Ghislaine Maxwell's ultimate humiliation: Epstein's sex trafficker girlfriend poses in outrageous outfits and exposes herself in dozens of photos released from the billionaire paedophile's files I was falsely accused of being the Brown University shooter... Silent Trump flees growing storm over Epstein'cover-up' as he jets off for holidays without ANY comment Truth about THIS photo of Karoline Leavitt's face... and why if she was non-binary and disabled, Vanity Fair would never have done this: KENNEDY Why Conan O'Brien'stopped party guests calling 911' on Nick Reiner: Insiders reveal disturbing new details of final hours before Rob and Michele murders After 27 years as a TV anchor I was suddenly pulled off screens. My boss's explanation was a brutal lesson in loyalty Emily in Paris cast left'aghast' and'walking on eggshells' as off-camera drama becomes overwhelming... and whispers swirl about a CURSE Doctors said my hip pain was just tendinitis from sitting all day at work.

Language identification is a crucial first step in multilingual systems such as chatbots and virtual assistants, enabling linguistically and culturally accurate user experiences. Errors at this stage can cascade into downstream failures, setting a high bar for accuracy. Yet, existing language identification tools struggle with key cases -- such as music requests where the song title and user language differ. Open-source tools like LangDetect, FastText are fast but less accurate, while large language models, though effective, are often too costly for low-latency or low-resource settings. We introduce PolyLingua, a lightweight Transformer-based model for in-domain language detection and fine-grained language classification. It employs a two-level contrastive learning framework combining instance-level separation and class-level alignment with adaptive margins, yielding compact and well-separated embeddings even for closely related languages. Evaluated on two challenging datasets -- Amazon Massive (multilingual digital assistant utterances) and a Song dataset (music requests with frequent code-switching) -- PolyLingua achieves 99.25% F1 and 98.15% F1, respectively, surpassing Sonnet 3.5 while using 10x fewer parameters, making it ideal for compute- and latency-constrained environments.

Personalization in LLMs often relies on costly human feedback or interaction logs, limiting scalability and neglecting deeper user attributes. To reduce the reliance on human annotations, we introduce GRAVITY (Generative Response with Aligned Values, Interests, and Traits of You), a framework for generating synthetic, profile-grounded preference data that captures users' interests, values, beliefs, and personality traits. By integrating demographic, cultural, and psychological frameworks -- including Hofstede's cultural dimensions, Schwartz's basic values, the World Values Survey, and Big Five OCEAN traits -- GRAVITY synthesizes preference pairs to guide personalized content generation. We evaluate GRAVITY on book descriptions for 400 Amazon users, comparing it to prompt-based conditioning, standard fine-tuning, and naive synthetic pair generation. Profile-grounded synthetic data consistently improves generation, especially across multiple cultures (USA, Brazil, Japan, India), achieving over 4% higher preference gains across baselines, with user studies showing that GRAVITY outputs are preferred over 86% of the time. Our results show that scenario-grounded synthetic data can capture richer user variation, reduce reliance on costly annotation, and produce more engaging, user-centered content, offering a scalable path for LLM personalization.

GPU prices could follow RAM's big rise Spotify's new playlist feature gives users more control over their recommendation algorithm Users in New Zealand will be able to write prompts for custom playlists. Spotify is attempting to give users more control over the music the streaming service recommends with a new playlist feature called Prompted Playlist. The beta feature is rolling out in New Zealand starting on December 11, and will let users write a custom prompt that Spotify can use -- alongside their listening history -- to create a playlist of new music. By tapping on Prompted Playlist, Spotify subscribers participating in the beta will be presented with a prompt field where they can type exactly what they want to hear and how they want Spotify's algorithm to respond. And while past AI features took users' individual taste into consideration, Spotify claims Prompted Playlist taps into your entire Spotify listening history, all the way back to day one.

PCWorld reports that Shelly's new Plug Gen4 smart plug launches at $19.99 with Matter certification and dual Wi-Fi/Zigbee connectivity. The device offers real-time energy monitoring, safety features, and integrates with Amazon Alexa and Apple Home ecosystems. Advanced users can create custom automations using Shelly's scripting language and JavaScript for tasks like rebooting networking equipment. If you're looking to take your first steps in the smart home space, nothing's easier than deploying a smart plug. Just stick one in an outlet, plug the lamp or small appliance you want to control into it, install a smartphone app, and you're done!

