Related papers: SHARCS: Shared Concept Space for Explainable Multi…

Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the…

Generating high-quality MCQs, especially those targeting diverse cognitive levels and incorporating common misconceptions into distractor design, is time-consuming and expertise-intensive, making manual creation impractical at scale.…

The goal of coordinated multi-robot exploration tasks is to employ a team of autonomous robots to explore an unknown environment as quickly as possible. Compared with human-designed methods, which began with heuristic and rule-based…

Recently, significant progress has been made in multi-modal continual learning, aiming to learn new tasks sequentially in multi-modal settings while preserving performance on previously learned ones. However, existing methods mainly focus…

Corrupted data sets containing noisy or missing observations are prevalent in various contemporary applications such as economics, finance and bioinformatics. Despite the recent methodological and algorithmic advances in high-dimensional…

In modern machine learning, pattern recognition replaces realtime semantic reasoning. The mapping from input to output is learned with fixed semantics by training outcomes deliberately. This is an expensive and static approach which depends…

Vision-language co-embedding networks, such as CLIP, provide a latent embedding space with semantic information that is useful for downstream tasks. We hypothesize that the embedding space can be disentangled to separate the information on…

Time series classification is a task of paramount importance, as this kind of data often arises in safety-critical applications. However, it is typically tackled with black-box deep learning methods, making it hard for humans to understand…

Real-world visual search systems involve deployments on multiple platforms with different computing and storage resources. Deploying a unified model that suits the minimal-constrain platforms leads to limited accuracy. It is expected to…

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directly understandable and…

Multimodal learning, which aims to understand and analyze information from multiple modalities, has achieved substantial progress in the supervised regime in recent years. However, the heavy dependence on data paired with expensive human…

Spatial reasoning, which requires ability to perceive and manipulate spatial relationships in the 3D world, is a fundamental aspect of human intelligence, yet remains a persistent challenge for Multimodal large language models (MLLMs).…

Advances in social media data dissemination enable the provision of real-time information during a crisis. The information comes from different classes, such as infrastructure damages, persons missing or stranded in the affected zone, etc.…

We introduce a novel framework for evaluating multimodal deep learning models with respect to their language understanding and generalization abilities. In this approach, artificial data is automatically generated according to the…

Modern deep neural networks have now reached human-level performance across a variety of tasks. However, unlike humans they lack the ability to explain their decisions by showing where and telling what concepts guided them. In this work, we…

Multimodal meta-learning is a recent problem that extends conventional few-shot meta-learning by generalizing its setup to diverse multimodal task distributions. This setup makes a step towards mimicking how humans make use of a diverse set…

Concept-based Models are neural networks that learn a concept extractor to map inputs to high-level concepts and an inference layer to translate these into predictions. Ensuring these modules produce interpretable concepts and behave…

Continual learning aims to update models under distribution shift without forgetting, yet many high-stakes deployments, such as healthcare, also require interpretability. In practice, models that adapt well (e.g., deep networks) are often…

Multimodal learning has been a field of increasing interest, aiming to combine various modalities in a single joint representation. Especially in the area of visiolinguistic (VL) learning multiple models and techniques have been developed,…