Knowledge catalogue
arXiv:2608.07620v1 Announce Type: new Abstract: Recent advances in flow matching models have substantially improved the quality of text-to-image generation, but have also raised increasing safety conc
arXiv:2608.00147v1 Announce Type: new Abstract: Vision-language pretraining learns rich medical image representations from radiology reports, but previous model variants commonly operate within a sing
arXiv:2607.28386v1 Announce Type: new Abstract: Image similarity underlies many computer vision applications, yet it is often unclear why two images receive a high or low similarity score. Existing ex
arXiv:2607.23237v1 Announce Type: cross Abstract: Effective flood risk management relies on accurate forecasting, yet the 'black box' nature of stateof-the-art Deep Learning models creates a barrier t
arXiv:2606.12629v3 Announce Type: replace-cross Abstract: The standard basis of transformer hidden states is a training-free, architecture-general feature basis for detecting concepts and, in language
arXiv:2607.06432v1 Announce Type: cross Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes,
arXiv:2607.04548v1 Announce Type: cross Abstract: Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing meth
arXiv:2607.03932v1 Announce Type: cross Abstract: LLMs can be conveniently adapted to a diverse set of tasks, e.g, prediction, question-answering tasks, etc, using appropriate prompts with few-shot ex
arXiv:2607.03397v1 Announce Type: new Abstract: Text-to-Image diffusion models often propagate harmful bias inherited from the training data. Existing bias mitigation techniques typically intervene on
arXiv:2606.11446v1 Announce Type: new Abstract: This research introduces a framework for incorporating Concept Bottleneck Models (CBMs) into 3D generative architectures to address the inherent 'semant
arXiv:2606.03792v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) successfully enables personalization in text-to-image generation by adapting pre-trained diffusion models to specific visual
arXiv:2606.01698v1 Announce Type: new Abstract: Deep learning has revolutionized medical image analysis, delivering exceptional diagnostic accuracy across diverse applications. Yet, the lack of interp
arXiv:2504.21072v2 Announce Type: replace-cross Abstract: The expansion of text-to-image diffusion models has raised concerns about harmful outputs, from fabricated depictions of public figures to sex
arXiv:2605.29836v1 Announce Type: cross Abstract: Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Id
arXiv:2505.20634v2 Announce Type: replace Abstract: Concept shift occurs when the distribution of labels conditioned on the features changes between domains, which can make even a well-tuned ML model
arXiv:2605.23141v1 Announce Type: new Abstract: A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipula
arXiv:2605.20309v1 Announce Type: new Abstract: Current personalization methods for generative vision models typically encode new concepts through continuous adapters or weight updates, yet provide li
arXiv:2605.19739v1 Announce Type: new Abstract: Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the
arXiv:2605.18830v1 Announce Type: new Abstract: Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identif
arXiv:2605.20110v1 Announce Type: new Abstract: Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-categ
arXiv:2605.18481v1 Announce Type: new Abstract: Interpreting the decisions of deep image classifiers remains challenging, particularly in black-box settings where model internals are inaccessible. We
arXiv:2605.18202v1 Announce Type: cross Abstract: Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reli
arXiv:2605.15688v1 Announce Type: cross Abstract: Concept Activation Vectors (CAVs) are a fundamental tool for concept-based explainability in deep learning, yet their practical utility is limited by
arXiv:2605.16046v1 Announce Type: cross Abstract: Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a s
arXiv:2605.10198v1 Announce Type: cross Abstract: Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-for
arXiv:2604.16871v1 Announce Type: cross Abstract: Neuro-symbolic Reinforcement Learning (NeSy-RL) combines symbolic reasoning with gradient-based optimization to achieve interpretable and generalizabl
arXiv:2604.14726v1 Announce Type: new Abstract: Online anomaly detection (OAD) plays a pivotal role in real-time analytics and decision-making for evolving data streams. However, existing methods ofte
arXiv:2505.11237v3 Announce Type: replace-cross Abstract: Metaphorical imagination, the ability to connect seemingly unrelated concepts, is fundamental to human cognition and communication. While unde
arXiv:2604.11802v1 Announce Type: new Abstract: Using psychological constructs such as the Big Five, large language models (LLMs) can imitate specific personality profiles and predict a user's persona
arXiv:2508.20765v2 Announce Type: replace-cross Abstract: The automatic understanding of video content is advancing rapidly. Empowered by deeper neural networks and large datasets, machines are increa
