Laura Bravo Sánchez

Hi! I’m a Ph.D. student at Stanford University where I’m advised by Prof. Serena Yeung-Levy.

My research focuses on understanding human social interaction and behavior through computer vision. I develop 3D human mesh estimation and, more broadly, video understanding models, with a focus on applications in healthcare. My goal is to create scalable AI systems to analyze complex social dynamics, particularly those behind parent-child interactions.

Previously I obtained my M.Sc and B.Sc at Universidad de los Andes in Biomedical Engineering and worked on computer vision for surgical scene understanding under Prof. Pablo Arbeláez.

You can download my CV here.

news

Mar 17, 2025	Check out our new paper MicroVQA accepted at CVPR 2025
Jan 10, 2025	I’ll be interning during the summer 2025 with Naver Labs Europe!

selected publications

MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research

James Burgess^*, J.H Nirschl^*, Laura Bravo-Sánchez^*, and 1 more author

CVPR, 2025

Bib PDF Code Website

@article{burgess2025microvqa,
  title = {MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research},
  author = {Burgess, James and Nirschl, J.H and Bravo-S{\'a}nchez, Laura and others},
  journal = {CVPR},
  year = {2025},
  pdf = {https://jmhb0.github.io/microvqa/},
  website = {https://jmhb0.github.io/microvqa/},
}

Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Models

Laura Bravo-Sánchez, Jaewoo Heo, Zhenzhen Weng, and 2 more authors

arXiv preprint arXiv:2410.00309, 2024

Bib PDF Code Website

@article{bravo2024ask,
  title = {Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Models},
  author = {Bravo-S{\'a}nchez, Laura and Heo, Jaewoo and Weng, Zhenzhen and Wang, Kuan-Chieh and Yeung-Levy, Serena},
  journal = {arXiv preprint arXiv:2410.00309},
  year = {2024},
  pdf = {https://arxiv.org/abs/2410.00309},
  website = {https://laubravo.github.io/apu_website/},
}

Artificial intelligence–powered 3D analysis of video-based caregiver-child interactions

Zhenzhen Weng, Laura Bravo-Sánchez, Zeyu Wang, and 9 more authors

Science Advances, 2025

Bib PDF Code

@article{weng2025harmoni,
  author = {Weng, Zhenzhen and Bravo-S\'anchez, Laura and Wang, Zeyu and Howard, Christopher and Xenochristou, Maria and Meister, Nicole and Kanazawa, Angjoo and Milstein, Arnold and Bergelson, Elika and Humphreys, Kathryn L. and Sanders, Lee M. and Yeung-Levy, Serena},
  title = {Artificial intelligence–powered 3D analysis of video-based caregiver-child interactions},
  journal = {Science Advances},
  year = {2025},
  pdf = {https://www.science.org/doi/abs/10.1126/sciadv.adp4422},
}

Diffusion-HPC: Synthetic Data Generation for Human Mesh Recovery in Challenging Domains

Zhenzhen Weng, Laura Bravo-Sánchez, and Serena Yeung-Levy

In 2024 International Conference on 3D Vision (3DV), 2024

Bib PDF Code Website

@inproceedings{weng2024diffusion,
  title = {Diffusion-HPC: Synthetic Data Generation for Human Mesh Recovery in Challenging Domains},
  author = {Weng, Zhenzhen and Bravo-S{\'a}nchez, Laura and Yeung-Levy, Serena},
  booktitle = {2024 International Conference on 3D Vision (3DV)},
  pages = {257--267},
  year = {2024},
  organization = {IEEE},
  website = {https://zzweng.github.io/projects/diffusion_hpc.html},
  pdf = {https://arxiv.org/pdf/2303.09541},
}

ISINet: an instance-based approach for surgical instrument segmentation

Cristina González^*, Laura Bravo-Sánchez^*, and Pablo Arbelaez

In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2020

Bib PDF Code

@inproceedings{gonzalez2020isinet,
  title = {ISINet: an instance-based approach for surgical instrument segmentation},
  author = {Gonz{\'a}lez, Cristina and Bravo-S{\'a}nchez, Laura and Arbelaez, Pablo},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages = {595--605},
  year = {2020},
  organization = {Springer},
  pdf = {https://arxiv.org/pdf/2007.05533},
}

Finding Four-Leaf Clovers: A Benchmark for Fine-Grained Object Localization

L. Bravo, A. Pardo, G. Perez and P. Arbelaez

The Sixth Workshop on Fine-Grained Visual Categorization (FGVC6), CVPR 2019., 2019

Bib PDF Poster Website

@article{BPPA_FGVC6,
  author = {{L. Bravo, A. Pardo, G. Perez and P. Arbelaez}},
  title = {{Finding Four-Leaf Clovers: A Benchmark for Fine-Grained Object Localization}},
  journal = {{The Sixth Workshop on Fine-Grained Visual Categorization (FGVC6), CVPR 2019.}},
  year = {2019},
  website = {https://www.gperezs.com/projects/flc.html},
  pdf = {https://drive.google.com/file/d/1RNsGo9rMAqz5Qc38fISueCR7VHoSEM4h/view},
  dataset = {https://drive.google.com/file/d/1fq6ZeVg2-CjRtKgcBcnKy9jLfUIabfe8/view?usp=sharing},
}