Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions

Clarification questions are an essential dialogue tool to signal misunderstanding, ambiguities, and under-specification in language use. While humans are able to resolve uncertainty by asking questions since childhood, modern dialogue systems struggle to generate effective questions. To make progress in this direction, in this work we take a collaborative dialogue task as a testbed and study how model uncertainty relates to human uncertainty -- an as yet under-explored problem. We show that model uncertainty does not mirror human clarification-seeking behavior, which suggests that using human clarification questions as supervision for deciding when to ask may not be the most effective way to resolve model uncertainty. To address this issue, we propose an approach to generating clarification questions based on model uncertainty estimation, compare it to several alternatives, and show that it leads to significant improvements in terms of task success. Our findings highlight the importance of equipping dialogue systems with the ability to assess their own uncertainty and exploit in interaction.

KGroot: Enhancing Root Cause Analysis through Knowledge Graphs and Graph Convolutional Neural Networks

Fault localization is challenging in online micro-service due to the wide variety of monitoring data volume, types, events and complex interdependencies in service and components. Faults events in services are propagative and can trigger a cascade of alerts in a short period of time. In the industry, fault localization is typically conducted manually by experienced personnel. This reliance on experience is unreliable and lacks automation. Different modules present information barriers during manual localization, making it difficult to quickly align during urgent faults. This inefficiency lags stability assurance to minimize fault detection and repair time. Though actionable methods aimed to automatic the process, the accuracy and efficiency are less than satisfactory. The precision of fault localization results is of paramount importance as it underpins engineers trust in the diagnostic conclusions, which are derived from multiple perspectives and offer comprehensive insights. Therefore, a more reliable method is required to automatically identify the associative relationships among fault events and propagation path. To achieve this, KGroot uses event knowledge and the correlation between events to perform root cause reasoning by integrating knowledge graphs and GCNs for RCA. FEKG is built based on historical data, an online graph is constructed in real-time when a failure event occurs, and the similarity between each knowledge graph and online graph is compared using GCNs to pinpoint the fault type through a ranking strategy. Comprehensive experiments demonstrate KGroot can locate the root cause with accuracy of 93.5% top 3 potential causes in second-level. This performance matches the level of real-time fault diagnosis in the industrial environment and significantly surpasses state-of-the-art baselines in RCA in terms of effectiveness and efficiency.

A novel hybrid time-varying graph neural network for traffic flow forecasting

Real-time and accurate traffic flow prediction is the foundation for ensuring the efficient operation of intelligent transportation systems.In existing traffic flow prediction methods based on graph neural networks (GNNs), pre-defined graphs were usually used to describe the spatial correlations of different traffic nodes in urban road networks. However, the ability of pre-defined graphs used to describe spatial correlation was limited by prior knowledge and graph generation methods. Although time-varying graphs based on data-driven learning can partially overcome the drawbacks of pre-defined graphs, the learning ability of existing adaptive graphs was limited. For example, time-varying graphs cannot adequately capture the inherent spatial correlations in traffic flow data.In order to solve these problems, we have proposed a hybrid time-varying graph neural network (HTVGNN) for traffic flow prediction.

DACR: Distribution-Augmented Contrastive Reconstruction for Time-Series Anomaly Detection

Anomaly detection in time-series data is crucial for identifying faults, failures, threats, and outliers across a range of applications. Recently, deep learning techniques have been applied to this topic, but they often struggle in real-world scenarios that are complex and highly dynamic, e.g., the normal data may consist of multiple distributions, and various types of anomalies may differ from the normal data to different degrees. In this work, to tackle these challenges, we propose Distribution-Augmented Contrastive Reconstruction (DACR). DACR generates extra data disjoint from the normal data distribution to compress the normal data's representation space, and enhances the feature extractor through contrastive learning to better capture the intrinsic semantics from time-series data. Furthermore, DACR employs an attention mechanism to model the semantic dependencies among multivariate time-series features, thereby achieving more robust reconstruction for anomaly detection. Extensive experiments conducted on nine benchmark datasets in various anomaly detection scenarios demonstrate the effectiveness of DACR in achieving new state-of-the-art time-series anomaly detection.

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

We present Universal Manipulation Interface (UMI) -- a data collection and policy learning framework that allows direct skill transfer from in-the-wild human demonstrations to deployable robot policies. UMI employs hand-held grippers coupled with careful interface design to enable portable, low-cost, and information-rich data collection for challenging bimanual and dynamic manipulation demonstrations. To facilitate deployable policy learning, UMI incorporates a carefully designed policy interface with inference-time latency matching and a relative-trajectory action representation. The resulting learned policies are hardware-agnostic and deployable across multiple robot platforms. Equipped with these features, UMI framework unlocks new robot manipulation capabilities, allowing zero-shot generalizable dynamic, bimanual, precise, and long-horizon behaviors, by only changing the training data for each task. We demonstrate UMI's versatility and efficacy with comprehensive real-world experiments, where policies learned via UMI zero-shot generalize to novel environments and objects when trained on diverse human demonstrations. UMI's hardware and software system is open-sourced at https://umi-gripper.github.io.

