<a href="https://petapixel.com/2025/11/12/canon-should-revisit-novel-touch-controls-and-heres-how/"><img width="1600" height="840" src="https://petapixel.com/assets/uploads/2025/11/canon-touchpad-op-ed-featured.jpg" class="attachment-card-large size-card-large wp-post-image" alt="Close-up comparison of the rear controls on two different camera bodies, showing various buttons, textured grips, and dials, including &quot;INFO&quot; and navigation buttons." decoding="async" /></a>The maligned Multifunction Touch Bar, commonly called the "Touch Bar," on the original Canon EOS R mirrorless camera is an excellent example of what happens when interesting, even good, ideas try to do too much. However, it's time for Canon to revisit the Touch Bar, or at least the underlying concept of expanded touch on modern mirrorless cameras. Technology is better now, lessons have been learned, and there is still room for improvement in camera ergonomics.
[<a href="https://petapixel.com/2025/11/12/canon-should-revisit-novel-touch-controls-and-heres-how/">Read More</a>]

لقد تعرضت شريط اللمس متعدد الوظائف في كاميرا كانون EOS R المرآة الأصلية للانتقادات بسبب تعقيدها. ومع ذلك، يجادل المقال بأن كانون يجب أن تعيد النظر في هذه الميزة أو المفهوم الأوسع للتحكم باللمس في الكاميرات المرآة الحديثة. مع التقدم التكنولوجي والدروس المستفادة من التجارب السابقة، هناك إمكانية لتحسين ergonomics الكاميرا. قد يؤدي إعادة النظر في شريط اللمس إلى تحسين تجربة المستخدم والوظائف، مما يجعلها ذات صلة في السوق اليوم.

La barra táctil multifuncional de la cámara sin espejo Canon EOS R original ha sido criticada por su complejidad. Sin embargo, el artículo argumenta que Canon debería reconsiderar esta característica o el concepto más amplio de controles táctiles en cámaras sin espejo modernas. Con los avances tecnológicos y las lecciones aprendidas de experiencias pasadas, hay potencial para mejorar la ergonomía de las cámaras. Revisitar la barra táctil podría llevar a una mejor experiencia de usuario y funcionalidad, haciéndola relevante en el mercado actual.

La barre tactile multifonction de l'appareil photo sans miroir Canon EOS R original a été critiquée pour sa complexité. Cependant, l'article soutient que Canon devrait reconsidérer cette fonctionnalité ou le concept plus large des commandes tactiles dans les appareils photo sans miroir modernes. Avec les avancées technologiques et les leçons tirées des expériences passées, il y a un potentiel pour améliorer l'ergonomie des appareils photo. Revisiter la barre tactile pourrait conduire à une meilleure expérience utilisateur et fonctionnalité, la rendant pertinente sur le marché actuel.

The Multifunction Touch Bar on the original Canon EOS R mirrorless camera has faced criticism for its complexity. However, the article argues that Canon should reconsider this feature or the broader concept of touch controls in modern mirrorless cameras. With advancements in technology and lessons learned from past experiences, there is potential for enhancing camera ergonomics. Revisiting the Touch Bar could lead to improved user experience and functionality, making it relevant in today's market.

Canon Should Revisit Novel Touch Controls, and Here’s How

arXiv:1906.07172v5 Announce Type: replace-cross 
Abstract: Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.

Equivariant neural networks and equivarification

arXiv:2311.13745v4 Announce Type: replace-cross 
Abstract: Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works have studied the iteration complexity of sampling, assuming access to an accurate diffusion model. In this work, we focus on understanding the sample complexity of training such a model; how many samples are needed to learn an accurate diffusion model using a sufficiently expressive neural network? Prior work showed bounds polynomial in the dimension, desired Total Variation error, and Wasserstein error. We show an exponential improvement in the dependence on Wasserstein error and depth, along with improved dependencies on other relevant parameters.

Improved Sample Complexity Bounds for Diffusion Model Training

arXiv:2410.22995v2 Announce Type: replace-cross 
Abstract: A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (LMMs). The deficiency is often masked by evaluation metrics that prioritize final-answer accuracy, creating an illusion of competence where genuine reasoning is absent. Using the domain of geometric problem-solving as a precise instrument, we probe this issue through tasks that require constructing visual aids. To this end, we introduce \textbf{VisAidMath}, a challenging benchmark, and our novel Three-Layered Funnel Evaluation Framework. This framework moves beyond simple accuracy (ACCU) to scrutinize the generation of valid visual aids (PVA) and the soundness of subsequent reasoning steps (SPRS). Our extensive experiments on state-of-the-art models, including Doubao-Seed-1.6 and o4, reveal a profound ``Reasoning Illusion''. We observe that high surface-level accuracy conceals a catastrophic failure in the models' ability to produce valid visual aids or to reason from them. Our findings expose a fundamental schism between visual perception and logical deduction in modern LMMs. We host an evaluation platform at CodaBench for testing publicly. Homepage: https://nlp2ct.github.io/VisAidMathHomepage/ Evaluation: https://www.codabench.org/competitions/7634/

