1.7k citations · 4.3k across the 154 of their papers we have counts for
173 papers
Visual Grounding First, Multimodal In-context Learning Follows
Minhyuk Seo, Minjae Lee, Chaeeun Lee +4
LLMs have shown strong in-context learning (ICL) capability, but extending it to Multimodal LLMs (MLLMs) remains challenging. Prior multimodal ICL methods often rely on ICL-specifi…
Forgetting, plasticity, and co-observation: a third facet of continual learning
Timm Hess, Abhishek Jha, Gido M. van de Ven +1
Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstac…
Learning visual representations for compositional analysis of artworks and photographs
Fatemeh Behrad, Tinne Tuytelaars, Johan Wagemans
Composition, the deliberate arrangement of visual elements, is central to how meaning, emotion, and aesthetic quality are conveyed in artwork, yet it remains among the least formal…
DemoBridge: A Simulation-in-the-Loop Toolkit for Single-View Human Demonstration Retargeting
Zehao Wang, Fabien Despinoy, Sergey Zakharov +2
We present DemoBridge, an toolkit that turns a single-view RGB stereo recording of a human hand demonstration into an executable, physics-validated robot-arm trajectory. Retargetin…
Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models
Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen +4
Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unl…
FF-JEPA: Long-Horizon Planning in World Models with Latent Planners
Sergi Masip, Jonathan Swinnen, Yutong Hu +2
Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing action trajectories using methods…
Multivariate Distributional Reinforcement Learning Using Sliced Divergences
Baptiste Debes, Tinne Tuytelaars
Distributional reinforcement learning (DRL) models the full return distribution rather than expectations, but extending it to multivariate settings remains challenging. Many common…
Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams
Jonathan Swinnen, Tinne Tuytelaars
In this work we introduce a novel approach to domain incremental learning, adapting models over time to evolving, non-stationary data. In contrast to other works, we do not attempt…
Eccentricity Confound in EEG-based Visual Attention Decoding from Gaze-Fixated Neural Tracking of Motion in Natural Videos
Yuanyuan Yao, Celina Salamanca Gonzalez, Simon Geirnaert +3
Objective. Decoding visual attention from brain signals during naturalistic video viewing has emerged as a new direction in brain-computer interface research. Current methods assum…
Project and Mix: Task-Semantic Prototypes for Few-Shot Image Classification
Dipam Goswami, Simone Magistri, Gido M. van de Ven +4
Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that exploiting few-shot image embedd…
Classifying Novel 3D-Printed Objects without Retraining: Towards Post-Production Automation in Additive Manufacturing
Fanis Mathioulakis, Gorjan Radevski, Silke GC Cleuren +4
Reliable classification of 3D-printed objects is essential for automating post-production workflows in industrial additive manufacturing. Despite extensive automation in other stag…
Distributional value gradients for stochastic environments
Baptiste Debes, Tinne Tuytelaars
Gradient-regularized value learning methods improve sample efficiency by leveraging learned models of transition dynamics and rewards to estimate return gradients. However, existin…
Position: Modular Memory is the Key to Continual Learning Agents
Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov +21
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these…
Sample-level EEG-based Selective Auditory Attention Decoding with Markov Switching Models
Yuanyuan Yao, Simon Geirnaert, Tinne Tuytelaars +1
Selective auditory attention decoding aims to identify the speaker of interest from listeners' neural signals, such as electroencephalography (EEG), in the presence of multiple con…
Self-Supervised Learning with a Multi-Task Latent Space Objective
Pierre-François De Plaen, Abhishek Jha, Luc Van Gool +2
We propose a multi-task formulation of self-predictive Siamese SSL in which each spatial transformation defines a distinct latent-space alignment task, solved by a dedicated predic…
Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
Sergi Masip, Gido M. van de Ven, Javier Ferrando +1
Catastrophic forgetting in continual learning is often measured at the performance or last-layer representation level, overlooking the underlying mechanisms. We introduce a mechani…
NewsRECON: News Article Retrieval for Image Contextualization
Jonathan Tonglet, Iryna Gurevych, Tinne Tuytelaars +1
Identifying when and where a news image was taken is crucial for journalists and forensic experts to produce credible stories and debunk misinformation. While many existing methods…
Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers
Fanis Mathioulakis, Gorjan Radevski, Tinne Tuytelaars
We introduce Eff-GRot, an approach for efficient and generalizable rotation estimation from RGB images. Given a query image and a set of reference images with known orientations, o…
When normalization hallucinates: unseen risks in AI-powered whole slide image processing
Karel Moens, Matthew B. Blaschko, Tinne Tuytelaars +3
Whole slide image (WSI) normalization remains a vital preprocessing step in computational pathology. Increasingly driven by deep learning, these models learn to approximate data di…
PEO: Training-Free Aesthetic Quality Enhancement in Pre-Trained Text-to-Image Diffusion Models with Prompt Embedding Optimization
Hovhannes Margaryan, Bo Wan, Tinne Tuytelaars
This paper introduces a novel approach to aesthetic quality improvement in pre-trained text-to-image diffusion models when given a simple prompt. Our method, dubbed Prompt Embeddin…
Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects
Georgios Kouros, Minye Wu, Tinne Tuytelaars
Accurate reconstruction and relighting of glossy objects remains a longstanding challenge, as object shape, material properties, and illumination are inherently difficult to disent…
Efficient Solutions for Mitigating Initialization Bias in Unsupervised Self-Adaptive Auditory Attention Decoding
Yuanyuan Yao, Simon Geirnaert, Tinne Tuytelaars +1
Decoding the attended speaker in a multi-speaker environment from electroencephalography (EEG) has attracted growing interest in recent years, with neuro-steered hearing devices as…
Is this chart lying to me? Automating the detection of misleading visualizations
Jonathan Tonglet, Jan Zimny, Tinne Tuytelaars +1
Misleading visualizations are a potent driver of misinformation on social media and the web. By violating chart design principles, they distort data and lead readers to draw inaccu…
Forgetting of task-specific knowledge in model merging-based continual learning
Timm Hess, Gido M van de Ven, Tinne Tuytelaars
This paper investigates the linear merging of models in the context of continual learning (CL). Using controlled visual cues in computer vision experiments, we demonstrate that mer…