Samyam Lamichhane
Research Assistant
Affiliation: NYU Abu Dhabi
Education: BA New York University Abu Dhabi
Research Areas: Reinforcement Learning, Computer Vision, Graph Machine Learning
Samyam Lamichhane is a researcher at New York University Abu Dhabi whose work focuses on reinforcement learning, computer vision, and graph machine learning. His earlier research explored embodied AI and vision-based systems, including projects in medical image analysis, robotic control, sign language translation, and dust accumulation quantification on photovoltaic panels using deep learning visual models. His work has involved applying reinforcement learning to control and decision-making tasks, alongside developing computer vision models for multimodal imaging, detection, and robotics-oriented systems.
Currently, at the Collaborative Intelligence Lab, his research centers on the intersection of reinforcement learning and graph machine learning, with a focus on transformer architectures, scalable subgraph sampling, and optimization methods for large-scale knowledge graphs. He has authored research publications and submissions in Elsevier journals and has received several honors across Abu Dhabi (NYUAD), New York (NYU Tandon), and Boston (MIT).
Summary of Research
Lamichhane's research focuses on improving how AI systems learn and reason over large-scale graph and relational data through efficient sampling, transformer-based modeling, and adaptive learning methods.