Multimodal Vision Research Laboratory

MVRL

Research Areas

View All Areas →
Biodiversity and Conservation Research

Biodiversity and Conservation

Using computer vision and remote sensing to monitor biodiversity and track environmental changes worldwide.

Explore →
Generative Multimodal AI Research

Generative Multimodal AI

Creating AI systems that generate images, 3D scenes, and multimodal content across diverse scales and sensors.

Explore →
Geospatial AI Research

Geospatial AI

Integrating AI with satellite imagery, maps, and location data to address global challenges.

Explore →
Medical Imaging Research

Medical Imaging

Using deep learning to improve medical diagnostics, from Alzheimer's detection to cancer screening.

Explore →

About Us

The Multimodal Vision Research Laboratory (MVRL) focuses on the development of multimodal representation learning techniques to interpret complex data at a global scale. Our research is primarily driven by challenges in ecology and geospatial science—from monitoring planetary-scale environmental changes to bridging the gap between overhead and ground-level perspectives. We extend these core methodologies to medical imaging, applying advanced visual understanding to improve diagnostic tools. At MVRL, we are dedicated to creating high-impact AI that transforms multi-source data into actionable insights for both planetary sustainability and human health.

Spotlight Publications

  1. 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).
    bibtex Reinforcement Learning Remote Sensing GeoAI GenAI
  2. 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 GenAI Remote Sensing GeoAI
  3. 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 International Conference on Computer Vision (ICCV).
    code website paper bibtex GenAI Geometry
  4. Thumbnail for Global and Local Entailment Learning for Natural World Imagery
    Sastry S, Dhakal A, Xing E, Khanal S, Jacobs N. 2025. Global and Local Entailment Learning for Natural World Imagery. In: IEEE International Conference on Computer Vision (ICCV).
    code website paper bibtex Remote Sensing Ecology GeoAI
  5. Thumbnail for ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval
    Xing E, Kolouju P, Pless R, Stylianou A, Jacobs N. 2025. ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
    code paper bibtex Vision-Language
  6. Thumbnail for RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings
    Dhakal A, Sastry S, Khanal S, Ahmad A, Xing E, Jacobs N. 2025. RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
    code paper bibtex Remote Sensing GeoAI
All Publications →

Recent News

Full Archives →