Silpa Vadakkeeveetil Sreelatha
silpavs.bsky.social
Silpa Vadakkeeveetil Sreelatha
@silpavs.bsky.social
PhD student at University of Surrey @ELLISforEurope | Visiting Researcher at @belongielab.bsky.social | Trustworthy Machine Learning – Interpretability – Generative Modelling
In this paper, we aim for responsible (fair and safe) text-to-image generation in diffusion models. Join me to discuss how we can improve generative models for better fairness and safety!

(5/5)
December 11, 2024 at 5:38 AM
(2) Concept Denoising Score Matching for Responsible Text-to-Image Generation
🗓️ Sun, Dec 15 | 🕗 8:15 a.m. PST | 📍 Safe Generative AI Workshop
Authors : Silpa Vadakkeeveetil Sreelatha, Sauradip Nag, @serge.belongie.com , Muhammad Awais, and Anjan Dutta

(4/5)
December 11, 2024 at 5:38 AM
We introduce DeNetDM, a debiasing method that improves robustness to spurious correlations. Our method requires no bias annotations or explicit data augmentation while performing on par with approaches that require either or both. More details can be found here : arxiv.org/abs/2403.19863

(3/5)
December 11, 2024 at 5:38 AM
(1) DeNetDM: Debiasing by Network Depth Modulation
🗓️ Thu, Dec 12 | 🕚 11 a.m. – 2 p.m. PST | 📍 East Exhibit Hall A-C #4309
Authors : Silpa Vadakkeeveetil Sreelatha *, Adarsh Kappiyath*, Abhra Chaudhuri, Anjan Dutta — * equal contribution

(2/5)
December 11, 2024 at 5:38 AM
Could you please add me? I am an ELLIS PhD student.
November 20, 2024 at 12:42 PM