
Dinura Dissanayake
Hello, I'm a research engineer at Mohamed bin Zayed University of Artificial Intelligence.
I'm currently interested in
Checkout my resume.
News
- September 2025 Started working as a Research Engineer at Mohamed bin Zayed University of Artificial Intelligence.
- August 2025 Our paper A Culturally-diverse Multilingual Multimodal Video Benchmark & Model, got accepted in EMNLP 2025 Main Conference.🔥.
- June 2025 Our paper Drivelmm-o1: A step-by-step reasoning dataset and large multimodal model for driving scenario understanding, got accepted in IROS 2025 as an oral presentation🔥.
- May 2025 Our paper Llamav-o1: Rethinking step-by-step visual reasoning in llms, got accepted in ACL Findings 2025🔥.
- February 2025 Our paper All languages matter: Evaluating lmms on culturally diverse 100 languages, got accepted in CVPR 2025 as a highlight paper🔥.
- September 2024 Our paper Multimodal Deep Convolutional Neural Network Pipeline for AI-Assisted Early Detection of Oral Cancer, got published in IEEE Access🔥.
- July 2024 Our paper A comprehensive dataset of annotated oral cavity images for diagnosis of oral cancer and oral potentially malignant disorders, got published in ScienceDirect Oral Oncology🔥.
- April 2024 Started working as a Research Assistant at Mohamed bin Zayed University of Artificial Intelligence.
- December 2023 Graduated from the Faculty of Engineering, University of Peradeniya with a First Class Honours in Bachelor of Science in Engineering (Computer Engineering)🎓.
- October, 2023 The multidisciplinary research project Oral Assessment and Screening Interactive System was demonstrated at Techno 2023, the largest engineering and technology exhibition in Sri Lanka. The University Stall of the University of Peradeniya was awarded the Gold Award for the best display of engineering projects.
- October, 2023 Won the Bronze award at the National ICT Awards NBQSA 2023 in the Student Category (technology) for the project 'Oral cavity image annotation and cancer prediction from white light images'.
Publications
A comprehensive dataset of annotated oral cavity images for diagnosis of oral cancer and oral potentially malignant disorders
Oral Oncology
Published: 2024
Multimodal Deep Convolutional Neural Network Pipeline for AI-Assisted Early Detection of Oral Cancer
IEEE Access
Published: 2024
Projects

Developed a multilingual conversational benchmark that incorporates cultural and linguistic diversity to evaluate the performance of current vision-language models (VLMs).

End-To-End Planning-Oriented Autonomous Driving
Improve already existing trajectory-guided control prediction method by introducing
depth perception and a new control mechanism.

Analysis Tool for Industrial Images
An analysis tool for increasing the performance of an injection mold maintenance device which uses image processing
techniques to identify stuck plastic particles on molds.

Remote Keyboard Tutoring System
The Remote Keyboard Tutoring System is a web-based system that can be attached to any (electronic) keyboard synthesizer through a MIDI connector. Once our system is connected to the keyboard, the user can interactively learn, play or teach in combination with the web application that we provide.

Oral Assesment and Screening Interactive System
A web-based, automated screening system that can boost the treatment process by early detection of
high-risk oral cancer patients.

CRC USING CUSTOMIZED NIOSII PROCESSOR
Improved performance of the Cyclic-Redundancy-Check algorithm by adding a custom instruction to
the MIPS ISA of NiosII processor. Implementation of hardware functionality using XOR and shift operations.

Compiler for Cool Language
The combination of a lexer, parser, semantic analyser, and code generator that can be used to compile programs written
in Cool programming language.


8-bit single cycle processor
The combination of a lexer, parser, semantic analyser, and code generator that can be used to compile programs written
in Cool programming language.

Image Processing techniques to detect damaged fruit
Image Filtering with OpenCV was used to create an algorithm to detect the deformities of fruit. Created application using python to continuously monitor given set of images.

Fractal generator
A tool to display Mandelbrot and Julia sets, for given parameters.
Use of multi-threading concepts in generating the images.

Tick-tact-toe
Classical Tick-tact-toe game implementation using Java event handeling and java model view controller architecture(MVC).
Skills & Experience
For over four years now I have been studying through my degree program as well as on my own in various different programming languages and techniques. I have experience in,
- Machine Learning
- Computer Vision
- Data Structures and Algorithms
- Embedded programming
- Full Stac Development
- Networking
Python
- 5+ Years of project and coding experience.
- Algorithms, Machine Learning, Embedded programming
Java
- 2+ Years of project and coding experience.
- Algorithms, OOP
C++
- 2+ Years of project and coding experience.
- Algorithms, OOP
HTML5
- 5+ Years of project and coding experience.
CSS
- 3+ Years of project and coding experience.
React-JS
- 2+ Years of project and coding experience.