Search: “concepts”

arXiv:2605.24856v1 Announce Type: cross Abstract: Concept formation in transformer language models is depth-extended, not a single-layer event: concepts emerge gradually across a contiguous region of

arXiv:2610.08552v1 Announce Type: new Abstract: Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally requ

arXiv:2502.08921v2 Announce Type: replace-cross Abstract: The task of text-to-image generation has achieved tremendous success in practice, with emerging concept generation models capable of producing

arXiv:2605.16405v1 Announce Type: new Abstract: Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakehol

arXiv:2610.01821v1 Announce Type: new Abstract: Understanding information processing in large language models (LLMs) requires dissecting the geometric organization of their internal token representati

arXiv:2609.39453v1 Announce Type: cross Abstract: Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent appr

arXiv:2610.05017v1 Announce Type: new Abstract: Concept-based methods provide a semantic level for interpreting and manipulating learned representations, but existing editing approaches are typically

arXiv:2610.13935v1 Announce Type: cross Abstract: Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods in

arXiv:2602.02726v2 Announce Type: replace-cross Abstract: Large language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information

arXiv:2601.03570v2 Announce Type: replace Abstract: Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and

arXiv:2605.20908v1 Announce Type: new Abstract: Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task perfo

arXiv:2610.09802v1 Announce Type: new Abstract: Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to tho

arXiv:2610.01331v1 Announce Type: new Abstract: Continual personalization of text-to-image diffusion models requires sequentially acquiring new concepts while retaining previously learned ones. Howeve

arXiv:2605.20385v1 Announce Type: new Abstract: Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding. However, the

arXiv:2505.06191v2 Announce Type: replace-cross Abstract: This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent

arXiv:2606.26891v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) promise transparent reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamental

arXiv:2606.21197v1 Announce Type: new Abstract: Vision Language Models (VLMs) have demonstrated impressive performance in tasks requiring joint understanding of images and text, such as image captioni

arXiv:2610.05601v1 Announce Type: new Abstract: Existing attacks on unlearned diffusion models assume that the erased concepts are known in advance and focus on recovering them. In practice, however,

arXiv:2608.03135v1 Announce Type: cross Abstract: Text-to-image diffusion models can generate individual concepts well, but they often omit or merge concepts incorrectly with multiple concepts. We tra

arXiv:2509.23926v4 Announce Type: replace Abstract: Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along dir

arXiv:2607.04525v1 Announce Type: cross Abstract: How concepts are represented in neural networks is a fundamental question in machine learning. The dominant view treats concept representations as sta

arXiv:2509.21379v3 Announce Type: replace-cross Abstract: Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making th

arXiv:2609.24821v1 Announce Type: new Abstract: The Linear Representation Hypothesis associates high-level concepts with directions in language models, but it remains unclear how these concept-related

arXiv:2608.31084v1 Announce Type: new Abstract: The Jacobian Lens (J-lens) is a recent tool for interpreting LLMs. It reads a hidden state as a ranked list of vocabulary tokens, leaving multi-token co

arXiv:2409.11972v4 Announce Type: replace-cross Abstract: Enabling robots to autonomously discover high-level spatial concepts (e.g., rooms and walls) from primitive geometric observations (e.g., plan

arXiv:2610.08086v1 Announce Type: new Abstract: The clinical integration of AI systems in digital dermatology relies heavily on human trust. Clinically interpretable visual concepts can act as interme

arXiv:2605.31503v1 Announce Type: new Abstract: Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision-language embedding models

arXiv:2604.11749v1 Announce Type: new Abstract: Language change both reflects and shapes social processes, and the semantic evolution of foundational concepts provides a measurable trace of historical

arXiv:2610.01864v1 Announce Type: cross Abstract: How can we understand what a music foundation model has learned extit{internally}? Most interpretability approaches, such as probing and Sparse Autoen

arXiv:2602.16917v2 Announce Type: replace Abstract: Modern vision models increasingly rely on rich semantic representations that extend beyond class labels to include descriptive concepts, attributes,

arXiv:2607.26825v1 Announce Type: new Abstract: Large language models (LLMs) encode rich concept-like information, but represent it implicitly through distributed statistical associations rather than

arXiv:2607.07267v1 Announce Type: cross Abstract: Claims about the universality of human concepts have been predominantly assessed through linguistic similarity across languages and cultures. However,

arXiv:2607.07264v1 Announce Type: new Abstract: Deep neural networks are widely deployed in high-stakes visual applications where interpretability is critical, yet existing explanations face a trade-o

arXiv:2606.24192v1 Announce Type: cross Abstract: Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only

arXiv:2605.28823v1 Announce Type: new Abstract: As the influence of LLMs expands, it is imperative to gain insight into their decisions. One way to do that is to develop probes that detect the presenc

arXiv:2605.01148v1 Announce Type: cross Abstract: Does structure in representations imply structure in computation? We study how Llama-3.1-8B reasons over cyclic concepts (e.g., 'what month is six mon

arXiv:2606.16193v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representati

arXiv:2508.05880v3 Announce Type: replace-cross Abstract: Understanding human emotions is central to user-facing AI applications, safety alignment, and the simulation of human behavior. As emotional s

arXiv:2607.08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large

arXiv:2607.02402v2 Announce Type: replace Abstract: Vision-language models (VLMs) can follow complex textual instructions, yet they struggle to reason from purely visual context. In particular, curren

arXiv:2606.28815v1 Announce Type: cross Abstract: Mathswitch is an open-source project that imports mathematical concept records from sources such as Wikidata, Wikipedia, MathWorld, Encyclopedia of Ma

arXiv:2604.17089v1 Announce Type: new Abstract: Continual learning aims to update models under distribution shift without forgetting, yet many high-stakes deployments, such as healthcare, also require

arXiv:2405.15662v2 Announce Type: replace Abstract: Machine unlearning aims to remove the influence of specified training data or knowledge from a trained model without requiring full retraining. This

arXiv:2609.30414v1 Announce Type: cross Abstract: Cognitive psychology has studied how people encode, use, and learn concepts that describe categories, and how they represent, recognize, and acquire c

arXiv:2609.04528v1 Announce Type: new Abstract: Humans can learn and generalize novel concepts from sparse data because they express knowledge in rich structural formats. In this paper, we propose tha

arXiv:2601.21282v2 Announce Type: replace Abstract: Recent advances in generative foundational models, often termed 'world models,' have propelled interest in applying them to critical tasks like robo