โญ Flagship Spotlight • PEFT & Foundation Model Compression
SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization
Seyed Mahmoud Sajjadi Mohammadabadi, Xiaolong Ma, Lei Yang, Feng Yan, Junshan Zhang
arXiv preprint arXiv:2604.08368 • 2026
35.1% Lower Memory & Sync Payload than LoRA | 1.54x Faster Sync | Under Review ICML 2026
Standard Low-Rank Adaptation (LoRA) scales linearly with model rank and weight matrix dimensions, incurring significant transmission costs during distributed edge adaptation. SOLAR reparameterizes low-rank projections into orthogonal latent subspaces, achieving 35% smaller memory footprint and transmission payloads across Vision Transformers (ViT), LLaMA-3, RoBERTa, and GPT-2 without degradation on downstream benchmarks (+0.3% GLUE score).
@article{sajjadi2026solar,
title = {{SOLAR}: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Ma, Xiaolong and Yang, Lei and Yan, Feng and Zhang, Junshan},
journal = {arXiv preprint arXiv:2604.08368},
year = {2026},
eprint = {2604.08368},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2604.08368}
}
๐ New Journal Article • Smart Grid & Multi-Agent RL
Sustainable Smart Grid Resilience and Renewable Integration Using Multi-Agent Reinforcement Learning
Seyed Mahmoud Sajjadi Mohammadabadi, Sayed Mohammad Sajjadi
Sustainability (MDPI, Vol. 18, Issue 20, 10574) • 2026
Open Access | +51% PV Hosting Capacity | 72.7% Fewer Feasibility Evaluations
Introduces a decentralized multi-agent reinforcement learning (MARL) framework integrating feeder reconfiguration, Q-learning-based fault restoration, coordinated battery energy storage dispatch, and communication-efficient training on the IEEE 33-bus and 179-bus Oberrhein networks. Restores 55.1% isolated load across all 496 double-fault pairs with 72.7% fewer evaluations and boosts PV hosting capacity by +51%.
@article{sajjadi2026sustainable,
title = {Sustainable Smart Grid Resilience and Renewable Integration Using Multi-Agent Reinforcement Learning},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Sajjadi, Sayed Mohammad},
journal = {Sustainability},
volume = {18},
number = {20},
pages = {10574},
year = {2026},
publisher = {MDPI},
doi = {10.3390/su182010574},
url = {https://www.mdpi.com/2071-1050/18/20/10574}
}
Federated Learning & Edge AI
Speed Up Federated Learning in Heterogeneous Environments: A Dynamic Tiering Approach
Seyed Mahmoud Sajjadi Mohammadabadi, Syed Zawad, Feng Yan, Lei Yang
IEEE Internet of Things Journal • 2025
Impact Factor: 9.0 | 31+ Citations
Heterogeneity in edge device compute and communication capacities introduces severe straggler delays in federated optimization. We introduce a dynamic tiering methodology grouping clients adaptively by throughput and latency, cutting federated training completion wall-clock time by over 80% without sacrificing model convergence or global classification accuracy.
@article{sajjadi2024tiering,
title = {Speed Up Federated Learning in Heterogeneous Environments: A Dynamic Tiering Approach},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Zawad, Syed and Yan, Feng and Yang, Lei},
journal = {IEEE Internet of Things Journal},
volume = {12},
number = {5},
pages = {5026--5035},
year = {2025},
publisher = {IEEE},
doi = {10.1109/JIOT.2024.3468511}
}
Federated Learning & Multi-Agent
Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning
Seyed Mahmoud Sajjadi Mohammadabadi, Lei Yang, Feng Yan, Junshan Zhang
2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS) • 2024
Acceptance Rate: 21.9% | 24+ Citations
Decentralized learning protocols suffer from severe communication overheads when agents possess unbalanced data allocations. We formulate a mathematically bounded communication-efficient workload balancer that reallocates computational stress across adjacent graph neighbors, delivering a 26% reduction in slow-agent compute burdens while guaranteeing consensus convergence.
