Bio-Ceramic Website Management
Managed and enhanced website content, boosting user satisfaction and traffic.
Managed and enhanced website content, boosting user satisfaction and traffic.
UX, configuration, stability, and documentation improvements for an open-source browser-agent interface.
AI agents and analytics sidecars for semantic CRM case retrieval, quality scoring, topic clustering, and operational insight.
A Python-based script for automating VPN connections.
An agentic review system that extracts claims, retrieves evidence, and ranks contradictions, missing evidence, and logic changes.
Production-ready local AI agents for document search, CRM workflows, messaging systems, OCR, analytics, and enterprise automation.
A hands-on learning repository for local LLMs, RAG, fine-tuning, instruction tuning, and practical AI engineering.
A hands-on repository for learning LangChain through chains, memory, RAG, tools, and custom agents.
Local-first extraction improvements, including Llama.cpp support and multilingual rendering fixes.
Optimized push notification services and improved codebase quality metrics.
OCR, indexing, and hybrid retrieval workflows for scanned enterprise documents and Persian-language search.
A local LLM application that maps natural-language requests to OracleDB search fields and structured filters.
A lightweight e-commerce platform designed to mirror Amazon’s functionality.
A step-by-step guide to mastering PyTorch, covering tensors, neural networks, and GPU utilization.
An in-depth exploration of Python, covering hot topics, useful libraries, and advanced programming concepts.
A Progressive Web App (PWA) for product identification and prize distribution.
A PyPI package that exposes embedding models through a shared FastAPI server and LangChain-compatible RemoteEmbeddings client.
Published in The 13th International Conference on Complex Networks and their Applications, 2024
In this work, we propose a novel framework that leverages dual reconstruction and contrastive learning to identify anomalies in attributed networks, addressing both structural and attribute-level outliers. Our experiments on benchmark datasets demonstrate significant performance improvements compared to existing methods.
Recommended citation: Zade, H.R., Zare, H., Ghassemi Parsa, M., Davardoust, H., Bagheri, M.S. (2025). DCOR: Anomaly Detection in Attributed Networks via Dual Contrastive Learning Reconstruction. In: Cherifi, H., Donduran, M., Rocha, L.M., Cherifi, C., Varol, O. (eds) Complex Networks & Their Applications XIII. COMPLEX NETWORKS 2024 2024. Studies in Computational Intelligence, vol 1189. Springer, Cham. https://doi.org/10.1007/978-3-031-82435-7_1
Download Paper
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.