Search: “concepts”

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: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:2606.23312v1 Announce Type: new Abstract: Operating in complex real-world environments requires robots to understand their surroundings on a functional semantic level. This demands a detailed mu

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:2605.09591v1 Announce Type: new Abstract: Segmentation is a fundamental vision task underlying numerous downstream applications. Recent promptable segmentation models, such as Segment Anything M

arXiv:2605.01609v1 Announce Type: new Abstract: We test whether the causal inner product of itet{park2024linear} -- defined by the unembedding covariance Sigma -- enables cross-lingual concept transpo

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:2608.10251v1 Announce Type: new Abstract: A transformer's answer lives on one axis: the direction its unembedding reads. Its intermediate states largely do not, and that off-axis position is usu

arXiv:2608.07254v1 Announce Type: cross Abstract: The increasing specialization of scientific research challenges existing classification systems, which provide effective representations of broad disc

arXiv:2607.23379v1 Announce Type: cross Abstract: Activation Oracles (AOs) are language models trained to answer natural-language questions about another model's internal activations. They offer a fle

arXiv:2607.20995v1 Announce Type: new Abstract: Distinguishing animate from inanimate concepts in written language requires more than shallow text processing, as it involves recognizing complex select

arXiv:2503.12999v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have demonstrated exceptional performance in various multi-modal tasks. Recently, there has been an increasing i

arXiv:2603.18528v2 Announce Type: replace Abstract: Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. M

arXiv:2606.22994v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have become an important tool for unsupervised concept discovery in large models. To make the resulting feature spaces more i

arXiv:2506.20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across

arXiv:2606.07180v1 Announce Type: new Abstract: The growing demand for transparency in automated decision-making has propelled eXplainable Artificial Intelligence (XAI) to the forefront of machine lea

arXiv:2605.30538v1 Announce Type: new Abstract: Disasters are inevitable and increasingly costly, and effective response depends on querying structured tabular data: precise, information-dense records

arXiv:2603.09787v2 Announce Type: replace Abstract: Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically b

arXiv:2605.29628v1 Announce Type: cross Abstract: Contrastive Language-Audio Pretraining (CLAP) models are widely used for audio understanding and support modality-agnostic condition swapping in many

arXiv:2602.17605v2 Announce Type: replace-cross Abstract: In environmental monitoring, data collection is often costly, sparse, and shaped by urgent public-health needs. This is particularly true for

arXiv:2605.24008v1 Announce Type: new Abstract: Fault detection for Deep Neural Networks (DNNs) has received increasing attention in recent years. While more advanced hybrid approaches have been propo

arXiv:2602.18956v3 Announce Type: replace Abstract: We introduce INDUCTION, a benchmark for finite structure concept synthesis in first order logic. Given small finite relational worlds with extension

arXiv:2605.23821v1 Announce Type: new Abstract: We propose a distributional theory of how hypernymy -- the ``is-a'' relation between general and specific concepts -- is encoded geometrically in langua

arXiv:2605.19374v1 Announce Type: cross Abstract: Vision-language alignment using chest X-rays and radiology reports has emerged as an advanced paradigm for zero-shot classification and grounding of c

arXiv:2605.18680v1 Announce Type: new Abstract: Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoe

arXiv:2601.21944v2 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability. Despite strong performance, thes

arXiv:2601.16836v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to a

arXiv:2605.08837v1 Announce Type: cross Abstract: Abstract concepts - justice, theory, availability - have no single perceivable referent; in the human brain, their meaning emerges from a web of exper

arXiv:2605.07078v1 Announce Type: new Abstract: Compositional generalization requires models to produce novel configurations from familiar parts. In diffusion models, prior compositional generation me

arXiv:2605.01144v1 Announce Type: new Abstract: Whole-slide images (WSIs) present a fundamental challenge for computational pathology due to their extreme resolution, multi-scale heterogeneity, and th

arXiv:2603.07529v2 Announce Type: replace Abstract: Concept erasure aims to remove unwanted attributes, such as social or demographic factors, from learned representations, while preserving their task

arXiv:2512.20817v2 Announce Type: replace Abstract: Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility int

arXiv:2509.13281v5 Announce Type: replace Abstract: Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simpl

arXiv:2604.14519v1 Announce Type: cross Abstract: Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a ne