I work as an Applied Scientist at Amazon. I completed my B.Sc. (Hons) degree from the Department of Electronic and Telecommunication Engineering, University of Moratuwa and completed my PhD at the Australian National University. My research interests include theoretical machine learning and computer vision. I am also a co-founder of ConscientAI and a research fellow at the University of Adelaide.

Career Highlights

• Applied scientist at Amazon
• Former postdoc at the Australian Institute for Machine Learning
• Co-Founder/Director at ConscientAI
• Former software engineer at WSO2
• Former software engineer at Neurotechnology Lab
• Former computer vision engineer at Hitech Solutions

Recent News

• December, 2022: A learnable radial-basis embedding for coordinate-MLPs accepted to AAAI (Oral), 2023
• September, 2022: On the frequency bias of coordinate-MLPs accepted to NeurIPS, 2022
• September, 2022: Robust normalizing flows using Bernstein-type polynomials accepted to BMVC, 2022
• July, 2022: Beyond Periodicity: Towards a unifying framework for activations in coordnate-MLPs accepted to ECCV (Oral), 2022
• July, 2022: Trading Positional Complexity vs Deepness in Coordinate Networks accepted to ECCV, 2022
• July, 2022: Few-Shot Class-Incremental Learning for 3D Point Cloud Objects accepted to ECCV, 2022
• July, 2022: Gaussian activated neural radiance fields for high fidelity reconstruction and pose estimation accepted to ECCV (Oral), 2022
• March, 2022: Enabling equivariance for arbitrary Lie groups accepted to CVPR, 2022
• September, 2021: Rethinking conditional GAN training: An approach using geometrically structured latent manifolds accepted to NeurIPS, 2021
• February, 2021: Completed PhD at the Australian National University
• January, 2021: Conditional Generative Modeling via Learning the Latent Space accepted to ICLR, 2021
• June, 2021: Synthesized feature based few-shot class-incremental learning on a mixture of subspaces accepted to ICCV, 2021
• June, 2020: Spectral-GANs for high-resolution 3D point-cloud generation accepted to IROS, 2020
• February, 2020: Representation learning on unit ball with 3d roto-translational equivariance accepted to IJCV
• December, 2019 Learned and Hand-crafted Feature Fusion in Unit Ball for 3D Object Classification won the best student paper award in ICPRAM, 2020
• 2020: Blended convolution and synthesis for efficient discrimination of 3D shapes accepted to WACV, 2020
• 2018: A context-aware capsule network for multi-label classification accepted to ECCV, 2018
• November, 2017: Completed M.Phil. at the University of Moratuwa
• 2017: Combined static and motion features for deep-networks-based activity recognition in videos accepted to TCSVT
• 2017: Micro Actions and Deep Static Features for Activity Recognition accepted to DICTA, 2017
• February, 2014: Completed B.Sc. (Hons) in Electronic and Telecommunication engineering at the University of Moratuwa.