@inproceedings{sajjadi2024icdcs,
title = {Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Yang, Lei and Yan, Feng and Zhang, Junshan},
booktitle = {2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS)},
pages = {680--691},
year = {2024},
organization = {IEEE},
doi = {10.1109/ICDCS60910.2024.00062}
}
Large Language Models & Surveys
A Survey of Large Language Models: Evolution, Architectures, Adaptation, Benchmarking, Applications, Challenges, and Societal Implications
Seyed Mahmoud Sajjadi Mohammadabadi, Burak Cem Kara, Can Eyupoglu, Can Uzay, Mehmet Serkan Tosun, Oktay Karakuล
Electronics • 2025
Open Access | 12+ Citations
A holistic investigation into the foundational lineage of Large Language Models (LLMs). Covers Transformer evolutions, mixture-of-experts (MoE), RLHF/DPO alignment, synthetic data curation, agentic orchestration frameworks, parameter-efficient adaptations, and deep ethical-safety paradigms.
@article{sajjadi2025llm,
title = {A Survey of Large Language Models: Evolution, Architectures, Adaptation, Benchmarking, Applications, Challenges, and Societal Implications},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Kara, Burak Cem and Eyupoglu, Can and Uzay, Can and Tosun, Mehmet Serkan and Karaku{\c{s}}, Oktay},
journal = {Electronics},
volume = {14},
number = {18},
pages = {3580},
year = {2025},
publisher = {MDPI},
doi = {10.3390/electronics14183580}
}
Self-Supervised Learning
A survey on self-supervised learning: Recent advances and open problems
Jianping Zhang, Lei Yang, Seyed Mahmoud Sajjadi Mohammadabadi, Feng Yan
Neurocomputing • 2025
Impact Factor: 6.5 | 18+ Citations
Systematic taxonomy synthesizing generative, contrastive, and predictive self-supervised learning algorithms across vision, natural language, multimodal representations, and graphs. Highlights sample efficiency bottlenecks, non-contrastive collapse mechanisms, and downstream cross-domain transfer bounds.
@article{zhang2025survey,
title = {A survey on self-supervised learning: Recent advances and open problems},
author = {Zhang, Jianping and Yang, Lei and Sajjadi Mohammadabadi, Seyed Mahmoud and Yan, Feng},
journal = {Neurocomputing},
volume = {655},
pages = {131409},
year = {2025},
publisher = {Elsevier},
doi = {10.1016/j.neucom.2024.131409}
}
LLM Surveys & Hallucinations
A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation
Seyed Mahmoud Sajjadi Mohammadabadi, Burak Cem Kara, Can Eyupoglu, Oktay Karakus
Preprints.org • 2026
7+ Citations | Detection & Mitigation Taxonomy
Comprehensive benchmark synthesizing the theoretical causes of factual hallucinations in LLMs. Unpacks internal activation entropy probing, retrieval-augmented grounding (RAG), self-consistency cross-examination, and decoding-time probability calibration mechanisms.
@article{sajjadi2026hallucination,
title = {A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Kara, Burak Cem and Eyupoglu, Can and Karakus, Oktay},
journal = {Preprints},
year = {2026},
doi = {10.20944/preprints202510.0000.v1}
}
Smart Grid & Cyber-Resilience
Generative Artificial Intelligence for Distributed Learning to Enhance Smart Grid Communication
Seyed Mahmoud Sajjadi Mohammadabadi, Mahmoudreza Entezami, Aidin Karimi Moghaddam, Mansour Orangian, Shayan Nejadshamsi
International Journal of Intelligent Networks • 2024
14+ Citations | Elsevier IJIN
Investigates generative AI models (diffusion models, VAEs, GANs) coupled with distributed edge computing to simulate synthetic grid disturbances, reconstruct missing telemetry packets, and augment transmission stability across high-latency wide-area power networks.
