InfoQ Homepage Mobile Content on InfoQ
-
Google's New LiteRT Accelerator Supercharges AI Workloads on Snapdragon-powered Android Devices
Google has introduced a new accelerator for LiteRT, called Qualcomm AI Engine Direct (QNN), to enhance on-device AI performance on Qualcomm-powered Android devices equipped with Snapdragon 8 SoCs. The accelerator delivers significant gains, offering up to a 100x speedup over CPU execution and 10x over GPU.
-
After Seven Years, Google Reinvents Android Navigation with Jetpack Navigation 3
Google has released the new Jetpack Navigation 3 library, which redesigns from the ground up notification handling in Android apps. The new library gives full control on the back stack and integrates seamlessly with Jetpack Compose's state management.
-
CameraX 1.5 Brings Advanced Video Recording and Image Capture to Android
CameraX 1.5 introduces support for capturing slow-motion and high frame-rate videos as well as unprocessed, uncompressed still images. These capabilities are enabled by the new SessionConfig API, which streamlines camera setup and configuration.
-
Android GenAI Prompt API Enables Natural Language Requests with Gemini Nano
The ML Kit GenAI Prompt API, now available in alpha, enables Android developers to send natural language and multimodal requests to Gemini Nano running on-device, extending the text summarization and image description capabilities introduced with the initial GenAI release.
-
Apple Previews SDK for Building Android Apps with Swift
The Swift SDK for Android, recently released as a nightly build, is designed to help developers to port their Swift packages to Android, making it easier to share code across platforms. While the SDK is still in preview, over 25% of packages in the Swift Package Index can already be compiled for Android.
-
Google Research Open-Sources the Coral NPU Platform to Help Build AI into Wearables and Edge Devices
Coral NPU is an open-source full-stack platform designed to help hardware engineers and AI developers overcome the limitations that prevent integrating AI in wearables and edge devices, including performance, fragmentation, and user trust.
-
Pixnapping: Side-Channel Vulnerability Allows Android Apps to Capture Sensitive Screen Data
A newly discovered class of attacks targets Android devices, allowing malicious apps to steal on-screen information from other apps using a technique known as pixel stealing. Dubbed Pixnapping, the attack leverages previously known side-channel vulnerabilities and affects virtually all apps, including Signal, Google Authenticator, Venmo, and many others.
-
Swift 6.2 Released with Improved Concurrency, Safer Raw-Memory Access, Wasm Support and More
The most significant new feature in Swift 6.2 is approachable concurrency, a default, low-complexity approach to writing safe concurrent applications. Swift 6.2 also introduces new features to simplify low-level programming, including the InlineArray and Span types, and adds support for WebAssembly.
-
Google Brings Optimized Resource Shrinking in Latest Android Gradle Plugin
The latest version of the Android Gradle Plugin (AGP) introduces an optimized resource-shrinking approach that unifies code optimization and resource shrinking, achieving up to 50% reduction in app size for apps that share significant resources and code across different form factor, says Google.
-
Android Studio Narwhal Extends Gemini AI Capabilities
The latest Android Studio Narwhal 3 Feature Drop introduces enhancements aimed at boosting developer productivity, including support for resizable Compose previews, new app Backup & Restore tools, and expanded Gemini capabilities such as automatic code generation from UI screenshots.
-
Jetpack Compose Enhances Scrolling, Lazy Lists, and More
The latest release of Jetpack Compose, as usual named after its introduction month, adds new APIs for rendering shadows, 2D scrolling, improved list performance, and more.
-
Swift 6.2 Introduces Approachable Concurrency to Simplify Concurrent Programming
Announced at its latest developer conference, WWDC25, Swift Approachable Concurrency is a new feature in Swift 6.2 designed to simplify concurrent programming for the most common use cases in mobile apps.
-
Apple Shares Details on Upcoming AI Foundation Models for iOS 26
In a recent tech report, Apple has provided more details on the performance and characteristics of the new Apple Intelligence Foundation Models that will be part of iOS 26, as announced at the latest WWDC 2025.
-
Arm Scalable Matrix Extension 2 Coming to Android to Accelerate On-Device AI
Available in the Armv9-A architecture, Arm Scalable Matrix Extension 2 (SME2) is a set of advanced CPU instructions designed to accelerate matrix heavy computation. The new Arm technology aims to help mobile developers to run advanced AI models directly on CPU with improved performance and efficiency, without requiring any changes to their apps.
-
Gemma 3n Introduces Novel Techniques for Enhanced Mobile AI Inference
Launched in early preview last May, Gemma 3n is now officially available. It targets mobile-first, on-device AI applications, using new techniques designed to increase efficiency and improve performance, such as per-layer embeddings and transformer nesting.