Advanced Vision & Intelligent Systems (AVIS) Research Lab

Publications

Journal articles, conference papers, and preprints by Dr. Md Mehedi Hasan and the AVIS Lab from 2022 to the present, newest first. Use the search box to filter by title, author, venue, or year. For citation counts and the full archive, including earlier work on 3D video quality and wheat phenotyping, see the Google Scholar profile.

Google Scholar profile
Research areas & highlights

Jump to: 2026 · 2025 · 2024 · 2023 · 2022

2026

Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning
Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?
Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque, Shifat E Arman, Md Mehedi Hasan
arXiv  ·  30 Sep 2026  ·  arxiv:2609.39901
Shows that in offline goal-conditioned RL the agent’s state representation, not the goal representation, is the real bottleneck; simple random Fourier positional encodings substantially improve performance on the hardest OGBench navigation tasks.
arXiv
reinforcement-learning
GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences
GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences
Abdul Monaf Chowdhury, MD Sameer Iqbal Chowdhury, Shifat E Arman, Md Mehedi Hasan
arXiv  ·  27 Sep 2026  ·  arxiv:2609.33259
GTRL (Grounded Transitive RL) — an offline goal-conditioned value-learning algorithm that grounds divide-and-conquer updates with a one-step temporal-difference target, so every state–goal pair receives an update. Achieves the highest average success rate across nineteen OGBench tasks spanning stochastic, deterministic, and stitching environments.
arXiv
reinforcement-learning
Thinking Like a Botanist: Challenging Multimodal Language Models with Intent Driven Chain-of-Inquiry
Thinking Like a Botanist: Challenging Multimodal Language Models with Intent Driven Chain-of-Inquiry
Syed Nazmus Sakib, Nafiul Haque, Shahrear Bin Amin, Hasan Muhammad Abdullah, Md Mehedi Hasan, Mohammad Zabed Hossain, Shifat E. Arman
Findings of the Association for Computational Linguistics: ACL 2026  ·  22 Apr 2026  ·  doi:10.18653/v1/2026.findings-acl.1741
Findings of ACL 2026. Introduces PlantInquiryVQA, a benchmark of 24,950 expert-curated plant images and 138,068 question–answer pairs for multi-step, intent-driven visual reasoning in plant disease diagnosis.
ACL Anthology
arXiv
vision-language-models plant-phenomics
VLM-Nav: Mapless UAV navigation using monocular vision driven by vision-language models
VLM-Nav: Mapless UAV navigation using monocular vision driven by vision-language models
Gobinda Chandra Sarker, AKM Azad, Sejuti Rahman, Md Mehedi Hasan
PLOS One  ·  03 Apr 2026  ·  doi:10.1371/journal.pone.0345778
Mapless obstacle avoidance for UAVs from a single monocular camera. RGB frames are converted to depth maps with DepthAnything-V2, and a vision-language model reasons over them to choose the next manoeuvre.
PLOS One
uav vision-language-models
FA-EEGNet: Enhancing EEGNet with Frequency-Adaptive Kernels for the classification of stroke rehabilitation movements
FA-EEGNet: Enhancing EEGNet with Frequency-Adaptive Kernels for the classification of stroke rehabilitation movements
Milakul Hasana Mim, Debjoty Roy Pranto, Md Mehedi Hasan
2026 5th International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE)  ·  29 Jan 2026  ·  doi:10.1109/ICECTE69292.2026.11429349
biomedical-signals
IG-CNN: An Information-Geometric Model for Automated Knee Osteoporosis Diagnosis from X-ray Images
IG-CNN: An Information-Geometric Model for Automated Knee Osteoporosis Diagnosis from X-ray Images
Mirza Afnan Islam, Aniruddha Majumder, Md Mehedi Hasan
2026 5th International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE)  ·  29 Jan 2026  ·  doi:10.1109/ICECTE69292.2026.11429443
medical-imaging
AGL Loss: Optimizing Binary Classification by Asymmetric Generalized Logarithmic Loss Function with Statistical Validation
AGL Loss: Optimizing Binary Classification by Asymmetric Generalized Logarithmic Loss Function with Statistical Validation
Md. Mahmudul Hasan, Md Mehedi Hasan, Shifat E Arman, AKM Azad
SSRN Preprint  ·  01 Jan 2026  ·  doi:10.2139/ssrn.6484120
Under review at IEEE Transactions on Neural Networks and Learning Systems.
machine-learning
SPARK: A Stochastic Optimizer for Fast Convergence in Neural Network
SPARK: A Stochastic Optimizer for Fast Convergence in Neural Network
Md. Mahmudul Hasan, AKM Azad, Md Mehedi Hasan
SSRN Preprint  ·  01 Jan 2026  ·  doi:10.2139/ssrn.6556339
machine-learning
VLM-Driven Intelligence for Autonomous UAV Navigation: A Cross-Modal Benchmarking Framework with Sim-to-Real Evaluation
VLM-Driven Intelligence for Autonomous UAV Navigation: A Cross-Modal Benchmarking Framework with Sim-to-Real Evaluation
Abyead Zarif Hassan, Samiha Tarannum Noor, AKM Azad, Md Mehedi Hasan
SSRN Preprint  ·  01 Jan 2026  ·  doi:10.2139/ssrn.7374301
A cross-modal UAV navigation framework that fuses monocular depth with vision-language models and issues MAVLink commands. It benchmarks six VLMs in simulation and flight-tests the best candidates on a Pixhawk 6C quadrotor.
uav vision-language-models
Beyond Euclidean Attention: Information-Geometric Deep Learning for Automated Bone Health Classification from Knee Radiographs
Beyond Euclidean Attention: Information-Geometric Deep Learning for Automated Bone Health Classification from Knee Radiographs
Mirza Afnan Islam, Aniruddha Majumder, Md Mehedi Hasan
SSRN Preprint  ·  01 Jan 2026  ·  doi:10.2139/ssrn.7524474
medical-imaging
Directional Spatial-Graph Byte Pair Encoding: Non-Neural Visual Tokenization via Thermodynamic Free Energy Minimization
Directional Spatial-Graph Byte Pair Encoding: Non-Neural Visual Tokenization via Thermodynamic Free Energy Minimization
Md. Mahmudul Hasan, Md Mehedi Hasan
SSRN Preprint  ·  01 Jan 2026  ·  doi:10.2139/ssrn.7671942
A deterministic, non-neural visual tokenizer that adapts Byte Pair Encoding to images by merging adjacent patches along a planar graph, with formal guarantees on the resulting visual tokens.
computer-vision

