Unit Grenoble
Unit Mission
To establish and sustain an internationally leading research environment in multimodal learning, with rigorous advances in computer vision and machine learning as its core, supported by other modalities including audio/speech, natural language, geospatial data, with applications to remote sensing, 3D vision, robotics, and medical imaging.
Participating Institutions
Research Agenda
The Grenoble Unit’s research portfolio spans several interlocking themes: (i) core algorithmic foundations (machine learning, computer vision, representation learning, domain adaptation, robustness, interpretability); (ii) modalities and their integration (vision, 3D vision, audio/speech, natural language, and spatial/geophysical data); and (iii) application‐driven domains (remote sensing and computational geoscience, robotics, and medical imaging).
