Search: “concepts”

arXiv:2607.04593v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large

arXiv:2606.30322v1 Announce Type: new Abstract: We propose a hybrid active-online learning framework for label-efficient concept drift adaptation in optical network failure detection. Using margin-bas

arXiv:2606.29888v1 Announce Type: cross Abstract: Vision-language models map images and text into a joint embedding space. However, these embeddings often entangle multiple semantic features, which li

arXiv:2606.25234v1 Announce Type: new Abstract: What is the geometry of a visual percept? The most widely used protocols for decomposing neural network representations into interpretable parts treat c

arXiv:2602.03448v2 Announce Type: replace Abstract: Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following text

arXiv:2606.10892v1 Announce Type: cross Abstract: To showcase products, merchants often incur substantial costs creating high-quality display images. Foreground Conditioned Outpainting (FCO) meets thi

arXiv:2606.09868v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial so

arXiv:2606.07789v1 Announce Type: new Abstract: Data stream mining is fundamentally challenged by concept drift, where distributional changes can degrade model performance. Despite the proliferation o

arXiv:2606.03864v1 Announce Type: cross Abstract: We introduce an explainable machine-learning approach that forecasts the structural precursors of scientific breakthroughs -- the emergence and intens

arXiv:2605.31591v1 Announce Type: new Abstract: Models for AI-based skin cancer screening suffer a severe performance drop when shifting from expert dermoscopic (source) images to consumer-grade clini

arXiv:2605.24294v1 Announce Type: cross Abstract: Android malware detectors often degrade after deployment because of concept drift, while full retraining at each maintenance step is costly. We propos

arXiv:2605.24903v1 Announce Type: cross Abstract: Machine learning based malware detectors become obsolete over time due to concept drift in benign and malware applications. Recent methods rely on ful

arXiv:2605.11247v1 Announce Type: new Abstract: This paper presents a proof-of-concept digital twin framework for simulation-driven diabetes modeling using benchmark clinical data, synthetic temporal

arXiv:2604.26997v1 Announce Type: cross Abstract: Autonomous AI agent ecosystems require stronger mechanisms for secure discovery, identity verification, capability attestation, and policy governance.

arXiv:2604.28119v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption

arXiv:2512.10955v2 Announce Type: replace Abstract: Visual concept personalization aims to transfer only specific image attributes, such as identity, expression, lighting, and style, into unseen conte

arXiv:2604.25376v1 Announce Type: new Abstract: Accurate brain lesion segmentation in MRI is vital for effective clinical diagnosis and treatment planning. Due to high annotation costs and strict data

arXiv:2604.22629v1 Announce Type: cross Abstract: This work proposes a structural approach to concept drift detection in malware classification using decision tree rulesets. Classifiers are trained ac

arXiv:2604.19648v1 Announce Type: cross Abstract: SAM3 advances open-vocabulary semantic segmentation by introducing a prompt-driven mask generation paradigm. However, in multi-class open-vocabulary s

arXiv:2604.15967v1 Announce Type: cross Abstract: Despite the remarkable synthesis capabilities of text-to-image (T2I) models, safeguarding them against content violations remains a persistent challen

arXiv:2601.04567v2 Announce Type: replace Abstract: Harmful memes are ever-shifting in the Internet communities, which are difficult to analyze due to their type-shifting and temporal-evolving nature.

arXiv:2512.09056v3 Announce Type: replace Abstract: Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurr

arXiv:2610.14091v1 Announce Type: new Abstract: Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting t

arXiv:2610.12345v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concepts can receive substantially dif

arXiv:2610.10301v1 Announce Type: new Abstract: Modern applications of AI rely on increasingly complex models. Explainable AI (XAI) has emerged as a set of techniques aimed at improving model transpar

arXiv:2610.08297v1 Announce Type: cross Abstract: Teleoperation serves as the fallback solution to autonomous driving but reliable functions of the teleoperation require a certain amount of mobile net

arXiv:2609.36079v1 Announce Type: new Abstract: When a doctor, a judge, or an engineer must decide whether to trust an AI model's output, they cannot avoid asking what the model understands. Purely ma

arXiv:2602.08059v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models can reproduce specific artists visual styles at extremely low cost, raising copyright and deployment safety con

arXiv:2609.34065v1 Announce Type: cross Abstract: Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people. Such ev

arXiv:2609.09124v1 Announce Type: new Abstract: Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, inform

arXiv:2608.23903v1 Announce Type: new Abstract: Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the pre

arXiv:2608.14130v1 Announce Type: cross Abstract: Computer vision models for generated facial content, such as face editing and privacy protection, increasingly affect people, requiring similarity met

arXiv:2608.12961v1 Announce Type: new Abstract: The OWL 2 EL profile is used in some of the largest production ontologies, including the Gene Ontology and SNOMED CT. Existing neuro-symbolic (NeSy) lea

arXiv:2607.25244v1 Announce Type: new Abstract: Foundation models for 12-lead electrocardiograms (ECGs) transfer well across clinical tasks, but the physiological knowledge encoded in their representa

arXiv:2606.29774v1 Announce Type: new Abstract: Long-horizon embodied manipulation requires agents to remember persistent objects, track changing scene states, and reuse prior interaction knowledge. H

arXiv:2606.29801v1 Announce Type: new Abstract: Text-to-image diffusion models remain vulnerable to adversarial prompts that elicit disallowed content, motivating reliable inference-time controls. A p

arXiv:2606.28789v1 Announce Type: cross Abstract: Artificial intelligence reaches the land registry not as another tool but as a value chain that turns data into intelligence and intelligence into eco

arXiv:2606.24808v1 Announce Type: cross Abstract: Quantum computers could outperform classical machines on important problems, but only if the errors that pervade quantum hardware can be corrected at

arXiv:2606.21935v1 Announce Type: new Abstract: Diffusion models excel at capturing multi-modal action distributions in robot imitation learning. However, in multi-task and long-horizon scenarios, mon

arXiv:2411.19700v5 Announce Type: replace Abstract: Explainable AI methods for vision models aim to identify the parts of the input that are important for the final prediction and subsequently relate

arXiv:2606.11218v1 Announce Type: cross Abstract: Ethical deliberation is often misunderstood as a search for single right or wrong answers, creating difficulties for non-ethically trained personnel w

arXiv:2603.02237v2 Announce Type: replace-cross Abstract: Representation steering offers a lightweight mechanism for controlling the behavior of large language models (LLMs) by intervening on internal

arXiv:2605.31053v1 Announce Type: cross Abstract: Controllable music editing is to modify high-level attributes while strictly preserving rhythmic and melodic structures. However, this task is challen

arXiv:2605.30671v1 Announce Type: new Abstract: Recovering ego-camera orientation from manipulation video is a prerequisite for disentangling hand motion from camera motion, a key step in imitation le

arXiv:2605.28215v1 Announce Type: new Abstract: In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use th

arXiv:2603.25722v2 Announce Type: replace Abstract: Contrastive vision-language (V&L) models remain a popular choice for various applications. However, several limitations have emerged, most notably t