2025

Exploring celestial classification: Astrophysical features-guided machine learning for spectral and morphological analysis
Exploring celestial classification: Astrophysical features-guided machine learning for spectral and morphological analysis
Md. Fairuz Siddiquee, Md Mehedi Hasan, Shifat E. Arman, Md. Shahedul Islam, AKM Azad
Astronomy and Computing  ·  29 Dec 2025  ·  doi:10.1016/j.ascom.2025.101048
machine-learning
Cotton seedling monitoring and growth stage classification integrating deep learning and feature engineering
Cotton seedling monitoring and growth stage classification integrating deep learning and feature engineering
Hasan Muhammad Abdullah, Muhaiminul Islam, Md. Shahinul Islam, Sudip Sen, Abdul Kaium Tuhin, Shifat E. Arman, Md Mehedi Hasan
Smart Agricultural Technology  ·  01 Dec 2025  ·  doi:10.1016/j.atech.2025.101619
A high-throughput phenotyping framework combining SeedlingNet, a lightweight residual CNN trained on UAV and ground-level imagery, with a biologically grounded Composite Stress Index to classify cotton growth stages and flag at-risk seedlings early.
plant-phenomics precision-agriculture
Enhancing Histological Cancer Cell Detection: Integrating XAI with Deep Learning for Improved Accuracy, Interpretability, and Clinical Trust
Enhancing Histological Cancer Cell Detection: Integrating XAI with Deep Learning for Improved Accuracy, Interpretability, and Clinical Trust
Apurba Roy, Shamaeta Paul Gupta, Muhaiminul Islam, Shifat E. Arman, AKM Azad, Naif Alotaibi, Asmaa Soliman Al-Moisheer, Salem Alyami, Md. Salahuddin Shah, Md Mehedi Hasan
Research Square Preprint  ·  21 Nov 2025  ·  doi:10.21203/rs.3.rs-8157817/v1
An ensemble of CNNs combined with super-resolution and explainable-AI methods (Grad-CAM, SHAP, LIME) for interpretable histological cancer cell detection.
medical-imaging explainable-ai
Counting Through Occlusion: Framework for Open World Amodal Counting
Counting Through Occlusion: Framework for Open World Amodal Counting
Safaeid Hossain Arib, Rabeya Akter, Abdul Monaf Chowdhury, Md Jubair Ahmed Sourov, Md Mehedi Hasan
arXiv  ·  16 Nov 2025  ·  arxiv:2511.12702
CountOCC — an amodal counting framework that reconstructs the features of occluded objects using hierarchical multimodal guidance, so objects hidden behind occluders are still counted.
arXiv
computer-vision
Development of an IoT-driven deep learning framework for smart energy prediction in commercial buildings
Development of an IoT-driven deep learning framework for smart energy prediction in commercial buildings
Gobinda Chandra Sarker, Md Mehedi Hasan, Md. Rakibul Hoque, Md. Khashrul Alam, M. Helal Uddin Ahmed
Journal of Building Engineering  ·  01 Oct 2025  ·  doi:10.1016/j.jobe.2025.113315
An IoT-driven deep learning framework for predicting energy consumption in commercial buildings.
iot deep-learning
SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases
SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases
Shifat E. Arman, Hasan Muhammad Abdullah, Syed Nazmus Sakib, RM Saiem, Shamima Nasrin Asha, Md Mehedi Hasan, Shahrear Bin Amin, S M Mahin Abrar
arXiv  ·  23 Aug 2025  ·  arxiv:2508.17107
A curated sugarcane leaf-disease dataset from Bangladesh, a very fast lightweight CNN for on-device diagnosis, and a progressive web app for field deployment.
arXiv
plant-phenomics precision-agriculture
Predicting Learning Styles with AI: Toward Adaptive and Personalized Education
