The Eufy Smart Display E10 is a fast, focused, and private way to manage your home security–provided you're living in Eufy's home security ecosystem. Smart displays aren't new, but Eufy's take on the category is a little different. Rather, it's a dedicated visual control panel for your Eufy-powered home security system, one that puts live video feeds, visitor alerts, and event summaries all in one place. Unlike an Echo Show or Nest Hub, it does it all without leaning on the cloud, serving up ads, or connecting to a server somewhere. The Eufy Smart Display E10 looks more like a small tablet than a security device.

While Large Language Models (LLMs) can serve as agents to simulate human behaviors (i.e., role-playing agents), we emphasize the importance of point-in-time role-playing. This situates characters at specific moments in the narrative progression for three main reasons: (i) enhancing users' narrative immersion, (ii) avoiding spoilers, and (iii) fostering engagement in fandom role-playing. To accurately represent characters at specific time points, agents must avoid character hallucination, where they display knowledge that contradicts their characters' identities and historical timelines. We introduce TimeChara, a new benchmark designed to evaluate point-in-time character hallucination in role-playing LLMs. Comprising 10,895 instances generated through an automated pipeline, this benchmark reveals significant hallucination issues in current state-of-the-art LLMs (e.g., GPT-4o). To counter this challenge, we propose Narrative-Experts, a method that decomposes the reasoning steps and utilizes narrative experts to reduce point-in-time character hallucinations effectively. Still, our findings with TimeChara highlight the ongoing challenges of point-in-time character hallucination, calling for further study.

Succinct event description based on multiple documents is critical to news systems as well as search engines. Different from existing summarization or event tasks, Multi-document Event Summarization (MES) aims at the query-level event sequence generation, which has extra constraints on event expression and conciseness. Identifying and summarizing the key event from a set of related articles is a challenging task that has not been sufficiently studied, mainly because online articles exhibit characteristics of redundancy and sparsity, and a perfect event summarization needs high level information fusion among diverse sentences and articles. To address these challenges, we propose a two-phase framework for the MES task, that first performs event semantic graph construction and dominant event detection via graph-sequence matching, then summarizes the extracted key event by an event-aware pointer generator. For experiments in the new task, we construct two large-scale real-world datasets for training and assessment. Extensive evaluations show that the proposed framework significantly outperforms the related baseline methods, with the most dominant event of the articles effectively identified and correctly summarized.