Hi, I'm Vihaan Misra!
PhD Student, Robotics Institute, Carnegie Mellon University
I am a PhD student at the Robotics Institute at CMU, working with Prof. Jean Oh in the Bot-Intelligence Group. Prior to joining CMU, I received my bachelor's in Electrical Engineering with a minor in AI from Netaji Subhas University of Technology.
My research focuses on multimodal generative models that bridge semantic understanding with physical constraints. I'm interested in how robots can create and manipulate their environment using different modalities like language, audio, and vision. This spans work on cross-modal translation, text-driven spatial arrangement with geometric constraints, and understanding how generative models encode abstract structural concepts like numerosity and spatial relationships. The common thread is building systems that are not just visually compelling but also physically grounded and controllable in meaningful ways.
Selected Publications
ShapeShift: Text-to-Mosaic Synthesis via Semantic Phase-Field Guidances
Under Review, SIGGRAPH 2026
If I Move, Do You Move? Investigating the Role of Interpersonal Synchrony in Human-Robot Joint Painting
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2025) - Forthcoming
AdaGen: Adaptive Generalized Knowledge Transfer Framework for Sensor-based Surface Classification
SN Computer Science (2024)
Sketch-to-Image Synthesis using Semantic Priors
RISS Working Papers' Journal | Robotics Institute Summer Scholars Journal (2022)
A Machine Learning Application for Raising WASH Awareness in the Times of COVID-19 Pandemic
Scientific Reports, Nature Publications (2022)
Robotics in Industry 4.0
Handbook of Smart Materials, Technologies, and Devices, Springer (2021)
Experience
Scholar
Twitter