About Me

Ehsan Latif

Dr. Ehsan Latif

AI Research Scientist

I am an AI Research Scientist focusing on LLMs, multi‑agent systems, and trustworthy AI. My work has been recognized with a Best Paper Nomination at AIED 2025, and published at top AI conferences such as NeurIPS, AAAI, AIED, IROS, and ICRA.

I co‑organized and chaired workshops/sessions at AIED 2024 and AIED 2025, and lead research across NSF/IES‑funded projects on automated scoring and AI‑augmented education. I train and deploy transformer models (BERT, GPT, LLaMA) and design multi‑agent algorithms and agentic workflows for coordination, planning, and tool use—bridging fundamental research with real‑world impact.

Previously, I advanced learning‑ and optimization‑driven coordination in distributed systems and localization/exploration (IROS, RA‑L), and I bring strong engineering experience in ROS/ROS2, CUDA, PyTorch/TensorFlow, AWS, Python/C++/Linux—bridging foundational research with real‑world deployment.

Skills & Expertise

Programming Languages

  • Python
  • C/C++/C#
  • Java
  • SQL
  • Django
  • JavaScript
  • TypeScript
  • Rust
  • Go
  • R

AI & Machine Learning

  • Transformer Models
  • LLMs (BERT, GPT, LLaMA)
  • PyTorch/TensorFlow
  • LangChain
  • HuggingFace
  • Natural Language Processing
  • Multi-Agent Reinforcement Learning
  • Evolutionary AI
  • Prompt/Agent Engineering
  • Retrieval-Augmented Generation

Tools & Technologies

  • ROS/ROS2
  • CUDA
  • AWS
  • Linux
  • Git
  • VSCode
  • Android Studio
  • Firebase
  • Docker
  • Kubernetes

Research Interests

Multi-Agent Systems

Designing multi‑agent AI systems for coordination, planning, and tool‑augmented reasoning. My research spans agent orchestration, communication protocols, collective decision‑making, and safety/robustness.

Large Language Models

Training, fine-tuning, and optimizing transformer-based language models for specific domains. Research on knowledge distillation, efficient inference, and model compression for real-world applications.

AI in Education

Applying AI to enhance educational assessment and instruction. Developing automatic scoring systems, intelligent tutoring, and AI-augmented educational tools with a focus on STEM education.

Trustworthy AI

Researching methods to enhance AI safety, robustness, and sustainability. Developing approaches to ensure AI systems are fair, explainable, and aligned with human values.

Academic Service

Guest Editor

International Journal of Science Education, Special Issue: The Game-Changer: Generative Artificial Intelligence for Science Education and Research (2024 – Present)

Conference Chair

Session Chair of "Technical Session 14: Automatic grading and assessment" at the 25th International Conference on Artificial Intelligence in Education.

Reviewer

Serving as a reviewer for multiple prestigious conferences and journals, including IEEE Robotics and Automation Letters (RA-L), IEEE Transactions of Learning Technologies (TLT), International Conference on Robotics and Automation (ICRA), International Conference on Intelligent Robots and Systems (IROS), and International Conference on Artificial Intelligence in Education (AIED).