Search: “concepts”

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: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:2605.28780v1 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:2605.18202v1 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:2605.16046v1 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:2605.14769v1 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

arXiv:2509.18831v2 Announce Type: replace-cross Abstract: Recent advances in diffusion models have significantly improved image and video synthesis. In addition, several concept control methods have b

arXiv:2604.13240v1 Announce Type: new Abstract: Mapping the spatial distribution of species is essential for conservation policy and invasive species management. Species distribution models (SDMs) are

arXiv:2604.11868v1 Announce Type: new Abstract: While medical Vision-Language models (VLMs) achieve strong performance on tasks such as tumor or organ segmentation and diagnosis prediction, their opaq

arXiv:2604.08846v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prom

arXiv:2610.17713v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has been widely used, yet the adapted model suffers catastrophic forgetting of pre-trained knowledge. While most

arXiv:2610.09031v1 Announce Type: new Abstract: Medical imaging models often operate as black boxes, limiting interpretability and systematic debugging. We introduce an easy-to-use, plug-and-play fram

arXiv:2610.02829v1 Announce Type: new Abstract: Large language models are increasingly used in clinical settings. However, research into the reliability and performance of these models has focused alm

arXiv:2609.39265v1 Announce Type: new Abstract: The Segment Anything Model (SAM) achieves remarkable performance in visual segmentation. The latest SAM3 extends promptable segmentation to concept-leve

arXiv:2609.38098v1 Announce Type: new Abstract: Current vision-language models (VLMs) encode visual information in dense hidden states where object identity, spatial layout, and local attributes are i

arXiv:2609.18163v1 Announce Type: new Abstract: Forecasting scientific relations can guide discovery by identifying promising connections before they emerge. Existing approaches often model concept se

arXiv:2609.13047v1 Announce Type: cross Abstract: Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a basic level at which people recognize and name objects w

arXiv:2608.30246v1 Announce Type: cross Abstract: The fundamental theorem of statistical learning states that, under suitable measurability assumptions, finite Vapnik--Chervonenkis (VC) dimension guar

arXiv:2608.23650v1 Announce Type: new Abstract: The perception of 3D space by mobile robots is rapidly moving from flat metric grid representations to hybrid metric-semantic graphs built from human-in

arXiv:2608.22858v1 Announce Type: cross Abstract: Existing data pruning methods predominantly rely on high-dimensional feature embeddings to measure sample importance. However, these compressed vector

arXiv:2608.15341v1 Announce Type: new Abstract: Text-to-image diffusion models can be misused to generate harmful content through adversarial or paraphrased prompts that bypass built-in safety mechani

arXiv:2602.20839v3 Announce Type: replace Abstract: Training-free image editing with diffusion models is highly desirable yet is complex and remains a significant challenge. While recent optimisation-

arXiv:2608.08159v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly reported to exhibit human-like neural and cognitive signatures, including concept cells, mental number lin

arXiv:2608.03118v1 Announce Type: new Abstract: This innovative practice full paper describes an AI-powered knowledge graph platform that connects SQL errors to conceptual gaps in undergraduate and gr

arXiv:2607.05088v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models have achieved striking progress but still struggle to synthesize rare concepts involving unusual attribute-object p

arXiv:2502.00684v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (DRL) has successfully addressed many complex control problems. However, the neural networks representing policies

arXiv:2606.28149v1 Announce Type: cross Abstract: In-context segmentation (ICS) requires a model to segment target regions in a query image using only a few reference images and their corresponding ma

arXiv:2606.26668v1 Announce Type: cross Abstract: Video customization based on Text-to-Video (T2V) models aims to learn specific features from reference data to generate controllable videos. While sig

arXiv:2606.22963v1 Announce Type: new Abstract: Concept segmentation models like Segment Anything Model 3 (SAM3) show strong generalization on natural images, yet their performance degrades in medical

arXiv:2606.04364v1 Announce Type: new Abstract: Concept bottleneck models (CBMs) predict a layer of human-named attributes before predicting a class, which makes their decisions auditable. On fine-gra

arXiv:2605.19848v1 Announce Type: new Abstract: In recent years, the black-box nature of deep learning models has limited their application in high-stakes domains such as medical diagnosis and finance

arXiv:2601.06162v4 Announce Type: replace-cross Abstract: Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into

arXiv:2605.16374v1 Announce Type: cross Abstract: Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has b

arXiv:2603.03066v2 Announce Type: replace Abstract: Existing AI-generated video quality assessment (AIGVQA) methods mainly focus on global perceptual realism and coarse text-video alignment, while ove

arXiv:2605.12639v1 Announce Type: new Abstract: Extreme ocean phenomena are challenging not only to predict but to diagnose, as accurate forecasts alone do not reveal the underlying physical drivers.

arXiv:2605.10261v1 Announce Type: new Abstract: TCAV (Testing with Concept Activation Vectors) is an interpretability method that assesses the alignment between the internal representations of a train

arXiv:2604.10303v1 Announce Type: new Abstract: High-quality Late Gadolinium Enhancement (LGE) MRI can be helpful for atrial fibrillation management, yet scan quality is frequently compromised by pati

arXiv:2610.14574v1 Announce Type: cross Abstract: In-context learning (ICL) allows large language models to use demonstrations without updating their parameters. For interactive agents, demonstrations