Search: “concepts”

arXiv:2605.23304v1 Announce Type: new Abstract: Hazard, as an abstract concept, is typically defined through cognitive-level logical reasoning rather than concrete examples. In contrast, existing haza

arXiv:2603.00975v2 Announce Type: replace-cross Abstract: Deployed text-to-image diffusion models increasingly require post-hoc concept unlearning for copyright claims, artist opt-outs, safety updates

arXiv:2605.01844v1 Announce Type: new Abstract: Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical

arXiv:2604.27553v1 Announce Type: new Abstract: When the visual style of text is considered, a wide variety can be observed in font, color, and size. However, when a word is read, its meaning is indep

arXiv:2504.11159v2 Announce Type: replace Abstract: In high-stakes domains, such as healthcare and industry, the explainability of AI-based decision-making has become crucial. Without insight into mod

arXiv:2604.19212v1 Announce Type: new Abstract: Graph neural networks (GNNs) are the standard for learning on graphs, yet they have limited expressive power, often expressed in terms of the Weisfeiler

arXiv:2505.20779v5 Announce Type: replace Abstract: A hallmark of human innovation is recombination -- the creation of novel ideas by integrating elements from existing concepts and mechanisms. In thi

arXiv:2604.16363v1 Announce Type: cross Abstract: Text-to-image models are commercially valuable assets often distributed under restrictive licenses, but such licenses are enforceable only when violat

arXiv:2512.05534v4 Announce Type: replace-cross Abstract: As AI models achieve remarkable capabilities across diverse domains, understanding what representations they learn and how they encode concept

arXiv:2610.14025v1 Announce Type: new Abstract: Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, that

arXiv:2603.28744v2 Announce Type: replace Abstract: The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposit

arXiv:2610.06897v1 Announce Type: new Abstract: Localizing latent structures in the activation space of language models (LMs) is central to understanding and controlling their behavior. Yet, localized

arXiv:2610.02673v1 Announce Type: cross Abstract: A theory draws many independent observations into one framework with novel hypotheses. A researcher building such a theory must synthesize observation

arXiv:2606.16996v2 Announce Type: replace-cross Abstract: Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabul

arXiv:2609.37198v1 Announce Type: new Abstract: Pretrained text-to-image models contain broad visual knowledge, yet they cannot reliably acquire or refine a specific visual identity from only a few re

arXiv:2512.09814v2 Announce Type: replace Abstract: Personalized Text-to-Image (PT2I) generation aims to produce customized images based on reference images. A prominent interest pertains to the integ

arXiv:2609.32556v1 Announce Type: cross Abstract: Based on an analysis of the role of language in thought and communication, this article proposes a new concept for designing corporate knowledge bases

arXiv:2602.00158v3 Announce Type: replace-cross Abstract: Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of them. Beyond

arXiv:2609.20427v1 Announce Type: cross Abstract: Automated pain recognition from facial expression could make continuous welfare assessment practical in sheep, but adoption depends on trust: a stockp

arXiv:2609.20408v1 Announce Type: cross Abstract: Large language models are usually interpreted through concepts that humans already possess: truthfulness, refusal, deception, personality, harmfulness

arXiv:2609.17749v1 Announce Type: new Abstract: A lot of expectations have been put for years on integrating domain expert knowledge in image classification models. Several approaches have been explor

arXiv:2609.13198v1 Announce Type: cross Abstract: One of the pivotal recent challenges in neural network interpretability is polysemanticity, where a single neuron is activated by multiple, often unre

arXiv:2609.06095v1 Announce Type: cross Abstract: Motivation: Undergraduate computing students increasingly turn to generative AI (GenAI) tools to understand abstract concepts through analogies. Analo

arXiv:2605.05593v2 Announce Type: replace Abstract: Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode a

arXiv:2609.01423v1 Announce Type: new Abstract: Image style is a highly abstract, human-constructed concept shaped by a range of visual factors and intrinsically entangled with content, yet a unified

arXiv:2608.30923v1 Announce Type: cross Abstract: Stream learning is commonly evaluated through predictive performance and adaptation to concept drift. However, sustained operation of a stream learner

arXiv:2608.22614v1 Announce Type: new Abstract: Interpretability research increasingly asks when concepts emerge during training and whether linear probes recover real structure, but in language model

arXiv:2608.12113v1 Announce Type: new Abstract: The same event can be reported from different perspectives depending on the experiences, background, and beliefs of the writer or speaker. A variety of

arXiv:2608.10843v1 Announce Type: new Abstract: First-order concept synthesis asks a system to infer one formula that classifies labeled objects consistently across several finite relational structure

arXiv:2608.08416v1 Announce Type: new Abstract: Probably Approximately Correct (PAC) learning [Val84] is a fundamental learning model that has been extensively investigated. In this model, H subseteq

arXiv:2608.05164v1 Announce Type: new Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but wh

arXiv:2510.14538v3 Announce Type: replace Abstract: Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.g. safety or structural cons

arXiv:2608.04864v1 Announce Type: cross Abstract: We introduce the neural echo as a tool for understanding the behavior of neural networks. It generalizes the model-based concepts of impulse responses

arXiv:2607.23368v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are demonstrating significant capabilities in medical tasks like radiology analysis, yet providing faithful and interpre

arXiv:2607.05409v1 Announce Type: cross Abstract: Introductory programming instruction relies on hands-on practice and short learning activities to support mastery of foundational concepts. Although m

arXiv:2607.02995v1 Announce Type: cross Abstract: Vision-language models can exhibit visual concept-conditioned divergence: given images containing demographic features, corporate logos, or ideologica

arXiv:2606.31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can

arXiv:2512.03578v3 Announce Type: replace-cross Abstract: Time series extrinsic regression (TSER) refers to the task of predicting a continuous target variable from an input time series. It appears in

arXiv:2606.24997v1 Announce Type: new Abstract: Geographic implicit neural representations (INRs) learn to map any coordinate on Earth to a location embedding, implicitly encoding geospatial data into

arXiv:2605.05220v2 Announce Type: replace-cross Abstract: Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment al

arXiv:2605.31513v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have demonstrated strong general multimodal capability and are increasingly deployed in downstream systems. This tr

arXiv:2605.28664v1 Announce Type: cross Abstract: Safety detection models require examples of HHH (Helpful, Harmless, Honest)-violating outputs for robust generalization, however such examples are sca

arXiv:2605.26332v1 Announce Type: cross Abstract: Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been

arXiv:2504.07756v2 Announce Type: replace Abstract: Understanding human behaviour, neuroscience and psychology using concepts from the domain of AI is increasing in popularity. Given the massive integ

arXiv:2605.19284v1 Announce Type: new Abstract: In the training data used by large language models (LLMs), the same latent concept is often presented in multiple distinct ways: the same facts appear i

arXiv:2605.19410v1 Announce Type: new Abstract: Segmentation has become easy when the concept is known, requiring retrieval of a learned visual grounding from text. It remains hard for open ad-hoc con