Jingtong Yue is a Carnegie Mellon University master’s student in Computer Vision with research interests spanning video generation, world models, robotics, and 3D vision. Her work focuses on developing controllable and physically grounded generative models that move beyond pixel-level synthesis toward realistic world simulation and embodied interaction.
Po-Hsuan Huang is a Carnegie Mellon University master’s student in Computer Vision with research interests spanning 3D vision, robotics, and large vision-language models. His work focuses on developing efficient autonomous systems and advanced perception pipelines, moving toward robust 4D scene understanding, intelligent agent interaction, and reliable multimodal models.
Vaishnavi Khindkar is a Carnegie Mellon University master’s student in Computer Vision at the Robotics Institute, with research interests spanning generative modeling, spatial intelligence, robotics perception, and 3D/4D scene understanding. Her work focuses on developing object-centric and geometry-aware learning frameworks that bridge visual perception with structured world representations for embodied AI. She is particularly interested in diffusion and flow-based generative models, representation learning, and controllable world models that move beyond pixel-level synthesis toward physically grounded reasoning and interaction.
I’m Badhrinarayanan K. V., a Master’s student in Computer Vision (MSCV) at Carnegie Mellon University, currently exploring 3D scene understanding, Gaussian Splatting, and multimodal Machine Learning. In my free time, I live to play football, basketball, and Valorant.