@article{sajjadi2024genai,
title = {Generative Artificial Intelligence for Distributed Learning to Enhance Smart Grid Communication},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Entezami, Mahmoudreza and Moghaddam, Aidin Karimi and Orangian, Mansour and Nejadshamsi, Shayan},
journal = {International Journal of Intelligent Networks},
volume = {5},
pages = {267--274},
year = {2024},
publisher = {Elsevier},
doi = {10.1016/j.ijin.2024.09.002}
}
Smart Grid & EV Ecosystems
Advancing Electric Vehicle Ecosystems: A Survey of Generative Artificial Intelligence and Distributed Machine Learning Applications
Seyed Mahmoud Sajjadi Mohammadabadi, Aidin Karimi Moghaddam, Mahmoudreza Entezami, Mostafa Seyedrezaei, Danial Charkhian, Behzad Moghaddam, Mohammad Sasani
Global Energy Interconnection • 2025
Peer-Reviewed Survey | Fleet Coordination & V2G
Comprehensive survey on EV fleet coordination, smart charging scheduling, vehicle-to-grid (V2G) power balancing, battery state-of-health (SOH) estimation (+44.5% accuracy), and CAN bus intrusion anomaly detection using distributed machine learning.
@article{sajjadi2025ev,
title = {Advancing Electric Vehicle Ecosystems: A Survey of Generative Artificial Intelligence and Distributed Machine Learning Applications},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Moghaddam, Aidin Karimi and Entezami, Mahmoudreza and Seyedrezaei, Mostafa and Charkhian, Danial and Moghaddam, Behzad and Sasani, Mohammad},
journal = {Global Energy Interconnection},
month = oct,
year = {2025}
}
Healthcare AI & Clinical Models
Identification and Classification of Rheumatoid Arthritis Using Artificial Intelligence and Machine Learning
Seyed Mahmoud Sajjadi Mohammadabadi, Mohammad Bagher Peikani
Diagnosing Musculoskeletal Conditions Using Artificial Intelligence and Machine Learning to Aid Interpretation of Clinical Imaging • 2025
9+ Citations | Elsevier Academic Press
Book chapter detailing machine learning architectures and computer vision pipelines for identifying bone erosions, synovitis, and joint space narrowing in rheumatoid arthritis clinical imaging, supporting early diagnosis and longitudinal treatment monitoring.
@incollection{sajjadi2025ra,
title = {Identification and Classification of Rheumatoid Arthritis Using Artificial Intelligence and Machine Learning},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Peikani, Mohammad Bagher},
booktitle = {Diagnosing Musculoskeletal Conditions Using Artificial Intelligence and Machine Learning to Aid Interpretation of Clinical Imaging},
publisher = {Academic Press},
pages = {123--145},
year = {2025},
doi = {10.1016/B978-0-443-15748-6.00007-4}
}
Healthcare AI & Clinical Models
Examination of AI's Role in Diagnosis, Treatment, and Patient Care
Seyed Mahmoud Sajjadi Mohammadabadi, Fatemeh Seyedkhamoushi, Maryam Mostafavi, Mohammad Bagher Peikani
Transforming Gender-Based Healthcare with AI and Machine Learning • 2024
8+ Citations | CRC Press Taylor & Francis
Synthesizes predictive analytics, natural language clinical notes interpretation, and automated triaging systems across inpatient and ambulatory settings, with particular focus on gender-specific disease manifestations and biomarker disparities.
@incollection{sajjadi2024aihealth,
title = {Examination of {AI}'s Role in Diagnosis, Treatment, and Patient Care},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Seyedkhamoushi, Fatemeh and Mostafavi, Maryam and Peikani, Mohammad Bagher},
booktitle = {Transforming Gender-Based Healthcare with AI and Machine Learning},
volume = {1},
publisher = {CRC Press},
pages = {221--238},
year = {2024},
doi = {10.1201/9781003456789-12}
}
Smart Grid & PMU Informatics
Towards Distributed Learning of PMU Data: A Federated Learning Based Event Classification Approach
Seyed Mahmoud Sajjadi Mohammadabadi, Yunchuan Liu, Abraham Canafe, Lei Yang
2023 IEEE Power & Energy Society General Meeting (PESGM) • 2023
21+ Citations | IEEE PESGM
Phasor Measurement Units (PMUs) stream mission-critical high-frequency voltage and current waveforms. We present a privacy-preserving federated deep learning framework allowing independent utility operators to train high-accuracy grid event classification networks without sharing proprietary telemetry, maintaining 88-90% accuracy across 3,877 real-world events.
