We consider decentralized online convex optimization with time-varying constraints and conduct performance analysis using two stringent metrics: network dynamic regret with respect to the online global solution benchmark, and hard constraint violation that does not allow any compensated violation over time and learners. We propose an efficient algorithm called Constrained Online Learning with Doubly-bounded Queue (COLDQ), which introduces a novel virtual queue that is both lower and upper bounded, allowing tight control of the constraint violation without needing the Slater’s condition. We prove via a new Lyapunov drift analysis that COLDQ providesO(T1+Vx/2) network dynamic regret andO(min{T3+Vx/4;TVg}) hard constraint violation, whereVxandVgcapture the dynamics of the loss and constraint functions. For the first time, the two bounds smoothly approach to the best-knownO(T1/2) regret andO(1) violation, as the dynamics of the losses and constraints diminish, under both centralized and decentralized settings. For strongly convex loss functions, COLDQ providesO(logT) static regret andO(min{T1/2(logT)1/2,TVg}) hard constraint violation. Simulation results based on synthetic and canonical datasets demonstrate that COLDQ substantially outperforms the state-of-the-art approaches for both convex and non-convex loss functions.

Despite their remarkable potential, Large Vision-Language Models (LVLMs) still face challenges with object hallucination, a problem where their generated outputs mistakenly incorporate objects that do not actually exist. Although most works focus on addressing this issue within the language-model backbone, our work shifts the focus to the image input source, investigating how specific image tokens contribute to hallucinations. Our analysis reveals a striking finding: a small subset of image tokens with high attention scores are the primary drivers of object hallucination. By removing these hallucinatory image tokens (only 1.5% of all image tokens), the issue can be effectively mitigated. This finding holds consistently across different models and datasets. Building on this insight, we introduce EAZY, a novel, training-free method that automatically identifies and Eliminates hAllucinations by Zeroing out hallucinatorY image tokens. We utilize EAZY for unsupervised object hallucination detection, achieving 15% improvement compared to previous methods. Additionally, EAZY demonstrates remarkable effectiveness in mitigating hallucinations while preserving model utility and seamlessly adapting to various LVLM architectures.

Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

We established a regional cooperative emergency care system of ST-elevation myocardial infarction patients based on the internet of things. In this article, the current status and problems of ST-elevation myocardial infarction patient emergency care have been studied and key influence factors are found. As the results, a shorter time from symptom onset to reperfusion is achieved with improved outcomes for patients with ST-segment elevation myocardial infarction (STEMI). Primary percutaneous coronary intervention (PCI) in patients with STEMI significantly reduces mortality and morbidity, particularly when door-to-balloon (D2B) time is <; 90 min. An expedited pre-hospital diagnosis and transfer pathway was developed, with rapid reperfusion times and favorable outcomes.

With the improvement of living standards and the intensified social competition, the population of various chronic diseases is gradually expanded. In this study, we use a mature domestic commercial Body Area Network as our experiment platform-IVT mhealth system, a remote health care and rescue system created by IVT Corporation. This system adopts several most advanced technologies and patents in the world. It is a remote health care and rescue system, which consists of sensors, the call center and network platform. With the collaboration of medical institutions and health advisory center, it has the function of monitoring, positioning and asking for help. This system has achieved a dynamic measurement of ECG, blood pressure, blood glucose and blood oxygen. The data of users collected by wireless blood pressure meter, oximeter, ECG analyzer can be automatically sent to the cloud via cell phone and be kept as materials on records. This system provides a good platform for remote guidance, quantitative real-time monitoring and timely two-way feedback, as well as dynamic evaluation and overall adjustment for exercise rehabilitation of people on a large scale.