Prafull Sharma

Prafull Sharma

Postdoctoral Associate, MIT

prafull (at) mit (dot) edu

I am a Postdoctoral Associate with Prof. Phillip Isola and Prof. Josh Tenenbaum in CSAIL and Brain and Cognitive Sciences Department. My research is focused on inferring and generating world models for novel games. I completed my PhD under the supervision of Prof. William T. Freeman and Prof. Frédo Durand in Computer Science & Artificial Intelligence Laboratory at MIT. My thesis was on learning low-level priors for both inference and generation of images. I also worked on non-line-of-sight imaging and generative models for computational photography. I pursued my undergraduate degree at Stanford where where I worked with Prof. Pat Hanrahan on efficient image processing for astronomy.

Publications

Evaluating Language Models' Evaluations of Games

Evaluating Language Models' Evaluations of Games

arXiv Preprint 2025

Katherine M Collins, Cedegao E Zhang, Graham Todd, Lance Ying, Mauricio Barba da Costa, Ryan Liu, Prafull Sharma, Adrian Weller, Ionatan Kuperwajs, Lionel Wong, Joshua B Tenenbaum, Thomas L Griffiths

Assessing Adaptive World Models in Machines with Novel Games

Assessing Adaptive World Models in Machines with Novel Games

arXiv Preprint 2025

Lance Ying, Katherine M Collins, Prafull Sharma, Cedric Colas, Kaiya Ivy Zhao, Adrian Weller, Zenna Tavares, Phillip Isola, Samuel J Gershman, Jacob D Andreas, Thomas L Griffiths, Francois Chollet, Kelsey R Allen, Joshua B Tenenbaum

MARBLE: Material Recomposition and Blending in CLIP-Space

MARBLE: Material Recomposition and Blending in CLIP-Space

CVPR 2025

Lance Ying, Katherine M Collins, Prafull Sharma, Cedric Colas, Kaiya Ivy Zhao, Adrian Weller, Zenna Tavares, Phillip Isola, Samuel J Gershman

ZeST: Zero-Shot Material Transfer from a Single Image

ECCV 2025

Ta-Ying Cheng, Prafull Sharma, Andrew Markham, Niki Trigoni, Varun Jampani

Alchemist: Parametric Control of Material Properties with Diffusion Models

CVPR 2024 (Oral)

Prafull Sharma, Varun Jampani, Yuanzhen Li, Xuhui Jia, Dmitry Lagun, Fredo Durand, Bill Freeman, Mark Matthews

Materialistic: Selecting Similar Materials in Images

SIGGRAPH 2023, ToG

Prafull Sharma, Julien Philip, Michael Gharbi, William T. Freeman, Fredo Durand, Valentin Deschaintre

Neural Groundplans: Persistent Neural Scene Representations from a Single Image

ICLR 2023

Prafull Sharma, Ayush Tewari, Yilun Du, Sergey Zakharov, Rares Ambrus, Adrien Gaidon, William T. Freeman, Fredo Durand, Joshua B. Tenenbaum, Vincent Sitzmann

What You Can Learn by Staring at a Blank Wall

ICCV 2021 (Oral)

Prafull Sharma, Miika Aittala, Yoav Y. Schechner, Antonio Torralba, Gregory W. Wornell, William T. Freeman, Frédo Durand

Self-supervised Speckle Reduction GAN for Synthetic Aperture Radar

Self-supervised Speckle Reduction GAN for Synthetic Aperture Radar

IEEE Radar Conference 2021

Michael Newey, Prafull Sharma

Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization

Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization

NeurIPS 2019

Miika Aittala, Prafull Sharma, Lukas Murmann, Adam Yedidia, Gregory Wornell, William T. Freeman, Frédo Durand

On the Importance of Label Quality for Semantic Segmentation

On the Importance of Label Quality for Semantic Segmentation

CVPR 2018

Aleksandar Zlateski, Ronnachai Jaroensri, Prafull Sharma, Frédo Durand

K-means++ vs. Behavioral Biometrics: One Loop to Rule Them All.

K-means++ vs. Behavioral Biometrics: One Loop to Rule Them All.

NDSS 2018

Parimarjan Negi, Prafull Sharma, Vivek Jain, Bahman Bahmani