相关论文: A11y-Compressor: A Framework for Enhancing the Eff…

Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at each iteration step. However, these screenshots exhibit highly…

The research focus of GUI agents is shifting from text-dependent to pure-vision-based approaches, which, though promising, prioritize comprehensive pre-training data collection while neglecting contextual modeling challenges. We probe the…

The quadratic complexity of self-attention constrains Large Language Models (LLMs) in processing long contexts, a capability essential for many advanced applications. Context compression aims to alleviate this computational bottleneck while…

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result…

Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or…

Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches…

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

While Large Language Model (LLM) agents show great potential for automated UI navigation such as automated UI testing and AI assistants, their efficiency has been largely overlooked. Our motivating study reveals that inefficient UI…

Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents where lengthy inputs incur high computational costs and…

As graph-structured data grow increasingly large, evaluating their robustness under adversarial attacks becomes computationally expensive and difficult to scale. To address this challenge, we propose to compress graphs into compact…

Retrieval-Augmented Generation (RAG) helps LLMs stay accurate, but feeding long documents into a prompt makes the model slow and expensive. This has motivated context compression, ranging from token pruning and summarization to…

This paper introduces the concept of abstracted model reduction: a framework to improve the tractability of structure-preserving methods for the complexity reduction of interconnected system models. To effectively reduce high-order,…

Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for closed-set decision tasks such as routing, shortlisting, gating,…

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication…

Graphical User Interface (GUI) agents have made significant progress in automating digital tasks through the utilization of computer vision and language models. Nevertheless, existing agent systems encounter notable limitations. Firstly,…

In this paper, we develop a framework to obtain graph abstractions for decision-making by an agent where the abstractions emerge as a function of the agent's limited computational resources. We discuss the connection of the proposed…

The proliferation of cloud-native architectures, characterized by microservices and dynamic orchestration, has rendered modern IT infrastructures exceedingly complex and volatile. This complexity generates overwhelming volumes of…

The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. In spite of the impressive success made by transformers in a variety of vision tasks, it still suffers from heavy…

We propose novel compression algorithms for time-varying channel state information (CSI) in wireless communications. The proposed scheme combines (lossy) vector quantisation and (lossless) compression. First, the new vector quantisation…

Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur substantially higher computational overhead than traditional…