OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Kanchana Ranasinghe
PhD student, State University of New York, Stony Brook
Joined
February 2020
Names
Kanchana Ranasinghe
(Preferred)
,
Kanchana Nisal Ranasinghe
Emails
****@gmail.com
(Confirmed)
,
****@mbzuai.ac.ae
(Confirmed)
,
****@cs.stonybrook.edu
(Confirmed)
,
****@apple.com
(Confirmed)
,
****@meta.com
(Confirmed)
,
****@google.com
(Confirmed)
,
****@salesforce.com
(Confirmed)
Personal Links
Homepage
Google Scholar
DBLP
ORCID
Semantic Scholar
Career & Education History
PhD student
State University of New York, Stony Brook
(stonybrook.edu)
2021
–
Present
Intern
Research, Google
(research.google.com)
2024
–
2024
Intern
Meta AI
(facebook.com)
2023
–
2023
Intern
Apple
(apple.com)
2022
–
2022
Research Assistant
Mohamed bin Zayed University of Artificial Intelligence
(mbzuai.ac.ae)
2020
–
2021
Undergrad student
University of Moratuwa
(mrt.ac.lk)
2015
–
2020
Advisors, Relations & Conflicts
PhD Advisor
Michael Ryoo
2021
–
Present
Expertise
Multi-modal input representations
2022
–
Present
Self-supervised Learning
2020
–
Present
Image Segmentation
2020
–
Present
Video Understanding
2017
–
Present
Publications
Future Optical Flow Prediction Improves Robot Control & Video Generation
Kanchana Ranasinghe
,
Honglu Zhou
,
Yu Fang
,
Luyu Yang
,
Le Xue
,
Ran Xu
,
Caiming Xiong
,
silvio savarese
,
Michael S Ryoo
,
Juan Carlos Niebles
CVPR 2026 Findings
Readers:
Everyone
Future Optical Flow Prediction Improves Robot Control & Video Generation
Kanchana Ranasinghe
,
Honglu Zhou
,
Yu Fang
,
Luyu Yang
,
Le Xue
,
Ran Xu
,
Caiming Xiong
,
silvio savarese
,
Michael S Ryoo
,
Juan Carlos Niebles
CVPR 2026 Workshop VideoWorldModel Poster
Readers:
Everyone
Pixel Motion Diffusion is What We Need for Robot Control
E-Ro Nguyen
,
Yichi Zhang
,
Kanchana Ranasinghe
,
Xiang Li
,
Michael S Ryoo
ICLR 2026 Conference Withdrawn Submission
Readers:
Everyone
Pixel Motion as Universal Representation for Robot Control
Kanchana Ranasinghe
,
Xiang Li
,
E-Ro Nguyen
,
Cristina Mata
,
Jongwoo Park
,
Michael S Ryoo
ICLR 2026 Conference Withdrawn Submission
Readers:
Everyone
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
Xiang Li
,
Cristina Mata
,
Jongwoo Park
,
Kumara Kahatapitiya
,
Yoo Sung Jang
,
Jinghuan Shang
,
Kanchana Ranasinghe
,
Ryan D Burgert
,
Mu Cai
,
Yong Jae Lee
,
Michael S Ryoo
ICLR 2025 Poster
Readers:
Everyone
Language Repository for Long Video Understanding
Kumara Kahatapitiya
,
Kanchana Ranasinghe
,
Jongwoo Park
,
Michael S Ryoo
Submitted to ICLR 2025
Readers:
Everyone
Understanding Long Videos with Multimodal Language Models
Kanchana Ranasinghe
,
Xiang Li
,
Kumara Kahatapitiya
,
Michael S Ryoo
ICLR 2025 Poster
Readers:
Everyone
Language Repository for Long Video Understanding
Kumara Kahatapitiya
,
Kanchana Ranasinghe
,
Jongwoo Park
,
Michael S Ryoo
Video-Langauge Models Poster
Readers:
Everyone
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA
Jongwoo Park
,
Kanchana Ranasinghe
,
Kumara Kahatapitiya
,
Wonjeong Ryu
,
Donghyun Kim
,
Michael S Ryoo
Video-Langauge Models Poster
Readers:
Everyone
Too Many Frames, not all Useful: Efficient Strategies for Long-Form Video QA
Jongwoo Park
,
Kanchana Ranasinghe
,
Kumara Kahatapitiya
,
Wonjeong Ryoo
,
Donghyun Kim
,
Michael S. Ryoo
CoRR 2024
Readers:
Everyone
View all 37 publications
Co-Authors
Abe Leite
Ajith A. Pasqual
Alexander T Toshev
Alexander Toshev
Brandon McKinzie
Caiming Xiong
Cristina Mata
Donghyun Kim
E-Ro Nguyen
Fahad Khan
Fahad Shahbaz Khan
Fatih Porikli
Harsha Ranasinghe
Hasindri Watawana
Honglu Zhou
Jathushan Rajasegaran
Jinghuan Shang
Jonathon Shlens
Jongwoo Park
Juan Carlos Niebles
Kumara Kahatapitiya
Le Xue
Luyu Yang
Mayuka Jayawardhana
Michael S Ryoo
View all 57 co-authors