Ibne Farabi Shihab

Ibne Farabi Shihab

Position
  • PhD Student
Ibne Farabi Shihab, a Ph.D. candidate in Computer Science working with Anuj Sharma, holds a Master’s in Artificial Intelligence from Iowa State University and a Bachelor’s in Computer Science from BRAC University. As a Data Scientist at SoilSerdem (2024), he developed a soil mapping engine that improved accuracy by 35% for 10+ farms. He also created AI solutions for Iowa DOT, using vision-language models to determine exact crash times and generate detailed descriptions. His internship as an Applied Scientist at Amazon (2025) focused on advancing knowledge graph embeddings for the buyer and abuse team. His teaching experience as a Graduate Assistant at Iowa State and The University of Vermont, covering Machine Learning and Deep Learning, earned praise for boosting student engagement. Ibne’s expertise in computer vision, crash analysis, and vision-language models, combined with his leadership, makes him a valuable asset to the academic community.

Contact

Social Media and Websites

Area of Expertise

  • Computer Vision
  • Reinforcement Learning
  • Knowledge Graph Embeddings

Education

  • B.Sc., Computer Science & Engineering, Brac University, 2018
  • M.S., Artificial Intelligence, Iowa State University, 2024

Publication

  1. Shihab, I. F., & Sharma, A. (2025). Crash time matters: Hybridmamba for fine-grained temporal localization in traffic surveillance footage. arXiv preprint arXiv:2504.03235.
  2. Shihab, I. F., Akter, S., & Sharma, A. (2025). Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments. arXiv preprint arXiv:2505.08299.
  3. Shihab, I. F., Akter, S., & Sharma, A. (2025). Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains. arXiv preprint arXiv:2505.07274.
  4. Shihab, I. F., Alvee, B. I., & Sharma, A. (2024). Leveraging Video-LLMs for Crash Detection and Narrative Generation: Performance Analysis and Challenges.
  5. Shihab, I. F., Bhagat, S. R., & Sharma, A. (2023, September). Robust and precise sidewalk detection with ensemble learning: Enhancing road safety and facilitating curb space management. In 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC) (pp. 5092-5099). IEEE.
  6. Shihab, I. F., Oishi, M. M., Islam, S., Banik, K., & Arif, H. (2018, December). A machine learning approach to suggest ideal geographical location for new restaurant establishment. In 2018 IEEE Region 10 Humanitarian Technology Conference (R10-HTC) (pp. 1-5). IEEE.
  7. Ahmed, S., Shihab, I. F., & Khokhar, A. (2025). Quantum-driven Zero Trust Architecture with Dynamic Anomaly Detection in 7G Technology: A Neural Network Approach. Measurement: Digitalization, 100005.