Adobe Systems (United States)

Text-to-image diffusion models have demonstrated significant capabilities to generate diverse and detailed visuals in various domains, and story visualization is emerging as a particularly promising application. However, as their use in real-world creative domains increases, the need for providing enhanced control, refinement, and the ability to modify images post-generation in a consistent manner becomes an important challenge. Existing methods often lack the flexibility to apply fine or coarse edits while maintaining visual and narrative consistency across multiple frames, preventing creators from seamlessly crafting and refining their visual stories. To address these challenges, we introduce Plot'n Polish, a zero-shot framework that enables consistent story generation and provides fine-grained control over story visualizations at various levels of detail.

Ultra-high-resolution (UHR) text-to-image synthesis faces significant hurdles, including immense computational costs and a scarcity of training data. To address these, we introduce RealUHR, an efficient and scalable framework for generating photorealistic 4K images. At its core, RealUHR employs a Patch-Cascade Flow Matching pipeline that ensures global coherence without costly patch fusion by initiating generation from a semantically meaningful structure. This enables highly efficient, few-step inference for independent patches. Our key contribution is Guidance-Consistent Adaptation (GCA), a novel two-stage strategy to resolve the fundamental objective mismatch in guidance-distilled models. GCA allows powerful backbones like FLUX to be effectively adapted for patch-aware UHR synthesis. The framework's detail-rendering capabilities are further enhanced by a non-uniform time schedule. Experiments show that RealUHR establishes superior performance in both quality and efficiency, and excels in zero-shot applications such as creative up-sampling and generative artifact suppression.

Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias problem, limiting their ability to retain high-frequency information, and often struggle with noise robustness. Motivated by recent trends in iterative refinement processes, we propose Iterative Implicit Neural Representations (I-INRs). This novel plug-and-play framework iteratively refines signal reconstructions to restore high-frequency details, improve noise robustness, and enhance generalization, ultimately delivering superior reconstruction quality. I-INRs integrate seamlessly into existing INR architectures with only a 0.5–2% increase in parameters. During reconstruction, the iterative refinement adds just 0.8–1.6% additional FLOPs over the baseline while delivering a substantial performance boost of up to +2.0 PSNR. Extensive experiments demonstrate that I-INRs consistently outperform WIRE, SIREN, and Gauss across various computer vision tasks, including image fitting, image denoising, and object occupancy prediction.

Abstract Adversarial attacks in computer vision exploit the vulnerabilities of machine learning models by introducing subtle perturbations to input data, often leading to incorrect predictions or classifications. These attacks have evolved in sophistication with the advent of deep learning, presenting significant challenges in critical applications, which can be harmful for society. However, there is also a rich line of research from a transformative perspective that leverages adversarial techniques for social good. Specifically, we examine the rise of proactive schemes, methods that encrypt input data using additional signals termed templates, to enhance the performance of deep learning models. By embedding these imperceptible templates into digital media, proactive schemes are applied across various applications, from simple image enhancements to complicated deep learning frameworks to aid performance, as compared to the passive schemes, which don’t change the input data distribution for their framework. The survey delves into the methodologies behind these proactive schemes, the data perturbation and template learning processes, and their application to modern computer vision and natural language processing applications. Additionally, it discusses the challenges, potential vulnerabilities, and future directions for proactive schemes, ultimately highlighting their potential to foster the responsible and secure advancement of deep learning technologies.

