{"id":124,"date":"2026-01-28T04:15:16","date_gmt":"2026-01-28T04:15:16","guid":{"rendered":"https:\/\/www.arifulemon.com\/?page_id=124"},"modified":"2026-04-29T11:07:17","modified_gmt":"2026-04-29T10:07:17","slug":"current-project","status":"publish","type":"page","link":"https:\/\/www.arifulemon.com\/index.php\/current-project\/","title":{"rendered":"Projects"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"124\" class=\"elementor elementor-124\">\n\t\t\t\t<div class=\"elementor-element elementor-element-82b3505 e-flex e-con-boxed e-con e-parent\" data-id=\"82b3505\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-193ed5e elementor-widget elementor-widget-heading\" data-id=\"193ed5e\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Ongoing Projects<\/h2>\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-9f7bfff e-flex e-con-boxed e-con e-parent\" data-id=\"9f7bfff\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-ea144dd elementor-widget elementor-widget-text-editor\" data-id=\"ea144dd\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p><span style=\"text-decoration: underline;\"><strong>Centralized Transactional Memory Scheduling<\/strong><\/span><\/p>\n<p>Working on this project involved designing and refining a detailed simulation of conflict-free transaction execution under adversarial conditions. I focused on modeling realistic transaction generation, congestion control, and processor scheduling while preserving strong execution guarantees across intervals. A key contribution was improving the adversarial model to balance object usage, minimize unnecessary conflicts, and prevent early overloads, resulting in more stable and interpretable system behavior. The project required careful reasoning about concurrency, fairness, and worst-case scenarios, as well as iterative debugging to align theoretical constraints with practical implementation. Overall, it strengthened my skills in systems modeling, algorithm design, and experimental validation.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-79282c1 elementor-widget__width-initial elementor-widget elementor-widget-image-gallery\" data-id=\"79282c1\" data-element_type=\"widget\" data-widget_type=\"image-gallery.default\">\n\t\t\t\t\t\t\t<div class=\"elementor-image-gallery\">\n\t\t\t\n\t\t<style type=\"text\/css\">\n\t\t\t#gallery-1 {\n\t\t\t\tmargin: auto;\n\t\t\t}\n\t\t\t#gallery-1 .gallery-item {\n\t\t\t\tfloat: left;\n\t\t\t\tmargin-top: 10px;\n\t\t\t\ttext-align: center;\n\t\t\t\twidth: 33%;\n\t\t\t}\n\t\t\t#gallery-1 img {\n\t\t\t\tborder: 2px solid #cfcfcf;\n\t\t\t}\n\t\t\t#gallery-1 .gallery-caption {\n\t\t\t\tmargin-left: 0;\n\t\t\t}\n\t\t\t\/* see gallery_shortcode() in wp-includes\/media.php *\/\n\t\t<\/style>\n\t\t<div id='gallery-1' class='gallery galleryid-124 gallery-columns-3 gallery-size-thumbnail'><dl class='gallery-item'>\n\t\t\t<dt class='gallery-icon landscape'>\n\t\t\t\t<a data-elementor-open-lightbox=\"yes\" data-elementor-lightbox-slideshow=\"79282c1\" data-elementor-lightbox-title=\"UHCL Poster Presentation 2026\" data-e-action-hash=\"#elementor-action%3Aaction%3Dlightbox%26settings%3DeyJpZCI6NjczLCJ1cmwiOiJodHRwczpcL1wvd3d3LmFyaWZ1bGVtb24uY29tXC93cC1jb250ZW50XC91cGxvYWRzXC8yMDI2XC8wNFwvVUhDTC1Qb3N0ZXItUHJlc2VudGF0aW9uLTIwMjYuanBnIiwic2xpZGVzaG93IjoiNzkyODJjMSJ9\" href='https:\/\/www.arifulemon.com\/wp-content\/uploads\/2026\/04\/UHCL-Poster-Presentation-2026.jpg'><img decoding=\"async\" width=\"150\" height=\"150\" src=\"https:\/\/www.arifulemon.com\/wp-content\/uploads\/2026\/04\/UHCL-Poster-Presentation-2026-150x150.jpg\" class=\"attachment-thumbnail