Search: “concepts”

arXiv:2507.06526v4 Announce Type: replace Abstract: Text-to-image diffusion models remain susceptible to generating undesirable or harmful content. Although concept unlearning mitigates this risk, exi

arXiv:2607.23492v1 Announce Type: new Abstract: Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while prese

arXiv:2606.26711v1 Announce Type: new Abstract: Transforming foundation segmentation models from human-prompted tools into auto-promptable annotators is critical for scalable medical data annotation.

arXiv:2507.07532v4 Announce Type: replace Abstract: While Prover-Verifier Games (PVGs) offer a promising path toward verifiability in nonlinear classification models, they have not yet been applied to

arXiv:2512.12469v3 Announce Type: replace Abstract: We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing others to self-org

arXiv:2605.14309v1 Announce Type: cross Abstract: Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove tar

arXiv:2609.03629v1 Announce Type: cross Abstract: Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative capabilities, yet their reliance on loosely curated tr

arXiv:2608.10985v1 Announce Type: new Abstract: Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infrin

arXiv:2510.27285v4 Announce Type: replace Abstract: Concept erasure methods aim to remove specific unsafe target concepts in diffusion models while preserving image generation utility. To address the

arXiv:2602.04093v2 Announce Type: replace Abstract: Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept ann

arXiv:2510.15770v3 Announce Type: replace Abstract: Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations. However, exis

arXiv:2609.38625v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remain

arXiv:2609.34750v1 Announce Type: cross Abstract: Concept-based explanations describe neural network predictions through human-understandable properties of inputs called concepts. The field encompasse

arXiv:2609.31154v1 Announce Type: new Abstract: Recent advances in text-to-image (T2I) generation have substantially improved visual synthesis, but have also raised increasing safety concerns due to t

arXiv:2609.09909v1 Announce Type: new Abstract: Although text-to-image diffusion models generally exhibit strong prompt-following ability, we identify a persistent and previously underexplored failure

arXiv:2606.22567v1 Announce Type: new Abstract: Few-shot prompt learning is an effective strategy for adapting CLIP to downstream tasks, but class-only prompt optimization can overfit base-class super

arXiv:2605.31186v1 Announce Type: new Abstract: Data streams are nowadays among the most frequently analyzed data structures, with the concept drift posing a major challenge encountered by processing

arXiv:2602.17949v2 Announce Type: replace-cross Abstract: Background: Clinical named entity recognition tools commonly map free text to Unified Medical Language System (UMLS) Concept Unique Identifier

arXiv:2604.21041v1 Announce Type: new Abstract: Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining.

arXiv:2511.12968v2 Announce Type: replace Abstract: Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semant

arXiv:2609.38603v1 Announce Type: new Abstract: While earth observation models have advanced substantially, they still lack interpretability. While concept-bottleneck models provide interpretability a

arXiv:2505.15450v3 Announce Type: replace Abstract: Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the

arXiv:2607.24101v1 Announce Type: cross Abstract: Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models. Existing evaluations

arXiv:2512.05038v2 Announce Type: replace Abstract: Concept vectors aim to enhance model interpretability by linking internal representations with human-understandable semantics, but their practical u

arXiv:2605.25574v1 Announce Type: cross Abstract: Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing st

arXiv:2605.20197v1 Announce Type: new Abstract: Medical concept extraction from electronic health records underpins many downstream applications, yet remains challenging because medically meaningful c

arXiv:2605.14210v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final out

arXiv:2605.01309v1 Announce Type: new Abstract: Long-tailed distributions are common in real-world recognition tasks, where a few head classes have many samples while most tail classes have very few.

arXiv:2604.24936v1 Announce Type: new Abstract: Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic r

arXiv:2610.07337v1 Announce Type: new Abstract: Removing copyrighted, unsafe, or user-specified concepts from a deployed text-to-image diffusion model is now a practical requirement. Weight-editing me

arXiv:2610.04605v1 Announce Type: new Abstract: Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful conce

arXiv:2609.38684v1 Announce Type: new Abstract: Knowledge-intensive language-model systems typically represent external knowledge as text chunks or static graphs, with limited support for concept evol

arXiv:2609.17855v1 Announce Type: new Abstract: Standardizing clinical language to SNOMED CT supports interoperability, analytics, and reusable phenotyping, but concept recommendation remains difficul

arXiv:2609.12731v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models inevitably internalize sensitive or non-compliant concepts from large-scale pretraining data, necessitating post-ho

arXiv:2608.26083v1 Announce Type: cross Abstract: Deep neural networks often exploit spurious associations in their training data, a failure known as shortcut learning. Concept-based explainability me

arXiv:2608.12829v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MM-DiTs) have demonstrated remarkable text-to-image generation performance, surpassing traditional U-Net-based diffus

arXiv:2607.20691v1 Announce Type: cross Abstract: Concept Bottleneck Models provide interpretable-by-design predictions by mediating diagnosis through human-understandable concepts, but in medical ima

arXiv:2607.17890v2 Announce Type: replace Abstract: Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment. Howeve

arXiv:2607.03973v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because re

arXiv:2606.07007v1 Announce Type: cross Abstract: We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs).

arXiv:2606.04326v1 Announce Type: cross Abstract: Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from i

arXiv:2605.19855v1 Announce Type: cross Abstract: Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or

arXiv:2603.07561v2 Announce Type: replace Abstract: Existing concept customization methods have achieved remarkable outcomes in high-fidelity and multi-concept customization. However, they often negle

arXiv:2605.01381v1 Announce Type: new Abstract: Understanding how neural models represent human-interpretable concepts is challenging. Prior work has explored linear concept subspaces from diverse per

arXiv:2610.01989v1 Announce Type: new Abstract: Concept erasure removes copyright-protected, privacy-sensitive, or otherwise undesirable concepts from pretrained text-to-image diffusion models to supp

arXiv:2609.36832v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models can generate realistic depictions of actions such as kicking, stabbing, and shooting, raising safety concerns that