European Large Open Multi-Modal Foundation Models For Robust Generalization On Arbitrary Data Streams

NumColor: Precise Numeric Color Control in Text-to-Image Generation

Auteurs: Muhammad Atif Butt, Diego Hernandez, Alexandra Gomez-Villa, Kai Wang, Javier Vazquez-Corral, Joost Van De Weijer
Éditeur: European Conference on Computer Vision (ECCV)

TuRTLe: A Unified Evaluation of LLMs for RTL Generation

Auteurs: Dario Garcia-Gasulla, Gokcen Kestor, Emanuele Parisi, Miquel Albert´ı-Binimelis, Cristian Gutierrez∗ Razine Moundir Ghorab∗, Orlando Montenegro∗, Bernat Homs∗, Miquel Moreto
Éditeur: MLCAD Symposium

MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data

Auteurs: Siarhei Sheludzko, Dhimitrios Duka, Bernt Schiele, Hilde Kuehne, Anna Kukleva
Éditeur: WACV

Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery

Auteurs: Xiao Liu, Nan Pu, Haiyang Zheng, Wenjing Li, Nicu Sebe, Zhun Zhong
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.00108

Effective Distillation to Hybrid xLSTM Architectures

Auteurs: Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied, Anamaria-Roberta Hartl, David Stap, Pieter-Jan Hoedt, Maximilian Beck, Sebastian Böck, Günter Klambauer, Sepp Hochreiter
Éditeur: Forty-Third International Conference on Machine Learning (ICML 2026)

From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition

Auteurs: Francesco Gentile, Nicola Dall'Asen, Francesco Tonini, Massimiliano Mancini, Lorenzo Vaquero, Elisa Ricci
Éditeur: CVPR

Evidence Triangulation for Multimodal Fact-Checking in the Wild

Auteurs: Stefanos-Iordanis Papadopoulos, Zacharias Chrysidis, Christos Koutlis, Symeon Papadopoulos, Panagiotis C. Petrantonakis
Éditeur: ECCV

Concept-Aware Batch Sampling Improves Language-Image Pretraining

Auteurs: Adhiraj Ghosh, Vishaal Udandarao, Thao Nguyen, Matteo Farina, Mehdi Cherti, Jenia Jitsev, Sewoong Oh, Elisa Ricci, Ludwig Schmidt, Matthias Bethge
Éditeur: CVPR 2026 Poster

FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy

Auteurs: Q. He, Z. Yang, W. Liang, C. Hao, N. Sebe, J. Tian
Éditeur: International Conference on Machine Learning

MAVias: Mitigate any Visual Bias

Auteurs: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.00126

Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling

Auteurs: Silvia Cappelletti, Tobia Poppi, Samuele Poppi, Zheng-Xin Yong, Diego Garcia-Olano, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Éditeur: ICPR

Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation

Auteurs: Chonghua Lv, Dong Zhao, Shuang Wang, Dou Quan, Ning Huyan, Nicu Sebe, Zhun Zhong
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Language Models Can Explain Visual Features via Steering

Auteurs: Javier Ferrando, Enrique Lopez-Cuena, Pablo Agustin Martin-Torres, Daniel Hinjos, Anna Arias-Duart, Dario Garcia-Gasulla
Éditeur: CVPR

Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models

Auteurs: Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin Vanschoren
Éditeur: Conference on Parsimony and Learning (CPAL 2026)

Does TabPFN Understand Causal Structures?

Auteurs: Omar Swelam, Lennart Purucker, Jake Robertson, Hanne Raum, Joschka Boedecker, Frank Hutter
Éditeur: EurIPS 2025 Workshop: AI for Tabular Data
DOI: 10.48550/ARXIV.2511.07236

Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation

Auteurs: Dimitrios Karageorgiou, Symeon Papadopoulos, Ioannis Kompatsiaris, Efstratios Gavves
Éditeur: European Conference on Computer Vision 2026 (ECCV 2026)

RaTA-Tool: Retrieval-Based Tool Selection with Multimodal Large Language Models

Auteurs: Gabriele Mattioli, Evelyn Turri, Sara Sarto, Lorenzo Baraldi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Éditeur: ICPR

Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation

Auteurs: Johannes Schusterbauer, Ming Gui, Yusong Li, Pingchuan Ma, Felix Krause, Björn Ommer
Éditeur: CVPR 2026 (accepted) + arXiv

Face Age Verification Vulnerabilities Under Simple Appearance Manipulations

Auteurs: Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos
Éditeur: BIAS Workshop, ECML PKDD

DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models

Auteurs: Walid Bousselham, Angie Boggust, Hendrik Strobelt, Hilde Kuehne
Éditeur: ECCV

TTRV: Test-Time Reinforcement Learning for Vision Language Models

Auteurs: Akshit Singh, Shyam Marjit, Wei Lin, Paul Gavrikov, Serena Yeung-Levy, Hilde Kuehne, Rogerio Feris, Sivan Doveh, James Glass, M. Jehanzeb Mirza
Éditeur: CVPR

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

Auteurs: Atanov Andrei (EPFL, Apple), Oğuzhan Fatih Kar (Apple), Jesse Allardice (Apple), Roman Bachmann (EPFL), David Griffiths (Apple), Devon Hjelm (Apple), Afshin Dehghan (Apple), Amir Zamir (EPFL)
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026

Revisiting Weight Regularization for Low-Rank Continual Learning

Auteurs: Yaoyue Zheng ~Yaoyue_Zheng1 , Yin Zhang, Joost van de Weijer, Gido M van de Ven, Shaoyi Du, Xuetao Zhang, Zhiqiang Tian
Éditeur: ICLR

ExplaiNavility: Interpretable Vision-and-Language Navigation with Reasoning Supervision

Auteurs: William Raccagni, Niyati Rawal, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Éditeur: ECCV Workshops

SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting

Auteurs: Mengjiao Ma, Qi Ma, Yue Li, Jiahuan Cheng, Runyi Yang, Bin Ren, Nikola Popovic, Mingqiang Wei, Nicu Sebe, Luc Van Gool, Theo Gevers, Martin R. Oswald, Danda Pani Paudel
Éditeur: 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Track on Datasets and Benchmarks

Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs

Auteurs: Arya Labroo, Ivaxi Sheth, Vyas Raina, Amaani Ahmed, Mario Fritz
Éditeur: EACL Main

A Scalable Vector Graphics Latent Space

Auteurs: Leonardo Zini, Elia Frigieri, Lorenzo Baraldi
Éditeur: ECCV

Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models

Auteurs: Zahraa Al Sahili, Ioannis Patras and Matthew Purver
Éditeur: Proceedings of IJCNLP/AACL

FineDialFact: A Benchmark for Fine-Grained Dialogue Fact Verification

Auteurs: Xiangyan Chen, Yufeng Li, Yujian Gan, Arkaitz Zubiaga and Matthew Purver
Éditeur: Proceedings of LREC

VB-Mitigator: An open-source framework for evaluating and advancing visual bias mitigation

Auteurs: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Éditeur: ECAI Workshops

SceneSplat: Gaussian Splatting-Based Scene Understanding with Vision-Language Pretraining

Auteurs: Yue Li, Qi Ma, Runyi Yang, Huapeng Li, Mengjiao Ma, Bin Ren, Nikola Popovic, Nicu Sebe, Ender Konukoglu, Theo Gevers, Luc Van Gool, Martin R. Oswald, Danda Pani Paudel
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.00472

Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals

Auteurs: Davide Lobba, Fulvio Sanguigni, Bin Ren, Marcella Cornia, Rita Cucchiara, Nicu Sebe
Éditeur: ICLR
DOI: 10.5281/ZENODO.19878279

Learning Quantifiable Visual Explanations Without Ground-Truth

Auteurs: Amritpal Singh, Andrey Barsky, Mohamed Ali Souibgui, Ernest Valveny, Dimosthenis Karatzas
Éditeur: ICPR

Multimodality as Supervision: Self-Supervised Specialization to the test space via Multimodality

Auteurs: Kunal Pratap Singh, Ali Garjani, Rishubh Singh, Muhammad Uzair Khattak, Jason Toskov, Efe Tarhan, Andrei Atanov, Oguzhan Fatih Kar (now at Apple), Amir Zamir (All authors at EPFL, unless explicitly indicated )
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026

DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation

Auteurs: Héctor Laria, Yiping Han, Julian D. Santamaria, Kai Wang, Bogdan Raducanu, Joost van de Weijer, Alexandra Gomez-Villa
Éditeur: European Conference on Computer Vision (ECCV)

Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets

Auteurs: Marianna Nezhurina, Tomer Porian, Giovanni Pucceti, Tommie Kerssies, Romain Beaumont, Mehdi Cherti, Jenia Jitsev
Éditeur: NeurIPS 2025 poster

TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

Auteurs: Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Begüm Demir, Nicu Sebe, Paolo Rota
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

DisMo: Disentangled Motion Representations for Open-World Motion Transfer

Auteurs: Thomas Ressler-Antal, Frank Fundel, Malek Ben Alaya, Stefan Andreas Baumann, Felix Krause, Ming Gui, Björn Ommer
Éditeur: NeurIPS

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

Auteurs: Thomas De Min, Subhankar Roy, Stéphane Lathuilière, Elisa Ricci, Massimiliano Mancini
Éditeur: ECCV

LOSC: LiDAR Open-voc Segmentation Consolidator

Auteurs: Nermin Samet, Gilles Puy, Renaud Marlet
Éditeur: arXiv

Probabilistic Precipitation Nowcasting with Rectified Flow Transformers

Auteurs: Johannes Schusterbauer, Jannik Wiese, Nick Stracke, Timy Phan, Björn Ommer
Éditeur: CVPR 2026 (accepted) + arXiv

Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation

Auteurs: Nikolai Röhrich, Isabell Hans, Felix Krause, Björn Ommer
Éditeur: German Conference on Pattern Recognition (GCPR)

MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization

Auteurs: Jan Büssing, Moritz Schlager, Timo Heiß, Tom Zehle, Matthias Feurer
Éditeur: arXiv

Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning

Auteurs: Jai Bardhan, Patrik Drozdik, Josef Sivic, Vladimir Petrik
Éditeur: European Conference on Computer Vision (ECCV) 2026

If open source is to win, it must go public

Auteurs: Joshua Tan, Nicholas Vincent, Katherine Elkins, Magnus Sahlgren, Joseph Low, David Pham, Sampo Pyysalo, Jenia Jitsev
Éditeur: ICML 2026 Position Paper Track Spotlight

Towards Pretraining Text Encoders for TabPFN

Auteurs: Mustafa Tajjar, Alexander Pfefferle, Lennart Purucker, Frank Hutter
Éditeur: 2nd ICML Workshop on Foundation Models for Structured Data

Pseudo-SD: Pseudo Controlled Stable Diffusion for Semi-Supervised and Cross-Domain Semantic Segmentation

Auteurs: Dong Zhao, Qi Zang, Shuang Wang, Nicu Sebe, Zhun Zhong
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.02079

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models

Auteurs: Tobia Poppi, Burak Uzkent, Amanmeet Garg, Lucas Porto, Garin Kessler, Yezhou Yang, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara, Florian Schiffers
Éditeur: EMNLP

nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN

Auteurs: Alexander Pfefferle, Johannes Hog, Lennart Purucker, Frank Hutter
Éditeur: arXiv

Learning Long-term Motion Embeddings for Efficient Kinematics Generation

Auteurs: Nick Stracke, Kolja Bauer, Stefan Andreas Baumann, Miguel Angel Bautista, Josh Susskind, Björn Ommer
Éditeur: CVPR 2026 (accepted) + arXiv

promptolution: A Unified, Modular Framework for Prompt Optimization

Auteurs: Tom Zehle, Timo Heiß, Moritz Schlager, Matthias Aßenmacher, Matthias Feurer
Publié dans: Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations), 2026
Éditeur: Association for Computational Linguistics
DOI: 10.18653/V1/2026.EACL-DEMO.21

SLU-2K: A Question-Based Benchmark for Semantic Evaluation of Sign Language Translation

Auteurs: Zeno Testa, Antonino Furnari, Lorenzo Baraldi, Natalia Díaz-Rodríguez
Éditeur: ECCV Workshops