The performance of algorithms, methods, and models tends to depend heavily on the distribution of cases on which they are applied, this distribution being specific to the applicative domain. After performing an evaluation in several domains, it is highly informative to compute a (weighted) mean performance and, as shown in this paper, to scrutinize what happens during this averaging. To achieve this goal, we adopt a probabilistic framework and consider a performance as a probability measure (e.g., a normalized confusion matrix for a classification task). It appears that the corresponding weighted mean is known to be the summarization, and that only some remarkable scores assign to the summarized performance a value equal to a weighted arithmetic mean of the values assigned to the domain-specific performances. These scores include the family of ranking scores, a continuum parameterized by user preferences, and that the weights to consider in the arithmetic mean depend on the user preferences. Based on this, we rigorously define four domains, named easiest, most difficult, preponderant, and bottleneck domains, as functions of user preferences. After establishing the theory in a general setting, regardless of the task, we develop new visual tools for two-class classification.

As artificial intelligence (AI) becomes embedded in personal and professional relationships, a new kind of power imbalance emerges from asymmetric memory capabilities. Human relationships have historically relied on mutual forgetting, the natural tendency for both parties to forget details over time, as a foundation for psychological safety, forgiveness, and identity change. By contrast, AI systems can record, store, and recombine interaction histories at scale, often indefinitely. We introduce Memory Power Asymmetry (MPA): a structural power imbalance that arises when one relationship partner (typically an AI-enabled firm) possesses a substantially superior capacity to record, retain, retrieve, and integrate the shared history of the relationship, and can selectively deploy that history in ways the other partner (the human) cannot. Drawing on research in human memory, power-dependence theory, AI architecture, and consumer vulnerability, we develop a conceptual framework with four dimensions of MPA (persistence, accuracy, accessibility, integration) and four mechanisms by which memory asymmetry is translated into power (strategic memory deployment, narrative control, dependence asymmetry, vulnerability accumulation). We theorize downstream consequences at individual, relational/firm, and societal levels, formulate boundary-conditioned propositions, and articulate six design principles for restoring a healthier balance of memory in human-AI relationships (e.g., forgetting by design, contextual containment, symmetric access to records). Our analysis positions MPA as a distinct construct relative to information asymmetry, privacy, surveillance, and customer relationship management, and argues that protecting mutual forgetting, or at least mutual control over memory, should become a central design and policy goal in the AI age.

Generative retrieval methods utilize generative sequential modeling techniques, such as transformers, to generate candidate items for recommender systems. These methods have demonstrated promising results in academic benchmarks, surpassing traditional retrieval models like two-tower architectures. However, current generative retrieval methods lack the scalability required for industrial recommender systems, and they are insufficiently flexible to satisfy the multiple metric requirements of modern systems. This paper introduces PinRec, a novel generative retrieval model developed for applications at Pinterest. PinRec utilizes outcome-conditioned generation, enabling modelers to specify how to balance various outcome metrics, such as the number of saves and clicks, to effectively align with business goals and user exploration. Additionally, PinRec incorporates multi-token generation to enhance output diversity while optimizing generation. Our experiments demonstrate that PinRec can successfully balance performance, diversity, and efficiency, delivering a significant positive impact to users using generative models. This paper marks a significant milestone in generative retrieval, as it presents, to our knowledge, the first rigorous study on implementing generative retrieval at the scale of Pinterest.

When you purchase through links in our articles, we may earn a small commission. Alexa+ has a new shopping feature that lets it "auto-buy" items on Amazon when they hit a certain price. Ready to send Alexa+ bargain hunting with your credit card? That's the idea behind the latest shopping feature for the revamped and AI-enhanced Alexa, who you can now snap up deals for you the moment she spots them. Launching today, Alexa+'s new "auto-buy" feature does pretty much what it says: It gives Alexa+ permission to buy items from Amazon on its own, using your default payment method.

Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the community. All previous methods tend to scale up the model parameters during training time. However, how to efficiently utilize and scale up computational resources during test time remains underexplored, which can prove to be a scaling-efficient approach and bring orthogonal improvements in LM domains. The key point in applying test-time scaling to DLRS lies in effectively generating diverse yet meaningful outputs for the same instance. We propose two ways: One is to explore the heterogeneity of different model architectures. The other is to utilize the randomness of model initialization under a homogeneous architecture. The evaluation is conducted across eight models, including both classic and SOTA models, on three benchmarks. Sufficient evidence proves the effectiveness of both solutions. We further prove that under the same inference budget, test-time scaling can outperform parameter scaling. Our test-time scaling can also be seamlessly accelerated with the increase in parallel servers when deployed online, without affecting the inference time on the user side. Code is available.