Aishwarya Agarwal
Aishwarya Agarwal
Adobe Research (Current) IIIT Hyderabad (Part-time PhD) IIT Bombay (BTech + MTech)
Hi! I'm a Research Associate in the Collaborative Creativity team at Adobe Research, India, and a part-time PhD student at CVIT, IIIT Hyderabad. I am advised by Dr. Vineet Gandhi and co-advised by Dr. Srikrishna Karanam at Adobe Research. My research interests include Representation Learning in Resource-constrained Scenarios, Explainable Computer Vision, and Customization of Diffusion Models (e.g., Stable Diffusion) for Text-to-Image Generation.
I graduated from IIT Bombay, India, in 2022 with a Bachelor’s degree in Electrical Engineering and a Master’s degree in AI & Data Science. My thesis was on Out-of-distribution generalization with applications in classification and retrieval where I worked under the supervision of Dr. Biplab Banerjee. During my undergraduate study, I spent six amazing months as a research intern at Adobe Research, India where I worked with Dr. Balaji Vasan Srinivasan on problems related to context-aware scene enrichment, and multimodal question answering.
Email: agarwal.aishwarya2013@gmail.com
Publications
2025
-
Training-free Color-Style Disentanglement for Constrained Text-to-Image Synthesis
In Computer Vision and Pattern Recognition Workshop (CVPRW): AI for Creative Visual Content Generation Editing and Understanding, 2025.
-
TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction
In Computer Vision and Pattern Recognition (CVPR), 2025.
-
Composing Parts for Expressive Object Generation
In Computer Vision and Pattern Recognition (CVPR), 2025.
-
An Image is Worth Multiple Words: Multi-attribute Inversion for Constrained Text-to-Image Synthesis
In Winter Conference on Applications of Computer Vision (WACV), 2025.
-
AlignIT: Enhancing Prompt Alignment in Customization of Text-to-Image Models
In Winter Conference on Applications of Computer Vision (WACV), 2025.
2024
-
Iterative Multi-Granular Image Editing Using Diffusion Models
In Winter Conference on Applications of Computer Vision (WACV), 2024.
2023
-
ASTAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis
In International Conference on Computer Vision (ICCV), 2023.
-
SketchBuddy: Context-Aware Sketch Enrichment and Enhancement
In ACM Multimedia Systems Conference (ACM MMSys), 2023.
-
Contrastive Learning of Semantic Concepts for Open-set Cross-domain Retrieval
In Winter Conference on Applications of Computer Vision (WACV), 2023.
2022
-
Semantics-Driven Generative Replay
for Few-Shot Class Incremental Learning
In ACM International Conference on Multimedia (ACM MM), 2022.