Scholar
Dinura Dissanayake
Google Scholar ID: HVIV99gAAAAJ
Research Engineer, MBZUAI
Citations & Impact
Citations
158
H-index
5
i10-index
5
Publications
7
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'How Good are Foundation Models in Step-by-Step Embodied Reasoning?' submitted to ICRA 2026 (September 2025)
- Paper 'A Culturally-diverse Multilingual Multimodal Video Benchmark & Model' accepted to EMNLP 2025 Main Conference (August 2025)
- Paper 'Drivelmm-o1: A step-by-step reasoning dataset and large multimodal model for driving scenario understanding' accepted as an oral presentation at IROS 2025 (June 2025)
- Paper 'Llamav-o1: Rethinking step-by-step visual reasoning in llms' accepted to ACL Findings 2025 (May 2025)
- Paper 'All languages matter: Evaluating lmms on culturally diverse 100 languages' accepted as a highlight paper at CVPR 2025 (February 2025)
- Paper 'Multimodal Deep Convolutional Neural Network Pipeline for AI-Assisted Early Detection of Oral Cancer' published in IEEE Access (September 2024)
- Paper 'A comprehensive dataset of annotated oral cavity images for diagnosis of oral cancer and oral potentially malignant disorders' published in ScienceDirect Oral Oncology (July 2024)
- The oral cancer screening project was demonstrated at Techno 2023, Sri Lanka’s largest engineering and technology exhibition, and won the Gold Award for best university display (October 2023)
- Project 'Oral cavity image annotation and cancer prediction from white light images' received Bronze Award in Student Category (Technology) at National ICT Awards NBQSA 2023 (October 2023)
