arXiv:2511.11313v2 Announce Type: replace 
Abstract: Large Vision-Language Models (LVLMs) have demonstrated strong multimodal reasoning capabilities on long and complex documents. However, their high memory footprint makes them impractical for deployment on resource-constrained edge devices. We present DocSLM, an efficient Small Vision-Language Model designed for long-document understanding under constrained memory resources. DocSLM incorporates a Hierarchical Multimodal Compressor that jointly encodes visual, textual, and layout information from each page into a fixed-length sequence, greatly reducing memory consumption while preserving both local and global semantics. To enable scalable processing over arbitrarily long inputs, we introduce a Streaming Abstention mechanism that operates on document segments sequentially and filters low-confidence responses using an entropy-based uncertainty calibrator. Across multiple long multimodal document benchmarks, DocSLM matches or surpasses state-of-the-art methods while using 82\% fewer visual tokens, 75\% fewer parameters, and 71\% lower latency, delivering reliable multimodal document understanding on lightweight edge devices. Code is available in the supplementary material.

DocSLM هو نموذج صغير للرؤية واللغة مصمم لفهم الوثائق الطويلة بكفاءة، حيث يعالج قيود النماذج الكبيرة للرؤية واللغة (LVLM) التي تتطلب ذاكرة كبيرة. يتضمن ضاغط متعدد الوسائط هرمي يقوم بترميز المعلومات البصرية والنصية وتخطيط الصفحة في تسلسل ثابت الطول، مما يقلل من استهلاك الذاكرة مع الحفاظ على المعاني المحلية والعالمية. بالإضافة إلى ذلك، يقدم آلية الامتناع المتدفقة التي تعمل على أجزاء الوثيقة بشكل متسلسل وتصفية الاستجابات ذات الثقة المنخفضة باستخدام مُعَدل عدم اليقين القائم على الانتروبيا.

DocSLM es un pequeño modelo de visión-lenguaje diseñado para una comprensión eficiente de documentos largos, abordando las limitaciones de los grandes modelos de visión-lenguaje (LVLM) que requieren una cantidad considerable de memoria. Incorpora un Compresor Multimodal Jerárquico que codifica la información visual, textual y de diseño en una secuencia compacta, reduciendo el consumo de memoria mientras se preserva la integridad semántica. Además, un mecanismo de Abstención en Streaming permite el procesamiento escalable de documentos extensos filtrando respuestas de baja confianza.

DocSLM est un petit modèle de vision-langage conçu pour une compréhension efficace des documents longs, répondant aux limitations des grands modèles de vision-langage (LVLM) qui nécessitent une mémoire substantielle. Il intègre un compresseur multimodal hiérarchique qui encode les informations visuelles, textuelles et de mise en page en une séquence compacte, réduisant l'utilisation de la mémoire tout en maintenant l'intégrité sémantique. De plus, un mécanisme d'abstention en streaming permet un traitement évolutif des documents longs en filtrant les réponses à faible confiance.

DocSLM is a Small Vision-Language Model designed for efficient long-document understanding, addressing the limitations of Large Vision-Language Models (LVLMs) that require substantial memory. It features a Hierarchical Multimodal Compressor that encodes visual, textual, and layout information into a compact sequence, reducing memory usage while maintaining semantic integrity. Additionally, a Streaming Abstention mechanism allows for scalable processing of lengthy documents by filtering low-confidence responses.

DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding

The story of the Ghost in the Shell’s main villain the Puppet Master hinted at a future where governments use hackers for espionage, at a time when most of the world had never connected to the internet.

الأنمي الكلاسيكي 'Ghost in the Shell' يقدم شخصية Puppet Master، التي تتنبأ بمستقبل تستخدم فيه الحكومات القراصنة للتجسس. ظهرت هذه التنبؤات في وقت كانت فيه غالبية سكان العالم لم تتصل بعد بالإنترنت، مما يبرز رؤية العرض لمشكلات الأمن السيبراني.

El clásico anime 'Ghost in the Shell' presenta al Puppet Master, un personaje que anticipa un futuro en el que los gobiernos utilizan hackers para el espionaje. Esta predicción surgió en un momento en que la mayoría de la población mundial aún no estaba conectada a Internet, destacando la previsión del programa sobre los problemas de ciberseguridad.

L'anime classique 'Ghost in the Shell' présente le Puppet Master, un personnage qui préfigure un avenir où les gouvernements utilisent des hackers pour l'espionnage. Cette prédiction est survenue à une époque où la majorité de la population mondiale n'était pas encore connectée à Internet, soulignant la prévoyance de l'émission concernant les problèmes de cybersécurité.

The classic anime 'Ghost in the Shell' features the Puppet Master, a character that foreshadows a future where governments utilize hackers for espionage. This prediction emerged at a time when the majority of the global population had yet to connect to the internet, highlighting the show's foresight regarding cybersecurity issues.

