相关论文: UI-JEPA: Towards Active Perception of User Intent …

Software development is shifting from traditional programming to AI-integrated applications that leverage generative AI and large language models (LLMs) during runtime. However, integrating LLMs remains complex, requiring developers to…

Recent advancements in multimodal large language models (MLLMs) have been noteworthy, yet, these general-domain MLLMs often fall short in their ability to comprehend and interact effectively with user interface (UI) screens. In this paper,…

User intent detection plays a critical role in question-answering and dialog systems. Most previous works treat intent detection as a classification problem where utterances are labeled with predefined intents. However, it is…

Discovering new intents is of great significance to establishing Bootstrapped Task-Oriented Dialogue System. Most existing methods either lack the ability to transfer prior knowledge in the known intent data or fall into the dilemma of…

Traditional control and planning for robotic manipulation heavily rely on precise physical models and predefined action sequences. While effective in structured environments, such approaches often fail in real-world scenarios due to…

In this paper, we provide an extensive analysis of multi-label intent classification using Large Language Models (LLMs) that are open-source, publicly available, and can be run in consumer hardware. We use the MultiWOZ 2.1 dataset, a…

Detecting user interface (UI) controls from software screenshots is a critical task for automated testing, accessibility, and software analytics, yet it remains challenging due to visual ambiguities, design variability, and the lack of…

Profile-based intent detection and slot filling are important tasks aimed at reducing the ambiguity in user utterances by leveraging user-specific supporting profile information. However, research in these two tasks has not been extensively…

For machines to effectively assist humans in challenging visual search tasks, they must differentiate whether a human is simply glancing into a scene (navigational intent) or searching for a target object (informational intent). Previous…

The emergence of advanced multimodal large language models (MLLMs) has significantly enhanced AI assistants' ability to process complex information across modalities. Recently, egocentric videos, by directly capturing user focus, actions,…

Large Language Models (LLMs) are increasingly integrated into everyday applications, but their prevalent cloud-based deployment raises growing concerns around data privacy and long-term sustainability. Running LLMs locally on mobile and…

To improve the accessibility of smart devices and to simplify their usage, building models which understand user interfaces (UIs) and assist users to complete their tasks is critical. However, unique challenges are proposed by UI-specific…

We introduce UIXPOSE, a source-code-agnostic framework that operates on both compiled and open-source apps. This framework applies Intention Behaviour Alignment (IBA) to mobile malware analysis, aligning UI-inferred intent with runtime…

Despite significant progress in robotic systems for operation within human-centric environments, existing models still heavily rely on explicit human commands to identify and manipulate specific objects. This limits their effectiveness in…

Intent recognition (IR) for speech commands is essential for artificial intelligence (AI) assistant systems; however, most existing approaches are limited to short commands and are predominantly developed for English. This paper addresses…

Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitable vulnerabilities…

Identifying user intent from mobile UI operation trajectories is critical for advancing UI understanding and enabling task automation agents. While Multimodal Large Language Models (MLLMs) excel at video understanding tasks, their real-time…

Enhancing Language Models' (LMs) ability to understand purchase intentions in E-commerce scenarios is crucial for their effective assistance in various downstream tasks. However, previous approaches that distill intentions from LMs often…

In natural human-to-human communication, multimodal user input is typically used to supplement explicit and complement implicit voice commands, with casualness allowing for flexible input modality combinations and tolerance for imprecise…

Token Communication (TokenCom) is a new paradigm, motivated by the recent success of Large AI Models (LAMs) and Multimodal Large Language Models (MLLMs), where tokens serve as unified units of communication and computation, enabling…