Research Activity

My research focuses on developing efficient and adaptive foundational models, with a primary emphasis on Generative Models. A major theme in my recent work has been exploring the intersection of model efficiency and generative architectures, including effective techniques for model distillation and the compression of large-scale models like Mixture-of-Experts (MoE). I am also keen to explore new research directions, including the interpretability of foundational models and reasoning capabilities in vision models.

I have also served as reviewer in conferences like CVPR, ICML, ICLR, WACV, AAMAS multiple times.


Publications

Masked Generative Nested Transformers paper thumbnail

Masked Generative Nested Transformers with Decode Time Scaling

Sahil Goyal, Debapriya Tula, Prateek Jain, Sujoy Paul et al.
ICML 2025 & ICLR (DeLTa Workshop) 2025

Design-o-meter paper thumbnail

Design-o-meter: Towards Evaluating and Refining Graphic Designs

Sahil Goyal, Abhinav Mahajan, KJ Joseph et al.
WACV 2025

Emotionally Enhanced Talking Face Generation paper thumbnail

Emotionally Enhanced Talking Face Generation

Sahil Goyal, Shagun Uppal, Sarthak Bhagat, et al.
ICCV (CVEU Workshop) 2023 & ACM MM (McGE Workshop) 2023

Emotional Talking Faces paper thumbnail

Emotional Talking Faces: Making Videos More Expressive and Realistic

Sahil Goyal, Shagun Uppal, Sarthak Bhagat, et al.
ACM MM Asia 2022