|
Shivam Singh I'm a Computer Science PhD student at Arizona State University specializing in computer vision and generative models, with a focus on controllable image and video generation. I am broadly interested in developing theoretical foundations and practical tools for generative models, for use-cases like image editing and personalization. I’m also interested in reinforcement learning (RL) to steer generative models to outputs closely aligned with human preferences. I have over 2 years of research experience in model fine-tuning and large-scale image generation. Previously, I completed my Bachelor’s degree in Computer Science at Jadavpur University, India where I worked as an undergraduate research assistant conducting research on AI in medical imaging. If you’d like to discuss research opportunities, please feel free to reach out via email. |
|
News |
PublicationsI'm interested in computer vision, deep learning, generative AI, and image processing. |
|
|
RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model for Referring Expression
Bimsara Pathiraja, Maitreya Patel, Shivam Singh, Yezhou Yang, Chitta Baral ICCV, 2025 project page / arXiv We develop RefEdit, an instruction-based editing model trained on 20,000 synthetic triplets, outperforms baselines trained on millions of samples in complex scene editing and achieves state-of-the-art results on referring expression and traditional benchmarks. |
|
Chimera: Compositional Image Generation using Part-Based Concepting
Shivam Singh, Yiming Chen, Agneet Chatterjee, Amit Raj, James Hays, Yezhou Yang, Chitta Baral Under Review, 2025 project page / arXiv Chimera is a personalized image generation model trained on a semantic part-based dataset, enabling novel object synthesis by combining parts from multiple images via textual instructions, outperforming baselines by 14% in compositional accuracy and 21% in visual quality. |
Teaching |
|
|
This website is inspired by Jon Barron and modified by Shivam Singh. |