arXiv:2511.11236v1 Announce Type: new 
Abstract: In recent years, image editing has garnered growing attention. However, general image editing models often fail to produce satisfactory results when confronted with new styles. The challenge lies in how to effectively fine-tune general image editing models to new styles using only a limited amount of paired data. To address this issue, this paper proposes a novel few-shot style editing framework. For this task, we construct a benchmark dataset that encompasses five distinct styles. Correspondingly, we propose a parameter-efficient multi-style Mixture-of-Experts Low-Rank Adaptation (MoE LoRA) with style-specific and style-shared routing mechanisms for jointly fine-tuning multiple styles. The style-specific routing ensures that different styles do not interfere with one another, while the style-shared routing adaptively allocates shared MoE LoRAs to learn common patterns. Our MoE LoRA can automatically determine the optimal ranks for each layer through a novel metric-guided approach that estimates the importance score of each single-rank component. Additionally, we explore the optimal location to insert LoRA within the Diffusion in Transformer (DiT) model and integrate adversarial learning and flow matching to guide the diffusion training process. Experimental results demonstrate that our proposed method outperforms existing state-of-the-art approaches with significantly fewer LoRA parameters.

تتناول الورقة المعنونة 'MoE LoRA الفعالة من حيث المعلمات لتحرير الأنماط المتعددة في عدد قليل من اللقطات' التحديات التي تواجه نماذج تحرير الصور العامة عند التكيف مع أنماط جديدة. تقترح إطارًا جديدًا لتحرير الأنماط في عدد قليل من اللقطات وتقدم مجموعة بيانات مرجعية تتضمن خمسة أنماط متميزة. يستخدم الإطار تكيفًا منخفض الرتبة لمزيج من الخبراء (MoE LoRA) فعال من حيث المعلمات، والذي يستخدم آليات توجيه محددة ومشتركة لضبط أنماط متعددة بشكل فعال. تهدف هذه الطريقة إلى تحسين أداء نماذج تحرير الصور مع الحد الأدنى من البيانات.

El artículo titulado 'MoE LoRA Eficiente en Parámetros para Edición Multi-Estilo de Pocos Ejemplos' aborda los desafíos que enfrentan los modelos generales de edición de imágenes al adaptarse a nuevos estilos. Propone un nuevo marco de edición de estilo de pocos ejemplos e introduce un conjunto de datos de referencia que comprende cinco estilos distintos. El marco utiliza una adaptación de bajo rango de mezcla de expertos (MoE LoRA) eficiente en parámetros, que emplea mecanismos de enrutamiento específicos y compartidos para afinar múltiples estilos de manera efectiva. Este enfoque busca mejorar el rendimiento de los modelos de edición de imágenes con datos mínimos.

L'article intitulé 'MoE LoRA à faible paramètre pour l'édition multi-style en quelques coups' aborde les défis rencontrés par les modèles d'édition d'images généraux lors de l'adaptation à de nouveaux styles. Il propose un nouveau cadre d'édition de style en quelques coups et introduit un ensemble de données de référence comprenant cinq styles distincts. Le cadre utilise une adaptation à faible rang de mélange d'experts multi-style (MoE LoRA) efficace en termes de paramètres, qui emploie des mécanismes de routage spécifiques et partagés pour affiner efficacement plusieurs styles. Cette approche vise à améliorer les performances des modèles d'édition d'images avec des données minimales.

The paper titled 'Parameter-Efficient MoE LoRA for Few-Shot Multi-Style Editing' addresses the challenges faced by general image editing models when adapting to new styles. It proposes a novel few-shot style editing framework and introduces a benchmark dataset comprising five distinct styles. The framework utilizes a parameter-efficient multi-style Mixture-of-Experts Low-Rank Adaptation (MoE LoRA) that employs style-specific and style-shared routing mechanisms to fine-tune multiple styles effectively. This approach aims to enhance the performance of image editing models with minimal data.

Parameter-Efficient MoE LoRA for Few-Shot Multi-Style Editing

Here's everything you need to know about the latest smart ring by Oura, based on a wearable expert's real-world usage.

Is the $500 Oura Ring 4 Ceramic worth it? I wore one for a month, and here's my advice

Samsung's QN90F QLED delivers great streaming and gaming performance, making it a strong holiday value.