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

Auteurs: Ulrich Prestel, Stefan Andreas Baumann, Nick Stracke, Björn Ommer
Éditeur: ECCV 2026 + arXiv

Probing Newtonian Mechanics in Video Generative Models with Real Physical Systems

Auteurs: Antonios Tragoudaras, Daniil Cherniavskii, Chenyu Zhang, Antonios Vozikis, Thijmen Nijdam, Derck W. E. Prinzhorn, Mark Bodracska, Nicu Sebe, Andrii Zadaianchuk, Efstratios Gavves
Éditeur: ICML

Towards Evaluating Data Priors for Tabular Foundation Models

Auteurs: Zeynep Türkmen, Kürşat Kaya, Alexander Pfefferle, Frank Hutter
Éditeur: 2nd ICML Workshop on Foundation Models for Structured Data

What If: Understanding Motion Through Sparse Interactions

Auteurs: Stefan Andreas Baumann, Nick Stracke, Timy Phan, Björn Ommer
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.00958

Deep Trajectory Supervision: Deep Supervision Strikes Back

Auteurs: H. Wang, W. Wang, J. Liu, H. Kuehne, and N. Sebe
Éditeur: International Conference on Machine Learning

Superpowering Open-Vocabulary Object Detectors for X-ray Vision

Auteurs: Pablo Garcia-Fernandez, Lorenzo Vaquero, Mingxuan Liu, Feng Xue, Daniel Cores, Nicu Sebe, Manuel Mucientes, Elisa Ricci
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.01931

Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints

Auteurs: Chenyangguang Zhang, Botao Ye, Boqi Chen, Alexandros Delitzas, Fangjinhua Wang, Marc Pollefeys, Xi Wang
Éditeur: ECCV

AlignCAT: Visual-Linguistic Alignment of Category and Attribute for Weakly Supervised Visual Grounding

Auteurs: Yidan Wang, Chenyi Zhuang, Wutao Liu, Pan Gao, Nicu Sebe
Publié dans: Proceedings of the 33rd ACM International Conference on Multimedia, 2025
Éditeur: ACM
DOI: 10.1145/3746027.3755751

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

Auteurs: Christian Gumbsch, Leonardo Barcellona, Lennard Schuenemann, Platon Karageorgis, Andrii Zadaianchuk, Zehao Wang, Sergey Zakharov, Fabien Despinoy, Rahaf Aljundi, Stratis Gavves
Éditeur: RLC

Driving on Registers

Auteurs: Ellington Kirby, Alexandre Boulch, Yihong Xu, Yuan Yin, Gilles Puy, Eloi Zablocki, Andrei Bursuc, Spyros Gidaris, Renaud Marlet, Florent Bartoccioni, Anh-Quan Cao, Nermin Samet, Tuan-Hung VU, Matthieu Cord
Éditeur: CVPR

Training-free Online Video Step Grounding

Auteurs: Luca Zanella, Massimiliano Mancini, Yiming Wang, Alessio Tonioni, Elisa Ricci
Éditeur: NeurIPS

Hyperbolic Busemann Neural Networks

Auteurs: Ziheng Chen, Bernhard Schölkopf, Nicu Sebe
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry

Auteurs: Ziheng Chen, Yue Song, Xiaojun Wu, Nicu Sebe
Éditeur: International Conference on Learning Representations (ICLR)

GenColorBench: A Color Evaluation Benchmark for Text-to-Image Generation Models

Auteurs: Muhammad Atif Butt, Alexandra Gomez-Villa, Tao Wu, Javier Vazquez-Corral, Joost Van De Weijer, Kai Wang
Éditeur: Computer Vision and Pattern Recognition (CVPR)

Schrödinger's Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics

Auteurs: Timy Phan, Jannik Wiese, Björn Ommer
Éditeur: European Conference on Computer Vision - ECCV

RegionReasoner: Region-Grounded Multi-Round Visual Reasoning

Auteurs: Wenfang Sun, Hao Chen, Yingjun Du, Yefeng Zheng, Cees G. M. Snoek
Éditeur: International Conference on Learning Representations
DOI: 10.48550/ARXIV.2602.03733

