Search: “concepts”

arXiv:2608.18185v1 Announce Type: cross Abstract: Fine-grained recognition often involves hierarchical label spaces, where a model may be confident about a coarse semantic concept while remaining unce

arXiv:2507.22423v3 Announce Type: replace Abstract: To engineer AGI, we should first capture the essence of intelligence in a species-agnostic form that can be evaluated, while being sufficiently gene

arXiv:2608.10295v1 Announce Type: cross Abstract: Frozen foundation-model (FM) embeddings are increasingly used as off-the-shelf brain-MRI representations, on the assumption that they capture anatomy.

arXiv:2608.10420v1 Announce Type: new Abstract: Reasoning shortcuts are solutions of a neurosymbolic system's rules that produce correct predictions through unintended concepts. A recent framework of

arXiv:2608.07594v1 Announce Type: cross Abstract: Interpretability is often treated as a tax on capability: language models are trained as opaque systems, then explained after the fact, with methods w

arXiv:2608.05455v1 Announce Type: new Abstract: When a student must learn concepts connected by prerequisite dependencies, when does the order of instruction matter, and what does it cost to find the

arXiv:2608.03529v1 Announce Type: new Abstract: Biomedical literature is increasingly mined for knowledge beyond the questions it was written to answer. Because the target concepts are not known in ad

arXiv:2608.03556v1 Announce Type: new Abstract: Soft wearable robots have evolved rapidly from proof-of-concept devices into promising platforms for rehabilitation, occupational assistance, and human

arXiv:2608.03006v1 Announce Type: new Abstract: Prerequisite relation learning is central to adaptive instruction, yet existing methods often formulate it as conventional link prediction, limiting the

arXiv:2608.02803v1 Announce Type: cross Abstract: Attention-based multiple instance learning (ABMIL) is the predominant approach for slide-level prediction in computational pathology, yet its attentio

arXiv:2608.03921v1 Announce Type: new Abstract: This paper offers a new interpretation of the Transformer during inference. Against the 'stochastic parrot' view that large language models merely repro

arXiv:2608.02321v1 Announce Type: cross Abstract: Graph functional dependencies (GFD) are a recently-developed concept aimed at capturing both topological structures in graphs and functional dependenc

arXiv:2607.24805v1 Announce Type: cross Abstract: AI Engram (Kwon et al., 2026) formalizes the four engram criteria of neuroscience as a constrained inverse problem in weight space and solves it close

arXiv:2607.24750v1 Announce Type: new Abstract: Large Language Models (LLMs) are temporally overexposed: trained on vast contemporary corpora, they encode present-day concepts that make them unreliabl

arXiv:2607.23496v1 Announce Type: new Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their sa

arXiv:2607.23883v1 Announce Type: new Abstract: In this paper, we examine the difficulties of using standard techniques for medical image classification due to long-tailed distributions (wherein rarer

arXiv:2607.24649v1 Announce Type: new Abstract: Large language models are increasingly used as social simulators, including as synthetic survey respondents. Most evaluations ask whether simulated outc

arXiv:2607.23052v1 Announce Type: cross Abstract: Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries

arXiv:2607.20924v1 Announce Type: new Abstract: Makeup-transfer applies the reference makeup to the source face while preserving the source identity. Despite advances in full-face editing by diffusion

arXiv:2607.12185v1 Announce Type: new Abstract: Embodied accounts of semantic memory highlight the role of sensorimotor systems in acquiring and storing knowledge. Congenitally blind populations offer

arXiv:2602.04718v2 Announce Type: replace-cross Abstract: A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activat

arXiv:2602.11391v4 Announce Type: replace Abstract: Objective: This study develops and validates a patient simulation framework that aligns with the National Institute of Standards and Technology (NIS

arXiv:2607.06120v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploi

arXiv:2602.24264v2 Announce Type: replace Abstract: Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although mod

arXiv:2607.02571v1 Announce Type: new Abstract: The Segment Anything Model with Concepts (SAM3) heralds a new paradigm for open-vocabulary segmentation through natural language interaction, offering s

arXiv:2401.10805v4 Announce Type: replace-cross Abstract: We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in a

arXiv:2311.17633v2 Announce Type: replace-cross Abstract: Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Tr

arXiv:2606.30262v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models often fail to faithfully render explicit textual descriptions, instead defaulting to strongly learned visual priors

arXiv:2606.24636v1 Announce Type: new Abstract: Cinematographic captioning aims to describe how a video is filmed using professional film-language concepts such as camera movement, shot size, depth of

arXiv:2404.11716v2 Announce Type: replace Abstract: Building Energy Management (BEM) is central to reducing energy use and CO2 emissions in the building sector. Although IoT technologies now provide e

arXiv:2606.11149v1 Announce Type: new Abstract: We study the problem of learning a drifting concept in the presence of Massart noise. In this framework, an online learner has access to a history of in

arXiv:2606.11105v1 Announce Type: cross Abstract: Hallucinations, where language models (LMs) generate factually ungrounded responses, pose serious risks, as users tend to blindly rely on them. This i

arXiv:2606.06735v1 Announce Type: new Abstract: Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior. More recently, spherical

arXiv:2606.03695v1 Announce Type: new Abstract: As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for safety a

arXiv:2606.03919v1 Announce Type: cross Abstract: Understanding and anticipating scientific change requires models that distinguish between endogenous consolidation and exogenous diffusion of scientif

arXiv:2606.02385v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and cont

arXiv:2512.20638v2 Announce Type: replace-cross Abstract: The evaluation of large language models relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics, but can

arXiv:2602.22968v3 Announce Type: replace Abstract: Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pur

arXiv:2602.15293v2 Announce Type: replace-cross Abstract: This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The

arXiv:2406.10238v2 Announce Type: replace Abstract: An infodemic refers to an enormous amount of true information and misinformation disseminated during a disease outbreak. Detecting misinformation at

arXiv:2509.21167v2 Announce Type: replace-cross Abstract: Most existing methods for concept unlearning in text-to-image diffusion models minimize a mean squared error (MSE) loss between the denoiser o

arXiv:2605.23937v1 Announce Type: new Abstract: Knowledge base (KB) embeddings aim at combining the capability of classical knowledge graph embeddings to generalize the information present in facts, t

arXiv:2605.25378v1 Announce Type: cross Abstract: Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Ada

arXiv:2605.22007v1 Announce Type: new Abstract: Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its gener

arXiv:2505.20650v5 Announce Type: replace-cross Abstract: Accurate interpretation of numerical data in financial reports is critical for markets and regulators. Although XBRL (eXtensible Business Repo

arXiv:2605.16477v1 Announce Type: cross Abstract: What does it mean to create a new concept, rather than retrieve a familiar one? Repeatedly sampling a generative model at the same prompt produces var