Why I recommend this Samsung QLED TV over pricier OLED models in 2025 - and don't regret it

<h1>
 
 
 AI Amnesia: Erasing Knowledge Without a Trace
</h1>

Imagine your AI model accidentally learned something it shouldn't have – sensitive customer data, for example. Current methods for deleting this information often require retraining the entire model, an expensive and time-consuming process. What if we could surgically remove that knowledge without starting from scratch?

The key lies in a novel approach: creating artificial "forgetting cues." We're teaching the model to unlearn specific data patterns by exposing it to carefully crafted synthetic examples. These examples are designed to strongly contradict the information we want the model to forget, effectively overwriting the problematic associations in its memory. This works even if you don’t have access to the original data you need to erase.

Think of it like this: you're trying to forget a bad song stuck in your head. Instead of trying to actively suppress it (which rarely works), you blast an even more catchy song. The new song overwrites the old one, effectively erasing it from your mental playlist.

Benefits of Selective Forgetting:

<ul>
<li> Enhanced Data Privacy: Remove sensitive data without compromising the overall model's performance.</li>
<li> Reduced Retraining Costs: Avoid full model retraining, saving significant time and resources.</li>
<li> Improved Model Security: Eliminate vulnerabilities introduced by unintentionally learned patterns.</li>
<li> Adaptable Learning: Enables continuous refinement of AI models based on evolving data landscapes.</li>
<li> Compliance Ready: Supports compliance with data privacy regulations like GDPR.</li>
<li> Scalable Solutions: Works efficiently even with limited access to training data.</li>
</ul>

Practical Tip: One challenge is ensuring the synthetic data accurately targets the information you want to remove without negatively impacting the model's ability to generalize. Rigorous testing and validation with holdout datasets are crucial.

The promise of AI that can truly 'forget' opens exciting possibilities for responsible AI development. By enabling precise data deletion, we pave the way for more secure, compliant, and adaptable machine learning systems. Imagine AI models that can adapt to changing ethical guidelines or quickly unlearn incorrect information, all without massive retraining efforts. This is a crucial step towards trustworthy and responsible AI that respects data privacy and aligns with societal values. Future exploration could include extending this to different data modalities and model architectures.

Related Keywords: machine unlearning, data privacy, few-shot learning, zero-shot learning, synthetic data, model editing, catastrophic forgetting, incremental learning, continual learning, deep learning, neural networks, data security, algorithmic fairness, responsible ai, ethical ai, federated unlearning, privacy-preserving ai, model retraining, AI governance, data deletion, GDPR compliance

يتناول المقال نهجًا جديدًا لمعالجة مشكلة نسيان الذكاء الاصطناعي، حيث قد تحتفظ نماذج الذكاء الاصطناعي عن غير قصد بمعلومات حساسة. تتطلب الطرق التقليدية لحذف هذه البيانات غالبًا إعادة تدريب كاملة للنموذج، وهو ما يعد مكلفًا ويستغرق وقتًا. تتضمن التقنية الجديدة إنشاء 'إشارات نسيان' اصطناعية تساعد النموذج على نسيان أنماط بيانات معينة من خلال تعريضه لأمثلة صناعية تتناقض مع المعلومات غير المرغوب فيها، مما يسمح بإزالة المعرفة المستهدفة دون الحاجة للوصول إلى البيانات الأصلية.

El artículo aborda un nuevo enfoque para tratar el problema de la amnesia de la IA, donde los modelos de IA pueden retener inadvertidamente información sensible. Los métodos tradicionales para eliminar estos datos a menudo requieren un reentrenamiento completo del modelo, lo que es costoso y lleva tiempo. La nueva técnica implica crear 'señales de olvido' artificiales que ayudan al modelo a desaprender patrones de datos específicos al exponerlo a ejemplos sintéticos que contradicen la información no deseada, permitiendo así la eliminación selectiva de conocimientos sin necesidad de acceder a l…

