Kinjawl Bhattacharyya

Hi! I am an incoming PhD student in Computer Science at UNC Chapel Hill, where I will be joining Prof. Roni Sengupta’s lab. My research will focus on physics-aware generative models for sim2real transfer and 3D perception, with applications to medical imaging and endoscopy videos.

I graduated in 2024 with a B.Tech. in Electrical Engineering from the Indian Institute of Technology (IIT) Kharagpur. Broadly, I am interested in using generative models to build learning systems that reason and generalize beyond controlled training settings and can communicate their uncertainty and limitations.

Previously, I worked in the Representation Learning Lab at IISc Bangalore with Prof. Prathosh A. P. on robustness and domain generalization for medical imaging, resulting in publications in Medical Image Analysis and at ICML 2025. I also interned at the Vision and Learning Lab, University of Alberta, supported by the Mitacs Globalink Research Internship. More recently, I was a Research Intern at the PALM Lab at the University of South Florida, where I worked with Prof. Anshuman Chhabra on reliability in language models, including abstention, uncertainty, and hallucination reduction.

You can find more details in my CV and Google Scholar profile. Feel free to reach out at kinjawl03@gmail.com or connect with me on LinkedIn.

news

Jun 08, 2026

I’ll be joining UNC Chapel Hill in Fall 2026 to pursue a PhD in Computer Science.

Aug 01, 2025

Started working as a Research Intern at the PALM Lab, University of South Florida under the supervision of Prof Anshuman Chhabra.

May 01, 2025

Our paper “LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation” has been accepted as a poster at ICML 2025.

May 15, 2024

Started working as a Pre-Doctoral Fellow at the ECE Department, IISc Bangalore, under the supervision of Dr. Prathosh AP, supported by the Kotak IISc AI-ML Centre Pre-Doctoral Fellowship.

Apr 27, 2024

Successfully completed my B.Tech in Electrical Engineering from IIT Kharagpur.

selected publications

ICML 2025

LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation

Piyush Tiwary, Kinjawl Bhattacharyya, and Prathosh AP

In Forty-second International Conference on Machine Learning, 2025

Abs Code Website

Medical image segmentation models often struggle to generalize across different domains due to various reasons. Domain Generalization (DG) methods overcome this either through representation learning or data augmentation (DAug). While representation learning methods seek domain-invariant features, they often rely on ad-hoc techniques and lack formal guarantees. DAug methods, which enrich model representations through synthetic samples, have shown comparable or superior performance to representation learning approaches. We propose LangDAug, a novel Langevin Data Augmentation for multi-source domain generalization in 2D medical image segmentation. LangDAug leverages Energy-Based Models (EBMs) trained via contrastive divergence to traverse between source domains, generating intermediate samples through Langevin dynamics. Theoretical analysis shows that LangDAug induces a regularization effect, and for GLMs, it upper-bounds the Rademacher complexity by the intrinsic dimensionality of the data manifold. Through extensive experiments on Fundus segmentation and 2D MRI prostate segmentation benchmarks, we show that LangDAug outperforms state-of-the-art domain generalization methods and effectively complements existing domain-randomization approaches.
Med. Image Anal.

Cycle consistent twin energy-based models for image-to-image translation

Piyush Tiwary, Kinjawl Bhattacharyya, and Prathosh AP

Medical Image Analysis, 2024

Abs HTML Code

Domain shift refers to change of distributional characteristics between the training (source) and the testing (target) datasets of a learning task, leading to performance drop. For tasks involving medical images, domain shift may be caused because of several factors such as change in underlying imaging modalities, measuring devices and staining mechanisms. Recent approaches address this issue via generative models based on the principles of adversarial learning albeit they suffer from issues such as difficulty in training and lack of diversity. Motivated by the aforementioned observations, we adapt an alternative class of deep generative models called the Energy-Based Models (EBMs) for the task of unpaired image-to-image translation of medical images. Specifically, we propose a novel method called the Cycle Consistent Twin EBMs (CCT-EBM) which employs a pair of EBMs in the latent space of an Auto-Encoder trained on the source data. While one of the EBMs translates the source to the target domain the other does vice-versa along with a novel consistency loss, ensuring translation symmetry and coupling between the domains. We theoretically analyze the proposed method and show that our design leads to better translation between the domains with reduced langevin mixing steps. We demonstrate the efficacy of our method through detailed quantitative and qualitative experiments on image segmentation tasks on three different datasets vis-a-vis state-of-the-art methods.