MATH+ML+X Lab Aviles-Rivero Lab

Preprint

Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
PDE Solvers Should Be Local: Fast, Stable Rollouts with Learned Local Stencils
CW Cheng, B Dong, C-B Schönlieb and AI Aviles-Rivero
Arxiv
Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
NeuTSFlow: Modeling Continuous Functions Behind Time Series Forecasting
H Xu, L Wu, X Wang, H Dang, CW Cheng AI Aviles-Rivero and Q Liu
Arxiv
Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
Deep Spectral Prior
Y Cheng, T Zeng, P Lio, C-B Schönlieb and AI Aviles-Rivero
Arxiv ||
Project Webpage
Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
A Fourier Neural Operator Approach for Modelling Exciton-Polariton Condensate Systems
Y Wang, ST Sathujoda, K Sawicki, K Gandhi, AI Aviles-Rivero and PG Lagoudakis
Arxiv
Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
Brain Foundation Models with Hypergraph Dynamic Adapter for Brain Disease Analysis
Z Deng, H Wang, Z Huang, Lipei Zhang, AI Aviles-Rivero, Chaoyu Liu, Junjun He, Zoe Kourtzi, and C-B Schönlieb
Arxiv
Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
Enhancing Brain Age Prediction and Neurodegeneration Detection with Contrastive Learning on Regional Biomechanical Properties
J. Träuble, L.V. Hiscox, C. Johnson, AI Aviles-Rivero, C.B. Schönlieb, G.S. Kaminski Schierle
Arxiv
ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting
ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting
G Yu, Y Li, J Wang, X Guo, AI Aviles-Rivero, T Yang, S Wang
Arxiv
You KAN Do It in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
You KAN Do It in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
Y Cheng, C–B Schönlieb and AI Aviles-Rivero
Arxiv
Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEs
Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEs
CW Cheng, J Huang, Y Zhang, G Yang, CB Schönlieb and AI Aviles-Rivero
Arxiv
Inertial Proximal Difference-of-Convex Algorithm with Convergent Bregman Plug-and-Play for Nonconvex Imaging
Inertial Proximal Difference-of-Convex Algorithm with Convergent Bregman Plug-and-Play for Nonconvex Imaging
TC Chow, C Huang, Z Wu, T Zeng and AI Aviles-Rivero
Arxiv
Contrastive Learning with Dynamic Localized Repulsion for Brain Age Prediction on 3D Stiffness Maps
Contrastive Learning with Dynamic Localized Repulsion for Brain Age Prediction on 3D Stiffness Maps
J Trauble, L Hiscox, C Johnson, CB Schönlieb, GK Schierle and AI Aviles-Rivero
Arxiv
NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning
NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning
Y Zhang, C-W Cheng, K Yu, Z He, CB Schönlieb and AI Aviles-Rivero
Arxiv
Learning Task-Specific Sampling Strategy for Sparse-View CT Reconstruction
Learning Task-Specific Sampling Strategy for Sparse-View CT Reconstruction
L Yang, J Huang, Y Fang, AI Aviles-Rivero, C-B Schonlieb, D Zhang and G Yang
Arxiv
Deep Block Proximal Linearised Minimisation Algorithm for Non-convex Inverse Problems
Deep Block Proximal Linearised Minimisation Algorithm for Non-convex Inverse Problems
C Huang, Z Wu, Y Cheng, T Zheng, C-B Schönlieb and AI Aviles-Rivero
Arxiv
Bilevel Hypergraph Networks for Multi-Modal Alzheimer’s Diagnosis
Bilevel Hypergraph Networks for Multi-Modal Alzheimer’s Diagnosis
AI Aviles-Rivero, CW Cheng, Z Deng, Z Kourtzi and C-B Schönlieb
Arxiv
MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation
MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation
J Huang, L Yang, F Wang, Y Wu, Y Nan, AI Aviles-Rivero, C-B Schönlieb, D Zhang, G Yang
Arxiv
TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations
TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations
Z Shen*, Y Cheng*, RH Chan, P Lio, C-B Schönlieb, AI Aviles-Rivero
Arxiv
Traffic Video Object Detection using Motion Prior
Traffic Video Object Detection using Motion Prior
L Liu, Y Cheng, D Chen, J He, P Lio, C-B Schönlieb, AI Aviles-Rivero
Arxiv
MammoDG
MammoDG: Generalisable Deep Learning Breaks the Limits of Cross-Domain Multi-Center Breast Cancer Screening
Y Yang, S Wang, L Liu, S Hickman, FJ Gilbert, C-B Schönlieb, AI Aviles-Rivero
Arxiv
HGIB
HGIB: Prognosis for Alzheimer’s Disease via Hypergraph Information Bottleneck
S Wang, AI Aviles-Rivero, Z Kourtzi, C-B Schönlieb
Arxiv
Homeomorphic Image Registration
Homeomorphic Image Registration via Conformal-Invariant Hyperelastic Regularisation
J Zou, N Debroux, L Liu, J Qin, C-B Schönlieb, AI Aviles-Rivero
Arxiv
PC-SwinMorph
PC-SwinMorph: Patch Representation for Unsupervised Medical Image Registration and Segmentation
L Liu, Z Huang, P Lio, C-B Schönlieb, AI Aviles-Rivero
Arxiv
1graphd
Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
AI Aviles-Rivero, N. Papadakis, R. Li, P Sellars, SM. Alsaleh, R. T Tan, C-B Schönlieb
Arxiv
DeepWalkers
Delving into Deep Walkers: A Convergence Analysis of Random-Walk-Based Vertex Embeddings
D Kloepfer, AI Aviles-Rivero, D Heydecker
Arxiv
deepRprior
Deep Reflection Prior
Y Yin, Q Fan, D Chen, Y Wang, AI Aviles-Rivero, R Li, C-B Schönlieb, D Lischinsky, B Chen
Arxiv
deepSSLv55
CycleCluster: Modernising Clustering Regularisation for Deep Semi-Supervised Classification
P Sellars, AI Aviles-Rivero, C-B Schönlieb
Arxiv
dimf
Dim the Lights! — Low-Rank Prior Temporal Data for Specular-Free Video Recovery
SM Alsaleh, AI Aviles-Rivero, N Debroux, JK Hahn
Arxiv

