Meta-reasoning Using Attention Maps and Its Applications in Cloud Robotics Adrian Lendinez 1, Renxi Qiu 1, Lanfranco Zanzi 2 and Dayou Li 1, Abstract -- Meta-reasoning, a branch of AI, focuses on reasoning about reasons. It has the potential to enhance robots' decision-making processes in unexpected situations. However, the concept has largely been confined to theoretical discussions and case-by-case investigations, lacking general and practical solutions when the V alue of Computation (V oC) is undefined, which is common in unexpected situations. In this work, we propose a revised meta-reasoning framework that significantly improves the scalability of the original approach in unexpected situations. This is achieved by incorporating semantic attention maps and unsupervised "attention" updates into the meta-reasoning processes. T o accommodate environmental dynamics, "lines of thought" are used to bridge context-specific objects with abstracted attentions, while meta-information is monitored and controlled at the meta-level for effective reasoning. The practicality of the proposed approach is demonstrated through cloud robots deployed in real-world scenarios, showing improved performance and robustness. I NTRODUCTION Significant progress has been made in probabilistic robotics to improve the adaptability and robustness of robot operations [1]. By integrating probabilistic models and statistical methods into perception and decision-making processes, robots can address structured uncertainty and randomness. However, to remain robust in unexpected situations, autonomous systems must also manage their reasoning processes, such as effectively handling uncertainties at the ground level and adapting objects at the conceptual level. This capability, known as meta-reasoning, facilitates reasoning about reasons [2].

In this paper, we present a global-to-local task-aware fault detection and identification algorithm to detect failures in a multi-spacecraft system performing a collaborative inspection (referred to as global) task. The inspection task is encoded as a cost functional $\costH$ that informs global (task allocation and assignment) and local (agent-level) decision-making. The metric $\costH$ is a function of the inspection sensor model, and the agent full-pose. We use the cost functional $\costH$ to design a metric that compares the expected and actual performance to detect the faulty agent using a threshold. We use higher-order cost gradients $\costH$ to derive a new metric to identify the type of fault, including task-specific sensor fault, an agent-level actuator, and sensor faults. Furthermore, we propose an approach to design adaptive thresholds for each fault mentioned above to incorporate the time dependence of the inspection task. We demonstrate the efficacy of the proposed method empirically, by simulating and detecting faults (such as inspection sensor faults, actuators, and sensor faults) in a low-Earth orbit collaborative spacecraft inspection task using the metrics and the threshold designed using the global task cost $\costH$.

Evaluating the quality of slide-based multimedia instruction is challenging. Existing methods like manual assessment, reference-based metrics, and large language model evaluators face limitations in scalability, context capture, or bias. In this paper, we introduce LecEval, an automated metric grounded in Mayer's Cognitive Theory of Multimedia Learning, to evaluate multimodal knowledge acquisition in slide-based learning. LecEval assesses effectiveness using four rubrics: Content Relevance (CR), Expressive Clarity (EC), Logical Structure (LS), and Audience Engagement (AE). We curate a large-scale dataset of over 2,000 slides from more than 50 online course videos, annotated with fine-grained human ratings across these rubrics. A model trained on this dataset demonstrates superior accuracy and adaptability compared to existing metrics, bridging the gap between automated and human assessments. We release our dataset and toolkits at https://github.com/JoylimJY/LecEval.

Autonomous robots must operate in diverse environments and handle multiple tasks despite uncertainties. This creates challenges in designing software architectures and task decision-making algorithms, as different contexts may require distinct task logic and architectural configurations. To address this, robotic systems can be designed as self-adaptive systems capable of adapting their task execution and software architecture at runtime based on their context.This paper introduces ROSA, a novel knowledge-based framework for RObot Self-Adaptation, which enables task-and-architecture co-adaptation (TACA) in robotic systems. ROSA achieves this by providing a knowledge model that captures all application-specific knowledge required for adaptation and by reasoning over this knowledge at runtime to determine when and how adaptation should occur. In addition to a conceptual framework, this work provides an open-source ROS 2-based reference implementation of ROSA and evaluates its feasibility and performance in an underwater robotics application. Experimental results highlight ROSA's advantages in reusability and development effort for designing self-adaptive robotic systems.

