Prerit Gupta

About Me

I am a Ph.D. student in Computer Science at Purdue University, working in the IDEAS Lab under the supervision of Prof. Aniket Bera. My research lies at the intersection of interactive human motion graphics, affective computing, and multimodal generative AI. My current work explores how multimodal learning frameworks—combining motion, text and music — can enable better contextualized and controlled generation. This includes building datasets and models for interactive and reactive motion generation, and context-sensitive human–AI interaction in immersive environments such as VR. Some of the upcoming projects I have been working on are related to exploring motion editing and long-term generation for two-person generation. Previously, I earned my B.Tech and M.Tech in Electronics and Electrical Communications from IIT Kharagpur.

Selected Publications

Prerit Gupta, Jason Alexander Fotso-Puepi, Zhengyuan Li, Jay Mehta, and Aniket Bera. MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025. [link]
Prerit Gupta, Shourya Verma, Ananth Grama, and Aniket Bera. DuetRAG: Multi-Modal 3D Motion Duet Dance Generation via Retrieval-Augmented Feature Guided Contrastive Rectified Flow. Under Review at IEEE/CVF Winter Conference for Applications in Computer Vision, 2026.
Prerit Gupta, Shourya Verma, Ananth Grama, and Aniket Bera. Unified Multi-Modal Interactive and Reactive 3D Motion Generation via Rectified Flow. Under Review at International Conference on Learning Representations (ICLR), 2026. [link]

About Me

Selected Publications

Contact