arXiv:2506.01196v2 Announce Type: replace-cross 
Abstract: We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of mapping natural language instructions and one or more RGBD observations to quasi-static robot actions. 3D-aware robot policies achieve state-of-the-art performance on precise robot manipulation tasks, but struggle with generalization to unseen instructions, scenes, and objects. On the other hand, VLAs excel at generalizing across instructions and scenes, but can be sensitive to camera and robot pose variations. We leverage prior knowledge embedded in language and vision foundation models to improve generalization of 3D-aware keyframe policies. OG-VLA unprojects input observations from diverse views into a point cloud which is then rendered from canonical orthographic views, ensuring input view invariance and consistency between input and output spaces. These canonical views are processed with a vision backbone, a Large Language Model (LLM), and an image diffusion model to generate images that encode the next position and orientation of the end-effector on the input scene. Evaluations on the Arnold and Colosseum benchmarks demonstrate state-of-the-art generalization to unseen environments, with over 40% relative improvements while maintaining robust performance in seen settings. We also show real-world adaption in 3 to 5 demonstrations along with strong generalization. Videos and resources at https://og-vla.github.io/

OG-VLA هو هيكل جديد يجمع بين نماذج العمل للغة الرؤية مع السياسات المدركة ثلاثية الأبعاد لتحسين مهام المناولة الروبوتية. يتناول التحدي المتمثل في ترجمة التعليمات باللغة الطبيعية والملاحظات RGBD إلى إجراءات روبوتية. بينما تتفوق السياسات المدركة ثلاثية الأبعاد في المهام الدقيقة، فإنها غالبًا ما تواجه صعوبة في التعميم على سيناريوهات جديدة. من ناحية أخرى، تتميز نماذج العمل للغة الرؤية بقدرتها على التعميم عبر التعليمات، لكنها قد تكون حساسة لتغيرات وضع الكاميرا والروبوت. يهدف OG-VLA إلى تحسين هذا التعميم من خلال الاستفادة من المعرفة الموجودة في نماذج اللغة والرؤية.

OG-VLA es una nueva arquitectura que combina modelos de acción de lenguaje visual con políticas conscientes de 3D para mejorar las tareas de manipulación robótica. Aborda el desafío de traducir instrucciones en lenguaje natural y observaciones RGBD en acciones robóticas. Mientras que las políticas conscientes de 3D sobresalen en tareas precisas, a menudo tienen dificultades para generalizar a nuevos escenarios. Por otro lado, los modelos de acción de lenguaje visual son hábiles en la generalización, pero pueden ser sensibles a las variaciones en la posición de la cámara y del robot. OG-VLA bus…

OG-VLA est une nouvelle architecture qui intègre les modèles d'action de langage visuel avec des politiques conscientes de la 3D pour améliorer les tâches de manipulation des robots. Elle s'attaque au défi de traduire des instructions en langage naturel et des observations RGBD en actions robotiques. Bien que les politiques conscientes de la 3D excellent dans les tâches précises, elles ont souvent du mal à se généraliser à de nouveaux scénarios. En revanche, les modèles d'action de langage visuel sont doués pour la généralisation, mais peuvent être sensibles aux variations de pose de la caméra…

OG-VLA is a new architecture that integrates Vision Language Action models with 3D-aware policies to enhance robot manipulation tasks. It addresses the challenge of translating natural language instructions and RGBD observations into robot actions. While 3D-aware policies excel in precise tasks, they often struggle with generalization to new scenarios. Conversely, VLAs are adept at generalizing across instructions but can be sensitive to variations in camera and robot poses. OG-VLA aims to improve this generalization by leveraging knowledge from language and vision models.

OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model

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:2511.14291v1 Announce Type: new 
Abstract: Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. Additionally, 3D scene generation is vital for advancing embodied AI and world models, which depend on diverse, high-quality scenes for learning and evaluation. In this work, we propose Gen3d, a novel method for generation of high-quality, wide-scope, and generic 3D scenes from a single image. After the initial point cloud is created by lifting the RGBD image, Gen3d maintains and expands its world model. The 3D scene is finalized through optimizing a Gaussian splatting representation. Extensive experiments on diverse datasets demonstrate the strong generalization capability and superior performance of our method in generating a world model and Synthesizing high-fidelity and consistent novel views.