Large Vision Language Models have demonstrated impressive versatile capabilities through extensive multimodal pre-training, but face significant limitations when incorporating specialized knowledge domains beyond their training distribution. These models struggle with a fundamental dilemma: direct adaptation approaches that inject domain-specific knowledge often trigger catastrophic forgetting of foundational visual-linguistic abilities. We introduce Structured Dialogue Fine-Tuning (SDFT), an effective approach that effectively injects domain-specific knowledge while minimizing catastrophic forgetting. Drawing inspiration from supervised fine-tuning in LLMs and subject-driven personalization in text-to-image diffusion models, our method employs a three-phase dialogue structure: Foundation Preservation reinforces pre-trained visual-linguistic alignment through caption tasks; Contrastive Disambiguation introduces carefully designed counterfactual examples to maintain semantic boundaries; and Knowledge Specialization embeds specialized information through chain-of-thought reasoning. Experimental results across multiple domains confirm SDFT's effectiveness in balancing specialized knowledge acquisition with general capability retention. Our key contributions include a data-centric dialogue template that balances foundational alignment with targeted knowledge integration, a weighted multi-turn supervision framework, and comprehensive evaluation across diverse knowledge types.

The development of Internet technology has led to an increased prevalence of misinformation, causing severe negative effects across diverse domains. To mitigate this challenge, Misinformation Detection (MD), aiming to detect online misinformation automatically, emerges as a rapidly growing research topic in the community. In this paper, we propose a novel plug-and-play augmentation method for the MD task, namely Misinformation Detection with Potential Commonsense Conflict (MD-PCC). We take inspiration from the prior studies indicating that fake articles are more likely to involve commonsense conflict. Accordingly, we construct commonsense expressions for articles, serving to express potential commonsense conflicts inferred by the difference between extracted commonsense triplet and golden ones inferred by the well-established commonsense reasoning tool COMET. These expressions are then specified for each article as augmentation. Any specific MD methods can be then trained on those commonsense-augmented articles. Besides, we also collect a novel commonsense-oriented dataset named CoMis, whose all fake articles are caused by commonsense conflict. We integrate MD-PCC with various existing MD backbones and compare them across both 4 public benchmark datasets and CoMis. Empirical results demonstrate that MD-PCC can consistently outperform the existing MD baselines.

Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual prototypes, hindered by shallow OS integration, fragile screenshot-based interaction, and disruptive execution. We present UFO2, a multiagent AgentOS for Windows desktops that elevates CUAs into practical, system-level automation. UFO2 features a centralized HostAgent for task decomposition and coordination, alongside a collection of application-specialized AppAgent equipped with native APIs, domain-specific knowledge, and a unified GUI--API action layer. This architecture enables robust task execution while preserving modularity and extensibility. A hybrid control detection pipeline fuses Windows UI Automation (UIA) with vision-based parsing to support diverse interface styles. Runtime efficiency is further enhanced through speculative multi-action planning, reducing per-step LLM overhead. Finally, a Picture-in-Picture (PiP) interface enables automation within an isolated virtual desktop, allowing agents and users to operate concurrently without interference. We evaluate UFO2 across over 20 real-world Windows applications, demonstrating substantial improvements in robustness and execution accuracy over prior CUAs. Our results show that deep OS integration unlocks a scalable path toward reliable, user-aligned desktop automation.