2025

Genuine Knowledge from Practice
Brain age prediction and early neurodegeneration detection using contrastive learning on brain biomechanics: a retrospective, multicentre study
J Träuble, LV Hiscox, CL Johnson, AI Aviles-Rivero, C–B Schönlieb and GS Kaminski Schierle
eBioMedicine – The Lancet Discovery Science
Arxiv
LANCET
Genuine Knowledge from Practice
Deep Block Proximal Linearised Minimisation Algorithm for Non-convex Inverse Problems
C Huang, Z Wu, Y Cheng, T Zheng, C–B Schönlieb and AI Aviles-Rivero
SIAM Journal on Mathematics of Data Science (SIMODS)
Arxiv
SIAM
Genuine Knowledge from Practice
D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
L Zhang, R Sun, Z Deng, Y Cheng, C-B Schönlieb, and AI Aviles-Rivero
NeurIPS 2025
Arxiv
NeurIPS
Genuine Knowledge from Practice
Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
CW Cheng*, Y Zhao*, Y Cheng, J Montoya, C-B Schönlieb, and AI Aviles-Rivero
MICCAI 2025
Arxiv
MICCAI
Genuine Knowledge from Practice
Motion Constrained Point Cloud Matching for Maritime Tracking
N Dalhaug, M Baerveldt, AI Aviles-Rivero, C-B Schönlieb, A Stahl, R Mester, E Førland Brekke
IEEE Access
Journal
IEEE Access
Genuine Knowledge from Practice
MAMBA4D: Efficient Long-Sequence Point CloudVideo Understanding with DisentangledSpatial-Temporal State Space Models
J Liu, J Han, L Liu, AI Aviles-Rivero, C Jiang, Z Liu and H Wang
CVPR 2025
Arxiv
CVPR
Single-Shot Plug-and-Play Methods for Inverse Problems.
Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey
A Essakine*, Y Cheng*, CW Cheng, L Zhang, Z Deng, L Zhu, C–B Schönlieb and AI Aviles-Rivero
Transactions on Machine Learning Research (TMLR)
Arxiv
TMLR
TrafficCAM
DiffMIC-v2: Medical Image Classification via Improved Diffusion Network
Y Yang, H Fu, AI Aviles-Rivero, Z Xing, and L Zhu
TMI
Arxiv
TMI
TrafficCAM
Cross-Modal Few-Shot Learning with Second-Order Neural Ordinary Differential Equations
Y Zhang*, CW Cheng*, J He, Z He, C-B Schönlieb, Y Chen and AI Aviles-Rivero
(*Equal Contribution)
AAAI 2025
Arxiv
AAAI

