Vibashan VS
Applied Scientist at Wayve
Maryland, United States
Summary
👤
Senior🎓
Top SchoolVibashan VS is an applied scientist and PhD researcher specializing in the intersection of computer vision and natural language processing, focused on building open-world, multi-modal foundation models and vision-agents for reasoning and planning. With eight years of experience spanning industry research roles at Wayve, NVIDIA, Qualcomm, and Salesforce, he has driven state-of-the-art results in open-vocabulary segmentation, video grounding, and hallucination estimation for multi-modal LLMs—work that has led to publications and patents. At Wayve he is applying language-aligned world models to enable vision–language–action policies for autonomous driving, translating academic advances into real-world control. His background includes top-ranked biomedical imaging results and robotics experiments from NUS and IIT Madras, reflecting a rare blend of medical, robotic, and autonomous vehicle vision expertise. Practical, publication-driven, and product-minded, he combines deep theoretical knowledge with hands-on system building across research and edge deployment.
8 years of coding experience
3 years of employment as a software developer
Indian Institute of Technology MadrasJohns Hopkins UniversityBachelor of Technology - BTech Instrumentation and Control Engineering, Bachelor of Technology - BTech Instrumentation and Control Engineering at National Institute of Technology, TiruchirappalliResearch Assistant Intern Deep Learning | Medical AI | Computer Vision |, Research Assistant Intern Deep Learning | Medical AI | Computer Vision | at National University of Singapore
Github Skills (18)
segmentation10
visual-recognition10
face-detection9
face-recognition9
ros-driver8
computer-vision8
object-detection8
openvr7
deep-learning7
slam-algorithms7
crazyflie6
ros6
robotics6
backbone5
nodes4
Programming languages (2)
Github contributions (5)
Vibashan/irg-sfda
Mar 2022 - Apr 2022
Official Pytorch codebase for Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection [CVPR 2023]
Contributions:9 commits, 22 pushes, 25 comments in 13 days
Vibashan/tt-sfuda
Mar 2022 - Mar 2022
Official Pytorch Code base for Target and Task specific Source-Free Domain Adaptive Image Segmentation
Contributions:9 commits, 2 PRs, 17 pushes in 1 day
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.