size-thumbnail\" alt=\"\" aria-describedby=\"gallery-1-673\" \/><\/a>\n\t\t\t<\/dt>\n\t\t\t\t<dd class='wp-caption-text gallery-caption' id='gallery-1-673'>\n\t\t\t\tUHCL Poster Presentation 2026\n\t\t\t\t<\/dd><\/dl><dl class='gallery-item'>\n\t\t\t<dt class='gallery-icon landscape'>\n\t\t\t\t<a data-elementor-open-lightbox=\"yes\" data-elementor-lightbox-slideshow=\"79282c1\" data-elementor-lightbox-title=\"UHCL Poster Presentation 2026 Group\" data-e-action-hash=\"#elementor-action%3Aaction%3Dlightbox%26settings%3DeyJpZCI6NjcxLCJ1cmwiOiJodHRwczpcL1wvd3d3LmFyaWZ1bGVtb24uY29tXC93cC1jb250ZW50XC91cGxvYWRzXC8yMDI2XC8wNFwvVUhDTC1Qb3N0ZXItUHJlc2VudGF0aW9uLTIwMjYtR3JvdXAuanBlZyIsInNsaWRlc2hvdyI6Ijc5MjgyYzEifQ%3D%3D\" href='https:\/\/www.arifulemon.com\/wp-content\/uploads\/2026\/04\/UHCL-Poster-Presentation-2026-Group.jpeg'><img decoding=\"async\" width=\"150\" height=\"150\" src=\"https:\/\/www.arifulemon.com\/wp-content\/uploads\/2026\/04\/UHCL-Poster-Presentation-2026-Group-150x150.jpeg\" class=\"attachment-thumbnail size-thumbnail\" alt=\"\" aria-describedby=\"gallery-1-671\" \/><\/a>\n\t\t\t<\/dt>\n\t\t\t\t<dd class='wp-caption-text gallery-caption' id='gallery-1-671'>\n\t\t\t\tUHCL Poster Presentation 2026\n\t\t\t\t<\/dd><\/dl><dl class='gallery-item'>\n\t\t\t<dt class='gallery-icon portrait'>\n\t\t\t\t<a data-elementor-open-lightbox=\"yes\" data-elementor-lightbox-slideshow=\"79282c1\" data-elementor-lightbox-title=\"UHCL Poster Presentation 2026 My Project\" data-e-action-hash=\"#elementor-action%3Aaction%3Dlightbox%26settings%3DeyJpZCI6NjcyLCJ1cmwiOiJodHRwczpcL1wvd3d3LmFyaWZ1bGVtb24uY29tXC93cC1jb250ZW50XC91cGxvYWRzXC8yMDI2XC8wNFwvVUhDTC1Qb3N0ZXItUHJlc2VudGF0aW9uLTIwMjYtTXktUHJvamVjdC5qcGVnIiwic2xpZGVzaG93IjoiNzkyODJjMSJ9\" href='https:\/\/www.arifulemon.com\/wp-content\/uploads\/2026\/04\/UHCL-Poster-Presentation-2026-My-Project.jpeg'><img decoding=\"async\" width=\"150\" height=\"150\" src=\"https:\/\/www.arifulemon.com\/wp-content\/uploads\/2026\/04\/UHCL-Poster-Presentation-2026-My-Project-150x150.jpeg\" class=\"attachment-thumbnail size-thumbnail\" alt=\"\" aria-describedby=\"gallery-1-672\" \/><\/a>\n\t\t\t<\/dt>\n\t\t\t\t<dd class='wp-caption-text gallery-caption' id='gallery-1-672'>\n\t\t\t\tUHCL Poster Presentation 2026\n\t\t\t\t<\/dd><\/dl><br style=\"clear: both\" \/>\n\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-9c96842 e-flex e-con-boxed e-con e-parent\" data-id=\"9c96842\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-ef064f1 elementor-widget elementor-widget-heading\" data-id=\"ef064f1\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Completed Projects<\/h2>\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-6f66c521 e-flex e-con-boxed e-con e-parent\" data-id=\"6f66c521\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-67b60f06 elementor-widget elementor-widget-text-editor\" data-id=\"67b60f06\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p><span style=\"text-decoration: underline;\"><strong>Optimizing AI Agent<\/strong><\/span><\/p>\n<p>My focus includes integrating support for multiple large language models to a custom AI Agent, allowing the system to leverage different LLMs to improve response quality, flexibility, and robustness. In parallel, I am optimizing prompt engineering strategies to make interactions more efficient and less chat-heavy, while still providing clear, step-by-step guidance. This involves refining prompts, managing context more effectively, and reducing unnecessary follow-up exchanges. The project aims to enhance the overall learning experience by delivering concise, instructional, and user-friendly AI assistance.