BAdd: Bias Mitigation Through Bias Addition

Auteurs: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2026
Éditeur: IEEE
DOI: 10.1109/ICCVW69036.2025.00795

An Empirical Study of Speculative Decoding for Small Language Models

Auteurs: Luca Mainardi, Selcuk Sandikci, Joaquin Vanschoren
Éditeur: Conference of the European Chapter of the Association for Computational Linguistics (EACL Main 2026)

Proper Velocity Neural Networks

Auteurs: Ziheng Chen , Zihan Su, Bernhard Schölkopf, Nicu Sebe
Éditeur: International Conference on Learning Representations (ICLR)

The Oracle’s Gambit: A Game-Theoretic Framework for Responsible AI Release

Auteurs: Christoph R. Landolt, Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Éditeur: 17th Conference on Game Theory and AI for Security (GameSec-26)

Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models

Auteurs: Jinlong Li, Liyuan Jiang, Haonan Zhang, Nicu Sebe
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Riemannian High-Order Pooling for Brain Foundation Models

Auteurs: Chen Hu, Ziheng Chen, Rui Wang, Yefeng Zheng, Nicu Sebe
Éditeur: International Conference on Learning Representations (ICLR)

Training-Free Personalization via Retrieval and Reasoning on Fingerprints

Auteurs: Deepayan Das, Davide Talon, Yiming Wang, Massimiliano Mancini, Elisa Ricci
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.00903

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation

Auteurs: Walid Bousselham, Hilde Kuehne, Cordelia Schmid
Éditeur: CVPR

Visualoverload: Probing visual understanding of vlms in really dense scenes

Auteurs: Paul Gavrikov, Wei Lin, M Jehanzeb Mirza, Soumya Jahagirdar, Muhammad Huzaifa, Sivan Doveh, James Glass, Serena Yeung-Levy, Hilde Kuehne
Éditeur: CVPR

(1D) Ordered Tokens Enable Efficient Test-Time Search

Auteurs: Zhitong Gao, Parham Rezaei, Ali Cy, Mingqiao Ye, Nataša Jovanović, Jesse Allardice, Afshin Dehghan, Amir Zamir, Roman Bachmann, Oğuzhan Fatih Kar
Éditeur: ICML 2026 (accepted) + arXiv

Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off

Auteurs: Davide Lobba, Fulvio Sanguigni, Bin Ren, Marcella Cornia, Rita Cucchiara, Nicu Sebe
Éditeur: ECCV

NotSoTiny: A Large, Living Benchmark for RTL Code Generation

Auteurs: Razine Moundir Ghorab, Emanuele Parisi, Cristian Gutierrez, Miquel Alberti-Binimelis, Miquel Moreto, Dario Garcia-Gasulla, Gokcen Kestor
Éditeur: DAC'26

Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

Auteurs: Yan Shu, Hangui Lin, Yexin Liu, Yan Zhang, Gangyan Zeng, Yan Li, Yu ZHOU, Ser-Nam Lim, Harry Yang, Nicu Sebe
Éditeur: 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

IPA: An Information-Reconstructive Input Projection Framework for Efficient Foundation Model Adaptation

Auteurs: Yuan Yin, Shashanka Venkataramanan, Tuan-Hung Vu, Andrei Bursuc, Matthieu Cord
Éditeur: TMLR

ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering

Auteurs: Alberto Compagnoni, Marco Morini, Sara Sarto, Federico Cocchi, Davide Caffagni, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Éditeur: CVPR

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning

Auteurs: Dipam Goswami, Simone Magistri, Kai Wang, Bartłomiej Twardowski, Andrew Bagdanov, Joost van de Weijer
Publié dans: Advances in Neural Information Processing Systems 38, 2026
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/085713-2179

A Large-Scale Instruction-Tuning Dataset and Models for Slovenian Vision-Language Tasks

Auteurs: Matej Martinc and Domen Vreš
Éditeur: LREC

Learning Transferable Motor Skills for Geometry-Aware Robotic Surface Tasks

Auteurs: Miroslav David, Karla Stepanova, Robert Babuska
Éditeur: ICRA - Geometry in the Age of Data‑Driven Robotics

Towards a General Attention Framework on Gyrovector Spaces for Matrix Manifolds

Auteurs: Rui Wang , Chen Hu, Xiaoning Song, Xiaojun Wu, Nicu Sebe, Ziheng Chen
Éditeur: Neural Information Processing Systems (NeurIPS)

Riemannian Networks over Full-Rank Correlation Matrices

Auteurs: Z. Chen, X. Wu, B. Schölkopf, N. Sebe
Éditeur: International Conference on Machine Learning

Can Calibration of Positional Encodings Enhance Long Context Utilization?