Generalizing across Temporal Domains with Koopman Operators

In the field of domain generalization, the task of constructing a predictive model capable of generalizing to a target domain without access to target data remains challenging. This problem becomes further complicated when considering evolving dynamics between domains. While various approaches have been proposed to address this issue, a comprehensive understanding of the underlying generalization theory is still lacking. In this study, we contribute novel theoretic results that aligning conditional distribution leads to the reduction of generalization bounds. Our analysis serves as a key motivation for solving the Temporal Domain Generalization (TDG) problem through the application of Koopman Neural Operators, resulting in Temporal Koopman Networks (TKNets). By employing Koopman Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains. Through empirical evaluations conducted on synthetic and real-world datasets, we validate the effectiveness of our proposed approach.

AI Hospital: Interactive Evaluation and Collaboration of LLMs as Intern Doctors for Clinical Diagnosis

The incorporation of Large Language Models (LLMs) in healthcare marks a significant advancement. However, the application has predominantly been limited to discriminative and question-answering tasks, which does not fully leverage their interactive potential. To address this limitation, our paper presents AI Hospital, a framework designed to build a real-time interactive diagnosis environment. To simulate the procedure, we collect high-quality medical records to create patient, examiner, and medical director agents. AI Hospital is then utilized for the interactive evaluation and collaboration of LLMs. Initially, we create a Multi-View Medical Evaluation (MVME) benchmark where various LLMs serve as intern doctors for interactive diagnosis. Subsequently, to improve diagnostic accuracy, we introduce a collaborative mechanism that involves iterative discussions and a dispute resolution process under the supervision of the medical director. In our experiments, we validate the reliability of AI Hospital. The results not only explore the feasibility of apply LLMs in clinical consultation but also confirm the effectiveness of the dispute resolution focused collaboration method.

Fast Transition-Aware Reconfiguration of Liquid Crystal-based RISs

Liquid crystal (LC) technology offers a cost-effective, scalable, energy-efficient, and continuous phase tunable realization of extremely large reconfigurable intelligent surfaces (RISs). However, LC response time to achieve a desired differential phase is significantly higher compared to competing silicon-based technologies (RF switches, PIN diodes, etc). The slow response time can be the performance bottleneck for applications where frequent reconfiguration of the RIS (e.g., to serve different users) is needed. In this paper, we develop an RIS phase-shift design that is aware of the transition behavior and aims to minimize the time to switch among multiple RIS configurations each serving a mobile user in a time-division multiple-access (TDMA) protocol. Our simulation results confirm that the proposed algorithm significantly reduces the time required for the users to achieve a threshold signal quality. This leads to a considerable improvement in the achievable throughput for applications, where the length of the TDMA time intervals is comparable with the RIS reconfiguration time.

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models

The permanence of online content combined with the enhanced authorship identification techniques calls for stronger computational methods to protect the identity and privacy of online authorship when needed, e.g., blind reviews for scientific papers, anonymous online reviews, or anonymous interactions in the mental health forums. In this paper, we propose an unsupervised inference-time approach to authorship obfuscation to address the unique challenges of authorship obfuscation: lack of supervision data for diverse authorship and domains, and the need for a sufficient level of revision beyond simple paraphrasing to obfuscate the authorship, all the while preserving the original content and fluency. We introduce JAMDEC, a user-controlled, inference-time algorithm for authorship obfuscation that can be in principle applied to any text and authorship. Our approach builds on small language models such as GPT2-XL in order to help avoid disclosing the original content to proprietary LLM's APIs, while also reducing the performance gap between small and large language models via algorithmic enhancement. The key idea behind our approach is to boost the creative power of smaller language models through constrained decoding, while also allowing for user-specified controls and flexibility. Experimental results demonstrate that our approach based on GPT2-XL outperforms previous state-of-the-art methods based on comparably small models, while performing competitively against GPT3.5 175B, a propriety model that is two orders of magnitudes larger.

In-Vivo Hyperspectral Human Brain Image Database for Brain Cancer Detection

The use of hyperspectral imaging for medical applications is becoming more common in recent years. One of the main obstacles that researchers find when developing hyperspectral algorithms for medical applications is the lack of specific, publicly available, and hyperspectral medical data. The work described in this paper was developed within the framework of the European project HELICoiD (HypErspectraL Imaging Cancer Detection), which had as a main goal the application of hyperspectral imaging to the delineation of brain tumors in real-time during neurosurgical operations. In this paper, the methodology followed to generate the first hyperspectral database of in-vivo human brain tissues is presented. Data was acquired employing a customized hyperspectral acquisition system capable of capturing information in the Visual and Near InfraRed (VNIR) range from 400 to 1000 nm. Repeatability was assessed for the cases where two images of the same scene were captured consecutively. The analysis reveals that the system works more efficiently in the spectral range between 450 and 900 nm. A total of 36 hyperspectral images from 22 different patients were obtained. From these data, more than 300 000 spectral signatures were labeled employing a semi-automatic methodology based on the spectral angle mapper algorithm. Four different classes were defined: normal tissue, tumor tissue, blood vessel, and background elements. All the hyperspectral data has been made available in a public repository.