<br \/><br \/><strong>Key Technical Highlights<\/strong><\/p>\n<ul>\n<li>Designed and implemented a <strong>multi-LLM AI system<\/strong> with provider-agnostic architecture and model-specific adapters<\/li>\n<li>Applied <strong>advanced prompt engineering<\/strong> to enforce guided, step-by-step tutoring behavior and prevent solution leakage<\/li>\n<li>Built <strong>context-aware retrieval mechanisms<\/strong> to ground AI responses in assignment-specific instructional data<\/li>\n<li>Developed <strong>semantic memory and session management<\/strong> for assignment-scoped AI conversations<\/li>\n<li>Integrated <strong>natural language understanding with structured user inputs<\/strong> for adaptive tutoring workflows<\/li>\n<li>Implemented <strong>option-based clarification strategies<\/strong> to reduce ambiguity and improve user decision-making<\/li>\n<li>Engineered <strong>controlled AI inference pipelines<\/strong> with token limits, verbosity control, and response constraints<\/li>\n<li>Designed and managed <strong>relational databases<\/strong> for chat history, session tracking, and user interaction logs<\/li>\n<li>Enabled <strong>secure execution and analysis of user-submitted code<\/strong> for real-time error diagnosis<\/li>\n<li>Performed <strong>cross-model evaluation<\/strong> to compare LLM behavior, latency, and instructional quality<\/li>\n<li>Implemented <strong>robust error handling and fallback mechanisms<\/strong> to improve system reliability<\/li>\n<\/ul>\n<p>Conducted <strong>iterative experimentation and evaluation<\/strong> to optimize AI response quality and user experience<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-5452b87 elementor-widget elementor-widget-button\" data-id=\"5452b87\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/www.arifulemon.com\/wp-content\/uploads\/2026\/04\/LeafTutor-Prompt-2026.pdf\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Download Project Paper<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Ongoing Projects Centralized Transactional Memory Scheduling Working on this project involved designing and refining a detailed simulation of conflict-free transaction execution under adversarial conditions. I focused on modeling realistic transaction generation, congestion control, and processor scheduling while preserving strong execution guarantees across intervals. A key contribution was improving the adversarial model to balance object usage, [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-124","page","type-page","status-publish","hentry"],"acf":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.arifulemon.com\/index.php\/wp-json\/wp\/v2\/pages\/124","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.arifulemon.com\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.arifulemon.com\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.arifulemon.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.arifulemon.com\/index.php\/wp-json\/wp\/v2\/comments?post=124"}],"version-history":[{"count":28,"href":"https:\/\/www.arifulemon.com\/index.php\/wp-json\/wp\/v2\/pages\/124\/revisions"}],"predecessor-version":[{"id":676,"href":"https:\/\/www.arifulemon.com\/index.php\/wp-json\/wp\/v2\/pages\/124\/revisions\/676"}],"wp:attachment":[{"href":"https:\/\/www.arifulemon.com\/index.php\/wp-json\/wp\/v2\/media?parent=124"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}