Shehan Munasinghe

shehan97

·

https://shehanmunasinghe.github.io/

AI & ML interests

Computer Vision, Multi-modal learning

Recent Activity

upvoted a paper 1 day ago

WorldGuide: Goal-Directed Video World Model for Procedural Task Execution

upvoted a paper 14 days ago

Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision

upvoted a paper about 1 month ago

Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding

View all activity

Organizations

shehan97 's datasets

None public yet