Auteurs: Tom Zehle, Matthias Aßenmacher
Publié dans: Findings of the Association for Computational Linguistics: EACL 2026, 2026
Éditeur: Association for Computational Linguistics
DOI: 10.18653/V1/2026.FINDINGS-EACL.120

QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain

Auteurs: Wenfang Sun, Yingjun Du, Gaowen Liu, Yefeng Zheng, Cees G. M. Snoek
Éditeur: WACV

How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation

Auteurs: Prabhant Singh, Sibylle Hess, Joaquin Vanschoren
Éditeur: International Conference on Learning Representations (ICLR 2026)

Diffusion Language Models: An Experimental Analysis

Auteurs: Thomas Bertolani, Davide Bucciarelli, Leonardo Zini, Marcella Cornia, Lorenzo Baraldi
Éditeur: CLiC-it

SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models

Auteurs: Sofian Chaybouti, Sanath Narayan, Yasser Dahou, Phúc H. Lê Khắc, Ankit Singh, Ngoc Huynh, Wamiq Reyaz Para, Hilde Kuehne, Hakim Hacid
Éditeur: CVPR

Beyond IID: How General Are Tabular Foundation Models, Really?

Auteurs: Lennart Purucker, Andrej Tschalzev, Nick Erickson, Gioia Blayer, David Holzmüller, Alan Arazi, Alexander Pfefferle, Mustafa Tajjar, Gaël Varoquaux, Frank Hutter
Éditeur: NeurIPS 2026 Evaluations and Datasets Track

FoodBench-QA: Overview of the Shared Task on Grounded Food and Nutrition Question Answering

Auteurs: Tome Eftimov, Ana Gjorgjevikj, Matej Martinc, Gjorgjina Cenikj, Sašo Džeroski, Barbara Koroušić Seljak
Éditeur: CL4Health workshop

Exploring Social Bias in Slovenia: The EEC-SL Dataset

Auteurs: Jaya Caporusso, Damar Hoogland, Boshko Koloski, Matthew Purver, Senja Pollak, Špela Vintar
Éditeur: LREC 2026

Intrinsic Lorentz Neural Network

Auteurs: Xianglong Shi, Ziheng Chen, Yunhan Jiang, Nicu Sebe
Éditeur: International Conference on Learning Representations (ICLR)

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

Auteurs: Felix Krause, Timy Phan, Ming Gui, Stefan Andreas Baumann, Vincent Tao Hu, Bjorn Ommer
Éditeur: ICCV

Envisioning the Future, One Step at a Time

Auteurs: Stefan Andreas Baumann, Jannik Wiese, Tommaso Martorella, Mahdi M. Kalayeh, Björn Ommer
Éditeur: CVPR 2026 (accepted) + arXiv

Guiding Token-Sparse Diffusion Models

Auteurs: Felix Krause, Stefan Andreas Baumann, Johannes Schusterbauer, Olga Grebenkova, Ming Gui, Vincent Tao Hu, Björn Ommer
Éditeur: CVPR 2026 (accepted) + arXiv

AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment

Auteurs: Anna Šárová Mikeštíková, Médéric Fourmy, Martin Cífka, Josef Sivic, Vladimir Petrik
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

On Large Multimodal Models as Open-World Image Classifiers

Auteurs: Alessandro Conti, Massimiliano Mancini, Enrico Fini, Yiming Wang, Paolo Rota, Elisa Ricci
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.01521

TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning

Auteurs: Aritra Bhowmik and Mohammad Mahdi Derakhshani and Dennis Koelma and Yuki M Asano and Martin R Oswald and Cees G M Snoek
Éditeur: ICCV

