About Me

I am working as a Research Scientist at Sync Labs, where I develop advanced AI-driven video editing tools. My work focuses on designing state-of-the-art generative architectures — spanning diffusion and flow matching models, GANs, and transformer-based networks — to enable precise, controllable modification of human appearance, lips, motion, and expression in video sequences. My models are being used by OTT platforms, movie studios, and online content creators.
I earned my Ph.D. in Artificial Intelligence from the Department of Electrical Engineering at the Indian Institute of Technology Bombay, where I developed resource-efficient neural architectures for computer vision tasks such as classification, segmentation, inpainting, and super-resolution. During my doctoral studies, I was associated with the MeDAL (Medical Imaging, Deep Learning, and Artificial Intelligence Lab) under the supervision of Prof. Amit Sethi.
I completed a six-month internship (July 2023 – January 2024) with the AI Camera Team of the Visual Intelligence Division at Samsung R&D Institute India, Bangalore (SRI-B), where I developed and optimized deep learning models for image classification, object detection, and generative tasks. These models have been integrated into Samsung's flagship Galaxy S24 series.
I returned to academic research at the Department of Physics, Indian Institute of Technology Madras, focusing on theoretical physics, quantum computing, and quantum information under Prof. Vaibhav Madhok.
Post-Graduate Engineering Trainee at the Engineering Research Centre of Tata Motors Limited, where I conducted vehicle performance and thermal analysis for braking systems.
M.Tech in Robotics at the Department of Mechanical Engineering, Indian Institute of Technology Kanpur, where I was part of the Center for Mechatronics. Under Prof. Ashish Dutta, I designed and prototyped a lower-extremity exoskeleton for rehabilitation.
B.Tech in Mechanical Engineering from NSS College of Engineering, University of Calicut.
I regularly serve as a reviewer for premier computer vision and machine learning conferences, including CVPR, ICCV, ECCV, ICLR, AAAI, and WACV.