Predicting Learning Styles with AI: Toward Adaptive and Personalized Education
Gobinda Chandra Sarker, Md Mehedi Hasan, Md. Rakibul Hoque, M. Helal Uddin Ahmed
2025 International Conference on Information Resources Management (CONF-IRM)  ·  01 Jul 2025  ·  url:https://aisel.aisnet.org/confirm2025/14
machine-learning
Predicting urban landslides in the hilly regions of Bangladesh leveraging a hybrid machine learning model and CMIP6 climate projections
Predicting urban landslides in the hilly regions of Bangladesh leveraging a hybrid machine learning model and CMIP6 climate projections
Md․ Ashraful Islam, Musabbir Ahmed Arrafi, Mehedi Hasan Peas, Tanvir Hossain, Md Mehedi Hasan, Sanzida Murshed, Monira Jahan Tania
Geosystems and Geoenvironment  ·  01 May 2025  ·  doi:10.1016/j.geogeo.2025.100354
machine-learning
PlantCareNet: an advanced system to recognize plant diseases with dual-mode recommendations for prevention
PlantCareNet: an advanced system to recognize plant diseases with dual-mode recommendations for prevention
Muhaiminul Islam, AKM Azad, Shifat E. Arman, Salem A. Alyami, Md Mehedi Hasan
Plant Methods  ·  23 Apr 2025  ·  doi:10.1186/s13007-025-01366-9
An end-to-end plant-disease diagnosis system that pairs a CNN classifier with expert-guided, knowledge-based recommendations for prevention and treatment.
plant-phenomics precision-agriculture
Design and Evaluation of ADANet: A High-Fidelity Motion Acquisition Framework for Assistive Gesture-Based Interfaces
Design and Evaluation of ADANet: A High-Fidelity Motion Acquisition Framework for Assistive Gesture-Based Interfaces
Md Ettashamul Haque, Atique Tajwar, Akm Azad, Salem A. Alyami, Md Mehedi Hasan
IEEE Access  ·  01 Jan 2025  ·  doi:10.1109/ACCESS.2025.3592079
robotics assistive-technology

2024

Spectral and Morphological Classification of Celestial Objects using Physics Informed Machine Learning
Spectral and Morphological Classification of Celestial Objects using Physics Informed Machine Learning
Md Fairuz Siddiquee, Md Mehedi Hasan
2024 IEEE 3rd International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON)  ·  29 Nov 2024  ·  doi:10.1109/RAAICON64172.2024.10928692
machine-learning
Development of an Accelerometer-based Data Acquisition System for Hand Gesture Recognition
Development of an Accelerometer-based Data Acquisition System for Hand Gesture Recognition
Atique Tajwar, Md. Ettashamul Haque, Md Mehedi Hasan
2024 IEEE 3rd International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON)  ·  29 Nov 2024  ·  doi:10.1109/RAAICON64172.2024.10928495
assistive-technology
FaceEngine: A Tracking-Based Framework for Real-Time Face Recognition in Video Surveillance System
FaceEngine: A Tracking-Based Framework for Real-Time Face Recognition in Video Surveillance System
Ahsan Imran, Riad Ahmed, Md Mehedi Hasan, M. Helal Uddin Ahmed, A. K. M. Azad, Salem A. Alyami
SN Computer Science  ·  31 May 2024  ·  doi:10.1007/s42979-024-02922-1
computer-vision
U-ActionNet: Dual-Pathway Fourier Networks With Region-of-Interest Module for Efficient Action Recognition in UAV Surveillance
U-ActionNet: Dual-Pathway Fourier Networks With Region-of-Interest Module for Efficient Action Recognition in UAV Surveillance
Abdul Monaf Chowdhury, Ahsan Imran, Md Mehedi Hasan, Riad Ahmed, Akm Azad, Salem A. Alyami
IEEE Access  ·  01 Jan 2024  ·  doi:10.1109/ACCESS.2024.3516586
uav computer-vision