2024

TrafficCAM
TrafficCAM: A Versatile Dataset for Traffic Flow Segmentation
Z Deng, Y Cheng, L Liu, S Wang, R Ke, C-B Schönlieb, AI Aviles-Rivero
IEEE Transactions on Intelligent Transportation Systems
Arxiv
Website
T-ITS
Single-Shot Plug-and-Play Methods for Inverse Problems.
Single-Shot Plug-and-Play Methods for Inverse Problems
Y Cheng, L Zhang, Z Shen, S Wang, L Yu, RH Chan, C-B Schönlieb, AI Aviles-Rivero
TMLR
Arxiv
TMLR
TrafficMOT: A Challenging Dataset for Multi-Object Tracking in Complex Traffic Scenarios.
TrafficMOT: A Challenging Dataset for Multi-Object Tracking in Complex Traffic Scenarios
L Liu, Y Cheng, Z Deng, S Wang, D Chen, X Hu, P Lio, C-B Schönlieb, AI Aviles-Rivero
ACM Multimedia 2024
Arxiv
ACM
Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba.
Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba
J Huang, L Yang, J F Zhang, A I Aviles-Rivero, C-B Schönlieb, G Yang
Medical Image Analysis (MedIA)
Arxiv
Journal
MedAI
Training-Free Feature Reconstruction with Sparse Optimization for Vision-Language Models.
Training-Free Feature Reconstruction with Sparse Optimization for Vision-Language Models
Y Zhang, K Yu, AI Aviles-Rivero, J Jia, Y Tang, Z He
ACM Multimedia 2024
Arxiv
ACM
Biophysics Informed Pathological Regularisation for Brain Tumour Segmentation.
Biophysics Informed Pathological Regularisation for Brain Tumour Segmentation
L Zhang, Y Cheng, L Liu, C-B Schönlieb, AI Aviles-Rivero
MICCAI 2024
Arxiv
MICCAI
Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization.
Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization
H Wu, Y Yang, AI Aviles-Rivero, J Ren, S Chen, H Chen, L Zhu
ECCV 2024
Arxiv
ECCV
LGRNet: Local-Global Reciprocal Network for Uterine Fibroid Segmentation in Ultrasound Videos.
LGRNet: Local-Global Reciprocal Network for Uterine Fibroid Segmentation in Ultrasound Videos
H Xu*, Y Yang*, AI Aviles-Rivero, G Yang, J Qin, L Zhu
MICCAI 2024
Arxiv
MICCAI
HAMLET: Graph Transformer Neural Operator for Partial Differential Equations.
HAMLET: Graph Transformer Neural Operator for Partial Differential Equations
A Bryutkin*, J Huang*, Z Deng, G Yang, C Schönlieb, AI Aviles-Rivero
ICML 2024
Arxiv
ICML
Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling.
Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling
G Yu, J Zou, X Hu, AI Aviles-Rivero, J Qin, S Wang
ICML 2024
Arxiv
ICML
Optimised Propainter for Video Diminished Reality Inpainting.
Optimised Propainter for Video Diminished Reality Inpainting
P Li*, L Liu*, C Schönlieb, AI Aviles-Rivero
Grand Challenge Dreaming ISBI 2024. Best Paper Award.
Arxiv
ISBI
The Missing U for Efficient Diffusion Models.
The Missing U for Efficient Diffusion Models
S Calvo-Ordonez, C-W Cheng, J Huang, L Zhang, G Yang, C Schönlieb, AI Aviles-Rivero
TMLR
Arxiv
TMLR
STADNet: Spatial-Temporal Attention-Guided Dual-Path Network for cardiac cine MRI super-resolution.
STADNet: Spatial-Temporal Attention-Guided Dual-Path Network for cardiac cine MRI super-resolution
J Lyu, S Wang, Y Tian, J Zou, S Dong, C Wang, AI Aviles-Rivero, J Qin
Medical Image Analysis
Journal
MIA
Continuous U-Net: Faster, Greater and Noiseless
Continuous U-Net: Faster, Greater and Noiseless
CW Cheng, C Runkel*, L Liu*, RH Chan, C-B Schönlieb, AI Aviles-Rivero
TMLR
Arxiv
Website
TMLR
Genuine Knowledge from Practice
Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal
Y Yang, H Wu, AI Aviles-Rivero, Y Zhang, J Qin, L Zhu
CVPR 2024
Arxiv
CVPR
Deep Learning-based Diffusion Tensor Cardiac Magnetic Resonance Reconstruction
Deep Learning-based Diffusion Tensor Cardiac Magnetic Resonance Reconstruction: A Comparison Study
J Huang, PF Ferreira, L Wang, Y Wu, AI Aviles-Rivero, C-B Schönlieb, ..., G Yang
Scientific Reports-Nature
Journal
Arxiv
Nature
NorMatch
NorMatch: Matching Normalizing Flows with Classifiers for Semi-Supervised Learning
Z Deng, R Ke, C-B Schönlieb, AI Aviles-Rivero
TMLR
Journal
Arxiv
Code Repository
TMLR
CoNIC Challenge
CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting
S Graham, ..., L Liu, AI Aviles-Rivero, ..., C-B Schönlieb, ..., NM Rajpoot
Medical Image Analysis
Journal
Code Repository
MIA