Elastic ViTs from Pretrained Models without Retraining

Auteurs: Walter Simoncini, Michael Dorkenwald, Tijmen Blankevoort, Cees G M Snoek, Yuki M Asano
Éditeur: NeurIPS

Benchmarking XAI Explanations with Human-Aligned Evaluations

Auteurs: Remi Kazmierczak, Steve Azzolin, Eloise Berthier, Anna Hedstrom, Patricia Delhomme, David Filliat, Nicolas Bousquet, Goran Frehse, Massimiliano Mancini, Baptiste Caramiaux, Andrea Passerini, Gianni Franchi
Éditeur: AAAI

Speedrunning Tabular Foundation Model Pretraining

Auteurs: Salih Bora Öztürk, Alexander Pfefferle, Frank Hutter
Éditeur: 2nd ICML Workshop on Foundation Models for Structured Data

MeVer at CheckThat! 2026: Cluster-Aware Hard-Negative Mining for Multilingual Scientific Source Retrieval

Auteurs: Juli Bakagianni, Symeon Papadopoulos
Éditeur: CLEF 2026 Working Notes

Tiny Inference-Time Scaling with Latent Verifiers

Auteurs: Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Éditeur: CVPR 2026 (Findings)

Scaling Vision-Language Models Is Not Enough to Mitigate Bias

Auteurs: Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos
Éditeur: ACM MM

Open-Vocabulary Domain Generalization in Urban-Scene Segmentation

Auteurs: Dong Zhao, Qi Zang, Nan Pu, Wenjing Li, Nicu Sebe, Zhun Zhong
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting

Auteurs: Paschalis Giakoumoglou, Dimitrios Karageorgiou, Symeon Papadopoulos, Panagiotis C. Petrantonakis
Éditeur: ICCV

A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling

Auteurs: Filippo Dainelli, Amirpasha Mozaffari, Marina Castaño, Aina Gaya i Àvila, Lluís Palma Garcia, Alessio Melli, Oscar Dimdore Miles, Amanda Duarte
Éditeur: ECML PKDD 2026 workshop

Towards Uniformity and Alignment for Multimodal Representation Learning

Auteurs: Wenzhe Yin , Pan Zhou, Zehao Xiao, Jie Liu, Shujian Yu, Jan-Jakob Sonke, Efstratios Gavves
Éditeur: ICML

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

Auteurs: Mainak Singha, Subhankar Roy, Sarthak Mehrotra, Ankit Jha, Moloud Abdar, Biplab Banerjee, Elisa Ricci
Publié dans: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026
Éditeur: IEEE
DOI: 10.1109/ICCV51701.2025.01660

Show Me Examples: Inferring Visual Concepts from Image Sets

Auteurs: Nick Stracke, Kolja Bauer, Stefan Andreas Baumann, Miguel Angel Bautista, Josh Susskind, Björn Ommer
Éditeur: European Conference on Computer Vision - ECCV

From Driving Videos to Simulatable Scenarios

Auteurs: Alexandre Levy, Ernest Valveny Llobet, Antonio M. Lopez
Éditeur: IEEE Intelligent Transportation Systems Conference (ITSC)

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

Auteurs: Haiyang Zheng, Nan Pu, Yaqi Cai, Teng Long, Wenjing Li, Nicu Sebe, Zhun Zhong
Éditeur: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners

Auteurs: Yunhan Wang, Eshika Khandelwal, Edson Araujo, Walid Bousselham, Nina Shvetsova, Hilde Kuehne
Éditeur: ECCV

Personalizing MLLMs via Reinforced Multimodal Reference Game

Auteurs: Deepayan Das, Davide Talon, Yiming Wang, Massimiliano Mancini, Elisa Ricci
Éditeur: ECCV

H <sub>2</sub> OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers

Auteurs: Wenhao Li, Mengyuan Liu, Hong Liu, Pichao Wang, Shijian Lu, Nicu Sebe
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 48, 2025, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2025.3608284