2023

FFT-UAVNet: FFT Based Human Action Recognition for Drone Surveillance System
FFT-UAVNet: FFT Based Human Action Recognition for Drone Surveillance System
Abdul Monaf Chowdhury, Ahsan Imran, Md Mehedi Hasan
2023 5th International Conference on Sustainable Technologies for Industry 5.0 (STI)  ·  09 Dec 2023  ·  doi:10.1109/sti59863.2023.10465205
uav computer-vision
An Explainable EEG-Based Human Activity Recognition Model Using Machine-Learning Approach and LIME
An Explainable EEG-Based Human Activity Recognition Model Using Machine-Learning Approach and LIME
Iqram Hussain, Rafsan Jany, Richard Boyer, AKM Azad, Salem A. Alyami, Se Jin Park, Md Mehedi Hasan, Md Azam Hossain
Sensors  ·  27 Aug 2023  ·  doi:10.3390/s23177452
biomedical-signals explainable-ai
WheatSpikeNet: an improved wheat spike segmentation model for accurate estimation from field imaging
WheatSpikeNet: an improved wheat spike segmentation model for accurate estimation from field imaging
M. A. Batin, Muhaiminul Islam, Md Mehedi Hasan, AKM Azad, Salem A. Alyami, Md Azam Hossain, Stanley J. Miklavcic
Frontiers in Plant Science  ·  25 Aug 2023  ·  doi:10.3389/fpls.2023.1226190
plant-phenomics
Robot-Assisted Training for Children with Autism Spectrum Disorder: A Review
Robot-Assisted Training for Children with Autism Spectrum Disorder: A Review
Md. Ariful Islam, Md Mehedi Hasan, Shamim Ahmed Deowan
Journal of Intelligent & Robotic Systems  ·  24 Jun 2023  ·  doi:10.1007/s10846-023-01872-9
robotics
Blockchain-Based Pension System Ensuring Security, Provenance and Efficiency
Blockchain-Based Pension System Ensuring Security, Provenance and Efficiency
Minhaz KAMAL, Chowdhury Mohammad ABDULLAH, Fairuz SHAIARA, Abu Raihan Mostofa KAMAL, Md Mehedi HASAN, Jik-Soo KIM, Md Azam HOSSAIN
IEICE Transactions on Information and Systems  ·  01 May 2023  ·  doi:10.1587/transinf.2022edl8099
blockchain
Improved Detection and Analysis of Wheat Spikes Using Multi-Stage Convolutional Neural Network
Improved Detection and Analysis of Wheat Spikes Using Multi-Stage Convolutional Neural Network
M A Batin, Muhaiminul Islam, Md Mehedi Hasan, Stanley J Miklavcic
Dhaka University Journal of Applied Science and Engineering  ·  04 Apr 2023  ·  doi:10.3329/dujase.v7i2.65090
plant-phenomics
Binocular Rivalry Impact on Macroblock-Loss Error Concealment for Stereoscopic 3D Video Transmission
Binocular Rivalry Impact on Macroblock-Loss Error Concealment for Stereoscopic 3D Video Transmission
Md Mehedi Hasan, Md. Azam Hossain, Naif Alotaibi, John F. Arnold, AKM Azad
Sensors  ·  30 Mar 2023  ·  doi:10.3390/s23073604
video-quality

2022

No-Reference Quality Assessment of Transmitted Stereoscopic Videos Based on Human Visual System
No-Reference Quality Assessment of Transmitted Stereoscopic Videos Based on Human Visual System
Md Mehedi Hasan, Md. Ariful Islam, Sejuti Rahman, Michael R. Frater, John F. Arnold
Applied Sciences  ·  07 Oct 2022  ·  doi:10.3390/app121910090
video-quality