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning

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

arXiv:2511.14691v1 Announce Type: cross 
Abstract: Attention is the brain's ability to selectively focus on a few specific aspects while ignoring irrelevant ones. This biological principle inspired the attention mechanism in modern Transformers. Transformers now underpin large language models (LLMs) such as GPT, but at the cost of massive training and inference energy, leading to a large carbon footprint. While brain attention emerges from neural circuits, Transformer attention relies on dot-product similarity to weight elements in the input sequence. Neuromorphic computing, especially spiking neural networks (SNNs), offers a brain-inspired path to energy-efficient intelligence. Despite recent work on attention-based spiking Transformers, the core attention layer remains non-neuromorphic. Current spiking attention (i) relies on dot-product or element-wise similarity suited to floating-point operations, not event-driven spikes; (ii) keeps attention matrices that suffer from the von Neumann bottleneck, limiting in-memory computing; and (iii) still diverges from brain-like computation. To address these issues, we propose the Spiking STDP Transformer (S$^{2}$TDPT), a neuromorphic Transformer that implements self-attention through spike-timing-dependent plasticity (STDP), embedding query--key correlations in synaptic weights. STDP, a core mechanism of memory and learning in the brain and widely studied in neuromorphic devices, naturally enables in-memory computing and supports non-von Neumann hardware. On CIFAR-10 and CIFAR-100, our model achieves 94.35\% and 78.08\% accuracy with only four timesteps and 0.49 mJ on CIFAR-100, an 88.47\% energy reduction compared to a standard ANN Transformer. Grad-CAM shows that the model attends to semantically relevant regions, enhancing interpretability. Overall, S$^{2}$TDPT illustrates how biologically inspired attention can yield energy-efficient, hardware-friendly, and explainable neuromorphic models.

Attention via Synaptic Plasticity is All You Need: A Biologically Inspired Spiking Neuromorphic Transformer

arXiv:2511.08955v2 Announce Type: replace-cross 
Abstract: Simulating microstructure evolution (MicroEvo) is vital for materials design but demands high numerical accuracy, efficiency, and physical fidelity. Although recent studies on deep learning (DL) offer a promising alternative to traditional solvers, the field lacks standardized benchmarks. Existing studies are flawed due to a lack of comparing specialized MicroEvo DL models with state-of-the-art spatio-temporal architectures, an overemphasis on numerical accuracy over physical fidelity, and a failure to analyze error propagation over time. To address these gaps, we introduce MicroEvoEval, the first comprehensive benchmark for image-based microstructure evolution prediction. We evaluate 14 models, encompassing both domain-specific and general-purpose architectures, across four representative MicroEvo tasks with datasets specifically structured for both short- and long-term assessment. Our multi-faceted evaluation framework goes beyond numerical accuracy and computational cost, incorporating a curated set of structure-preserving metrics to assess physical fidelity. Our extensive evaluations yield several key insights. Notably, we find that modern architectures (e.g., VMamba), not only achieve superior long-term stability and physical fidelity but also operate with an order-of-magnitude greater computational efficiency. The results highlight the necessity of holistic evaluation and identify these modern architectures as a highly promising direction for developing efficient and reliable surrogate models in data-driven materials science.

MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction

<a href="https://petapixel.com/2025/11/18/canon-faces-lawsuit-over-wi-fi-in-cameras-and-printers/"><img width="1600" height="840" src="https://petapixel.com/assets/uploads/2025/05/canon-logo-red-background.jpg" class="attachment-card-large size-card-large wp-post-image" alt="White &quot;Canon&quot; logo in bold, stylized font centered on a red gradient background." decoding="async" fetchpriority="high" /></a>Canon Inc. and its U.S. subsidiary, Canon USA, are facing a new patent infringement lawsuit filed by Irish company Malikie Innovations Ltd. The suit alleges that Canon’s cameras, printers, and companion mobile app use Wi-Fi technology covered by six patents held by Malikie that pertain to how devices wirelessly connect to networks or apps for tasks such as photo sharing and printing.
[<a href="https://petapixel.com/2025/11/18/canon-faces-lawsuit-over-wi-fi-in-cameras-and-printers/">Read More</a>]

Canon Faces Lawsuit Over Wi-Fi in Cameras and Printers

<a href="https://petapixel.com/2025/11/18/chris-niccolls-and-jordan-drake-return-to-the-camera-store-for-one-day/"><img width="1600" height="840" src="https://petapixel.com/assets/uploads/2025/11/Chris-Niccolls-and-Jordan-Drake-Return-to-The-Camera-Store-For-One-Day.jpg" class="attachment-card-large size-card-large wp-post-image" alt="Two men stand behind a glass display counter in a camera store; one wears a floral shirt and leans forward, the other in a black shirt gestures playfully with a smile. Camera gear and accessories are visible in the background." decoding="async" /></a>Chris Niccolls and Jordan Drake are returning to The Camera Store (TCS), where their career started! For one day only and in celebration of reaching 250,000 subscribers, the duo are heading back behind the counter to reprise their old roles.
[<a href="https://petapixel.com/2025/11/18/chris-niccolls-and-jordan-drake-return-to-the-camera-store-for-one-day/">Read More</a>]

Chris Niccolls and Jordan Drake Return to The Camera Store (For One Day)

<a href="https://petapixel.com/2025/11/18/zeniko-launches-50-universal-dual-dial-retro-mini-flash/"><img width="1600" height="840" src="https://petapixel.com/assets/uploads/2025/11/zeniko-flash-featured.jpg" class="attachment-card-large size-card-large wp-post-image" alt="Two compact rectangular camera accessories, one silver and one black, each featuring dials on top, a rectangular light on the front, and a USB port on the side, are shown on a plain light background." decoding="async" /></a>Zeniko has introduced the ZA12 Dual Dial Retro Mini Flash, a compact lighting solution designed for photographers seeking portable illumination. According to Zeniko, the flash delivers even, powerful light using the company’s optical technology, which pairs a xenon tube with a Fresnel lens.
[<a href="https://petapixel.com/2025/11/18/zeniko-launches-50-universal-dual-dial-retro-mini-flash/">Read More</a>]

Canon Should Revisit Novel Touch Controls, and Here’s How

Was this article worth reading? Share it