Knowledge catalogue
arXiv:2608.26083v1 Announce Type: cross Abstract: Deep neural networks often exploit spurious associations in their training data, a failure known as shortcut learning. Concept-based explainability me
arXiv:2608.25245v1 Announce Type: cross Abstract: LLM-generated search queries are widely used to augment IR evaluation, yet they may contain concepts that presuppose answer-side document knowledge, v
arXiv:2608.12829v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MM-DiTs) have demonstrated remarkable text-to-image generation performance, surpassing traditional U-Net-based diffus
arXiv:2608.13465v1 Announce Type: cross Abstract: Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Mach
arXiv:2607.20691v1 Announce Type: cross Abstract: Concept Bottleneck Models provide interpretable-by-design predictions by mediating diagnosis through human-understandable concepts, but in medical ima
arXiv:2607.17890v2 Announce Type: replace Abstract: Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment. Howeve
arXiv:2607.03973v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because re
arXiv:2607.05274v1 Announce Type: new Abstract: Training-free concept erasure is an attractive mechanism for controlling text-to-image diffusion models, but precise erasure often comes at the cost of
arXiv:2606.07007v1 Announce Type: cross Abstract: We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs).
arXiv:2606.04326v1 Announce Type: cross Abstract: Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from i
arXiv:2606.04797v1 Announce Type: new Abstract: Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the
arXiv:2605.19855v1 Announce Type: cross Abstract: Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or
arXiv:2603.07561v2 Announce Type: replace Abstract: Existing concept customization methods have achieved remarkable outcomes in high-fidelity and multi-concept customization. However, they often negle
arXiv:2605.01381v1 Announce Type: new Abstract: Understanding how neural models represent human-interpretable concepts is challenging. Prior work has explored linear concept subspaces from diverse per
arXiv:2610.01989v1 Announce Type: new Abstract: Concept erasure removes copyright-protected, privacy-sensitive, or otherwise undesirable concepts from pretrained text-to-image diffusion models to supp
arXiv:2610.01302v1 Announce Type: new Abstract: Concept erasure suppresses a target concept while preserving behavior on unrelated inputs. Existing closed-form methods were designed for 2D image diffu
arXiv:2609.36832v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models can generate realistic depictions of actions such as kicking, stabbing, and shooting, raising safety concerns that
arXiv:2609.36982v1 Announce Type: cross Abstract: Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners i
arXiv:2609.37786v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) built on vision-language models such as CLIP represent a latent space as human-understandable concepts. These represent
arXiv:2604.03114v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) may need to forget visual concepts after deployment because of privacy, copyright, licensing, safety, or policy
We continue to iterate on the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format. But a big question remains: How can you sha
arXiv:2606.08477v1 Announce Type: new Abstract: Knowledge extraction from symbolic data often produces abstractions that are formally defined but not immediately interpretable by users. Formal Concept
arXiv:2605.28902v1 Announce Type: new Abstract: Concept erasure has emerged as a promising approach to mitigate undesired or unsafe content in diffusion models, yet existing methods still face signifi
arXiv:2605.22469v1 Announce Type: new Abstract: Evaluating single-concept personalization in text-to-image diffusion requires measuring both concept preservation, which captures identity fidelity to a
arXiv:2601.14330v2 Announce Type: replace Abstract: Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, reveal
arXiv:2510.25512v2 Announce Type: replace-cross Abstract: Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they fun
arXiv:2604.11986v1 Announce Type: new Abstract: We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, conc
arXiv:2610.06928v1 Announce Type: new Abstract: We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence. We hypothesize a
arXiv:2610.02278v1 Announce Type: new Abstract: Cognitive diagnosis (CD) is a fundamental task in intelligent education that profiles learner proficiency over knowledge concepts. In real-world learnin
arXiv:2609.23065v1 Announce Type: new Abstract: Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input-
arXiv:2609.01433v1 Announce Type: new Abstract: Concept erasure aims to suppress unsafe, privacy-sensitive, or undesirable generations in text-to-image diffusion models while preserving benign semanti