How the classic anime ‘Ghost in the Shell’ predicted the future of cybersecurity 30 years ago

<p>Text-to-image diffusion models have become the workhorses of generative imaging. They can paint photorealistic scenes, mimic art styles, and blend concepts in ways that were science fiction a few years ago. Yet they stumble embarrassingly on a skill that even small children master: basic spatial reasoning.</p>

<p>Ask a state-of-the-art model for “a dog to the right of a teddy bear” and you often get:</p>

<ul>
<li>The dog on the left</li>
<li>One of the objects missing</li>
<li>Or a bizarre hybrid where dog and teddy are fused into a single creature</li>
</ul>

<p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F49rtb08366xdl284o4z0.jpg" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F49rtb08366xdl284o4z0.jpg" alt=" " width="800" height="532"></a></p>

<p>These failures become more severe for unusual compositions like “a giraffe above an airplane”. Traditional fixes range from expensive fine-tuning to brittle, hand-written loss functions at inference time—but both options come with significant downsides.</p>

<p>NVIDIA’s Learn-to-Steer framework (accepted to WACV 2026) proposes a different path: instead of hard-coding spatial rules or retraining the entire model, it learns a data-driven objective that can “steer” diffusion at inference time. The method reads the model’s own cross-attention maps, trains a lightweight classifier to detect spatial relations, and then uses that classifier’s gradient as a learned loss to nudge the generation towards layouts that match the prompt.</p>

<p>In this blog, we’ll unpack:</p>

<ul>
<li>What makes spatial reasoning so fragile in current diffusion models</li>
<li>How Learn-to-Steer learns spatial constraints from the model itself</li>
<li>How it steers images during generation without changing model weights</li>
<li>The top gains on spatial benchmarks like GenEval and T2I-CompBench</li>
<li>The trade-offs in compute cost and generality, and what this implies for future generative systems</li>
</ul>

<h1>
  
  
  Why Spatial Reasoning Fails in Text-to-Image Diffusion
</h1>

<h2>
  
  
  What Makes Spatial Relations So Difficult for Diffusion Models?
</h2>

<p>Modern diffusion models (e.g., Stable Diffusion, Flux) are excellent at what should appear in an image—objects, styles, textures—but much less reliable at where those objects should be.</p>

<p>Several factors contribute:</p>

<h3>
  
  
  Weak supervision of spatial language
</h3>

<ul>
<li>Training data rarely comes with precise annotations like “object A is left of object B”.
</li>
<li>Captions often describe content loosely, so phrases like “on top of” or “to the right of” are under-specified.</li>
</ul>

<h3>
  
  
  Entangled visual concepts
</h3>

<ul>
<li>When two objects frequently co-occur, models may treat them as a single visual blob.</li>
<li>This leads to object fusion, where a “cat on a bookshelf” becomes a cat-bookshelf chimera.</li>
</ul>

<h3>
  
  
  Benchmark saturation without spatial coverage
</h3>

<ul>
<li>Many standard text-to-image benchmarks emphasize realism and style, not relational accuracy.</li>
<li>Models can score highly while still being spatially confused.</li>
</ul>

<p>Empirical studies confirm three recurring failure modes on spatial benchmarks:</p>

<ul>
<li>Incorrect placement: Objects appear in the wrong relative position.</li>
<li>Missing entities: One or more requested objects never appear.</li>
<li>Merged entities: Two objects get mashed into a single, incoherent form.</li>
</ul>

<p>The model “knows” the objects you asked for, but it doesn’t reliably understand where to place them.</p>

<h1>
  
  
  Why Fine-Tuning and Handcrafted Losses Are Not Enough
</h1>

<p>Two broad strategies have tried to patch this gap:</p>

<h2>
  
  
  Fine-tuning for spatial awareness
</h2>

<ul>
<li>Retrain the diffusion model on datasets with explicit layouts or spatial annotations.</li>
<li>Methods like COMPASS show that this can significantly improve spatial accuracy.</li>
<li>But this comes at a cost: expensive retraining, sensitivity to dataset bias, and often regressions in other capabilities such as color fidelity or counting.</li>
</ul>

<h2>
  
  
  Handcrafted test-time losses
</h2>

<ul>
<li>At inference, inject extra loss terms that penalize spatial errors (e.g., overlapping activation maps, incorrect ordering).</li>
<li>These losses must be manually designed to approximate relations like “left of” or “above”.</li>
<li>In practice, these heuristics are fragile, often over-fitting simple cases and failing on more complex layouts.</li>
</ul>

<p>In short, we’ve lacked a solution that is:</p>

<ul>
<li>Data-driven rather than rule-based</li>
<li>Plug-and-play at inference time (no full retraining)</li>
<li>Targeted enough to improve spatial reasoning without damaging other strengths</li>
</ul>

<p>This is where Learn-to-Steer enters.</p>

<h1>
  
  
  How Learn-to-Steer Works: Data-Driven Steering at Inference
</h1>

<h2>
  
  
  How Cross-Attention Maps Provide a Spatial Signal
</h2>

<p>During diffusion, at each denoising step, the model computes cross-attention maps that connect text tokens to image regions. For a prompt like “a dog to the right of a teddy bear”, you can think of:</p>

<ul>
<li>One set of attention maps for “dog”</li>
<li>Another set for “teddy bear”</li>
<li>Additional context around words like “right” or “of”</li>
</ul>

<p>These maps form a rich, high-dimensional signal describing where in the image the model currently believes each word should manifest. Prior work has used cross-attention to locate objects or edit images; Learn-to-Steer goes further by treating them as a feature space in which spatial relations can be learned.</p>

<h2>
  
  
  How a Relation Classifier Becomes a Learned Loss
</h2>

<p>The core idea of Learn-to-Steer is to train a small relation classifier that takes cross-attention maps for two objects and predicts the spatial relation between them (left-of, right-of, above, below, etc.).</p>

<p>The pipeline looks like this:</p>

<h3>
  
  
  Collect supervision
</h3>

<ul>
<li>Use images where the true relation between object A and object B is known (from datasets like GQA and synthetic layouts).</li>
<li>For each image, invert it through the diffusion model with a descriptive prompt to recover cross-attention maps for the relevant tokens.</li>
</ul>

<p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fi9dbjsdc4c8yjz2r88k4.jpg" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fi9dbjsdc4c8yjz2r88k4.jpg" alt=" " width="800" height="446"></a></p>