L'article traite d'une nouvelle approche pour résoudre le problème de l'amnésie de l'IA, où les modèles d'IA peuvent involontairement conserver des informations sensibles. Les méthodes traditionnelles pour supprimer ces données nécessitent souvent un réentraînement complet du modèle, ce qui est coûteux et long. La nouvelle technique consiste à créer des 'cues d'oubli' artificiels qui aident le modèle à désapprendre des schémas de données spécifiques en lui présentant des exemples synthétiques qui contredisent les informations indésirables, permettant ainsi une suppression ciblée des connaissan…

The article discusses a novel approach to address the issue of AI amnesia, where AI models may inadvertently retain sensitive information. Traditional methods for deleting such data often require complete retraining of the model, which is costly and time-consuming. The new technique involves creating artificial 'forgetting cues' that help the model unlearn specific data patterns by presenting it with synthetic examples that contradict the unwanted information, allowing for targeted knowledge removal without needing access to the original data.

AI Amnesia: Erasing Knowledge Without a Trace

Baseus' Enercore CG11 travel adapter is one of the better designed ones I've tested, although its best feature isn't immediately apparent.

Traveling soon? Why this one charger is the only one you'll ever need to pack

Turning materials like wood chips, crop residues and municipal solid waste into fuels and chemicals is important for our country's energy independence.

طور الباحثون نماذج حاسوبية متقدمة تهدف إلى تحسين التنبؤات لعمليات طحن الكتلة الحيوية. تركز هذه الابتكارات على تحويل مواد مثل رقائق الخشب، بقايا المحاصيل، والنفايات الصلبة البلدية إلى وقود ومواد كيميائية قيمة، وهو أمر مهم لتعزيز استقلالية الطاقة في البلاد. من المتوقع أن تعمل النماذج على تحسين كفاءة معالجة الكتلة الحيوية، مما يساهم في حلول الطاقة المستدامة.

Investigadores han desarrollado modelos informáticos avanzados destinados a mejorar las predicciones para los procesos de molienda de biomasa. Esta innovación se centra en convertir materiales como astillas de madera, residuos de cultivos y residuos sólidos municipales en combustibles y productos químicos valiosos, lo que es crucial para mejorar la independencia energética del país. Se espera que los modelos optimicen la eficiencia del procesamiento de biomasa, contribuyendo así a soluciones energéticas sostenibles.

Des chercheurs ont développé des modèles informatiques avancés visant à améliorer les prévisions pour les processus de broyage de la biomasse. Cette innovation se concentre sur la conversion de matériaux tels que les copeaux de bois, les résidus de culture et les déchets solides municipaux en combustibles et produits chimiques précieux, ce qui est crucial pour renforcer l'indépendance énergétique du pays. Les modèles devraient optimiser l'efficacité du traitement de la biomasse, contribuant ainsi à des solutions énergétiques durables.

Researchers have developed advanced computer models aimed at improving predictions for biomass milling processes. This innovation focuses on converting materials such as wood chips, crop residues, and municipal solid waste into valuable fuels and chemicals, which is crucial for enhancing energy independence in the country. The models are expected to optimize the efficiency of biomass processing, thereby contributing to sustainable energy solutions.

Researchers develop computer models for better biomass milling predictions

The most interesting aspect of the latest Even Realities glasses may be their limitations.

I've tried several AI smart glasses (including Meta Ray-Bans) in 2025 - these are the most comfortable

arXiv:2511.11434v1 Announce Type: new 
Abstract: Recent advances in unified multimodal models (UMMs) have enabled impressive progress in visual comprehension and generation. However, existing datasets and benchmarks focus primarily on single-turn interactions, failing to capture the multi-turn, context-dependent nature of real-world image creation and editing. To address this gap, we present WEAVE, the first suite for in-context interleaved cross-modality comprehension and generation. Our suite consists of two complementary parts. WEAVE-100k is a large-scale dataset of 100K interleaved samples spanning over 370K dialogue turns and 500K images, covering comprehension, editing, and generation tasks that require reasoning over historical context. WEAVEBench is a human-annotated benchmark with 100 tasks based on 480 images, featuring a hybrid VLM judger evaluation framework based on both the reference image and the combination of the original image with editing instructions that assesses models' abilities in multi-turn generation, visual memory, and world-knowledge reasoning across diverse domains. Experiments demonstrate that training on WEAVE-100k enables vision comprehension, image editing, and comprehension-generation collaboration capabilities. Furthermore, it facilitates UMMs to develop emergent visual-memory capabilities, while extensive evaluations on WEAVEBench expose the persistent limitations and challenges of current approaches in multi-turn, context-aware image generation and editing. We believe WEAVE provides a view and foundation for studying in-context interleaved comprehension and generation for multi-modal community.

