},
  title={Dependency-Aware Reliable Orchestration for Smart-IoT Control with Reasoning-Aligned LLMs},
  year={2026},
  volume={},
  number={},
  pages={1-6},
  keywords={Modeling;Printing;Internet of Things;Planning;Learning (artificial intelligence);Large language models;Feedback;Training;Safety;Application programming interfaces;Large language models;dependency-aware orchestration;reinforcement learning from execution feedback;smart IoT;edge inference;structured generation;plan verification;chain-of-thought},
  doi={10.1109/ICECET65726.2026.11632566}}

@inproceedings{vfmvlmvisionfoundationmo2025,
  title     = {VFM-VLM: Vision Foundation Model and Vision Language Model based Visual Comparison for 3D Pose Estimation},
  author    = {Md Selim Sarowar and Sungho Kim},
  booktitle = {Institute of Electronics and Information Engineers Conference, South Korea},
  year      = {2025}
  % TODO: verify entry type, add volume/pages/doi
}

@inproceedings{vlm6dvlmbased6dofposeest2025,
  title     = {VLM6D: VLM based 6DoF Pose Estimation based on RGB-D Images},
  author    = {Md Selim Sarowar and Sungho Kim},
  booktitle = {Institute of Electronics and Information Engineers Conference, South Korea},
  year      = {2025}
  % TODO: verify entry type, add volume/pages/doi
}

@article{handgesturerecognitionsy2025,
  title     = {Hand Gesture Recognition Systems: A Review of Methods, Datasets, and Emerging Trends},
  author    = {Md Selim Sarowar, Nur E Jannatul Farjana, et al.},
  journal = {International Journal of Computer Applications},
  year      = {2025}
  % TODO: verify entry type, add volume/pages/doi
}

@inproceedings{improvementofdenoisingin2022,
  title     = {Improvement of Denoising in Images Using Generic Image Denoising Network (GID Net)},
  author    = {Md Selim Sarowar, Kaustav Dutta, and Rasmita Lenka},
  booktitle = {IEEE 2nd International Conference on Applied Electromagnetics, Signal Processing and Communication (AESPC), Nov. 2021},
  year      = {2022}
  % TODO: verify entry type, add volume/pages/doi
}