Related papers: MAML: Towards a Faster Web in Developing Regions

Transformers have revolutionized the machine learning landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being…

Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. Existing benchmarks are either designed…

With the worldwide growth of remote communication and telepresence, network measurements form a cornerstone of effective performance assessment and diagnostics for Internet users. Most often, users seek for overall connection performance…

Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source models and…

In modern software development, the JavaScript ecosystem of various frameworks and libraries used to develop contemporary web applications presents many advantages. JavaScript is a widely known interpreted programming language, simple to…

Multimodal large language models (MLLMs) have shown impressive success across modalities such as image, video, and audio in a variety of understanding and generation tasks. However, current MLLMs are surprisingly poor at understanding…

Despite its popularity, several recent works question the effectiveness of MAML when test tasks are different from training tasks, thus suggesting various task-conditioned methodology to improve the initialization. Instead of searching for…

Several recently devised machine learning (ML) algorithms have shown improved accuracy for various predictive problems. Model searches, which explore to find an optimal ML algorithm and hyperparameter values for the target problem, play a…

Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remain largely unexplored. To close this gap, we present…

Model-Agnostic Meta-Learning (MAML), a popular gradient-based meta-learning framework, assumes that the contribution of each task or instance to the meta-learner is equal. Hence, it fails to address the domain shift between base and novel…

We introduce MacroBench, a code-first benchmark that evaluates whether LLMs can synthesize reusable browser-automation programs (macros) from natural-language goals by reading HTML/DOM and emitting Selenium. MacroBench instantiates seven…

Delivering Rich User eXperience (RUX) with the current explosion of smartphone as real ubiquitous computing device requires adaptive application architecture. Rich Mobile Application (RMA) is likely the candidate architecture for future…

Front-end engineering involves a complex workflow where engineers conceptualize designs, translate them into code, and iteratively refine the implementation. While recent benchmarks primarily focus on converting visual designs to code, we…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in automated front-end engineering, e.g., generating UI code from visual designs. However, existing front-end UI code generation benchmarks have the…

A common challenge in personalized user preference prediction is the cold-start problem. Due to the lack of user-item interactions, directly learning from the new users' log data causes serious over-fitting problem. Recently, many existing…

Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on library-style repositories, leaving mobile application development largely unexplored despite its…

Interest in deploying Deep Neural Network (DNN) inference on edge devices has resulted in an explosion of the number and types of hardware platforms to use. While the high-level programming interface, such as TensorFlow, can be readily…

Large language models (LLMs) have opened new opportunities for automated mobile app exploration, an important and challenging problem that used to suffer from the difficulty of generating meaningful UI interactions. However, existing…

Web scraping is a powerful technique that extracts data from websites, enabling automated data collection, enhancing data analysis capabilities, and minimizing manual data entry efforts. Existing methods, wrappers-based methods suffer from…

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…