Silpa Vadakkeeveetil Sreelatha

About

I am an ELLIS Ph.D. student specializing in trustworthy and responsible generative AI, co-advised by Dr. Anjan Dutta (University of Surrey), Prof. Serge Belongie (University of Copenhagen), and Dr. Muhammad Awais (University of Surrey). I am affiliated with the Surrey Institute for People-Centred AI, Centre for Vision, Speech and Signal Processing (CVSSP), and the Pioneer Centre for Artificial Intelligence in Copenhagen. Before my Ph.D., I worked as a researcher (2019–2022) at Tata Research and Innovation Labs under Dr. Shirish Subhash Karande.

My research addresses trustworthiness and equity in generative AI, with a focus on diffusion model interpretability, fairness, and bias mitigation in text-to-image generation. My long-term vision is to build interpretability tools that give us a deeper understanding of what AI systems learn, and use that understanding as a lever to systematically improve fairness, reliability, and safety across a wide range of applications.

Responsible AI Generative Models Fairness & Bias Interpretability Computer Vision Diffusion Models

Always happy to chat about research or explore collaborations. Feel free to reach out!

Publications & Patents

^‡ Equal contribution.

RAIGen: Rare Attribute Identification in Text-to-Image Generative Models

Silpa Vadakkeeveetil Sreelatha, Dan Wang, Serge Belongie, Muhammad Awais, Anjan Dutta

ICML 2026 paper project page

Earlier version presented as MADGen at UPLB Workshop, EurIPS 2025.

RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation

Silpa Vadakkeeveetil Sreelatha, Sauradip Nag, Muhammad Awais, Serge Belongie, Anjan Dutta

NeurIPS 2025 paper code project page

Earlier version presented as Concept Denoising Score Matching at SafeGenAI Workshop, NeurIPS 2024.

DeNetDM: Debiasing by Network Depth Modulation

Silpa Vadakkeeveetil Sreelatha^‡, Adarsh Kappiyath^‡, Abhra Chaudhuri, Anjan Dutta

NeurIPS 2024 paper code project page

Self-Supervised Enhancement of Latent Discovery in GANs

Adarsh Kappiyath^‡, Silpa Vadakkeeveetil Sreelatha^‡, S Sumitra

AAAI 2022 paper

Understanding Advertisements with BERT

Kanika Kalra, Bhargav Kurma, Silpa Vadakkeeveetil Sreelatha, Manasi Patwardhan, Shirish Karande

ACL 2020 paper

Disentanglement based Active Learning

Adarsh Kappiyath^‡, Silpa Vadakkeeveetil Sreelatha^‡, S Sumitra

IJCNN 2021 paper code

Method and system for visio-linguistic understanding using contextual language model reasoners

Sai Sree Bhargav Kurma, Kanika Kalra, Silpa Vadakkeeveetil Sreelatha, Manasi Patwardhan, Shirish Subhash Karande

US Patent patent

Awards & Honours

2026

120,000 GPU Hours — Isambard-AI AIRR

Awarded compute time on the UK national HPC (Isambard-AI AIRR) to scale trustworthiness experiments in text-to-image generation (project: TrustDiff).
2023

ELLIS PhD Student

Selected for the European Laboratory for Learning and Intelligent Systems PhD program — one of Europe's most competitive AI PhD programs (~5% acceptance rate).
2019

Department of Space Fellowship

Awarded by the Department of Space, India for M.Tech at IIST.
2018

Finalist, Microsoft AI Challenge

Selected as a finalist in the Microsoft AI Challenge.
2017

GATE — Top 1.4%

Ranked 1,349 out of 96,878 candidates (98.6th percentile) in the All India Graduate Aptitude Test in Engineering.

Updates

Jul 2026	Heading to Seoul for ICML 2026 to present RAIGen, then straight to Lisbon for the ELLIS PhD Symposium. A busy summer ahead!
Feb 2026	Wrapped up a wonderful six months in Copenhagen and headed back to Surrey.
Jan 2026	Gave an invited talk on Responsible Text-to-Image Diffusion Models at DTU Compute — my first invited talk!
Dec 2025	Got to present our work at EurIPS in Copenhagen.
Aug 2025	Had a fantastic time at the ELLIS PhD Symposium in Warsaw — great talks, great people and good food. Thanks to the ELSA Mobility Grant for funding this trip!
Aug 2025	Kicked off my ELLIS research visit at Pioneer Centre for AI, University of Copenhagen. So excited for this!
Jun 2023	Officially started my PhD at the University of Surrey. A new chapter begins!
Dec 2020	Attended NeurIPS 2020 — my very first in-person conference. Still one of my favourite memories.
Jun 2019	Joined TCS Research as a Deep Learning researcher.

Academic Service

Conference reviewing — ICLR (2024–2026), NeurIPS (2023–2026), CVPR (2024–2025), ICML (2024), ICCV (2025)

Workshop reviewing — WiCV CVPR 2023, SafeGenAI NeurIPS 2024

Teaching — Teaching Assistant, Applied Machine Learning, University of Surrey (2023, 2024); Mentor, M.Tech course projects on diffusion models, University of Surrey (~50 students)

Supervision — Co-supervisor, MSc Dissertation on controllable image editing using diffusion models, University of Surrey (2024–2025); Co-supervisor, MSc Dissertation on building robust classifiers using generative models, IIST (2022–2023)

Invited Talks

2026

Towards Responsible Text-to-Image Diffusion Models

DTU Compute, Technical University of Denmark, Copenhagen, Denmark.

Vita

Full resume available as a PDF.

Jun 2023 – present

University of Surrey

Ph.D. Student, People-Centred Artificial Intelligence
Jul 2019 – Apr 2022

TCS Research

Researcher, Deep Learning & AI
Jul 2017 – Jun 2019

Indian Institute of Space Science and Technology

M.Tech., Machine Learning and Computing
Aug 2012 – May 2016

Government Engineering College, Sreekrishnapuram

B.Tech., Computer Science and Engineering