أدت التطورات الأخيرة في النماذج متعددة الوسائط الموحدة (UMMs) إلى تقدم ملحوظ في الفهم والتوليد البصري. ومع ذلك، تركز مجموعات البيانات الحالية بشكل أساسي على التفاعلات ذات الدور الواحد، متجاهلة الطبيعة المعتمدة على السياق لإنشاء وتحرير الصور في العالم الحقيقي. لمعالجة هذه الفجوة، تم تقديم WEAVE، وهي أول مجموعة لفهم وتوليد متعدد الوسائط في السياق، والتي تتضمن WEAVE-100k، مجموعة بيانات تحتوي على 100 ألف عينة متداخلة وWEAVEBench، معيار يتضمن 100 مهمة.

Los avances recientes en modelos multimodales unificados (UMMs) han permitido un progreso significativo en la comprensión y generación visual. Sin embargo, los conjuntos de datos existentes se centran principalmente en interacciones de un solo turno, descuidando la naturaleza dependiente del contexto de la creación y edición de imágenes en el mundo real. Para abordar esta brecha, se ha presentado WEAVE, la primera suite para la comprensión y generación intercalada en contexto, que incluye WEAVE-100k, un conjunto de datos de 100K muestras intercaladas y WEAVEBench, un banco de pruebas con 100 t…

Les avancées récentes dans les modèles multimodaux unifiés (UMMs) ont permis des progrès significatifs dans la compréhension et la génération visuelles. Cependant, les ensembles de données existants se concentrent principalement sur des interactions à un tour, négligeant la nature dépendante du contexte des créations et des modifications d'images dans le monde réel. Pour combler cette lacune, la suite WEAVE a été introduite, comprenant WEAVE-100k, un ensemble de données avec 100K échantillons entrelacés, et WEAVEBench, un banc d'essai avec 100 tâches, tous deux conçus pour améliorer les capaci…

Recent advancements in unified multimodal models (UMMs) have led to significant progress in visual comprehension and generation. However, existing datasets primarily focus on single-turn interactions, neglecting the multi-turn, context-dependent nature of real-world image creation and editing. To bridge this gap, the WEAVE suite has been introduced, featuring WEAVE-100k, a dataset with 100K interleaved samples, and WEAVEBench, a benchmark with 100 tasks, both designed to enhance comprehension and generation capabilities in a multi-turn context.

WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation

arXiv:2511.10941v1 Announce Type: new 
Abstract: Diffusion model (DM)-based channel estimation, which generates channel samples via a posteriori sampling stepwise with denoising process, has shown potential in high-precision channel state information (CSI) acquisition. However, slow sampling speed is an essential challenge for recent developed DM-based schemes. To alleviate this problem, we propose a novel flow matching (FM)-based generative model for multiple-input multiple-output (MIMO) channel estimation. We first formulate the channel estimation problem within FM framework, where the conditional probability path is constructed from the noisy channel distribution to the true channel distribution. In this case, the path evolves along the straight-line trajectory at a constant speed. Then, guided by this, we derive the velocity field that depends solely on the noise statistics to guide generative models training. Furthermore, during the sampling phase, we utilize the trained velocity field as prior information for channel estimation, which allows for quick and reliable noise channel enhancement via ordinary differential equation (ODE) Euler solver. Finally, numerical results demonstrate that the proposed FM-based channel estimation scheme can significantly reduce the sampling overhead compared to other popular DM-based schemes, such as the score matching (SM)-based scheme. Meanwhile, it achieves superior channel estimation accuracy under different channel conditions.

تقدم المقالة نموذجًا مبتكرًا قائمًا على مطابقة التدفق (FM) لتقدير قنوات MIMO. تتناول هذه الطريقة التحدي المتمثل في بطء سرعة أخذ العينات المرتبطة بالأنظمة القائمة على نماذج الانتشار (DM) من خلال صياغة مشكلة تقدير القناة ضمن إطار عمل FM. تُظهر الطريقة المقترحة إمكانية تحقيق دقة تقدير قنوات متفوقة وتقليل كبير في عبء أخذ العينات مقارنة بالطرق القائمة على DM الموجودة.

