Despite significant progress in auto-regressive image generation, inference remains slow due to the sequential nature of AR models and the ambiguity of image tokens, even when using speculative decoding. Recent works attempt to address this with relaxed speculative decoding but lack theoretical grounding. In this paper, we establish the theoretical basis of relaxed SD and propose COOL-SD, an annealed relaxation of speculative decoding built on two key insights. The first analyzes the total variation (TV) distance between the target model and relaxed speculative decoding and yields an optimal resampling distribution that minimizes an upper bound of the distance. The second uses perturbation analysis to reveal an annealing behaviour in relaxed speculative decoding, motivating our annealed design. Together, these insights enable COOL-SD to generate images faster with comparable quality, or achieve better quality at similar latency. Experiments validate the effectiveness of COOL-SD, showing consistent improvements over prior methods in speed-quality trade-offs.

ABSTRACT With the increasing prevalence of smartphones and advancements in sensors, smartphone‐based solutions for physiological parameter monitoring appear to offer notable advantages over traditional methods, potentially enhancing safety, convenience and efficiency. This paper aims to present a systematic survey of smartphone sensor‐based physiological parameter monitoring apps, with particular discussions of gaps between their current functional capabilities and recent advances. We conducted a systematic analysis of relevant apps available on the App Store and Google Play, mainly focusing on four vital signs: heart rate (HR), blood pressure(BP), body temperature (BT) and respiratory rate (RR), as well as oxygen saturation (), blood glucose (BG) and haemoglobin (Hb). The analysis revealed that HR measurement apps were the most prevalent, while BP, , BT and RR measurement apps were comparatively fewer, and no smartphone sensor‐based BG measurement apps were identified. The contact photoplethysmography method is widely adopted by current apps, while non‐contact approach holds potential. Novel techniques require further investigation beyond laboratory settings to enhance robustness. Smartphone‐based measurement of physiological parameters shows promise, though further research and development are needed to bridge the gap between current capabilities and the demands of accurate, real‐world health monitoring.

Recent advances in mobile technologies (like WiFi 6 and 5G) do not seem to deliver the promised access bandwidth. To effectively characterize mobile access bandwidth in the wild, we work with a major commercial mobile bandwidth testing app to conduct a long-term (2020-2023) and large-scale (involving 4.76M users) measurement study in China, based on coarse-grained general statistics and fine-grained sampling diagnostics. Our study presents distinct facts as to WiFi, 5G, and 4G: in the past few years, the average WiFi download bandwidth exhibits a considerable rise (by 119.7% ), the average 5G download bandwidth constantly decreases (by a total of 20.2% ) despite the enormous infrastructure investments, while the average 4G download bandwidth first declines (by 22.1% ) and then increases (by 22.5% ). The situations of upload bandwidths are generally similar to those of download bandwidths, except that 5G upload bandwidths manifestN-shaped$(\nearrow \searrow \nearrow )$fluctuations. Our cross-layer and cross-technology analysis reveals a variety of impact factors as well as their complicated interplay as the root causes, such as the bottlenecks in underlying infrastructure (e.g., communication devices and wired Internet access), the traffic offloading from one access technology to another, the influence of the COVID-19 pandemic, and the side effects of aggressively migrating radio resources from 4G to 5G. With the longitudinal, holistic picture of today's mobile access bandwidth, we finally provide multifold practical implications on closing the technology gaps.

Access bandwidth measurement is crucial to emerging Internet applications for network-aware content delivery. However, today’s bandwidth testing services (BTSes) are slow and costly—the tests take a long time to run, consume a great deal of data usage, and usually require large-scale test server deployments. The inefficiency and high cost of BTSes root in their methodologies that use excessive temporal/spatial redundancies for combating noises in Internet measurement. In particular, compared to downlink BTSes, uplink BTSes are subject to more severe performance problems and technical challenges. This paper presents FastUpBTS to make uplink BTS fast and cheap while maintaining high accuracy. The key idea is to strategically accommodate and exploit the noise rather than repetitively and exhaustively suppress the impact of noise. This is achieved by a novel statistical sampling framework termed fuzzy rejection sampling. We build FastUpBTS as an end-to-end BTS that implements fuzzy rejection sampling based on memorization-reinforced throughput denoising, data-driven server selection, and informed multi-homing support. Our evaluation shows that with only 30 test servers, FastUpBTS achieves the same level of accuracy compared to the state-of-the-art BTS (SpeedTest.net) that deploys ~16,000 servers. Most importantly, FastUpBTS makes bandwidth tests$5.4\times $faster and$6.8\times $more data-efficient.

Recent advances in mobile technologies such as 5G and WiFi 6E do not seem to deliver the promised mobile access bandwidth. To effectively characterize mobile access bandwidth in the wild, we work with a major commercial mobile bandwidth testing app to analyze mobile access bandwidths of 3.54M end users in China, based on fine-grained measurement and diagnostic information. Our analysis presents a surprising and frustrating fact---in the past two years, the average WiFi bandwidth remains largely unchanged, while the average 4G/5G bandwidth decreases remarkably. Our analysis further reveals the root causes---the bottlenecks in the underlying infrastructure (e.g., devices and wired Internet access) and side effects of aggressively migrating radio resources from 4G to 5G---with implications on closing the technology gaps. Additionally, our analysis provides insights on building ultra-fast, ultra-light bandwidth testing services (BTSes) at scale. Our new design dramatically reduces the test time of the commercial BTS from 10 seconds to 1 second on average, with a 15× reduction on the backend cost.

This article studies how today's cloud storage services support collaborative file editing. As a tradeoff for transparency and user-friendliness, they do not ask collaborators to use version control systems but instead implement their own heuristics for handling conflicts, which however often lead to unexpected and undesired experiences. With specialized measurements and reverse engineering, we unravel a number of their design and implementation issues as the root causes of poor experiences. Driven by the findings, we propose to reconsider the collaboration support of cloud storage services from a novel perspective ofoperationswithout using any locks. To enable this idea, we design intelligent and efficient approaches to the inference and transformation of users’ editing operations, as well as optimizations to the maintenance of files’ historical versions and the update of individual files. We build an open-source system UFC2 (User-Friendly Collaborative Cloud) to embody our design, which can avoid most (98%) conflicts with little (2%) overhead.