Deepak Sridhar

San Diego, California

I am a third year PhD student at UCSD specializing in Computer Vision, advised by Prof. Nuno Vasconcelos. My research focuses on multimodal generative AI, with interests spanning multimodal generation, editing, and understanding. I am also interested in efficient personalization methods.

My recent work is an efficient diffusion model framework (link) that offers high prompt compliance, controllability, modularity, editing and applicability to multimodal content generation (video, audio and 3D), understanding and editing. Previously, I have worked on some fundamental vision problems such as efficient classification and detection in images and videos.

Outside of Research, I love to go on hiking and exploring the nature. I also love to participate in outdoor adventures.

news

Sep 29, 2024	Gave a oral presentation of my PromptSliders paper at the Unlearning and Model Editing Workshop in ECCV’24.
Sep 25, 2024	Paper on “Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis” accepted to NeurIPS’24! .
Aug 16, 2024	Paper on “Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models” accepted to ECCV’24-Unlearning and Model Editing Workshop! .
Dec 1, 2023	New preprint available on arXiv! SCHEME: Scalable Channel Mixer for Vision Transformers.
Sep 26, 2022	Started my PhD in Fall 2022 with Jacobs Fellow Award (Highest recognition in ECE at UCSD).

selected publications

2024

Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis

Deepak Sridhar, Abhishek Peri, Rohit Rachala, and 1 more author

In Neural Information Processing Systems, 2024

Bib PDF

@inproceedings{neuripssridhar24,
  author = {Sridhar, Deepak and Peri, Abhishek and Rachala, Rohit and Vasconcelos, Nuno},
  title = {Adapting Diffusion Models for Improved Prompt Compliance   and Controllable Image Synthesis},
  booktitle = {Neural Information Processing Systems},
  year = {2024}
}

Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models

Deepak Sridhar, and Nuno Vasconcelos

In In Proceedings of the IEEE/CVF European Conference on Computer Vision Workshops, 2024

Bib PDF

@inproceedings{eccvsridhar24,
  author = {Sridhar, Deepak and Vasconcelos, Nuno},
  title = {Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models},
  booktitle = {In Proceedings of the IEEE/CVF European Conference on Computer Vision Workshops},
  year = {2024}
}

2023

SCHEME: Scalable Channel Mixer for Vision Transformers

Deepak Sridhar, Yunsheng Li, and Nuno Vasconcelos

2023

Bib PDF

@misc{sridhar2024schemescalablechannelmixer,
  title = {SCHEME: Scalable Channel Mixer for Vision Transformers},
  author = {Sridhar, Deepak and Li, Yunsheng and Vasconcelos, Nuno},
  year = {2023},
  eprint = {2312.00412},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
}

2021

Class semantics-based attention for action detection

Deepak Sridhar, Niamul Quader, Srikanth Muralidharan, and 3 more authors

In In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021

Bib PDF Supp

@inproceedings{sridhar21,
  author = {Sridhar, Deepak and Quader, Niamul and Muralidharan, Srikanth and Li, Yaoxin and Dai, Peng and Lu, Juwei},
  title = {Class semantics-based attention for action
                  detection},
  booktitle = {In Proceedings of the IEEE/CVF International
                  Conference on Computer Vision},
  year = {2021}
}