Artificial intelligence service delivery has undergone a substantial transformation away from rigid licensing arrangements toward flexible consumption-driven monetization structures. Conventional flat-rate pricing schemes inadequately reflect the dynamic nature of AI computational demands. Resource requirements vary considerably based on model sophistication, inference intensity, and data handling complexity. Credit and token mechanisms function as standardized abstraction units. Such units separate billing processes from underlying infrastructure technicalities. Customers benefit from adaptable budget management capabilities through these monetization structures. Combined pricing models integrating committed spending with prepaid credit reserves enable greater operational flexibility. Overflow consumption calculations provide additional adaptability for variable demand scenarios. Implementation difficulties persist concerning pricing clarity and consumption unpredictability. Maintaining customer confidence remains a paramount consideration for service providers. The architectural underpinnings of consumption-oriented AI pricing receive thorough examination within the present article. Calibration techniques converting usage metrics into pricing units warrant detailed attention. Operational hurdles and ethical dimensions are addressed alongside supervisory frameworks, ensuring responsible deployment. The central contribution involves integrating technical pricing structures with transparency safeguards. Such integration facilitates responsible AI adoption scaling across varied implementation scenarios while preserving economic sustainability and stakeholder trust throughout the monetization lifecycle.

Laryngeal Carcinoma (LC) represents the most widely malignancy in the neck and head region. It is associated with risk factors such as alcohol consumption, smoking, and exposure to environmentally harmful substances. In its early stages, this disease is difficult to diagnose, leading to a poor prognosis for patients. This research attempts to discover the potential for improving the diagnostic accuracy of laryngeal cancer using some techniques of Machine Learning (ML) and deep learning (DL). This work demonstrates the use of advanced models and mechanisms, including convolutional neural networks (CNNs), support vector machines (SVMs), and random forests, to analyze laryngeal images taken from narrow-band imaging (NBI) computed tomography (CT). The study includes preprocessing methods such as normalization, denoising, segmentation, and data augmentation, which enhance the performance and effectiveness of the models. The project aims to evaluate the performance of models using metrics such as sensitivity, accuracy, specificity, and the F1 measure, so that it contributes to developing effective tools that help physicians make accurate data-driven diagnostic and treatment decisions. Ultimately, the research presents potential future applications of these technologies, based on integrated images and clinical data analysis, to predict disease progression and survival rates. These efforts will contribute to more effective tools for diagnosing and treating laryngeal cancer.

Multi-modal multi-task (M3T) foundation models (FMs) have recently shown transformative potential in artificial intelligence, with emerging applications in education. However, their deployment in real-world educational settings is hindered by privacy regulations, data silos, and limited domain-specific data availability. We introduce M3T Federated Foundation Models (FedFMs) for education: a paradigm that integrates federated learning (FL) with M3T FMs to enable collaborative, privacy-preserving training across decentralized institutions while accommodating diverse modalities and tasks. Subsequently, this perspective paper aims to unveil M3T FedFMs as a promising yet underexplored approach to the education community, explore its potentials, and reveal its related future research directions. We outline how M3T FedFMs can advance three critical pillars of next-generation intelligent education systems: (i) privacy preservation, by keeping sensitive multi-modal student and institutional data local; (ii) personalization, through modular architectures enabling tailored models for students, instructors, and institutions; and (iii) equity and inclusivity, by facilitating participation from underrepresented and resource-constrained entities. We finally identify various open research challenges, including studying of (i) inter-institution heterogeneous privacy regulations, (ii) the non-uniformity of data modalities' characteristics, (iii) the unlearning approaches for M3T FedFMs, (iv) the continual learning frameworks for M3T FedFMs, and (v) M3T FedFM model interpretability, which must be collectively addressed for practical deployment.

We reflect on an evaluation of an immersive analytics application (Tableau for visionOS) conducted at a large enterprise business intelligence (BI) conference. Conducting a study in such a context offered an opportunistic setting to gather diverse feedback. However, this setting also highlighted the challenge of evaluating usability while also assessing potential utility, as feedback straddled between the novelty of the experience and the practicality of the application in participants' analytical workflows. This formative evaluation with 22 participants allowed us to gather insights with respect to the usability of Tableau for visionOS, along with broader perspectives on the potential for head-mounted displays (HMDs) to promote new ways to engage with BI data. Our experience suggests a need for new evaluation considerations that integrate qualitative and quantitative measures and account for unique interaction patterns with 3D representations and interfaces accessible via an HMD. Overall, we contribute an enterprise perspective on evaluation methodologies for immersive analytics.