<h3>
  
  
  Train a classifier on attention patterns
</h3>

<ul>
<li>Input: attention maps for object A and object B.</li>
<li>Output: predicted relation (e.g., “A is left of B”).</li>
</ul>

<p>Naively, however, this leads to a subtle but serious issue: relation leakage.</p>

<h2>
  
  
  How Dual Inversion Solves the “Relation Leakage” Problem
</h2>

<p>If you always invert images with a correct prompt (e.g., “a dog to the left of a cat”), hints about the word “left” can leak into the attention patterns. A naïve classifier might then “cheat” by reading out linguistic artefacts instead of learning genuine visual geometry.</p>

<p>To prevent this, Learn-to-Steer uses a dual inversion strategy:</p>

<ul>
<li>For each image with a true relation (say, dog left of cat), create two prompts:

<ul>
<li>A positive prompt with the correct relation (“dog to the left of a cat”).</li>
<li>A negative prompt with an incorrect relation (“dog above a cat”).</li>
</ul>


</li>

<li>Run inversion with both prompts, obtaining two sets of attention maps.</li>

<li>Label both sets with the true relation (left-of), because that is what the image actually depicts.</li>

</ul>

<p>The classifier sees pairs of attention maps that share the same underlying geometry but differ in the relation words used in the prompt. To succeed, it must ignore the unreliable linguistic cue and zero in on the geometric evidence in the attention patterns. This breaks the leakage shortcut and yields a classifier that actually understands “left-of” in terms of where things appear in the model’s internal vision.</p>

<p>To improve robustness, NVIDIA combines:</p>

<ul>
<li>Real images (complex, natural scenes)</li>
<li>Synthetic images (simpler, cleaner attention patterns akin to generation scenarios)</li>
</ul>

<h1>
  
  
  How Learn-to-Steer Guides Images During Generation
</h1>

<h2>
  
  
  Step-by-Step: From Prompt to Steered Latent
</h2>

<p>Once the relation classifier is trained, Learn-to-Steer uses it at inference time as a learned objective:</p>

<h3>
  
  
  Parse the spatial prompt
</h3>

<ul>
<li>Extract subject, relation, and object from the text (e.g., subject = dog, relation = right-of, object = teddy bear).</li>
</ul>

<h3>
  
  
  Run diffusion as usual—but with checkpoints
</h3>

<ul>
<li>As the model denoises latent noise into an image, periodically extract cross-attention maps for the subject and object tokens.</li>
</ul>

<h3>
  
  
  Evaluate spatial correctness
</h3>

<ul>
<li>Feed these maps into the relation classifier, which outputs a probability distribution over relations.</li>
<li>Compare this distribution to the desired relation from the prompt, and compute a loss (e.g., cross-entropy).</li>
</ul>

<h3>
  
  
  Backpropagate into the latent
</h3>

<ul>
<li>Compute the gradient of this loss with respect to the latent representation at that timestep.</li>
<li>Nudge the latent in the direction that increases the classifier’s confidence in the correct relation.</li>
</ul>

<h3>
  
  
  Continue the diffusion process
</h3>

<ul>
<li>Let the denoising proceed from the adjusted latent.</li>
<li>Repeat this steering a number of times (often during the earlier half of the diffusion steps).</li>
</ul>

<h2>
  
  
  Support for Multiple Architectures and Relations
</h2>

<p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F578a9bjc7gmtemh0jbsj.jpg" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F578a9bjc7gmtemh0jbsj.jpg" alt=" " width="800" height="477"></a></p>

<p>A key advantage of Learn-to-Steer is that it’s architecture-agnostic:</p>

<ul>
<li>It has been demonstrated on both UNet-based models (like Stable Diffusion 1.4/2.1) and MMDiT-style models (like Flux).</li>
<li>The only requirement is access to a text-image alignment signal (cross-attention or similar).</li>
</ul>

<p>It can also handle prompts with multiple constraints, such as:</p>

<p>“A frog above a sneaker below a teapot.”</p>

<p>Here, Learn-to-Steer alternates attention between relations:</p>

<ul>
<li>At one timestep, optimize the frog–sneaker relation.</li>
<li>At another, optimize the sneaker–teapot relation.</li>
</ul>

يهدف Learn-to-Steer من NVIDIA إلى معالجة قيد كبير في نماذج الانتشار من النص إلى الصورة، التي تعاني من ضعف في التفكير المكاني الأساسي. يمكن لهذه النماذج إنشاء صور فوتوغرافية واقعية، لكنها غالبًا ما تضع الأشياء في غير موضعها، مثل وضع كلب على اليسار بدلاً من اليمين بجانب دمية دب. تهدف هذه الخطوة إلى تحسين دقة الصور المولدة من خلال تعزيز الفهم المكاني.

El Learn-to-Steer de NVIDIA busca abordar una limitación significativa en los modelos de difusión de texto a imagen, que luchan con el razonamiento espacial básico. Estos modelos pueden crear imágenes fotorealistas, pero a menudo colocan mal los objetos en relación entre sí, como poner un perro a la izquierda de un oso de peluche en lugar de a la derecha. Este avance tiene como objetivo mejorar la precisión de las imágenes generadas al mejorar la comprensión espacial.

Le Learn-to-Steer de NVIDIA vise à résoudre une limitation importante des modèles de diffusion texte-image, qui ont du mal avec le raisonnement spatial de base. Ces modèles peuvent créer des images photoréalistes mais placent souvent mal les objets les uns par rapport aux autres, comme mettre un chien à gauche d'un ours en peluche au lieu de la droite. Cette avancée vise à améliorer l'exactitude des images générées en renforçant la compréhension spatiale.