El artículo presenta un nuevo modelo generativo basado en el emparejamiento de flujos (FM) para la estimación de canales MIMO. Este enfoque aborda el desafío de la lenta velocidad de muestreo asociada con los esquemas basados en modelos de difusión (DM) al formular el problema de estimación de canales dentro del marco de FM. El método propuesto muestra un potencial para una precisión de estimación de canales superior y una reducción significativa de la sobrecarga de muestreo en comparación con los métodos DM existentes.

L'article présente un nouveau modèle génératif basé sur l'appariement de flux (FM) pour l'estimation de canaux MIMO. Cette approche répond au défi de la lenteur de la vitesse d'échantillonnage associée aux schémas basés sur les modèles de diffusion (DM) en formulant le problème d'estimation de canal dans le cadre du FM. La méthode proposée montre un potentiel pour une précision d'estimation de canal supérieure et une réduction significative de la surcharge d'échantillonnage par rapport aux méthodes DM existantes.

The article presents a novel flow matching (FM)-based generative model for multiple-input multiple-output (MIMO) channel estimation. This approach addresses the slow sampling speed challenge associated with diffusion model (DM)-based schemes by formulating the channel estimation problem within the FM framework. The proposed method shows potential for superior channel estimation accuracy and significantly reduced sampling overhead compared to existing DM-based methods.

Flow matching-based generative models for MIMO channel estimation

arXiv:2511.07947v2 Announce Type: replace-cross 
Abstract: Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through black-box queries. Model watermarking counters MEAs by embedding forensic markers for ownership verification. Current black-box watermarks prioritize MEA survival through representation entanglement, yet inadequately explore resilience against sequential MEAs and removal attacks. Our study reveals that this risk is underestimated because existing removal methods are weakened by entanglement. To address this gap, we propose Watermark Removal attacK (WRK), which circumvents entanglement constraints by exploiting decision boundaries shaped by prevailing sample-level watermark artifacts. WRK effectively reduces watermark success rates by at least 88.79% across existing watermarking benchmarks.
  For robust protection, we propose Class-Feature Watermarks (CFW), which improve resilience by leveraging class-level artifacts. CFW constructs a synthetic class using out-of-domain samples, eliminating vulnerable decision boundaries between original domain samples and their artifact-modified counterparts (watermark samples). CFW concurrently optimizes both MEA transferability and post-MEA stability. Experiments across multiple domains show that CFW consistently outperforms prior methods in resilience, maintaining a watermark success rate of at least 70.15% in extracted models even under the combined MEA and WRK distortion, while preserving the utility of protected models.

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks

arXiv:2511.11688v1 Announce Type: new 
Abstract: Diffusion probabilistic models have set a new standard for generative fidelity but are hindered by a slow iterative sampling process. A powerful training-free strategy to accelerate this process is Schedule Optimization, which aims to find an optimal distribution of timesteps for a fixed and small Number of Function Evaluations (NFE) to maximize sample quality. To this end, a successful schedule optimization method must adhere to four core principles: effectiveness, adaptivity, practical robustness, and computational efficiency. However, existing paradigms struggle to satisfy these principles simultaneously, motivating the need for a more advanced solution. To overcome these limitations, we propose the Hierarchical-Schedule-Optimizer (HSO), a novel and efficient bi-level optimization framework. HSO reframes the search for a globally optimal schedule into a more tractable problem by iteratively alternating between two synergistic levels: an upper-level global search for an optimal initialization strategy and a lower-level local optimization for schedule refinement. This process is guided by two key innovations: the Midpoint Error Proxy (MEP), a solver-agnostic and numerically stable objective for effective local optimization, and the Spacing-Penalized Fitness (SPF) function, which ensures practical robustness by penalizing pathologically close timesteps. Extensive experiments show that HSO sets a new state-of-the-art for training-free sampling in the extremely low-NFE regime. For instance, with an NFE of just 5, HSO achieves a remarkable FID of 11.94 on LAION-Aesthetics with Stable Diffusion v2.1. Crucially, this level of performance is attained not through costly retraining, but with a one-time optimization cost of less than 8 seconds, presenting a highly practical and efficient paradigm for diffusion model acceleration.

