To understand the complex interactions in modern software, engineers often rely on high-frequency telemetry (HFT) data generated via tools like eBPF. However, today's database systems are too slow for HFT's rate and volume and cannot process HFT within the limited resources available on individual host machines. Mach is a new storage engine for collecting and querying HFT. Key to Mach is the Temporal Skip Log (TSL)---a lightweight, write-optimized, log-based data structure specialized for HFT. Mach supports high ingest rates and makes data immediately queryable while operating within a limited on-host resource envelope. Our demo shows how Mach helps engineers collect and query HFT in near real-time when diagnosing performance problems. In contrast, current systems and data reduction techniques fail to keep up. While a widely used time series database (InfluxDB) drops much of the HFT, the audience will see how Mach loses no data and allows them to interactively explore HFT from application and kernel events as they arrive.

Retrieving similar products is a critical functionality required by many e-commerce websites as well as dynamic product advertising systems. Retargeting and Prospecting are two major forms of dynamic product advertising. Typically, after a user interacts with a product on an advertiser website (e.g., Macy's), when the user later visits a website (e.g., yahoo.com) supported by a dynamic product advertising system, the same product may be shown to the user as a Retargeting product ad, while some similar products may be shown to the user as Prospecting product ads on the web page. Similar products can enrich users' ad experience based on users' intent on the Prospecting product ads through which the users interacted. These product ads can also serve as substitutes when Retargeting ad candidates are out of stock. However, it is challenging to retrieve similar products among billions of products in a product catalog efficiently. Deep Siamese models allow efficient retrieval but do not put enough emphasize on key product attributes. To improve the quality of the similar products, we propose to first use a Siamese Transformer-based model to retrieve similar products and then refine them with the attribute "product name" that indicates the type of a product (e.g., running shoes, engagement ring, etc.) for post filtering. We propose a novel product name generation model that fine tunes a pre-trained Transformer-based language model with a sequence to sequence objective. To the best of our knowledge, this is the first work using a generative approach for identifying product attributes. We introduce two applications of the proposed approach for the dynamic product advertising system of Yahoo for Retargeting and Prospecting respectively. Offline evaluation and online A/B testing shows that the proposed approach retrieves high quality similar products, leading to an increase of ad clicks and ad revenue.

People are increasingly using mobile video to communicate, collaborate, and share experiences while on the go. Yet this presents challenges in adequately sharing camera views with remote users. In this paper, we study the use of semi-autonomous drones for video conferencing, where an outdoor user (using a smartphone) is connected to a desktop user who can explore the environment from the drone's perspective. We describe findings from a study where pairs collaborated to complete shared navigation and search tasks. We illustrate the benefits of providing the desktop user with a view that is elevated, manipulable, and decoupled from the outdoor user. In addition, we articulate how participants overcame challenges in communicating environmental information and navigational cues, negotiated control of the view, and used the drone as a tool for sharing experiences. This provides a new way of thinking about mobile video conferencing where cameras that are decoupled from both users play an integral role in communication, collaboration, and sharing experiences.

Recent mobile technology has provided new opportunities for creating remote assistance systems. However, mobile support systems present a particular challenge: both the camera and display are held by the user, leading to shaky video. When pointing or drawing annotations, this means that the desired target often moves, causing the gesture to lose its intended meaning. To address this problem, we investigate annotation stabilization techniques, which allow annotations to stick to their intended location. We studied two annotation systems, using three different forms of annotations, with both tablets and head-mounted displays. Our analysis suggests that stabilized annotations and head-mounted displays are only beneficial in certain situations. However, the simplest approach of automatically freezing video while drawing annotations was surprisingly effective in facilitating the completion of remote assistance tasks.

Physiotherapy patients exercising at home alone are at risk of re-injury since they do not have corrective guidance from a therapist. To explore solutions to this problem, we designed Physio@Home, a prototype that guides people through prerecorded physiotherapy exercises using real-time visual guides and multi-camera views. Our design addresses several aspects of corrective guidance, including: plane and range of movement, joint positions and angles, and extent of movement. We evaluated our design, com-paring how closely people could follow exercise movements under various feedback conditions. Participants were most accurate when using our visual guide and multi-views. We provide suggestions for exercise guidance systems drawn from qualitative findings on visual feedback complexity.