I'm a Senior AI Researcher at Dolby Laboratories Inc. working on Generative modelling and Computer Vision. Previously I was a PhD student in the Department of Computer Science and Engineering at IIT Kanpur where I was advised by Prof. Piyush Rai and Prof. Vinay P. Namboodiri (University of Bath).

Education

2018—2025

Indian Institute of Technology Kanpur

Integrated M.Tech. - Ph.D. in Computer Science and Engineering

Advisor: Prof. Piyush Rai & Prof. Vinay P. Namboodiri (University of Bath)

Thesis: Towards Expressive and Compact Deep Generative Models: Attentive Flows and Block-wise Diffusion Models

2016—2018

Ramakrishna Mission Vivekananda Educational and Research Institute

M.Sc. in Computer Science

Thesis: A Medoid-Based Weighting Scheme for Qualitative Improvement of Nearest Neighbor Decision Rule

2013—2016

Ramakrishna Mission Vidyamandira

B.Sc. in Computer Science

Publications

Computer Vision and Pattern Recognition (under review) 2025

Patch-Diffusion with Dynamic Retrieval-Augmented Guidance via Permutation-Invariant Conditioning

Pal, Shivam; Mukherjee, A; Namboodiri, Vinay P; Rai, Piyush

British Machine Vision Conference (BMVC) 2024

RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-Guidance

Mukherjee, A; Banerjee, S; Rai, P; Namboodiri, VP

British Machine Vision Conference (BMVC) 2023

Attentive Contractive Flow with Lipschitz Constrained Self-Attention

Mukherjee, A; Patro, BN; Namboodiri, V

Transactions on Machine Learning Research (TMLR) 2022

DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents

Pandey, K; Mukherjee, A; Rai, P; Kumar, A

Neural Information Processing System (NeurIPS) Workshop 2021

VAEs meet Diffusion Models: Efficient and High-Fidelity Generation

Pandey, K; Mukherjee, A; Rai, P; Kumar, A

Atmospheric Environment 2024

A Hybrid Approach for Integrating Micro-Satellite Images and Sensors Network-Based Ground Measurements Using Deep Learning for High-Resolution Prediction of Fine Particulate Matter (PM2.5) over an Indian City, Lucknow

Tripathi, Sachchida; Jain, Vaishali; Mukherjee, Avideep; Madhwal, Sandeep; Bergin, Michael H.; Bhave, Prakash; Carlson, David; Jiang, Ziyang; Rai, Piyush

International Conference on Robotics and Automation (ICRA) 2024

Verse: Virtual-gradient Aware Streaming Lifelong Learning with Anytime Inference

Banerjee, S; Verma, VK; Mukherjee, A; Gupta, D; Namboodiri, VP; Rai, P

European Geosciences Union - General Assembly 2023

Predicting PM2.5 based on micro-satellite imagery and low-cost sensor network using CNN-RT-RF Joint Model

Tripathi, S; Jain, V; Mukherjee, A; Banerjee, S; Rai, P; Madhwal, S

Springer Nature Applied Sciences 2018

A medoid-based weighting scheme for nearest-neighbor decision rule toward effective text categorization

Mukherjee, A; Basu, T

International Conference on Data Science 2018

An Effective Nearest Neighbor Classification Technique Using Medoid Based Weighting Scheme

Mukherjee, A; Basu, T

Experience

January 2025 - Present

Senior AI Researcher Dolby Laboratories Inc.

Manager: Claus Bauer

Working on Computer Vision, Generative Modelling and Attribution

August 2022 - December 2024

Senior Student Research Associate Indian Institute of Technology Kanpur

Advisor: Prof. Sachida Nand Tripathi & Prof. Piyush Rai

Developed novel algorithms for prediction of PM 2.5 concentration in the environment.

Summer 2021

Software Development Engineering Intern Linkedin Corporation

Manager: Vipin Gupta

Worked on developing text-to-image geneative models using GANs.

Summer 2017

Summer Intern Indian Statistical Institute, Kolkata

Advisor: Prof. Partha Pratim Mohanty

Worked on developing classical solutions to unconstrained video recognition using SIFT and HOG features.