NVIDIA's Learn-to-Steer is set to address a significant limitation in text-to-image diffusion models, which struggle with basic spatial reasoning. These models can create photorealistic images but often misplace objects in relation to one another, such as placing a dog to the left of a teddy bear instead of the right. This advancement aims to enhance the accuracy of generated images by improving spatial understanding.

What Is Learn-to-Steer? NVIDIA’s 2025 Spatial Fix for Text-to-Image Diffusion

<p>The $5tn firm handily beat expectations, but analysts are awaiting projections for future demand for firm’s AI chips</p><p>Nvidia shares are rising in after-market trading after the company posted third quarter earnings that beat Wall Street estimates.<strong> </strong>All eyes were on Nvidia, the bellwether for the AI industry and the most valuable publicly traded company in the world, as analysts and investors hoped the chipmaker’s third-quarter earnings would assuage concerns about whether the high-flying valuations of AI firms have peaked.</p><p>“Blackwell sales are off the charts, and cloud GPUs are sold out,” said Jensen Huang, founder and CEO of Nvidia in a press release. “Compute demand keeps accelerating and compounding across training and inference – each growing exponentially. We’ve entered the virtuous cycle of AI. The AI ecosystem is scaling fast – with more new foundation model makers, more AI startups, across more industries, and in more countries. AI is going everywhere, doing everything, all at once.”</p> <a href="https://www.theguardian.com/technology/2025/nov/19/nvidia-earning-report">Continue reading...</a>

تجاوزت شركة إنفيديا توقعات وول ستريت مع نتائجها للربع الثالث، مما أظهر طلبًا قويًا على شرائح الذكاء الاصطناعي الخاصة بها. ارتفعت أسهم الشركة في التداول بعد السوق، مما يعكس ثقة المستثمرين وسط مخاوف بشأن تقييم سوق الذكاء الاصطناعي. وأبرز الرئيس التنفيذي جينسن هوانغ مبيعات قياسية ونظامًا بيئيًا سريع التوسع في مجال الذكاء الاصطناعي، مما يشير إلى نظرة إيجابية لمستقبل الشركة.

Nvidia superó las expectativas de Wall Street con sus ganancias del tercer trimestre, mostrando una fuerte demanda por sus chips de IA. Las acciones de la compañía aumentaron en el comercio posterior al cierre, reflejando la confianza de los inversores en medio de preocupaciones sobre la valoración del mercado de IA. El CEO Jensen Huang destacó las ventas récord y un ecosistema de IA en rápida expansión, indicando una perspectiva positiva para el futuro de la empresa.

Nvidia a dépassé les attentes de Wall Street avec ses résultats du troisième trimestre, montrant une forte demande pour ses puces d'IA. Les actions de l'entreprise ont augmenté lors des échanges après la clôture, reflétant la confiance des investisseurs face aux préoccupations concernant la valorisation du marché de l'IA. Le PDG Jensen Huang a souligné des ventes record et un écosystème IA en pleine expansion, indiquant une perspective positive pour l'avenir de l'entreprise.

Nvidia exceeded Wall Street expectations with its third-quarter earnings, showcasing strong demand for its AI chips. The company's shares rose in after-market trading, reflecting investor confidence amid concerns about the AI market's valuation. CEO Jensen Huang highlighted record sales and a rapidly expanding AI ecosystem, indicating a positive outlook for the company's future.

‘AI is going everywhere, doing everything:’ Nvidia beats Wall Street estimates amid market selloff and AI bubble fears

The SanDisk ExtremeFit USB-C flash drive is barely three grams, but offers 1TB of external storage and impressive speeds.

I refused to believe this coin-sized gadget was a storage drive, until I tried it for myself

<p>Swift 6.3 is bringing significant enhancements to Embedded Swift, the subset of Swift designed for resource-constrained environments like microcontrollers. Here's what's new:</p>

<h2>
  
  
  Key Improvements
</h2>

<h3>
  
  
  Libraries &amp; Standard Library
</h3>

<ul>
<li>
<strong>Floating-point printing</strong>: The <code>description</code> and <code>debugDescription</code> properties now work for Float, Double, and other floating-point types with a new all-Swift implementation</li>
<li>
<strong>Better diagnostics</strong>: New <code>EmbeddedRestrictions</code> diagnostic group warns about unsupported language constructs</li>
<li>
<strong>Swift MMIO 0.1.x</strong>: Includes code generation from SVD files and improved debugging with SVD2LLDB plugin</li>
</ul>

<h3>
  
  
  C Interoperability
</h3>

<ul>
<li>
<strong><code>@c</code> attribute</strong>: Define C-compatible functions and enums (from SE-0495)
</li>
</ul>

<div class="highlight js-code-highlight">
<pre class="highlight swift"><code><span class="kd">@c</span><span class="p">(</span><span class="kt">MyLib_initialize</span><span class="p">)</span>
<span class="kd">public</span> <span class="kd">func</span> <span class="nf">initialize</span><span class="p">()</span> <span class="p">{</span> <span class="o">...</span> <span class="p">}</span>
</code></pre>

</div>



<ul>
<li>
<strong>Improved type matching</strong>: Better tolerance for mismatching C signatures, eliminating cryptic deserialization errors</li>
</ul>

<h3>
  
  
  Debugging
</h3>

<ul>
<li>
<strong>Enhanced LLDB support</strong>: Better value printing for Embedded Swift types</li>
<li>
<strong>Core dump inspection</strong>: Dictionary, Array, and other common types now inspectable without a live process</li>
<li>
<strong>ARMv7m exception unwinding</strong>: Complete backtraces through exception frames</li>
</ul>

