Menglong Cui, Pengzhi Gao, Wei Liu, Jian Luan, Bin 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.

Mobile operating systems, such as Android, are increasingly used across diverse applications, where ensuring high responsiveness to user interactions is critical, particularly in mission-critical and real-time scenarios. Mobile operating systems typically process user interaction events and UI rendering on the same thread, commonly referred to as the main thread of a mobile application. As a result, user interaction handling can face significant delays when blocked by overloaded UI rendering tasks, compromising responsiveness. Existing mobile operating systems lack effective mechanisms to mitigate this issue. This paper addresses the problem by restructuring the UI rendering workflow to improve responsiveness in the presence of heavy rendering workloads. Specifically, two techniques are proposed that are tailored to whether the event handling results require screen display. Experimental results demonstrate improvements in both average-case and worst-case response times of event handling, enhancing the UI responsiveness. Although the implementation focuses on Android, the proposed approaches are adaptable to other mobile operating systems with similar rendering architectures, such as iOS and HarmonyOS.

Using large language models (LLMs) for machine translation via in-context learning (ICL) has become an interesting research direction of machine translation (MT) in recent years. Its main idea is to retrieve a few translation pairs as demonstrations from an additional datastore (parallel corpus) to guide translation without updating the LLMs. However, the underlying noise of retrieved demonstrations usually dramatically deteriorate the performance of LLMs. In this paper, we propose a robust method to enable LLMs to achieve robust translation with ICL. The method incorporates a multi-view approach, considering both sentence- and word-level information, to select demonstrations that effectively avoid noise. At the sentence level, a margin-based score is designed to avoid semantic noise. At the word level, word embeddings are utilized to evaluate the related tokens and change the weight of words in demonstrations. By considering both sentence- and word-level similarity, the proposed method provides fine-grained demonstrations that effectively prompt the translation of LLMs. Experimental results demonstrate the effectiveness of our method, particularly in domain adaptation.

Electrophoretic displays (EPDs), also known as e-paper, offer a paper-like visual experience by reflecting ambient light, making them distinct from traditional LCD or LED displays. They are favored for their eye comfort, energy efficiency, and material flexibility, which make them appealing for a wide range of embedded devices, including eReaders, smartphones, tablets, and wearables. However, EPDs face a significant challenge: the necessity for a fast refresh rate (to maintain an acceptable display performance) introduces a pronounced ghosting effect. This effect results in noticeable color discrepancies between the displayed and source images, harming the user experience and hindering EPDs’ broader application in devices requiring dynamic content display. This article proposes a software-based solution to address the ghosting issue in EPDs. Our approach involves developing analytical models to predict the occurrence of ghosting effects and adjusting the source images to counteract the anticipated color deviations, which can reduce the perceivable ghosts on the display. Experimental evaluation conducted on real-world EPDs validates the effectiveness of our proposed approach in reducing the ghosting effect.

It becomes more and more common for people to have multiple mobile devices. This opens the opportunity of multi-surface computing in which users interact with an app using multiple devices simultaneously. Recently, a system called FLUID was developed, which can distribute User Interface (UI) elements of an app to multiple devices to support multi-surface computing. FLUID enables general, flexible and transparent multi-device interaction, which cannot be achieved by previous approaches such as screen mirroring, app migration, and customized app development on multiple devices. However, the practicality of FLUID is still severely limited because it requires that (1) the app source codes must be available and (2) the same app is pre-installed on all devices. This paper presents PRUID, a UI distribution system that is free from the above-mentioned limitations of FLUID. PRUID captures and extracts relevant information about UI elements to be distributed completely at run time, without requiring the app source code. An app-independent UI agent is designed to dock and render the UI components distributed to the guest device, so pre-installation of the app on guest devices is not required. We developed representative use cases to demonstrate the usage and evaluate the performance of PRUID. The evaluation results show that the extra overhead incurred due to the UI information extraction at run time is marginal and PRUID provides a smooth user experience.

Since the ImageNet competition was held in 2012, the machine learning algorithm has performed very well on the image classification task. In object classification task, there are still some problems. For example, similar categories are difficult to be distinguished in images. In addition, with the increasing number of object categories, the background of scene has become another crucial issue in object classification. This paper focuses on image object recognition and makes two major contributions to tackle these issues. Firstly, we propose a semantic refinement method that analyzes the relationship among similar categories in images from the perspective of semantic knowledge. The knowledge of the relationship between semantics comes from a wide range of open knowledge. Secondly, we utilize the knowledge graph method to create the image knowledge graph with multiple categories in images. Our method exploits the knowledge from the adjacency matrix computed on train data to merge relevant classes into graph. We conduct extensive experiments on large-scale image datasets (ImageNet), demonstrating the effectiveness of our approach. Further, our method participates in ILSVRC 2012 challenges, and obtain the new state-of-the-art results on the ImageNet (82.43%).