collaborators

6 papers

cs.AI2026

Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents

Seyed Moein Abtahi, Rasa Rahnema, Hetkumar Patel +3

The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment…

cs.DB2025

From HNSW to Information-Theoretic Binarization: Rethinking the Architecture of Scalable Vector Search

Seyed Moein Abtahi, Majid Fekri, Tara Khani +1

Modern semantic search and retrieval-augmented generation (RAG) systems rely predominantly on in-memory approximate nearest neighbor (ANN) indexes over high-precision floating-poin…

cs.CR2025

Securing LLM-Generated Embedded Firmware through AI Agent-Driven Validation and Patching

Seyed Moein Abtahi, Akramul Azim

Large Language Models (LLMs) show promise in generating firmware for embedded systems, but often introduce security flaws and fail to meet real-time performance constraints. This p…

cs.SE2025

WALL: A Web Application for Automated Quality Assurance using Large Language Models

Seyed Moein Abtahi, Akramul Azim

As software projects become increasingly complex, the volume and variety of issues in code files have grown substantially. Addressing this challenge requires efficient issue detect…

eess.SY2025

Algorithmic Approaches to Enhance Safety in Autonomous Vehicles: Minimizing Lane Changes and Merging

Seyed Moein Abtahi, Akramul Azim

The rapid advancements in autonomous vehicle (AV) technology promise enhanced safety and operational efficiency. However, frequent lane changes and merging maneuvers continue to po…

cs.SE2025

Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements

Seyed Moein Abtahi, Akramul Azim

This study examined code issue detection and revision automation by integrating Large Language Models (LLMs) such as OpenAI's GPT-3.5 Turbo and GPT-4o into software development wor…