portrait

I'm a PhD student at Princeton with the good fortune of being advised by Prof. Niraj K Jha. I currently live in Powai Princeton Philadelphia. I work on scalable data-curation, architectures, and training objectives for large-scale generative models, with an emphasis on adaptive and efficient inference. Previously, I interned at Adobe Research. In a past life, I spent four years at IIT-Bombay studying Electrical Engineering. I like running on obscure trails, books, picking my guitar, thrifting antique cameras, and development economics.

CV / Twitter / Github / LinkedIn / Emailfirstname[dot]lastname[at]gmail[dot]com

Selected Work (scholar page)

Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need
Bhishma Dedhia, Yuval Kansal, Niraj K Jha
arXiv, under submission
[website] [arXiv] [pdf]
Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks
Bhishma Dedhia, David Bourgin, Krishna Kumar Singh, Yuheng Li, Yan Kang, Niraj K Jha, Yuchen Liu
International Conference on Computer Vision (ICCV) 2025
[website] [arXiv] [pdf]
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations
Bhishma Dedhia, Niraj K Jha
Transactions of Machine Learning Research (TMLR), 2025
[arXiv] [pdf] [code]
Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
Hongjie Wang, Bhishma Dedhia, Niraj K Jha
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[website] [arXiv] [pdf]
Im-Promptu: In-Context Composition from Image Prompts
Bhishma Dedhia, Michael Chang, Jake C. Snell, Thomas L. Griffiths, Niraj K. Jha
Neural Information Processing Systems (NeurIPS), 2023
[website] [arXiv] [pdf] [code]
SCouT: Synthetic Counterfactuals via Spatiotemporal Transformers for Actionable Healthcare
Bhishma Dedhia* , Roshini Balasubramanian* , Niraj K Jha
ACM Transactions on Computing for Healthcare 2023
[arXiv] [pdf] [code]
FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?
Shikhar Tuli, Bhishma Dedhia, Shreshth Tuli, Niraj K Jha
Journal of AI Research 2023
[arXiv] [pdf] [code]