@inproceedings{sajjadi2023pesgm,
title = {Towards Distributed Learning of {PMU} Data: A Federated Learning Based Event Classification Approach},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Liu, Yunchuan and Canafe, Abraham and Yang, Lei},
booktitle = {2023 IEEE Power & Energy Society General Meeting (PESGM)},
pages = {1--5},
year = {2023},
organization = {IEEE},
doi = {10.1109/PESGM52003.2023.10252874}
}
Smart Grid Cyber-Resilience
Feature Collusion Attack on PMU Data-Driven Event Classification
Amir Ghasemkhani, Rutuja Sanjeev Haridas, Seyed Mahmoud Sajjadi Mohammadabadi, Lei Yang
2024 IEEE PES Innovative Smart Grid Technologies (ISGT) • 2024
16+ Citations | IEEE ISGT
Examines adversarial vulnerability in data-driven smart grid anomaly detectors. Formulates a feature collusion attack where coordinated minor perturbations across multiple PMU measurement channels evade detection while causing severe misclassification of power system faults.
@inproceedings{ghasemkhani2024isgt,
title = {Feature Collusion Attack on {PMU} Data-Driven Event Classification},
author = {Ghasemkhani, Amir and Haridas, Rutuja Sanjeev and Sajjadi Mohammadabadi, Seyed Mahmoud and Yang, Lei},
booktitle = {2024 IEEE PES Innovative Smart Grid Technologies (ISGT)},
pages = {1--5},
year = {2024},
organization = {IEEE},
doi = {10.1109/ISGT59692.2024.10454123}
}
Foundation Models & AI Theory
From Generative AI to Innovative AI: An Evolutionary Roadmap
Seyed Mahmoud Sajjadi Mohammadabadi
arXiv preprint arXiv:2503.11419 • 2025
Sole Author | Evolutionary Synthesis Roadmap
Analyzes the transition from pattern-replicating Generative AI to autonomous hypothesis generation and scientific discovery in Innovative AI. Proposes a structural roadmap integrating meta-learning, symbolic grounding, and causal exploration.
@article{mohammadabadi2025innovative,
title = {From Generative {AI} to Innovative {AI}: An Evolutionary Roadmap},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud},
journal = {arXiv preprint arXiv:2503.11419},
year = {2025}
}
Multi-Agent Game Theory
Simultaneous Learning and State Estimation in Repeated Matrix Games
Seyed Mahmoud Sajjadi Mohammadabadi, Majid Nili Ahmadabadi, Hamed Kebriaei
4th International Conference on Information Technology Management, Communication and Computer (ICITMCC) • 2014
Foundational Game-Theoretic Framework
Presents an adaptive framework for multi-agent stochastic matrix games where agents simultaneously learn optimal policies while estimating incomplete latent state transitions and opponent belief dynamics.
@inproceedings{sajjadi2014matrix,
title = {Simultaneous Learning and State Estimation in Repeated Matrix Games},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud and Nili, Majid and Kebriaei, Hamed},
booktitle = {4th International Conference on Information Technology Management, Communication and Computer},
pages = {298--301},
year = {2014}
}
Ph.D. Dissertation
Distributed Machine Learning in Heterogeneous Edge Networks
Seyed Mahmoud Sajjadi Mohammadabadi
University of Nevada, Reno • 2025
105-Page Doctoral Thesis | Advisor: Dr. Lei Yang
Comprehensive doctoral dissertation formulating mathematical optimization theories and empirical frameworks for heterogeneous edge intelligence: Dynamic Tiering Federated Learning (DTFL), Communication-Efficient Workload Balancing (ComDML), and SplitPair Low-Rank SVD parameter compression.