The significant computational demands of pretrained language models (PLMs), which often require dedicated hardware, present a substantial challenge in serving them efficiently, especially in multi-tenant environments. To address this, we introduce HMI, a Hierarchical knowledge management-based Multi-tenant Inference system, designed to manage tenants with distinct PLMs resource-efficiently. Our approach is three-fold: Firstly, we categorize PLM knowledge into general, domain-specific, and task-specific. Leveraging insights on knowledge acquisition across different model layers, we construct hierarchical PLMs (hPLMs) by extracting and storing knowledge at different levels, significantly reducing GPU memory usage per tenant. Secondly, we establish hierarchical knowledge management for hPLMs generated by various tenants in HMI. We manage domain-specific knowledge with acceptable storage increases by constructing and updating domain-specific knowledge trees based on frequency. We manage task-specific knowledge within limited GPU memory through parameter swapping. Finally, we propose system optimizations to enhance resource utilization and inference throughput. These include fine-grained pipelining via hierarchical knowledge prefetching to overlap CPU and I/O operations with GPU computations, and optimizing parallel implementations with batched matrix multiplications. Our experimental results demonstrate that the proposed HMI can efficiently serve up to 10,000 hPLMs (hBERTs and hGPTs) on a single GPU, with only a negligible compromise in accuracy.

Unresolved questions about how autonomous vehicles (AVs) should meet the informational needs of riders hinder real-world adoption. Complicating our ability to satisfy rider needs is that different people, goals, and driving contexts have different criteria for what constitutes interaction success. Unfortunately, most human-AV research and design today treats all people and situations uniformly. It is crucial to understand how an AV should communicate to meet rider needs, and how communications should change when the human-AV complex system changes. I argue that understanding the relationships between different aspects of the human-AV system can help us build improved and adaptable AV communications. I support this argument using three empirical studies. First, I identify optimal communication strategies that enhance driving performance, confidence, and trust for learning in extreme driving environments. Findings highlight the need for task-sensitive, modality-appropriate communications tuned to learner cognitive limits and goals. Next, I highlight the consequences of deploying faulty communication systems and demonstrate the need for context-sensitive communications. Third, I use machine learning (ML) to illuminate personal factors predicting trust in AVs, emphasizing the importance of tailoring designs to individual traits and concerns. Together, this dissertation supports the necessity of transparent, adaptable, and personalized AV systems that cater to individual needs, goals, and contextual demands. By considering the complex system within which human-AV interactions occur, we can deliver valuable insights for designers, researchers, and policymakers. This dissertation also provides a concrete domain to study theories of human-machine joint action and situational awareness, and can be used to guide future human-AI interaction research. [shortened for arxiv]

Tabular data, structured as rows and columns, is among the most prevalent data types in machine learning classification and regression applications. Models for learning from tabular data have continuously evolved, with Deep Neural Networks (DNNs) recently demonstrating promising results through their capability of representation learning. In this survey, we systematically introduce the field of tabular representation learning, covering the background, challenges, and benchmarks, along with the pros and cons of using DNNs. We organize existing methods into three main categories according to their generalization capabilities: specialized, transferable, and general models. Specialized models focus on tasks where training and evaluation occur within the same data distribution. We introduce a hierarchical taxonomy for specialized models based on the key aspects of tabular data -- features, samples, and objectives -- and delve into detailed strategies for obtaining high-quality feature- and sample-level representations. Transferable models are pre-trained on one or more datasets and subsequently fine-tuned on downstream tasks, leveraging knowledge acquired from homogeneous or heterogeneous sources, or even cross-modalities such as vision and language. General models, also known as tabular foundation models, extend this concept further, allowing direct application to downstream tasks without fine-tuning. We group these general models based on the strategies used to adapt across heterogeneous datasets. Additionally, we explore ensemble methods, which integrate the strengths of multiple tabular models. Finally, we discuss representative extensions of tabular learning, including open-environment tabular machine learning, multimodal learning with tabular data, and tabular understanding. More information can be found in the following repository: https://github.com/LAMDA-Tabular/Tabular-Survey.