Silpa Vadakkeeveetil Sreelatha

About

I am an ELLIS Ph.D. student specializing in Machine Learning and Computer Vision, 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 (PAI), CVSSP at the University of Surrey, and the Pioneer Centre for Artificial Intelligence in Copenhagen.

Before my Ph.D., I worked as a full-time researcher (2019–2022) at Tata Research and Innovation Labs, focusing on Deep Learning and AI under Dr. Shirish Subhash Karande.

My research focuses on discovering interpretable representations within deep learning models to advance fairness, robustness, and transparency in both discriminative and generative models.

I am always open to collaborations — feel free to reach out!

News

• Oct 2025 Our paper on identifying unknown biases in diffusion models accepted in UPLB Workshop, NeurIPS 2025!
• Sep 2025 Our paper on Responsible T2I generation accepted in NeurIPS 2025!
• Aug 2025 Attending ELLIS PhD Symposium, Warsaw, Poland!
• Aug 2025 Excited to begin my ELLIS Research visit at Pioneer Centre for AI, University of Copenhagen!
• Sep 2024 Our paper on Responsible T2I generation accepted in SafeGenAI workshop, NeurIPS 2024!
• Sep 2024 Our paper on Debiasing accepted in NeurIPS 2024. See you in Vancouver!
• Jun 2023 Excited to start as a PhD student at the University of Surrey.
• Dec 2022 Shortlisted for the prestigious ELLIS PhD program!
• Nov 2021 Our paper on Interpretable latent discovery in GANs accepted in AAAI 2022.
• Apr 2021 Our work on Disentanglement based Active Learning accepted at IJCNN 2021.
• Apr 2020 Our paper on Advertisement understanding accepted in ACL 2020.
• Dec 2020 Thrilled to attend my first-ever in-person conference — NeurIPS 2020!
• Apr 2020 Our work on Disentanglement based Active Learning accepted at CtrlGen workshop, NeurIPS 2020.
• Jun 2019 Started working as Deep Learning Researcher at TCS Research.

Publications & Patents

^‡ Equal contribution.

Papers

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

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

  NeurIPS'25

  Project Page Paper Code

• Concept Denoising Score Matching for Responsible Text-to-Image Generation

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

  Safe Generative AI Workshop, NeurIPS 2024

  Paper

• DeNetDM: Debiasing by Network Depth Modulation

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

  NeurIPS'24

  Project Page Paper Code

• Self-Supervised Enhancement of Latent Discovery in GANs

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

  AAAI'22

  Paper

• Understanding Advertisements with BERT

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

  ACL'22

  Paper

• Disentanglement based Active Learning

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

  IJCNN'21

  Paper Code

Patents

• 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

Academic Service

Conference Reviewing: ICLR (2024–2026), NeurIPS (2023–2025), CVPR (2024), ICML (2024), ICCV (2025)

Workshop Reviewing: WiCV CVPR'2023, SafeGenAI NeurIPS'2024

Vita

Full resume in PDF.

• June 2023 - now
  University of Surrey Ph.D. Student — People-Centred Artificial Intelligence
• July 2019-April 2022
  TCS Research Researcher — Deep Learning & AI
• July 2017 – June 2019
  Indian Institute of Space Science and Technology, India M.Tech. Student — Machine Learning and Computing
• Aug 2012 - May 2016
  Government Engineering College, Sreekrishnapuram B.Tech Student — Computer Science and Engineering