<h3>
  
  
  Linking &amp; Compilation
</h3>

<ul>
<li>
<strong><code>@section</code> and <code>@used</code> attributes</strong>: Control where globals are emitted and ensure symbols aren't stripped (SE-0492)</li>
<li>
<strong>Weak symbol definitions</strong>: Fixes duplicate symbol errors in diamond dependencies</li>
<li>
<strong><code>@export</code> attribute</strong>: Better control over function visibility (SE-0497)</li>
</ul>




<p><em>Want to dive deeper? Read the <a href="https://www.swift.org/blog/embedded-swift-improvements-coming-in-swift-6.3/" rel="noopener noreferrer">full announcement</a> on Swift.org</em></p>

تقدم Swift 6.3 تحسينات كبيرة على Embedded Swift، مما يعزز وظيفته في البيئات ذات الموارد المحدودة مثل المتحكمات الدقيقة. تشمل التحسينات الرئيسية قدرات جديدة لطباعة الأعداد العشرية، وتشخيصات أفضل مع مجموعة EmbeddedRestrictions، وإدخال Swift MMIO 0.1.x لتوليد الشيفرة وتصحيح الأخطاء.

Swift 6.3 presenta mejoras significativas en Embedded Swift, aumentando su funcionalidad para entornos con recursos limitados como microcontroladores. Las mejoras clave incluyen nuevas capacidades de impresión de números de punto flotante, mejores diagnósticos con el grupo EmbeddedRestrictions y la introducción de Swift MMIO 0.1.x para la generación de código y la depuración.

Swift 6.3 apporte des améliorations significatives à Embedded Swift, renforçant sa fonctionnalité pour les environnements à ressources limitées comme les microcontrôleurs. Les principales améliorations comprennent de nouvelles capacités d'impression de nombres à virgule flottante, de meilleurs diagnostics avec le groupe EmbeddedRestrictions, et l'introduction de Swift MMIO 0.1.x pour la génération de code et le débogage.

Swift 6.3 introduces significant upgrades to Embedded Swift, enhancing its functionality for resource-constrained environments like microcontrollers. Key improvements include new floating-point printing capabilities, better diagnostics with the EmbeddedRestrictions group, and the introduction of Swift MMIO 0.1.x for code generation and debugging.

Embedded Swift Gets Major Upgrades in Swift 6.3

<a href="https://www.techspot.com/news/110317-judge-dismisses-lawsuit-twice-due-alleged-deepfake-video.html" target="_blank"><img src="https://www.techspot.com/images2/news/ts3_thumbs/2025/11/2025-11-19-ts3_thumbs-252.jpg" width="800" height="560" style="padding: 15px 0" title="Judge dismisses lawsuit twice due to alleged deepfake video testimony" /></a><br />A California housing dispute is getting media attention over allegations that lawyers presented a deepfake video as witness testimony. NBC News reports that Judge Victoria Kolakowski became suspicious after the supposed witness showed signs that something was not right, including a monotone voice, fuzzy facial features, and repeated facial expressions....<br /><br /><a href="https://www.techspot.com/news/110317-judge-dismisses-lawsuit-twice-due-alleged-deepfake-video.html">Read Entire Article</a><br /><br />

تجذب نزاع سكني في كاليفورنيا الانتباه الإعلامي بعد ظهور مزاعم بأن المحامين قدموا فيديو مزيف كدليل شهود. أعربت القاضية فيكتوريا كولاكوفسكي عن شكوكها بشأن الفيديو، مشيرة إلى صوت الشاهد الأحادي، وملامح الوجه غير الواضحة، وتكرار التعبيرات. أدى ذلك إلى رفض الدعوى القضائية مرتين.

Una disputa de vivienda en California ha llamado la atención de los medios tras las alegaciones de que los abogados presentaron un video deepfake como testimonio. La jueza Victoria Kolakowski expresó su escepticismo sobre el video, señalando la voz monótona del testigo, rasgos faciales borrosos y expresiones repetitivas. Esto llevó al desestimado de la demanda en dos ocasiones.

Un litige immobilier en Californie suscite l'attention des médias après des allégations selon lesquelles des avocats auraient présenté une vidéo deepfake comme témoignage. La juge Victoria Kolakowski a exprimé des doutes sur la vidéo, notant la voix monotone du témoin, des traits faciaux flous et des expressions répétitives. Cela a conduit à l'annulation de la poursuite à deux reprises.

A California housing dispute has drawn attention after allegations surfaced that lawyers presented a deepfake video as witness testimony. Judge Victoria Kolakowski expressed skepticism about the video, noting the witness's monotone voice, unclear facial features, and repetitive expressions. This led to the dismissal of the lawsuit on two occasions.

Judge dismisses lawsuit twice due to alleged deepfake video testimony

arXiv:2511.14072v1 Announce Type: new 
Abstract: Large Vision-Language Models (LVLMs) usually suffer from prohibitive computational and memory costs due to the quadratic growth of visual tokens with image resolution. Existing token compression methods, while varied, often lack a high-level semantic understanding, leading to suboptimal merges, information redundancy, or context loss. To address these limitations, we introduce CORE (Compact Object-centric REpresentations), a new paradigm for visual token compression. CORE leverages an efficient segmentation decoder to generate object masks, which serve as a high-level semantic prior to guide the merging of visual tokens into a compact set of object-centric representations. Furthermore, a novel centroid-guided sorting mechanism restores a coherent spatial order to the merged tokens, preserving vital positional information. Extensive experiments show that CORE not only establishes a new state-of-the-art on six authoritative benchmarks for fixed-rate compression, but also achieves dramatic efficiency gains in adaptive-rate settings. Even under extreme compression, after aggressively retaining with only 2.2% of all visual tokens, CORE still maintains 97.4% of baseline performance. Our work demonstrates the superiority of object-centric representations for efficient and effective LVLM processing.

