Shweta Mahajan

About

Shweta Mahajan is a Senior Machine Learning Researcher at Qualcomm AI Research. Prior to this, from 2022 to 2023, she was a Postdoctoral Researcher in the Computer Vision Group at The University of British Columbia working alongside Prof. Leonid Sigal and Dr. Kwang Moo Yi. She was also a Postdoctoral Affiliate at The Vector Institute of AI in Toronto. She completed her Ph.D. from Technische Universität Darmstadt under the supervision of Prof. Stefan Roth in 2022; received her M.Sc from Universität des Saarlandes in 2017, where she was the member of the Machine Learning Group and the Max Planck Institute of Informatics.

Employment

• Qualcomm (United States)

Education

• Technische Universität Darmstadt Ph.D
  2018 - 2022

Projects & Funding

Projects & funding information is unavailable.

Publications (8)

• Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models
  2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 DOI: 10.1109/cvpr52733.2024.00650
  +Save
• Unsupervised Keypoints from Pretrained Diffusion Models
  2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 DOI: 10.1109/cvpr52733.2024.02153
  +Save
• ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models
  2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 DOI: 10.1109/cvpr52733.2024.00647
  +Save
• Make-A-Story: Visual Memory Conditioned Consistent Story Generation
  2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 DOI: 10.1109/cvpr52729.2023.00246
  +Save
• PixelPyramids: Exact Inference Models from Lossless Image Pyramids
  2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2021 DOI: 10.1109/iccv48922.2021.00657
  +Save
• Diverse Image Captioning with Grounded Style
  2021 DOI: 10.1007/978-3-030-92659-5_27
  +Save
• Normalizing Flows With Multi-Scale Autoregressive Priors
  2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020 DOI: 10.1109/cvpr42600.2020.00844
  +Save
• Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings
  2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) 2019 DOI: 10.1109/iccvw.2019.00557
  +Save