Nathan Jacobs

Nathan Jacobs

Professor of Computer Science & Engineering
Vice Provost for Artificial Intelligence
Director, Multimodal Vision Research Laboratory
Washington University in St. Louis

I develop new computer vision and AI methods for understanding the physical and natural world. My lab's research spans multimodal representation learning, geospatial foundation models, and generative modeling, with models that learn from satellite imagery, ground-level photos, sound, and text. We apply these methods with collaborators on problems in agriculture, ecology, forestry, air quality, natural hazards, and public health. As Vice Provost for Artificial Intelligence, I help make that kind of collaboration work across an entire university.

Research Lab  /  CV  /  Scholar  /  Github  /  LinkedIn

What I Work On

Novel AI methods

My lab develops computer vision and machine learning methods that connect many ways of observing the world, from satellite imagery and ground-level photos to sound and text. Recent examples include TaxaBind, a shared embedding space for six kinds of ecological data, and TerraDiT, a generative Earth model that won a best paper award at ECCV 2026's TerraBytes workshop. We publish at CVPR, ICCV, ECCV, NeurIPS, and WACV, and release code, models, and data.

Lab research areas →

AI for impact

Much of our most consequential work is part of larger collaborative efforts, where we contribute AI methods and models:

AI across a university

As Vice Provost for Artificial Intelligence at WashU, I help lead university-wide strategy for AI in research and education: shared AI infrastructure, support for researchers in every discipline who want to use AI in their work, AI in teaching and learning, and partnerships with industry, government, and foundations.

AI at WashU →

People

I have advised 14 PhD graduates. Six hold tenure-track faculty positions, and others work at leading technology companies including Microsoft, Zillow, and Kitware. I have also mentored many MS and undergraduate researchers who have gone on to graduate study and industry careers.

Lab members and alumni →

Selected Research

See my lab's page for a complete listing of publications.

  1. Thumbnail for Trajectory-aware Cross-view Geo-Localization with Sequential Observations
    Gao T, Lin J, Beaulieu D, Jacobs N. 2026. Trajectory-aware Cross-view Geo-Localization with Sequential Observations. In: European Conference on Computer Vision (ECCV).
    website paper bibtex
  2. Thumbnail for Tesselating The Earth
    Cher D, Iqbal H, Xing E, Wei B, Jacobs N. 2026. Tesselating The Earth. In: European Conference on Computer Vision (ECCV).
    code paper bibtex
  3. Thumbnail for TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
    Wei B, Sastry S, Cher D, Xing E, Jacobs N. 2026. TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive. In: European Conference on Computer Vision (ECCV).
    code website paper bibtex
  4. Thumbnail for UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving
    Xiong Z, Ye X, Yaman B, Cheng S, Lu Y, Luo J, Jacobs N, Ren L. 2026. UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving. In: European Conference on Computer Vision (ECCV).
    website paper bibtex
  5. Thumbnail for ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology
    Sastry S, Khanal S, Dhakal A, Lin J, Cher D, Jarosz P, Jacobs N. 2026. ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
    code website paper press bibtex
  6. Thumbnail for SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images
    Dhakal A, Khanal S, Sastry S, Arndt J, Dias PA, Lunga D, Jacobs N. 2026. SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
    code paper bibtex
  7. Thumbnail for PRUE: A Practical Recipe for Field Boundary Segmentation at Scale
    Muhawenayo G, Robinson C, Khanal S, Fang Z, Corley I, Wollam A, Gao T, Strnad L, Avery R, Estes L, Tárano AM, Jacobs N, Kerner H. 2026. PRUE: A Practical Recipe for Field Boundary Segmentation at Scale. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
    paper press bibtex
  8. Thumbnail for DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments
    Sarkar A, Sastry S, Pirinen A, Jacobs N, Vorobeychik Y. 2026. DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS).
    paper bibtex
  9. Thumbnail for VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics
    Cher D, Wei B, Sastry S, Jacobs N. 2026. VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics. In: IEEE Winter Conference on Applications of Computer Vision (WACV).
    paper bibtex
  10. Thumbnail for Towards Open-World Generation of Stereo Images and Unsupervised Matching
    Qiao F, Xiong Z, Xing E, Jacobs N. 2025. Towards Open-World Generation of Stereo Images and Unsupervised Matching. In: IEEE/CVF International Conference on Computer Vision (ICCV).
    code paper bibtex

I'm glad to hear from people and organizations working on AI for science, Earth observation, or AI in research and education. Email: jacobsn@wustl.edu