يقدم المقال CORE (تمثيلات مركزة حول الكائنات)، وهو نهج جديد لضغط الرموز البصرية في نماذج اللغة والرؤية الكبيرة (LVLMs). تعاني طرق ضغط الرموز التقليدية غالبًا من تكاليف حسابية وذاكرة مرتفعة بسبب النمو التربيعي للرموز البصرية مع دقة الصورة. يستخدم CORE مُفكك تشفير تقسيم فعال لإنشاء أقنعة كائنات، مما يوفر إطارًا دلاليًا لتوجيه دمج الرموز البصرية في تمثيلات مركزة. بالإضافة إلى ذلك، آلية فرز موجهة بواسطة المركز تستعيد ترتيبًا مكانيًا متماسكًا للرموز المدمجة، مما يحافظ على المعلومات الموضعية الحيوية.

El artículo presenta CORE (Representaciones Compactas Centradas en Objetos), un nuevo enfoque para la compresión de tokens visuales en Modelos de Lenguaje de Visión Grande (LVLMs). Los métodos de compresión de tokens tradicionales a menudo enfrentan altos costos computacionales y de memoria debido al crecimiento cuadrático de los tokens visuales con la resolución de la imagen. CORE utiliza un decodificador de segmentación eficiente para generar máscaras de objetos, proporcionando un marco semántico para guiar la fusión de tokens visuales en representaciones compactas. Además, un mecanismo de o…

L'article présente CORE (Compact Object-centric REpresentations), une nouvelle approche de compression des tokens visuels dans les Modèles de Vision-Langage de Grande Taille (LVLMs). Les méthodes de compression de tokens traditionnelles rencontrent souvent des problèmes de coûts computationnels et de mémoire élevés en raison de l'augmentation quadratique des tokens visuels avec la résolution d'image. CORE utilise un décodeur de segmentation efficace pour créer des masques d'objets, fournissant un cadre sémantique pour fusionner les tokens visuels en représentations compactes. De plus, un mécan…

The article introduces CORE (Compact Object-centric REpresentations), a novel approach to visual token compression in Large Vision-Language Models (LVLMs). Traditional token compression methods often struggle with high computational and memory costs due to the quadratic increase in visual tokens with image resolution. CORE utilizes an efficient segmentation decoder to create object masks, providing a semantic framework for merging visual tokens into compact representations. Additionally, a centroid-guided sorting mechanism ensures the spatial order of tokens is maintained, enhancing the overal…

CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs

arXiv:2511.14159v1 Announce Type: new 
Abstract: Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-world applications. However, existing robustness benchmarks typically focus on hallucination or misleading textual inputs, while largely overlooking the equally critical challenge posed by misleading visual inputs in assessing visual understanding. To fill this important gap, we introduce MVI-Bench, the first comprehensive benchmark specially designed for evaluating how Misleading Visual Inputs undermine the robustness of LVLMs. Grounded in fundamental visual primitives, the design of MVI-Bench centers on three hierarchical levels of misleading visual inputs: Visual Concept, Visual Attribute, and Visual Relationship. Using this taxonomy, we curate six representative categories and compile 1,248 expertly annotated VQA instances. To facilitate fine-grained robustness evaluation, we further introduce MVI-Sensitivity, a novel metric that characterizes LVLM robustness at a granular level. Empirical results across 18 state-of-the-art LVLMs uncover pronounced vulnerabilities to misleading visual inputs, and our in-depth analyses on MVI-Bench provide actionable insights that can guide the development of more reliable and robust LVLMs. The benchmark and codebase can be accessed at https://github.com/chenyil6/MVI-Bench.

تم تقديم MVI-Bench كمعيار شامل يهدف إلى تقييم متانة نماذج اللغة والرؤية الكبيرة (LVLM) ضد المدخلات البصرية المضللة. تركز المعايير الحالية بشكل أساسي على المدخلات النصية، متجاهلة التأثير الكبير للتمثيل البصري الخاطئ. يصنف MVI-Bench المدخلات البصرية المضللة إلى ثلاثة مستويات هرمية: المفهوم البصري، السمة البصرية، والعلاقة البصرية، ويشمل 1248 حالة سؤال وجواب بصرية (VQA) تم توضيحها لتسهيل تقييمات دقيقة للمتانة.

MVI-Bench se presenta como un benchmark integral destinado a evaluar la robustez de los Modelos de Lenguaje-Visión de Gran Escala (LVLM) frente a entradas visuales engañosas. Los benchmarks existentes se han centrado principalmente en entradas textuales, pasando por alto el impacto significativo de la representación visual errónea. MVI-Bench clasifica las entradas visuales engañosas en tres niveles jerárquicos: Concepto Visual, Atributo Visual y Relación Visual, e incluye 1,248 instancias de Preguntas y Respuestas Visuales (VQA) anotadas para facilitar evaluaciones detalladas de robustez.

MVI-Bench est présenté comme un benchmark complet visant à évaluer la robustesse des grands modèles de vision-langage (LVLM) face aux entrées visuelles trompeuses. Les benchmarks traditionnels se sont principalement concentrés sur les entrées textuelles, négligeant l'impact significatif de la mauvaise représentation visuelle. MVI-Bench classe les entrées visuelles trompeuses en trois niveaux hiérarchiques : concept visuel, attribut visuel et relation visuelle, et comprend 1 248 instances de questions-réponses visuelles (VQA) annotées pour faciliter des évaluations de robustesse détaillées.