Towards Stable Source-Free Domain Adaptive Semantic Segmentation

Auteurs: Dong Zhao, Qi Zang, Nan Pu, Jinlong Li, Shuang Wang, Nicu Sebe, Zhun Zhong
Publié dans: International Journal of Computer Vision, Numéro 134, 2026, ISSN 0920-5691
Éditeur: Springer Science and Business Media LLC
DOI: 10.1007/S11263-026-02929-6

GateRA: Token-aware Modulation for Parameter-Efficient Fine-tuning

Auteurs: Jie Ou, Shuaihong Jiang, Yingjun Du, Cees G. M. Snoek
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 40, 2026, ISSN 2374-3468
Éditeur: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V40I38.40538

Bridging modalities: a Survey and Taxonomy of Automated Multimodal Machine Learning (MMAutoML)

Auteurs: Blaž Škrlj, Aljaž Osojnik
Publié dans: Artificial Intelligence Review, 2026, ISSN 1573-7462
Éditeur: Springer Science and Business Media LLC
DOI: 10.1007/S10462-026-11624-4

Fully- and semi-supervised hierarchical multi-label image classification with graph learning

Auteurs: Marjan Stoimchev, Boshko Koloski, Jurica Levatić, Dragi Kocev, Sašo Džeroski
Publié dans: Information Sciences, Numéro 754, 2026, ISSN 0020-0255
Éditeur: Elsevier BV
DOI: 10.1016/J.INS.2026.123641

The rise of AI in weather and climate information and its impact on global inequality

Auteurs: Amirpasha Mozaffari, Amanda Duarte, Lina Teckentrup, Stefano Materia, Gina E. C. Charnley, Lluís Palma, Eulália Baulenas, Dragana Bojovic, Paula Checchia, Aude Carréric, Francisco Doblas-Reyes
Publié dans: npj Climate Action, 2026, ISSN 2731-9814
Éditeur: Springer Science and Business Media LLC
DOI: 10.1038/S44168-026-00412-Z

GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models

Auteurs: Moreno D’Incà, Elia Peruzzo, Massimiliano Mancini, Xingqian Xu, Humphrey Shi, Nicu Sebe
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 47, 2025, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2025.3592901

Multimodal-Conditioned Latent Diffusion Models for Fashion Image Editing

Auteurs: Alberto Baldrati, Davide Morelli, Marcella Cornia, Marco Bertini, Rita Cucchiara
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, Numéro 22, 2026, ISSN 1551-6857
Éditeur: Association for Computing Machinery (ACM)
DOI: 10.1145/3789212

The Aloe Family recipe for open and specialized healthcare LLMs

Auteurs: Dario Garcia-Gasulla, Jordi Bayarri-Planas, Ashwin Kumar Gururajan, Enrique Lopez-Cuena, Adrian Tormos, Daniel Hinjos, Pablo Bernabeu-Perez, Anna Arias-Duart, Pablo Agustin Martin-Torres, Marta Gonzalez-Mallo, Sergio Alvarez-Napagao, Eduard Ayguadé-Parra, Ulises Cortés
Publié dans: npj Digital Medicine, Numéro 9, 2026, ISSN 2398-6352
Éditeur: Springer Science and Business Media LLC
DOI: 10.1038/S41746-026-02637-Y

Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts

Auteurs: Haiyang Zheng, Nan Pu, Wenjing Li, Nicu Sebe, Zhun Zhong
Publié dans: International Journal of Computer Vision, Numéro 134, 2026, ISSN 0920-5691
Éditeur: Springer Science and Business Media LLC
DOI: 10.1007/S11263-026-02970-5

ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains

Auteurs: Artemis Llabrés, Marc Serra Ortega, Tomàs Ockier, Samuel Ortega Cuadra, Amritpal Singh, Christos Georgakilas, Andrey Barsky, Ernest Valveny, Dimosthenis Karatzas
Publié dans: Lecture Notes in Computer Science, Document Analysis and Recognition – ICDAR 2026, 2026
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-36042-7_20

Publications

Télécharger Télécharger le contenu de la page

European Large Open Multi-Modal Foundation Models For Robust Generalization On Arbitrary Data Streams

Resultats de projets

Publications

Télécharger Télécharger le contenu de la page