arXiv:2506.01004v3 Announce Type: replace-cross Abstract: Unlike traditional video editing or inpainting, video semantic mixing fuses a reference concept with a moving target entity to produce a hybri
arXiv:2603.08309v3 Announce Type: replace Abstract: Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than
arXiv:2609.15334v1 Announce Type: cross Abstract: Medical imaging modalities such as ultrasound and X-ray are widely used in clinical practice, where diagnosis follows a structured, evidence-driven wo
arXiv:2609.11995v1 Announce Type: new Abstract: Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains chall
arXiv:2609.07004v1 Announce Type: new Abstract: Accurate segmentation of pulmonary lesions is essential for effective clinical diagnosis and treatment strategies. Existing segmentation approaches ofte
arXiv:2608.26887v1 Announce Type: new Abstract: LLMs are thought to track 'belief states,' i.e., running probability distributions over the latent variables that govern language (Shai et al., 2024; Sa
arXiv:2608.22584v1 Announce Type: new Abstract: Two-stage neuro-symbolic architectures provide an elegant paradigm for visual problem solving by cleanly separating connectionist perception of predefin
arXiv:2608.21277v1 Announce Type: new Abstract: State-of-the-art multivariate time-series forecasters can model complex temporal and cross-variable dependencies, yet their opaque representations provi
arXiv:2506.14790v3 Announce Type: replace Abstract: Recurring concept drift is pervasive in real-world online time series, where the underlying data-generating process repeatedly alternates between a
arXiv:2608.16669v1 Announce Type: new Abstract: Recent advances in pathology foundation models have enabled accurate prediction of spatial transcriptomics (ST) from routine H&E images. However, existi
arXiv:2608.03708v1 Announce Type: new Abstract: Text-to-image diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single
arXiv:2607.29200v1 Announce Type: new Abstract: Ultrasound imaging has become increasingly widespread in clinical practice due to its portability, low cost and real-time capability, making ultrasound
arXiv:2607.22494v1 Announce Type: cross Abstract: Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk factors are be
arXiv:2511.05865v3 Announce Type: replace-cross Abstract: Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised signifi
arXiv:2510.02655v2 Announce Type: replace Abstract: This paper offers a new concept of {it possibility} as an alternative to the now-a-days standard concept originally introduced by L.A. Zadeh in 1978
arXiv:2606.24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation met
arXiv:2606.24570v1 Announce Type: new Abstract: Vision-language contrastive pretraining has become the dominant recipe for 3D medical foundation models, leveraging the large volumes of paired scans an
arXiv:2411.05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification. However, interpreting their predictions is cha
arXiv:2606.07688v1 Announce Type: cross Abstract: Generative recommendation formulates next-item prediction as autoregressive generation over semantic ID (SID) sequences derived from users' historical
arXiv:2606.06994v1 Announce Type: new Abstract: What makes a sentence encoder produce good concept representations? We approach this through the lens of representational compositionality: an encoder s
arXiv:2605.28780v1 Announce Type: new Abstract: Vision classifiers can exploit spurious correlations, achieving high in-distribution accuracy yet failing under distribution shift. Existing approaches
arXiv:2605.24603v1 Announce Type: new Abstract: A sparse 8-layer code transformer develops dedicated neural circuitry for every Python construct tested, and that circuitry is organised by a clean comp
arXiv:2605.25263v1 Announce Type: cross Abstract: Current language modeling approaches are built around tokens. Text corpora are split into tokens, and models are trained by performing computations on
arXiv:2605.22743v1 Announce Type: new Abstract: Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challengi
arXiv:2605.14769v1 Announce Type: new Abstract: De novo crystal generation, a central task in materials discovery, aims to generate crystals that are simultaneously valid, stable, unique, and novel. E
arXiv:2605.14270v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-to-image generation, yet they frequently suffer from concept omiss
arXiv:2605.07600v1 Announce Type: cross Abstract: Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, canno
arXiv:2605.07140v1 Announce Type: cross Abstract: Skeleton-based human activity recognition has achieved strong empirical performance, yet most existing models remain black boxes and difficult to inte
arXiv:2605.05103v1 Announce Type: new Abstract: We introduce the **Concept Field** of a text corpus: a local drift field with pointwise uncertainty, estimated in sentence-embedding space from the delt
arXiv:2603.10377v2 Announce Type: replace-cross Abstract: Sparse autoencoders can localize where concepts live in language models, but not how they interact during multi-step reasoning. We propose Cau