News

Latest Updates

  • DEC'25
    Our paper Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images has been accepted at ISBI 2026.
  • DEC'25
    Our paper Survival Modeling from Whole Slide Images via Patch-Level Graph Clustering and Mixture Density Experts has been accepted at ISBI 2026.
  • OCT'25
    Our paper WaveMix: A Resource-efficient Neural Network for Image Analysis has been accepted at ICML 2026.
  • OCT'25
    Our paper Normalizing Flow-Based Metric for Image Generation has been accepted at ICML 2026.
  • OCT'25
    Our paper Convolutional Xformers for Vision has been accepted at ICML 2026.
  • OCT'25
    I defended my Ph.D. thesis: Resource-efficient Architectures for Computer Vision.
  • AUG'25
    Our book chapter A Comparative Study of Deep Neural Network Architectures in Magnification Invariant Breast Cancer Histopathology Image Analysis has been published in BIOSTEC 2024 Selected Papers (Springer).
  • JUL'25
    Our paper FLD+: a data-efficient evaluation metric for generative models has been accepted at ICCV 2025.
  • JUL'25
    Our paper WavePaint: a resource-efficient token-mixer for self-supervised inpainting has been accepted at ICCV 2025.
  • MAR'25
    Our paper Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision has been published in Transactions on Machine Learning Research (TMLR).
  • NOV'24
    Our paper Evaluation Metric for Quality Control and Generative Models in Histopathology Images has been accepted at ISBI 2025.
  • NOV'24
    Our paper PathoGen-X: A Cross-Modal Genomic Feature Trans-Align Network for Enhanced Survival Prediction from Histopathology Images has been accepted at ISBI 2025.
  • OCT'24
    Our paper WaveMixSR-V2, enhancing super-resolution with higher efficiency, has been accepted at AAAI 2025.
  • SEP'24
    Our paper EDSNet: Efficient-DSNet for Video Summarization is available as an arXiv preprint.
  • AUG'24
    Our paper PawFACS for pet facial action recognition has been accepted at BMVC 2024.
  • MAY'24
    Our paper FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch has been accepted at IEEE BigData 2024.
  • APR'24
    Our paper Adversarial Transport Terms for Unsupervised Domain Adaptation has been accepted at ICPR 2024.
  • MAR'24
    Our paper Advancing Gene Selection in Oncology: A Fusion of Deep Learning and Sparsity for Precision Gene Selection is available as an arXiv preprint.
  • FEB'24
    Our paper Magnification Invariant Medical Image Analysis has received the Best Student Paper Award at Bioimaging 2024.
  • JAN'24
    Successfully completed a six-month internship with the AI Camera Team at Samsung R&D Institute, Bangalore.
  • OCT'23
    Our paper WaveMixSR: a resource-efficient neural network for image super-resolution has been accepted at WACV 2024.
  • AUG'23
    Our paper Heterogeneous Graphs Model Spatial Relationships for Breast Cancer Diagnosis has been accepted at MICCAI 2023.
  • MAR'23
    Our paper Resource-efficient Image Inpainting has been accepted as a Tiny paper at ICLR 2023.
  • OCT'21
    Our paper Resource-efficient Hybrid X-formers for Vision has been accepted at WACV 2022.
  • JUL'21
    Our paper "So You Think You're Funny?": Rating the Humour Quotient in Standup Comedy has been accepted at EMNLP 2021.
  • DEC'25
    Our paper Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images has been accepted at ISBI 2026.
  • DEC'25
    Our paper Survival Modeling from Whole Slide Images via Patch-Level Graph Clustering and Mixture Density Experts has been accepted at ISBI 2026.
  • OCT'25
    Our paper WaveMix: A Resource-efficient Neural Network for Image Analysis has been accepted at ICML 2026.
  • OCT'25
    Our paper Normalizing Flow-Based Metric for Image Generation has been accepted at ICML 2026.
  • OCT'25
    Our paper Convolutional Xformers for Vision has been accepted at ICML 2026.
  • OCT'25
    I defended my Ph.D. thesis: Resource-efficient Architectures for Computer Vision.
  • AUG'25
    Our book chapter A Comparative Study of Deep Neural Network Architectures in Magnification Invariant Breast Cancer Histopathology Image Analysis has been published in BIOSTEC 2024 Selected Papers (Springer).
  • JUL'25
    Our paper FLD+: a data-efficient evaluation metric for generative models has been accepted at ICCV 2025.
  • JUL'25
    Our paper WavePaint: a resource-efficient token-mixer for self-supervised inpainting has been accepted at ICCV 2025.
  • MAR'25
    Our paper Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision has been published in Transactions on Machine Learning Research (TMLR).
  • NOV'24
    Our paper Evaluation Metric for Quality Control and Generative Models in Histopathology Images has been accepted at ISBI 2025.
  • NOV'24
    Our paper PathoGen-X: A Cross-Modal Genomic Feature Trans-Align Network for Enhanced Survival Prediction from Histopathology Images has been accepted at ISBI 2025.
  • OCT'24
    Our paper WaveMixSR-V2, enhancing super-resolution with higher efficiency, has been accepted at AAAI 2025.
  • SEP'24
    Our paper EDSNet: Efficient-DSNet for Video Summarization is available as an arXiv preprint.
  • AUG'24
    Our paper PawFACS for pet facial action recognition has been accepted at BMVC 2024.
  • MAY'24
    Our paper FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch has been accepted at IEEE BigData 2024.
  • APR'24
    Our paper Adversarial Transport Terms for Unsupervised Domain Adaptation has been accepted at ICPR 2024.
  • MAR'24
    Our paper Advancing Gene Selection in Oncology: A Fusion of Deep Learning and Sparsity for Precision Gene Selection is available as an arXiv preprint.
  • FEB'24
    Our paper Magnification Invariant Medical Image Analysis has received the Best Student Paper Award at Bioimaging 2024.
  • JAN'24
    Successfully completed a six-month internship with the AI Camera Team at Samsung R&D Institute, Bangalore.
  • OCT'23
    Our paper WaveMixSR: a resource-efficient neural network for image super-resolution has been accepted at WACV 2024.
  • AUG'23
    Our paper Heterogeneous Graphs Model Spatial Relationships for Breast Cancer Diagnosis has been accepted at MICCAI 2023.
  • MAR'23
    Our paper Resource-efficient Image Inpainting has been accepted as a Tiny paper at ICLR 2023.
  • OCT'21
    Our paper Resource-efficient Hybrid X-formers for Vision has been accepted at WACV 2022.
  • JUL'21
    Our paper "So You Think You're Funny?": Rating the Humour Quotient in Standup Comedy has been accepted at EMNLP 2021.

Expertise

What I Work On

Deep Learning & Generative Models

Diffusion & flow matching, GANs, transformers, and token-mixers — resource-efficient, faster, smaller.

Computer Vision & Video Editing

Controllable editing of appearance, lips, and expression in video — super-resolution, inpainting, segmentation,action detection, motion transfer.

Medical Imaging & Health AI

Histopathology over whole-slide images, survival modeling, and magnification-invariant analysis for diagnosis.

Science & Engineering

Theoretical physics, quantum computing, robotics, and exoskeletons.

Python PyTorch TensorFlow CUDA OpenCV MATLAB C++ Git