Personal AI assistants (e.g., Apple Intelligence, Meta AI) offer proactive recommendations that simplify everyday tasks, but their reliance on sensitive user data raises concerns about privacy and trust. To address these challenges, we introduce the Guardian of Data (GOD), a secure, privacy-preserving framework for training and evaluating AI assistants directly on-device. Unlike traditional benchmarks, the GOD model measures how well assistants can anticipate user needs-such as suggesting gifts-while protecting user data and autonomy. Functioning like an AI school, it addresses the cold start problem by simulating user queries and employing a curriculum-based approach to refine the performance of each assistant. Running within a Trusted Execution Environment (TEE), it safeguards user data while applying reinforcement and imitation learning to refine AI recommendations. A token-based incentive system encourages users to share data securely, creating a data flywheel that drives continuous improvement. Specifically, users mine with their data, and the mining rate is determined by GOD's evaluation of how well their AI assistant understands them across categories such as shopping, social interactions, productivity, trading, and Web3. By integrating privacy, personalization, and trust, the GOD model provides a scalable, responsible path for advancing personal AI assistants. For community collaboration, part of the framework is open-sourced at https://github.com/PIN-AI/God-Model.

Amazon's new and improved version of Alexa is here, and it's called Alexa . The next-gen upgrade is more conversational, can execute complex tasks, and is much more personalized. While the rollout starts next month on select Echo Show devices, Amazon claims it'll eventually be available on every Alexa-powered device the company has shipped. It'll cost 20 per month but will be free for Amazon customers. Here's everything you need to know about Amazon's new and improved virtual assistant.

Following years of development, Amazon's next-generation digital assistant is ready for public use. The model powering Alexa can detect tone and mood and respond accordingly, with a completely new voice -- one that sounds more natural. Moreover, it's only necessary to say "Alexa" once to wake the assistant. It will then follow the conversation. Panay said Alexa has contextual awareness, with the ability to "remember" earlier parts of a conversation.

It's sort of out of character for Amazon to be hosting a devices event in February, as opposed to its usual Fall launch. But this morning (February 26) at 10am ET, the company is holding a presentation in New York City. As it's done in the past, Amazon won't be livestreaming this event, and you won't be able to watch Panos Panay and his colleagues present to members of the media. Don't worry about FOMO, though. Engadget will be attending and liveblogging the event, so if you follow our updates it'll almost feel like you're right there with us! We'll have commentary and contextualization on the announcements, as well as the in-person vibes and quality of snacks.

Cross-Domain Sequential Recommendation (CDSR) aims to predict future user interactions based on historical interactions across multiple domains. The key challenge in CDSR is effectively capturing cross-domain user preferences by fully leveraging both intra-sequence and inter-sequence item interactions. In this paper, we propose a novel method, Image Fusion for Cross-Domain Sequential Recommendation (IFCDSR), which incorporates item image information to better capture visual preferences. Our approach integrates a frozen CLIP model to generate image embeddings, enriching original item embeddings with visual data from both intra-sequence and inter-sequence interactions. Additionally, we employ a multiple attention layer to capture cross-domain interests, enabling joint learning of single-domain and cross-domain user preferences. To validate the effectiveness of IFCDSR, we re-partitioned four e-commerce datasets and conducted extensive experiments. Results demonstrate that IFCDSR significantly outperforms existing methods.

Recommender systems leveraging deep learning models have been crucial for assisting users in selecting items aligned with their preferences and interests. However, a significant challenge persists in single-criteria recommender systems, which often overlook the diverse attributes of items that have been addressed by Multi-Criteria Recommender Systems (MCRS). Shared embedding vector for multi-criteria item ratings but have struggled to capture the nuanced relationships between users and items based on specific criteria. In this study, we present a novel representation for Multi-Criteria Recommender Systems (MCRS) based on a multi-edge bipartite graph, where each edge represents one criterion rating of items by users, and Multiview Dual Graph Attention Networks (MDGAT). Employing MDGAT is beneficial and important for adequately considering all relations between users and items, given the presence of both local (criterion-based) and global (multi-criteria) relations. Additionally, we define anchor points in each view based on similarity and employ local and global contrastive learning to distinguish between positive and negative samples across each view and the entire graph. We evaluate our method on two real-world datasets and assess its performance based on item rating predictions. The results demonstrate that our method achieves higher accuracy compared to the baseline method for predicting item ratings on the same datasets. MDGAT effectively capture the local and global impact of neighbours and the similarity between nodes.

Apple's iPhone voice-to-text feature is sparking controversy after a viral TikTok video showed a user speaking the word "racist," which at first showed up as "Trump" before switching back to "racist." Fox News Digital was able to replicate the issue multiple times. The voice-to-text dictation feature was observed briefly flashing "Trump" when a user said "racist" before it quickly changed back to "racist" – just like in the viral TikTok video. However, "Trump" did not appear every time a user said "racist." The voice-to-text feature also wrote words like "reinhold" and "you" when a user said "racist."

The AgentSociety Challenge is the first competition in the Web Conference that aims to explore the potential of Large Language Model (LLM) agents in modeling user behavior and enhancing recommender systems on web platforms. The Challenge consists of two tracks: the User Modeling Track and the Recommendation Track. Participants are tasked to utilize a combined dataset from Yelp, Amazon, and Goodreads, along with an interactive environment simulator, to develop innovative LLM agents. The Challenge has attracted 295 teams across the globe and received over 1,400 submissions in total over the course of 37 official competition days. The participants have achieved 21.9% and 20.3% performance improvement for Track 1 and Track 2 in the Development Phase, and 9.1% and 15.9% in the Final Phase, representing a significant accomplishment. This paper discusses the detailed designs of the Challenge, analyzes the outcomes, and highlights the most successful LLM agent designs. To support further research and development, we have open-sourced the benchmark environment at https://tsinghua-fib-lab.github.io/AgentSocietyChallenge.

Recommendation systems are now an integral part of our daily lives. We rely on them for tasks such as discovering new movies, finding friends on social media, and connecting job seekers with relevant opportunities. Given their vital role, we must ensure these recommendations are free from societal stereotypes. Therefore, evaluating and addressing such biases in recommendation systems is crucial. Previous work evaluating the fairness of recommended items fails to capture certain nuances as they mainly focus on comparing performance metrics for different sensitive groups. In this paper, we introduce a set of comprehensive metrics for quantifying gender bias in recommendations. Specifically, we show the importance of evaluating fairness on a more granular level, which can be achieved using our metrics to capture gender bias using categories of recommended items like genres for movies. Furthermore, we show that employing a category-aware fairness metric as a regularization term along with the main recommendation loss during training can help effectively minimize bias in the models' output. We experiment on three real-world datasets, using five baseline models alongside two popular fairness-aware models, to show the effectiveness of our metrics in evaluating gender bias. Our metrics help provide an enhanced insight into bias in recommended items compared to previous metrics. Additionally, our results demonstrate how incorporating our regularization term significantly improves the fairness in recommendations for different categories without substantial degradation in overall recommendation performance.

William Phelps was at work when he got the call from the FBI that he had to return home at once. It was December 2023 and his wife, Aurora Phelps, was in big trouble, something to do with a fraud scheme. About a dozen agents turned his apartment upside down looking for evidence in their case, and William Phelps wouldn't see his wife again. That is, until this week, when William came to learn the scope of the allegations against his wife. According to federal prosecutors, Aurora was the perpetrator of a deadly romance scam, connecting with older men on the internet, then drugging them and stealing from their bank accounts.