تقدم Gen3d طريقة جديدة لتوليد مشاهد ثلاثية الأبعاد عالية الجودة وغير محددة المجال من صورة واحدة، مما يعالج قيود تقنيات إعادة البناء ثلاثي الأبعاد العصبية الحالية التي تعتمد على التقاطات متعددة الزوايا الكثيفة. بعد إنشاء سحابة النقاط الأولية من صورة RGBD، تقوم Gen3d بتوسيع نموذج العالم الخاص بها وتكمل المشهد ثلاثي الأبعاد من خلال تحسين تمثيل التشتت الغاوسي. تظهر التجارب قدرتها القوية على التعميم وأداءها المتفوق في توليد نموذج عالمي وتوليد مشاهد جديدة عالية الدقة ومتسقة، وهو أمر حيوي لتقدم الذكاء الاصطناعي المجسد ونماذج العالم.

Gen3d es un método innovador para generar escenas 3D de alta calidad y sin dominio a partir de una sola imagen, abordando las limitaciones de las técnicas actuales de reconstrucción 3D neuronal que dependen de capturas multivista densas. Al crear una nube de puntos inicial a partir de una imagen RGBD, Gen3d expande su modelo del mundo y finaliza la escena 3D mediante la optimización de una representación de splatting gaussiano. Los experimentos demuestran su fuerte capacidad de generalización y su rendimiento superior en la síntesis de vistas nuevas de alta fidelidad y consistentes, lo cual es…

Gen3d est une méthode novatrice pour générer des scènes 3D de haute qualité et sans domaine à partir d'une seule image, répondant aux limitations des techniques actuelles de reconstruction 3D neuronale qui dépendent de captures multi-vues denses. En créant un nuage de points initial à partir d'une image RGBD, Gen3d élargit son modèle du monde et finalise la scène 3D grâce à l'optimisation de la représentation par splatting gaussien. Des expériences démontrent sa forte capacité de généralisation et sa performance supérieure dans la synthèse de vues nouvelles fidèles et cohérentes, essentielles …

Gen3d is a novel method for generating high-quality, domain-free 3D scenes from a single image, addressing the limitations of current neural 3D reconstruction techniques that rely on dense multi-view captures. By creating an initial point cloud from an RGBD image, Gen3d expands its world model and finalizes the 3D scene through Gaussian splatting optimization. Experiments demonstrate its strong generalization capabilities and superior performance in synthesizing high-fidelity and consistent novel views, which are crucial for advancing embodied AI and world models.

GEN3D: Generating Domain-Free 3D Scenes from a Single Image

arXiv:2508.01249v3 Announce Type: replace-cross 
Abstract: Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces critical security risks, particularly in the presence of prompt injection attacks. In this work, we propose a novel insight that treats the agent runtime traces as structured programs with analyzable semantics. Thus, we present AgentArmor, a program analysis framework that converts agent traces into graph intermediate representation-based structured program dependency representations (e.g., CFG, DFG, and PDG) and enforces security policies via a type system. AgentArmor consists of three key components: (1) a graph constructor that reconstructs the agent's runtime traces as graph-based intermediate representations with control and data flow described within; (2) a property registry that attaches security-relevant metadata of interacted tools \& data, and (3) a type system that performs static inference and checking over the intermediate representation. By representing agent behavior as structured programs, AgentArmor enables program analysis for sensitive data flow, trust boundaries, and policy violations. We evaluate AgentArmor on the AgentDojo benchmark, the results show that AgentArmor can reduce the ASR to 3\%, with the utility drop only 1\%.

AgentArmor هو إطار لتحليل البرامج مصمم لتعزيز أمان وكلاء نماذج اللغة الكبيرة (LLM) ضد هجمات حقن الأوامر. من خلال اعتبار آثار تشغيل الوكلاء كبرامج منظمة، يقوم AgentArmor بتحويل هذه الآثار إلى تمثيلات قائمة على الرسوم البيانية، مما يسمح بفرض سياسات الأمان من خلال نظام نوعي. يتكون الإطار من ثلاثة مكونات: مُنشئ الرسوم البيانية، سجل الخصائص، ومُنفذ سياسات الأمان، بهدف تقليل المخاطر المرتبطة بالسلوك الديناميكي لوكلاء LLM.

