The navigation app Waze is dropping Google Assistant support for iPhones, citing "ongoing difficulties" with integrating the service. The company says it plans on replacing it with an "enhanced voice integration solution" at some point in the future. Google Assistant will still work for Android users. This is happening a full year after iPhone users began reporting issues related to Google Assistant, with many people noting that voice commands were totally broken. Waze says that it has "not been working as intended for over a year" and that it would rather "phase out Google Assistant on iOS" instead of "patching a feature that has faced ongoing difficulties." As previously stated, Google Assistant for Waze will continue to work on Android phones.

As artificial intelligence becomes more and more ingrained in daily life, we present a novel system that uses deep learning for music recommendation and emotion-based detection. Through the use of facial recognition and the DeepFace framework, our method analyses human emotions in real-time and then plays music that reflects the mood it has discovered. The system uses a webcam to take pictures, analyses the most common facial expression, and then pulls a playlist from local storage that corresponds to the mood it has detected. An engaging and customised experience is ensured by allowing users to manually change the song selection via a dropdown menu or navigation buttons. By continuously looping over the playlist, the technology guarantees continuity. The objective of our system is to improve emotional well-being through music therapy by offering a responsive and automated music-selection experience.

"Greetings, Lovers, Legends, and Gods of Desire!" read the Partiful invite for the pre-Valentine's Day gathering. On this night, we will surrender to his playful whims." Then, sternly and in all caps: "YOU MUST BE PRE-APPROVED TO GET IN." A couple of days later, a text blast came in; the planners of this in-person dating meetup for singles were budgeting for 200 attendees, but more than 1,000 people applied, so there'd be a venue change. RSVPs closed at 3 pm sharp the day of the event. Then, at night, Barbarossa Lounge in San Francisco's Financial District welcomed the lucky guests who managed to get their names on the list. The event, Love in the Stars, was hosted by local event promoter Spice King and the online platform Paloma, which describes itself as a dating-oriented members club. Per the invitation's instructions, attendees dressed to signal their status; the singles wore a dash of red to make themselves identifiable as the ones looking for love. Their non-single supporters wore a splash of white or gold to signal they were already spoken for. Within an hour, there was no room to move. Small talk and awkward flirting filled every inch of the dark bar, with the question "So, do you like working in tech?" bouncing around at the same tempo as the clubby beats. Welcome to Silicon Valley's in-person dating scene. These regular events are only accessible to those already in the know. They feature pre-vetted guest lists; invite-only gatherings at villas in Hillsborough, one of the wealthiest towns in California; WhatsApp groups that gather monthly in apartments around town; and private parties with secret locations promising Stanford alumni and "creatives" in attendance. In an area that's notoriously tough on daters, at a time when dating app fatigue is at an all-time high, the appetite for ways to find love face-to-face is growing into a frenzy. "We have all collectively realized that dating apps are the worst," says Allie Hoffman, the founder of the two-year-old organization The Feels, a nationwide in-person dating event series with a strong presence in San Francisco. "There is no intention around how depleting, bot-y, ghosty, breadcrumb-y, gaslight-y and fishy they are.

With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models, resulting in a lack of transferability. In real-world scenarios, attackers often cannot access detailed information about the target model, making query-based attacks unfeasible. To address this challenge, we propose a technique called Acoustic Representation Optimization that aligns adversarial perturbations with low-level acoustic characteristics derived from speech representation models. Rather than relying on model-specific, higher-layer abstractions, our approach leverages fundamental acoustic representations that remain consistent across diverse ASR architectures. By enforcing an acoustic representation loss to guide perturbations toward these robust, lower-level representations, we enhance the cross-model transferability of adversarial examples without degrading audio quality. Our method is plug-and-play and can be integrated with any existing attack methods. We evaluate our approach on three modern ASR models, and the experimental results demonstrate that our method significantly improves the transferability of adversarial examples generated by previous methods while preserving the audio quality.

Smart LED light bulbs are one of the easiest ways to get into the IoT space. These smart lighting solutions let you control your home's illumination from your phone and other connected devices, and in addition to that practicality, they also inject some fun into your space. Color-changing bulbs have a plethora of RGB options for you to customize the lighting mood for your next movie night, date night or game day, or you can opt for cozy warm white light when you need to unwind at the end of a long day. It goes without saying that many of these smart LED light bulbs work with Amazon's Alexa and the Google Assistant, so if you already have a smart home setup in the works, you can find one that fits into your chosen ecosystem. And arguably the best thing about these devices is that they can fit into any budget; affordable and advanced options have flooded the space over the past few years. We've tested out a bunch of smart lights over the years, and these are our current favorites. If you've done any research into smart lights, you've probably come across Philips Hue bulbs.