@phdthesis{sajjadi2025dissertation,
title = {Distributed Machine Learning in Heterogeneous Edge Networks},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud},
school = {University of Nevada, Reno},
year = {2025},
note = {ProQuest Dissertation Publishing, 32286545}
}
Master's Thesis
Simultaneous State Estimation and Reinforcement Learning in Stochastic Matrix Games
Seyed Mahmoud Sajjadi Mohammadabadi
University of Tehran • 2014
M.Sc. Thesis | University of Tehran
Investigates reinforcement learning under partial observability and stochastic payoff matrices. Formulates coupled estimator-actor convergence guarantees for competitive and cooperative multi-agent equilibrium discovery.
@mastersthesis{sajjadi2014thesis,
title = {Simultaneous State Estimation and Reinforcement Learning in Stochastic Matrix Games},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud},
school = {University of Tehran},
year = {2014}
}
Open Source Catalog & Index
Awesome AI Coding Tools: A Curated Taxonomy of Autonomous Agents, Foundation Architectures, and Research Benchmarks
Seyed Mahmoud Sajjadi Mohammadabadi
Open Source Software Artifact • 2026
Open Source Flagship | 100+ Curated Tools
Authoritative taxonomy categorizing autonomous code agents, terminal CLIs, IDE integrations, local model runners (Ollama, vLLM), and SWE-bench reproducible evaluations for professional software engineering and AI research workflows.
@misc{sajjadi2026awesomecoding,
title = {Awesome {AI} Coding Tools: A Curated Taxonomy of Autonomous Agents, Foundation Architectures, and Research Benchmarks},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud},
year = {2026},
howpublished = {\url{https://github.com/mahmoudsajjadi/awesome-ai-coding-tools}}
}
Open Source Catalog & Index
Awesome AI Research Tools: A Curated Catalog of Literature Discovery, LaTeX, and Reproducibility Workflows
Seyed Mahmoud Sajjadi Mohammadabadi
Open Source Software Artifact • 2026
Academic Workflow Index | Discovery & LaTeX Tools
Curated academic catalog covering semantic literature search, citation graph discovery, AI-assisted LaTeX composition, figure generation, and scientific reproducibility frameworks for researchers and doctoral scientists.
@misc{sajjadi2026awesomeresearch,
title = {Awesome {AI} Research Tools: A Curated Catalog of Literature Discovery, {LaTeX}, and Reproducibility Workflows},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud},
year = {2026},
howpublished = {\url{https://github.com/mahmoudsajjadi/awesome-ai-research-tools}}
}
Software Benchmark Artifact
Dynamic Tiering-Based Federated Learning (DTFL)
Seyed Mahmoud Sajjadi Mohammadabadi
Open Source Software Artifact • 2024
Reproducibility Suite | Cited in IEEE IoT-J 2025
Open-source benchmark suite implementing dynamic client tiering, straggler-resilient scheduling, and non-IID partitioning across simulated heterogeneous edge clusters. Cited in IEEE Internet of Things Journal 2025.
@misc{sajjadi2024dtfl,
title = {Dynamic Tiering-Based Federated Learning ({DTFL})},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud},
year = {2024},
howpublished = {\url{https://github.com/mahmoudsajjadi/DTFL}}
}
Software Benchmark Artifact
Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning (ComDML)
Seyed Mahmoud Sajjadi Mohammadabadi
Open Source Software Artifact • 2024
Reproducibility Suite | Cited in IEEE ICDCS 2024
Production-ready decentralized multi-agent training benchmark implementing gossip-based neighbor synchronization, load rebalancing, and communication-constrained consensus protocols. Cited in IEEE ICDCS 2024.
@misc{sajjadi2024comdml,
title = {Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning ({ComDML})},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud},
year = {2024},
howpublished = {\url{https://github.com/mahmoudsajjadi/ComDML}}
}