AgentArmor es un marco de análisis de programas diseñado para mejorar la seguridad de los agentes de Modelos de Lenguaje Grande (LLM) contra ataques de inyección de prompts. Al tratar las trazas de ejecución de los agentes como programas estructurados, AgentArmor convierte estas trazas en representaciones basadas en grafos, permitiendo la aplicación de políticas de seguridad a través de un sistema de tipos. El marco consta de tres componentes: un constructor de grafos, un registro de propiedades y un ejecutor de políticas de seguridad, con el objetivo de mitigar los riesgos asociados al compor…

AgentArmor est un cadre d'analyse de programme conçu pour améliorer la sécurité des agents de Modèle de Langage de Grande Taille (LLM) contre les attaques par injection de prompt. En considérant les traces d'exécution des agents comme des programmes structurés, AgentArmor convertit ces traces en représentations basées sur des graphes, permettant l'application de politiques de sécurité via un système de types. Le cadre se compose de trois composants : un constructeur de graphes, un registre de propriétés et un enforceur de politiques de sécurité, visant à atténuer les risques associés au compor…

AgentArmor is a program analysis framework designed to enhance the security of Large Language Model (LLM) agents against prompt injection attacks. By treating agent runtime traces as structured programs, AgentArmor converts these traces into graph-based representations, enabling the enforcement of security policies through a type system. The framework consists of three components: a graph constructor, a property registry, and a security policy enforcer, aiming to mitigate the risks associated with the dynamic behavior of LLM agents.

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection

arXiv:2504.00844v2 Announce Type: replace-cross 
Abstract: In Scene Graph Generation (SGG), structured representations are extracted from visual inputs as object nodes and connecting predicates, enabling image-based reasoning for diverse downstream tasks. While fully supervised SGG has improved steadily, it suffers from training bias due to limited curated data and long-tail predicate distributions, leading to poor predicate diversity and degraded downstream performance. We present PRISM-0, a zero-shot open-vocabulary SGG framework that leverages foundation models in a bottom-up pipeline to capture a broad spectrum of predicates. Detected object pairs are filtered, described via a Vision-Language Model (VLM), and processed by a Large Language Model (LLM) to generate fine- and coarse-grained predicates, which are then validated by a Visual Question Answering (VQA) model. PRISM-0 modular, dataset-independent design enriches existing SGG datasets such as Visual Genome and produces diverse, unbiased graphs. While operating entirely in a zero-shot setting, PRISM-0 achieves performance on par with state-of-the-art weakly-supervised models on SGG benchmarks and even state-of-the-art supervised methods in tasks such as Sentence-to-Graph Retrieval.

PRISM-0 هو إطار جديد لتوليد الرسوم البيانية للمشاهد (SGG) يعالج قيود الطرق التقليدية المعتمدة على الإشراف، والتي غالبًا ما تعاني من تحيزات في التدريب وتنوع محدود في الصفات. يستخدم هذا الإطار المفتوح بدون إطلاق نماذج أساسية في نهج تصاعدي لتحسين استخراج الصفات من المدخلات المرئية. من خلال تصفية أزواج الكائنات المكتشفة واستخدام نموذج رؤية-لغة (VLM) ونموذج لغة كبير (LLM)، يقوم PRISM-0 بتوليد مجموعة واسعة من الصفات، التي يتم التحقق منها من خلال نموذج إجابة على الأسئلة المرئية (VQA)، مما يعزز مجموعات البيانات الموجودة مثل Visual Genome.

PRISM-0 es un nuevo marco para la Generación de Grafos de Escena (SGG) que aborda las limitaciones de los métodos supervisados tradicionales, que a menudo sufren de sesgos de entrenamiento y una diversidad limitada de predicados. Este marco de vocabulario abierto y sin disparos utiliza modelos fundamentales en un enfoque ascendente para mejorar la extracción de predicados a partir de entradas visuales. Al filtrar pares de objetos detectados y emplear un Modelo de Visión-Lenguaje (VLM) y un Modelo de Lenguaje Grande (LLM), PRISM-0 genera una amplia gama de predicados, validados a través de un m…

PRISM-0 est un nouveau cadre de génération de graphes de scène (SGG) qui répond aux limitations des méthodes supervisées traditionnelles, souvent affectées par des biais d'entraînement et une diversité limitée des prédicats. Ce cadre à vocabulaire ouvert et sans coupure utilise des modèles de base dans une approche ascendante pour améliorer l'extraction des prédicats à partir des entrées visuelles. En filtrant les paires d'objets détectées et en utilisant un modèle de vision-langage (VLM) et un modèle de langage large (LLM), PRISM-0 génère une large gamme de prédicats, validés par un modèle de…

PRISM-0 is a newly introduced framework for Scene Graph Generation (SGG) that addresses the limitations of traditional supervised methods, which often suffer from training bias and limited predicate diversity. This zero-shot open-vocabulary framework utilizes foundation models in a bottom-up approach to enhance predicate extraction from visual inputs. By filtering detected object pairs and employing a Vision-Language Model (VLM) and a Large Language Model (LLM), PRISM-0 generates a wide range of predicates, validated through a Visual Question Answering (VQA) model, thereby enriching existing d…

PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks

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.

OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model

Was this article worth reading? Share it