Recent advancements in AI-driven conversational agents have exhibited immense potential of AI applications. Effective response generation is crucial to the success of these agents. While extensive research has focused on leveraging multiple auxiliary data sources (e.g., knowledge bases and personas) to enhance response generation, existing methods often struggle to efficiently extract relevant information from these sources. There are still clear limitations in the ability to combine versatile conversational capabilities with adherence to known facts and adaptation to large variations in user preferences and belief systems, which continues to hinder the wide adoption of conversational AI tools. This paper introduces a novel method, Conversational Agent for Multi-Source Auxiliary Context with Sparse and Symmetric Latent Interactions ( CoMAC), for conversation generation, which employs specialized encoding streams and post-fusion grounding networks for multiple data sources to identify relevant persona and knowledge information for the conversation. CoMAC also leverages a novel text similarity metric that allows bi-directional information sharing among multiple sources and focuses on a selective subset of meaningful words. Our experiments show that CoMAC improves the relevant persona and knowledge prediction accuracies and response generation quality significantly over two state-of-the-art methods.

The two primary tasks in the search recommendation system are search relevance matching and click-through rate (CTR) prediction -- the former focuses on seeking relevant items for user queries whereas the latter forecasts which item may better match user interest. Prior research typically develops two models to predict the CTR and search relevance separately, then ranking candidate items based on the fusion of the two outputs. However, such a divide-and-conquer paradigm creates the inconsistency between different models. Meanwhile, the search relevance model mainly concentrates on the degree of objective text matching while neglecting personalized differences among different users, leading to restricted model performance. To tackle these issues, we propose a unified \textbf{P}ersonalized Search RElevance Matching and CTR Prediction Fusion Model(PRECTR). Specifically, based on the conditional probability fusion mechanism, PRECTR integrates the CTR prediction and search relevance matching into one framework to enhance the interaction and consistency of the two modules. However, directly optimizing CTR binary classification loss may bring challenges to the fusion model's convergence and indefinitely promote the exposure of items with high CTR, regardless of their search relevance. Hence, we further introduce two-stage training and semantic consistency regularization to accelerate the model's convergence and restrain the recommendation of irrelevant items. Finally, acknowledging that different users may have varied relevance preferences, we assessed current users' relevance preferences by analyzing past users' preferences for similar queries and tailored incentives for different candidate items accordingly. Extensive experimental results on our production dataset and online A/B testing demonstrate the effectiveness and superiority of our proposed PRECTR method.

Efficiently searching for relevant case studies is critical in architectural design, as designers rely on precedent examples to guide or inspire their ongoing projects. However, traditional text-based search tools struggle to capture the inherently visual and complex nature of architectural knowledge, often leading to time-consuming and imprecise exploration. This paper introduces ArchSeek, an innovative case study search system with recommendation capability, tailored for architecture design professionals. Powered by the visual understanding capabilities from vision-language models and cross-modal embeddings, it enables text and image queries with fine-grained control, and interaction-based design case recommendations. It offers architects a more efficient, personalized way to discover design inspirations, with potential applications across other visually driven design fields. The source code is available at https://github.com/danruili/ArchSeek.

Apple Intelligence is fast becoming a disaster. Announced in June 2024 at Apple's World Wide Developer Conference, the artificial intelligence system arrived on the whole iPhone 16 family in October (and iPhone 15 Pro handsets, too), bringing things like generative tools for folks who can't be bothered to write emails, and summaries for those who can't be bothered to read, well, just about anything. December's addition, Genmoji--an AI emoji generator--didn't exactly bring much by way of excitement either. At the heart of the Apple Intelligence we were actually promised is a new Siri, an upgraded version of Apple's voice assistant, enhanced with some of the same smarts that made ChatGPT so beguiling at its launch in 2022. Amazon made similar moves recently with its upgrade to Alexa, but a more intelligent Siri is still MIA. It was meant to be here already.

Graph Neural Networks (GNNs) have demonstrated remarkable performance in various graph-based machine learning tasks, yet evaluating the importance of neighbors of testing nodes remains largely unexplored due to the challenge of assessing data importance without test labels. To address this gap, we propose Shapley-Guided Utility Learning (SGUL), a novel framework for graph inference data valuation. SGUL innovatively combines transferable data-specific and modelspecific features to approximate test accuracy without relying on ground truth labels. By incorporating Shapley values as a preprocessing step and using feature Shapley values as input, our method enables direct optimization of Shapley value prediction while reducing computational demands. SGUL overcomes key limitations of existing methods, including poor generalization to unseen test-time structures and indirect optimization. Experiments on diverse graph datasets demonstrate that SGUL consistently outperforms existing baselines in both inductive and transductive settings. SGUL offers an effective, efficient, and interpretable approach for quantifying the value of test-time neighbors.