2023

Contrastive Registration for Unsupervised Medical Image Segmentation
Contrastive Registration for Unsupervised Medical Image Segmentation
L Liu, AI Aviles-Rivero, and C-B Schönlieb
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Arxiv
Journal
Code Repository
TNNLS
Beyond U: Making Diffusion Models Faster & Lighter
Beyond U: Making Diffusion Models Faster & Lighter
S Calvo-Ordonez, J Huang, L Zhang, G Yang, C-B Schonlieb, AI Aviles-Rivero
NeurIPS 2023 W/ on Diffusion Models
Arxiv
Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation
Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation
Y Yang, AI Aviles-Rivero, Y Liu, H Fu, W Wang, L Zhu
ICCV 2023
Arxiv
Conference
Code Repository
ICCV
CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?
CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?
J Huang, AI Aviles-Rivero, C-B Schönlieb, G Yang
MICCAI 2023
Arxiv
Conference
MICCAI
DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
Y Yang, H Fu, AI Aviles-Rivero, C-B Schönlieb, L Zhu
MICCAI 2023 (early accept)
Arxiv
Conference
Code Repository
MICCAI
Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness
Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness
Y Cheng, L Liu, S Wang, Y Jin, C-B Schönlieb, AI Aviles-Rivero
ICLR 2023 W-TML4H
Arxiv
Website
SCOTCH and SODA: A Transformer Video Shadow Detection Framework
SCOTCH and SODA: A Transformer Video Shadow Detection Framework
L Liu, J Prost, L Zhu, N Papadakis, P Lio, C-B Schönlieb, AI Aviles-Rivero
CVPR 2023
Arxiv
Conference
Website
CVPR
ViGU: Vision GNN U-Net for Fast MRI
ViGU: Vision GNN U-Net for Fast MRI
J Huang, AI Aviles-Rivero, CB Schonlieb, G Yang
ISBI 2023
Arxiv
ISBI
Gray Whale Detection in Satellite Imagery using Deep Learning
Gray Whale Detection in Satellite Imagery using Deep Learning
KM Green, ..., AI Aviles-Rivero, ..., CB Schonlieb, ... and JA Jackson
Remote Sensing in Ecology and Conservation
Journal