تناقش الورقة المعنونة 'تحسين الجدول الهرمي لعملية أخذ العينات السريعة والموثوقة لنماذج الانتشار' التقدم في النماذج الاحتمالية للانتشار، المعروفة بدقتها التوليدية ولكن تواجه تحديات بسبب بطء عمليات أخذ العينات. يقدم المؤلفون استراتيجية جديدة بدون تدريب تُسمى تحسين الجدول الزمني، تهدف إلى تحسين توزيع خطوات الزمن لتعزيز جودة العينات مع الالتزام بمبادئ الفعالية، والتكيف، والموثوقية، والكفاءة. يقدم المُحسّن الهرمي للجدول الزمني (HSO) إطار عمل جديدًا لتحسين ثنائي المستوى لمعالجة هذه التحديات.

El artículo titulado 'Optimización de Horarios Jerárquicos para un Muestreo Rápido y Robusto de Modelos de Difusión' discute los avances en modelos probabilísticos de difusión, conocidos por su fidelidad generativa pero que enfrentan desafíos debido a procesos de muestreo lentos. Los autores presentan una estrategia sin entrenamiento llamada Optimización de Horarios, que busca optimizar la distribución de pasos de tiempo para mejorar la calidad de las muestras, respetando principios de efectividad, adaptabilidad, robustez y eficiencia. El propuesto Optimizador de Horarios Jerárquicos (HSO) ofr…

L'article intitulé 'Optimisation Hiérarchique des Horaires pour un Échantillonnage Rapide et Robuste des Modèles de Diffusion' aborde les avancées dans les modèles probabilistes de diffusion, connus pour leur fidélité générative mais confrontés à des défis en raison de processus d'échantillonnage lents. Les auteurs introduisent une stratégie sans formation appelée Optimisation des Horaires, visant à optimiser la distribution des étapes de temps pour améliorer la qualité des échantillons tout en respectant les principes d'efficacité, d'adaptabilité, de robustesse et d'efficacité. Le nouvel Opti…

The paper titled 'Hierarchical Schedule Optimization for Fast and Robust Diffusion Model Sampling' discusses advancements in diffusion probabilistic models, which are known for their generative fidelity but face challenges due to slow sampling processes. The authors introduce a training-free strategy called Schedule Optimization, aimed at optimizing the distribution of timesteps to enhance sample quality while adhering to principles of effectiveness, adaptivity, robustness, and efficiency. The proposed Hierarchical-Schedule-Optimizer (HSO) offers a bi-level optimization framework to address th…

Hierarchical Schedule Optimization for Fast and Robust Diffusion Model Sampling

arXiv:2511.12098v1 Announce Type: new 
Abstract: Generating synthetic CT images from CBCT or MRI has a potential for efficient radiation dose planning and adaptive radiotherapy. However, existing CNN-based models lack global semantic understanding, while Transformers often overfit small medical datasets due to high model capacity and weak inductive bias. To address these limitations, we propose a DINOv3-Guided Cross Fusion (DGCF) framework that integrates a frozen self-supervised DINOv3 Transformer with a trainable CNN encoder-decoder. It hierarchically fuses global representation of Transformer and local features of CNN via a learnable cross fusion module, achieving balanced local appearance and contextual representation. Furthermore, we introduce a Multi-Level DINOv3 Perceptual (MLDP) loss that encourages semantic similarity between synthetic CT and the ground truth in DINOv3's feature space. Experiments on the SynthRAD2023 pelvic dataset demonstrate that DGCF achieved state-of-the-art performance in terms of MS-SSIM, PSNR and segmentation-based metrics on both MRI$\rightarrow$CT and CBCT$\rightarrow$CT translation tasks. To the best of our knowledge, this is the first work to employ DINOv3 representations for medical image translation, highlighting the potential of self-supervised Transformer guidance for semantic-aware CT synthesis. The code is available at https://github.com/HiLab-git/DGCF.

Parameter-Efficient MoE LoRA for Few-Shot Multi-Style Editing

Was this article worth reading? Share it