Kanchana Ranasinghe

Computer Science · Physical Sciences

8h-index529citations40works1.52yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Multimodal Machine Learning Applications(13), Domain Adaptation and Few-Shot Learning(12), Generative Adversarial Networks and Image Synthesis(8), Human Pose and Action Recognition(7), Topic Modeling(4)

Publications40 total

IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance
ArXiv.org·2026Open Access
IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance
arXiv (Cornell University)·2026Open Access
Future Optical Flow Prediction Improves Robot Control & Video Generation
ArXiv.org·2026Open Access
Future Optical Flow Prediction Improves Robot Control & Video Generation
arXiv (Cornell University)·2026Open Access
Robotic VLA Benefits from Joint Learning with Motion Image Diffusion
arXiv (Cornell University)·2025Open Access
Robotic VLA Benefits from Joint Learning with Motion Image Diffusion
ArXiv.org·2025Open Access
CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings
arXiv (Cornell University)·2025Open Access
Pixel Motion as Universal Representation for Robot Control
arXiv (Cornell University)·2025Open Access
Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentation
arXiv (Cornell University)·2025Open Access
Language Repository for Long Video Understanding
2025· 4 citedOpen Access
LatentCRF: Continuous CRF for Efficient Latent Diffusion
arXiv (Cornell University)·2024Open Access
CoPT: Unsupervised Domain Adaptive Segmentation Using Domain-Agnostic Text Embeddings
Lecture notes in computer science·2024· 1 cited
Diffusion Illusions: Hiding Images in Plain Sight
2024· 10 cited
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
arXiv (Cornell University)·2024· 2 citedOpen Access
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs
2024· 17 cited
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA
arXiv (Cornell University)·2024Open Access
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs
arXiv (Cornell University)·2024Open Access
Understanding Long Videos with Multimodal Language Models
arXiv (Cornell University)·2024Open Access
Hierarchical Text-to-Vision Self Supervised Alignment for Improved Histopathology Representation Learning
arXiv (Cornell University)·2024Open Access
Language Repository for Long Video Understanding
arXiv (Cornell University)·2024Open Access
page 1 of 2Next →

Frequent Co-authors

Michael S. Ryoo(19), Muzammal Naseer(9), Fahad Shahbaz Khan(8), Salman Khan(6), Cristina Mata(6), Kumara Kahatapitiya(5), Jongwoo Park(5), Ryan Burgert(4), Mayuka Jayawardhana(4), Sahan Liyanaarachchi(4), Harsha Ranasinghe(4), Michael S Ryoo(4), Honglu Zhou(4), Caiming Xiong(4), Savarese Silvio(4), Munawar Hayat(3), Sameera Ramasinghe(3), Ranga Rodrigo(3), Sadeep Jayasumana(3), Xiang Li(3)