MVI-Bench is introduced as a comprehensive benchmark aimed at evaluating the robustness of Large Vision-Language Models (LVLMs) against misleading visual inputs. Traditional benchmarks have primarily focused on textual inputs, neglecting the significant impact of visual misrepresentation. MVI-Bench categorizes misleading visual inputs into three hierarchical levels: Visual Concept, Visual Attribute, and Visual Relationship, and includes 1,248 annotated Visual Question Answering (VQA) instances to facilitate detailed robustness assessments.

MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs

arXiv:2511.14109v1 Announce Type: new 
Abstract: Visual Place Recognition (VPR) aims to match query images against a database using visual cues. State-of-the-art methods aggregate features from deep backbones to form global descriptors. Optimal transport-based aggregation methods reformulate feature-to-cluster assignment as a transport problem, but the standard Sinkhorn algorithm symmetrically treats source and target marginals, limiting effectiveness when image features and cluster centers exhibit substantially different distributions. We propose an asymmetric aggregation VPR method with geometric constraints for locally aggregated descriptors, called $A^2$GC-VPR. Our method employs row-column normalization averaging with separate marginal calibration, enabling asymmetric matching that adapts to distributional discrepancies in visual place recognition. Geometric constraints are incorporated through learnable coordinate embeddings, computing compatibility scores fused with feature similarities, thereby promoting spatially proximal features to the same cluster and enhancing spatial awareness. Experimental results on MSLS, NordLand, and Pittsburgh datasets demonstrate superior performance, validating the effectiveness of our approach in improving matching accuracy and robustness.

$A^2$GC-VPR هو أسلوب جديد للتعرف على الأماكن البصرية (VPR) يتناول قيود أساليب التجميع التقليدية في مطابقة صور الاستعلام مع قاعدة بيانات. من خلال اعتماد نهج تجميع غير متماثل مع قيود هندسية، يعزز هذا الأسلوب فعالية مطابقة الميزات، خاصة عند التعامل مع توزيعات متباينة لميزات الصورة ومراكز التجمع. تستخدم التقنية متوسطات تطبيع الصفوف والأعمدة مع تضمينات إحداثيات قابلة للتعلم لتحسين درجات التوافق لوصفيات التجميع المحلي.

$A^2$GC-VPR es un nuevo método para el Reconocimiento Visual de Lugares (VPR) que aborda las limitaciones de los métodos de agregación tradicionales al emparejar imágenes de consulta con una base de datos. Al emplear un enfoque de agregación asimétrica con restricciones geométricas, este método mejora la efectividad del emparejamiento de características, especialmente cuando se enfrentan a distribuciones variables de características de imagen y centros de clúster. La técnica utiliza promedios de normalización fila-columna y embeddings de coordenadas aprendibles para mejorar las puntuaciones de…

$A^2$GC-VPR est une nouvelle méthode pour la reconnaissance de lieux visuels (VPR) qui s'attaque aux limites des méthodes d'agrégation traditionnelles dans l'appariement d'images de requête à une base de données. En adoptant une approche d'agrégation asymétrique avec des contraintes géométriques, cette méthode améliore l'efficacité de l'appariement des caractéristiques, en particulier lorsqu'il s'agit de distributions variées des caractéristiques d'image et des centres de clusters. La technique utilise une moyenne de normalisation ligne-colonne et des embeddings de coordonnées apprenables pour…

$A^2$GC-VPR is a new method for Visual Place Recognition (VPR) that addresses the limitations of traditional aggregation methods in matching query images to a database. By employing an asymmetric aggregation approach with geometric constraints, this method enhances the effectiveness of feature matching, particularly when dealing with varying distributions of image features and cluster centers. The technique utilizes row-column normalization averaging and learnable coordinate embeddings to improve compatibility scores for locally aggregated descriptors.

$A^2$GC: $A$symmetric $A$ggregation with Geometric Constraints for Locally Aggregated Descriptors

arXiv:2511.14247v1 Announce Type: new 
Abstract: Multi-agents rely on accurate poses to share and align observations, enabling a collaborative perception of the environment. However, traditional GNSS-based localization often fails in GNSS-denied environments, making consistent feature alignment difficult in collaboration. To tackle this challenge, we propose a robust GNSS-free collaborative perception framework based on LiDAR localization. Specifically, we propose a lightweight Pose Generator with Confidence (PGC) to estimate compact pose and confidence representations. To alleviate the effects of localization errors, we further develop the Pose-Aware Spatio-Temporal Alignment Transformer (PASTAT), which performs confidence-aware spatial alignment while capturing essential temporal context. Additionally, we present a new simulation dataset, V2VLoc, which can be adapted for both LiDAR localization and collaborative detection tasks. V2VLoc comprises three subsets: Town1Loc, Town4Loc, and V2VDet. Town1Loc and Town4Loc offer multi-traversal sequences for training in localization tasks, whereas V2VDet is specifically intended for the collaborative detection task. Extensive experiments conducted on the V2VLoc dataset demonstrate that our approach achieves state-of-the-art performance under GNSS-denied conditions. We further conduct extended experiments on the real-world V2V4Real dataset to validate the effectiveness and generalizability of PASTAT.

