Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
How I Used the JVM’s JDWP to Cut GlassFish Redeploys from 2 Minutes to 5 Seconds
Published:
Reducing my GlassFish redeploy loop from roughly two minutes to about five seconds, using JDWP hot-swap. No IntelliJ Ultimate, no JRebel, no custom JVM.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
Team_Syrax at BLP-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in Bangla
Published in Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), co-located with EMNLP 2023, 2023
Semi-supervised self-training, back-translation, and a transformer ensemble for detecting violence-inciting Bangla text. Ranked 12th in post-evaluation of the BLP-2023 shared task.
Recommended citation: Omar Faruqe Riyad, Trina Chakraborty, and Abhishek Dey. 2023. Team_Syrax at BLP-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in Bangla. In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), pages 247–254, Singapore. Association for Computational Linguistics.
Download Paper
Deja Vu at SemEval 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning
Published in Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), co-located with NAACL 2024, 2024
Compares fine-tuned and prompted language models on the BRAINTEASER lateral-thinking benchmark, with data augmentation to improve robustness on commonsense reasoning.
Recommended citation: Trina Chakraborty, Marufur Rahman, and Omar Riyad. 2024. Deja Vu at SemEval 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1239–1244, Mexico City, Mexico. Association for Computational Linguistics.
Download Paper
AdversaryAI at BLP-2025 Task 2: A Think, Refine, and Generate (TriGen) System with LoRA and Self-Refinement for Code Generation
Published in Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), co-located with IJCNLP-AACL 2025, 2025
A Bangla code generation system combining LoRA fine-tuning of open-source models with Chain-of-Thought prompting and an execution-guided self-refinement loop.
Recommended citation: Omar Faruqe Riyad and Jahedul Alam Junaed. 2025. AdversaryAI at BLP-2025 Task 2: A Think, Refine, and Generate (TriGen) System with LoRA and Self-Refinement for Code Generation. In Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), pages 629–641, Mumbai, India. Association for Computational Linguistics.
Download Paper
talks
Agentic Software Engineering with Claude Code
Published:
A session on agentic software engineering workflows using Claude Code — covering planning, sub-agents, hooks, skills, MCP, and the feedback loops that make an AI coding agent reliable on real codebases.
teaching
Enterprise Web Development with JEE, JSF, and PrimeFaces
Course Instructor, Dynamic Learning, Dynamic Solution Innovators, 2024
I am the lead instructor for Enterprise Web Development with JEE, JSF, and PrimeFaces at Dynamic Learning, an initiative by Dynamic Solution Innovators.