Efstratios Gavves

Efstratios Gavves

Causal Computer Vision & Learning Dynamics

Associate Professor UvA

Co-founder Ellogon.AI

What is the role of dynamics and causality for Deep Learning that not only understands but also interfaces with the physical world?<

This question fascinates me and drives my research on Causal Computer Vision. The vision is Embodied General Intelligence and eventually, a novel paradigm of Cyberphysical AI.

With Cyberphysical AI I want to address the fundamental chasm between information and matter, that is the observation that machines in the digital world and machines in the physical world work fantastically in isolation, but cannot easily be combined. Bridging the digital and physical world will be key in not only Robot Learning but also automating Biomedical, Health, IoT, Manufacting, Sciences, and so on with AI.

My research is supported by an ERC StG and NWO VIDI, and academic-industry ICAI labs: QUVA with Qualcomm, and POP-AART with Elekta and NKI.

News

→ Ilze presents Modulated Neural ODEs in NeurIPS 2023.
→ Miltos presents Latent Field Discovery in Interacting Dynamical Systems with Neural Fields in NeurIPS 2023.
→ Haochen presents Causal Identifiability from Temporal Intervened Sequences in ICCV 2023 as oral.
→ Mohammad presents Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations in ICCV 2023.
→ Lucas had Spatio-temporal physics-informed learning: A novel approach to CT perfusion analysis in acute ischemic stroke in IEEE MedIA 2023.
→ Wenzhe had PC-Reg: A pyramidal prediction-correction approach for large deformation image registration in IEEE MedIA 2023.

Awards

 
 
 
 
 
European Research Council
ERC Starting Grant
European Research Council
Sep 2020 – Present
Award comes with personal funding of €1.5M to hire 3 Ph.D.s and 1 PostDoc
 
 
 
 
 
Netherlands Science Foundation
NWO VIDI
Netherlands Science Foundation
Sep 2020 – Present
Award comes with personal funding of €800K to hire 2 Ph.D.s and 1 PostDoc
 
 
 
 
 
ELLIS Europe
ELLIS Scholar
ELLIS Europe
Sep 2020 – Present
Scholar of the ELLIS network of AI excellence in Europe

Publications

Quickly discover relevant content by filtering publications.
(2023). BISCUIT: Causal Representation Learning from Binary Interactions. Association for Uncertainty in Artificial Intelligence.

Cite

(2023). Graph Switching Dynamical Systems. International Conference on Machine Learning.

Cite

(2023). Latent Field Discovery In Interacting Dynamical Systems With Neural Fields. Neural Information Processing Systems.

Cite

(2023). Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN. International Conference on Learning Representations.

Cite

(2023). Modulated Neural ODEs. Neural Information Processing Systems.

Cite

(2023). Neural Modulation Fields for Conditional Cone Beam Neural Tomography. SynS and ML Workshop, ICML.

Cite

(2023). Noise2Aliasing: Unsupervised Deep Learning for View Aliasing and Noise Reduction in 4DCBCT. Medical Image Computing and Computer Assisted Intervention Society.

Cite

(2023). PC-Reg: A pyramidal prediction–correction approach for large deformation image registration. Journal on Medical Image Analysis.

Cite

(2023). Spatio-temporal physics-informed learning: A novel approach to CT perfusion analysis in acute ischemic stroke. Journal on Medical Image Analysis.

Cite

(2023). Time does tell: Self-supervised time-tuning of dense image representations. IEEE International Conference on Computer Vision.

Cite

Team

Ph.D. students

Avatar

Ilze Auzina

Space-time generative & bayesian learning

Avatar

Leonard Bereska

Space-time memory neural nets

Avatar

Alex Gabel

Neural network dynamical systems

Avatar

David Knigge

Space-time geometric deep learning

Avatar

Miltos Kofinas

Deep spatiotemporal forecasting

Avatar

Phillip Lippe

Temporal causality & causal representation learning

Avatar

Jie Liu

Interactive image segmentation

Avatar

Yongtuo Liu

Long-term spatiotemporal learning

Avatar

Andreas Panteli

Object detection computational pathology

Avatar

Samuele Papa

Deep generative learing in CBCT

Avatar

Mohammad Salehi

Efficient spatiotemporal learning

Avatar

Yoni Schirris

Weakly supervised deep learning computational pathology

Avatar

Lucas de Vries

Spatiotemporal forecasting in brain CT

Avatar

Riccardo Valperga

System dynamics & neural networks

Avatar

Haochen Wang

Video segmentation & tracking

Avatar

Wenzhe Yin

Spatiotemporal medical image registation

Post-doctoral researchers

Avatar

Nikita Moriakov

Deep inverse models in CBCT

Avatar

Adeel Pervez

Harmonic analysis & neural nets

Alumni

Avatar

Yunlu Chen

3D implicit neural representations

Avatar

Riaan Zoetmulder

Deep transfer learning in medical imaging

Contact