يقدم المقال إطارًا جديدًا للإدراك التعاوني بدون GNSS باستخدام تحديد المواقع بواسطة LiDAR، حيث يتناول التحديات التي تواجهها البيئات التي تفتقر إلى GNSS. غالبًا ما تواجه طرق تحديد المواقع التقليدية صعوبات في هذه البيئات، مما يعيق التعاون الفعال بين أنظمة الوكلاء المتعددة. تتضمن الحلول المقترحة مولد وضع خفيف الوزن مع ثقة (PGC) لتقدير الأوضاع وتمثيلات الثقة، بالإضافة إلى محول التوافق الزماني المكاني الواعي بالوضع (PASTAT) الذي يقوم بأداء التوافق المكاني مع مراعاة الثقة. كما تم تقديم مجموعة بيانات محاكاة جديدة، V2VLoc، التي يمكن تكييفها لمهام تحديد المواقع بواسطة LiDAR والاكتشاف التعاوني.

El artículo presenta un nuevo marco para la percepción colaborativa sin GNSS utilizando la localización por LiDAR, abordando los desafíos que se enfrentan en entornos sin GNSS. Los métodos de localización tradicionales a menudo tienen dificultades en estos entornos, lo que dificulta la colaboración efectiva entre sistemas multiagente. La solución propuesta incluye un Generador de Pose con Confianza (PGC) para estimar poses y confianza, junto con el Transformador de Alineación Espacio-Temporal Consciente de la Pose (PASTAT) para el alineamiento espacial. Se introduce un nuevo conjunto de datos …

L'article présente un nouveau cadre pour la perception collaborative sans GNSS utilisant la localisation par LiDAR, abordant les défis rencontrés dans les environnements privés de GNSS. Les méthodes de localisation traditionnelles peinent souvent dans ces contextes, entravant la collaboration efficace entre systèmes multi-agents. La solution proposée comprend un générateur de pose léger avec confiance (PGC) pour estimer les poses et la confiance, ainsi qu'un transformateur d'alignement spatio-temporel conscient de la pose (PASTAT) pour l'alignement spatial. Un nouveau jeu de données de simulat…

The article presents a new framework for GNSS-free collaborative perception using LiDAR localization, addressing the challenges faced in GNSS-denied environments. Traditional localization methods often struggle in these settings, hindering effective collaboration among multi-agent systems. The proposed solution includes a lightweight Pose Generator with Confidence (PGC) for estimating poses and confidence, alongside the Pose-Aware Spatio-Temporal Alignment Transformer (PASTAT) for spatial alignment. A new simulation dataset, V2VLoc, is introduced, which supports LiDAR localization and collabor…

V2VLoc: Robust GNSS-Free Collaborative Perception via LiDAR Localization

arXiv:2511.14210v1 Announce Type: cross 
Abstract: We introduce Orion, a visual agent framework that can take in any modality and generate any modality. Using an agentic framework with multiple tool-calling capabilities, Orion is designed for visual AI tasks and achieves state-of-the-art results. Unlike traditional vision-language models that produce descriptive outputs, Orion orchestrates a suite of specialized computer vision tools, including object detection, keypoint localization, panoptic segmentation, Optical Character Recognition, and geometric analysis, to execute complex multi-step visual workflows. The system achieves competitive performance on MMMU, MMBench, DocVQA, and MMLongBench while extending monolithic vision-language models to production-grade visual intelligence. By combining neural perception with symbolic execution, Orion enables autonomous visual reasoning, marking a transition from passive visual understanding to active, tool-driven visual intelligence.

أورايون هو إطار جديد لوكيل بصري قادر على معالجة وتوليد أنماط متعددة. يستخدم إطارًا وكيلًا مع قدرات متعددة لاستدعاء الأدوات، محققًا نتائج رائدة في مهام الذكاء الاصطناعي البصري. على عكس نماذج الرؤية-اللغة التقليدية، يستخدم أورايون أدوات رؤية حاسوبية متخصصة لتنفيذ سير عمل بصري معقد، محققًا أداءً تنافسيًا في معايير مثل MMMU وMMBench وDocVQA وMMLongBench. يمثل هذا النظام تحولًا نحو الاستدلال البصري المستقل، مما يعزز الذكاء البصري.

Orion es un nuevo marco de agente visual capaz de procesar y generar diversas modalidades. Utiliza un marco agentivo con múltiples capacidades de llamada a herramientas, logrando resultados de vanguardia en tareas de IA visual. A diferencia de los modelos tradicionales de visión-lenguaje, Orion emplea herramientas especializadas de visión por computadora para flujos de trabajo visuales complejos, alcanzando un rendimiento competitivo en benchmarks como MMMU, MMBench, DocVQA y MMLongBench. Este sistema marca una transición hacia el razonamiento visual autónomo, mejorando la inteligencia visual.

Orion est un nouveau cadre d'agent visuel capable de traiter et de générer diverses modalités. Il utilise un cadre agentique avec plusieurs capacités d'appel d'outils, atteignant des résultats de pointe dans les tâches d'IA visuelle. Contrairement aux modèles traditionnels de vision-langage, Orion utilise des outils de vision par ordinateur spécialisés pour des flux de travail visuels complexes, obtenant des performances compétitives sur des benchmarks tels que MMMU, MMBench, DocVQA et MMLongBench. Ce système marque un tournant vers le raisonnement visuel autonome, améliorant l'intelligence vi…

Orion is a newly introduced visual agent framework capable of processing and generating various modalities. It employs an agentic framework with multiple tool-calling capabilities, achieving state-of-the-art results in visual AI tasks. Unlike traditional vision-language models, Orion utilizes specialized computer vision tools for complex visual workflows, achieving competitive performance on benchmarks like MMMU, MMBench, DocVQA, and MMLongBench. This system marks a shift towards autonomous visual reasoning, enhancing visual intelligence.

DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding

Was this article worth reading? Share it