Author

Sameera Ramasinghe

Observed name: Ramasinghe, Sameera

Observed institutions: Australian National University, Commonwealth Scientific and Industrial Research Organisation, Amazon (United States), University of Moratuwa, Data61, The University of Adelaide

ORCID: 0000-0002-3574-1592

Observed ORCID: 0000-0002-3574-1592

OpenAlex ID: A5102777273

Accept the Modality Gap: An Exploration in the Hyperbolic Space

2024 · Sameera Ramasinghe, Violetta Shevchenko, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 22

GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation

2022 · Chng, Shin-Fang, Ramasinghe, Sameera, et al. · arXiv (Cornell University) · 19

PDF

Recognition of badminton strokes using dense trajectories

2014 · Sameera Ramasinghe, K. G. Manosha Chathuramali, et al. · International Conference on Information and Automation for Sustainability (ICIAfS) · 18

A Sampling Theory Perspective on Activations for Implicit Neural Representations

2024 · Saratchandran, Hemanth, Ramasinghe, Sameera, et al. · arXiv (Cornell University) · 15

PDF

Combined Static and Motion Features for Deep-Networks-Based Activity Recognition in Videos

2017 · Sameera Ramasinghe, Jathushan Rajasegaran, et al. · IEEE Transactions on Circuits and Systems for Video Technology · 15

PDF

Action recognition by single stream convolutional neural networks: An approach using combined motion and static information

2015 · Sameera Ramasinghe, Ranga Rodrigo · Asian Conference on Pattern Recognition · 15

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising

2024 · Xianghui Yang, Yan Zuo, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 10

PDF

Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval

2025 · Ziwei Wang, Sameera Ramasinghe, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 8

PDF

BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling

2024 · Sameera Ramasinghe, Violetta Shevchenko, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 8

PDF

Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism

2025 · Sameera Ramasinghe, Thalaiyasingam Ajanthan, et al. · neural information processing systems · 7

PDF

How You Start Matters for Generalization

2022 · Ramasinghe, Sameera, MacDonald, Lachlan, et al. · arXiv (Cornell University) · 6

PDF

On Regularizing Coordinate-MLPs

2022 · Ramasinghe, Sameera, MacDonald, Lachlan, et al. · arXiv (Cornell University) · 6

PDF

Conditional Generative Modeling via Learning the Latent Space

2020 · Ramasinghe, Sameera, Ranasinghe, Kanchana, et al. · arXiv (Cornell University) · 6

PDF

Abnormal activity recognition using spatio-temporal features

2014 · K. G. Manosha Chathuramali, Sameera Ramasinghe, et al. · International Conference on Information and Automation for Sustainability (ICIAfS) · 6

NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training

2026 · Dolatabadi, Hadi Mohaghegh, Ajanthan, Thalaiyasingam, et al. · arXiv (Cornell University) · 5

PDF

Neural Experts: Mixture of Experts for Implicit Neural Representations

2024 · Yizhak Ben-Shabat, Chamin Hewa Koneputugodage, et al. · neural information processing systems · 5

PDF

LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration

2023 · Hossain, Md. Ismail, Elahi, M M Lutfe, et al. · arXiv (Cornell University) · 5

PDF

Curvature-Aware Training for Coordinate Networks

2023 · Hemanth Saratchandran, Shin-Fang Chng, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 5

PDF

Rethinking conditional GAN training: An approach using geometrically structured latent manifolds

2020 · Ramasinghe, Sameera, Farazi, Moshiur, et al. · arXiv (Cornell University) · 5

PDF

Nesterov Method for Asynchronous Pipeline Parallel Optimization

2025 · Ajanthan, Thalaiyasingam, Ramasinghe, Sameera, et al. · arXiv (Cornell University) · 4

PDF

AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism

2026 · Ajanthan, Thalaiyasingam, Ramasinghe, Sameera, et al. · arXiv (Cornell University) · 3

PDF

Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data

2025 · Yiqun Duan, Sameera Ramasinghe, et al. · International Joint Conference on Neural Networks (IJCNN) · 3

PDF

The Gate Always Closes: On Injecting Auxiliary Signals into Frozen Vision-Language Models

2026 · Farazi, Moshiur, Ramasinghe, Sameera, et al. · arXiv (Cornell University) · 1

PDF

Factored Gossip DiLoCo: Reducing Blocking Communication in DiLoCo

2026 · Koneputugodage, Chamin Hewa, Ajanthan, Thalaiyasingam, et al. · arXiv (Cornell University) · 1

PDF

HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning

2026 · Farazi, Moshiur, Ramasinghe, Sameera, et al. · arXiv (Cornell University) · 1

PDF

Works count: 41

Citation count: 200

H-index: 8

I10-index: 7