arXiv:2609.00054v1 Announce Type: new Abstract: Formal Concept Analysis (FCA) is an approach for conceptual classification building and rule discovery from a binary table describing a set of objects b
arXiv:2608.20809v1 Announce Type: cross Abstract: Breast ultrasound diagnosis relies on clinically meaningful semantic concepts, yet most deep learning methods adopt end-to-end image-to-label paradigm
arXiv:2608.06300v1 Announce Type: new Abstract: Automatic speaking assessment systems are increasingly deployed in high-stakes settings to mark second language (L2) learners' speaking tests, making it
arXiv:2606.30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color. To bridge the gap between opaqu
arXiv:2606.29282v1 Announce Type: new Abstract: Concept erasure aims to prevent image generative models from producing unsafe content while preserving their general generative capability. Meanwhile, n
arXiv:2606.29069v1 Announce Type: new Abstract: Concept-based Explainable AI (C-XAI) seeks human-understandable explanations grounded in semantic concepts, yet validation is limited by the scarcity of
arXiv:2605.26460v1 Announce Type: cross Abstract: Multi-Modal Diffusion Transformers (MM-DiTs) encode rich representations for training-free concept grounding, but existing attention-based methods oft
arXiv:2605.27116v1 Announce Type: new Abstract: Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-wor
arXiv:2605.25765v1 Announce Type: cross Abstract: Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attracti
arXiv:2605.25848v1 Announce Type: cross Abstract: Concept probes extracted from transformer residual streams are only as reliable as the layer from which they are extracted. The common practice of pro
arXiv:2605.25304v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) have emerged as a cornerstone approach for interpretable machine learning, providing human-understandable intermediate
arXiv:2605.20612v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) have emerged as a prominent paradigm for interpretable deep learning, learning by grounding predictions in human-unders
arXiv:2605.07785v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) in medical imaging aim to improve model interpretability by predicting intermediate clinical concepts before final diag
arXiv:2506.05014v2 Announce Type: replace-cross Abstract: We propose a novel, flexible, and efficient framework for designing Concept Bottleneck Models (CBMs) that enables practitioners to explicitly
arXiv:2604.09405v1 Announce Type: new Abstract: As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted char
arXiv:2609.35096v1 Announce Type: new Abstract: Deepfake detection methods have become increasingly effective yet most provide limited insight into the evidence behind their predictions. However, in f
arXiv:2602.07919v2 Announce Type: replace-cross Abstract: Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods
arXiv:2609.12163v1 Announce Type: new Abstract: Existing evaluations of concept unlearning in text-to-image (T2I) diffusion models primarily rely on attack success rates obtained through automated adv
arXiv:2609.13072v1 Announce Type: cross Abstract: Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary conce
arXiv:2609.09055v1 Announce Type: new Abstract: Vision transformers (ViTs) have achieved remarkable generalization across visual domains, yet little is known about how they internally represent the st
arXiv:2609.05575v1 Announce Type: cross Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability
arXiv:2608.07857v1 Announce Type: cross Abstract: Foundation models provide transferable CT representations, but predictions based directly on these embeddings are difficult to interpret. We developed
arXiv:2608.07353v1 Announce Type: cross Abstract: Understanding concepts is fundamental to generalization. Despite their impressive performance on a wide range of tasks, Large Language Models (LLMs) s
arXiv:2608.02930v1 Announce Type: new Abstract: We revisit higher-arity atomic concept learning through the geometry of hypercubes and hyperplanes of ground instances. Our starting point is the observ
arXiv:2605.12122v1 Announce Type: cross Abstract: Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among
arXiv:2605.06440v2 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining classifier input
arXiv:2602.19019v2 Announce Type: replace Abstract: Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without a
arXiv:2609.39263v1 Announce Type: new Abstract: A concept subspace's effect on model behavior does not establish how it relates to the output readout. We introduce a two-sided geometric diagnostic tha
arXiv:2608.29311v1 Announce Type: new Abstract: Classic Formal Concept Analysis (FCA) primarily focuses on the positive relationships between objects and attributes and does not have mechanisms for ha