Previous work on long-form audio generation using global-view diffusion or iterative generation demands significant training or inference costs. While recent advancements in multi-view joint diffusion for panoramic generation provide an efficient option, they struggle with spectrum generation with severe overlap distortions and high cross-view consistency costs. We initially explore this phenomenon through the connectivity inheritance of latent maps and uncover that averaging operations excessively smooth the high-frequency components of the latent map. To address these issues, we propose Swap Forward (SaFa), a frame-level latent swap framework that synchronizes multiple diffusions to produce a globally coherent long audio with more spectrum details in a forward-only manner. At its core, the bidirectional Self-Loop Latent Swap is applied between adjacent views, leveraging stepwise diffusion trajectory to adaptively enhance high-frequency components without disrupting low-frequency components. Furthermore, to ensure cross-view consistency, the unidirectional Reference-Guided Latent Swap is applied between the reference and the non-overlap regions of each subview during the early stages, providing centralized trajectory guidance. Quantitative and qualitative experiments demonstrate that SaFa significantly outperforms existing joint diffusion methods and even training-based long audio generation models. Moreover, we find that it also adapts well to panoramic generation, achieving comparable state-of-the-art performance with greater efficiency and model generalizability. Project page is available at https://swapforward.github.io/.

Embodied manipulation is a fundamental ability in the realm of embodied artificial intelligence. Although current embodied manipulation models show certain generalizations in specific settings, they struggle in new environments and tasks due to the complexity and diversity of real-world scenarios. The traditional end-to-end data collection and training manner leads to significant data demands. Decomposing end-to-end tasks into atomic skills helps reduce data requirements and improves the task success rate. However, existing methods are limited by predefined skill sets that cannot be dynamically updated. To address the issue, we introduce a three-wheeled data-driven method to build an atomic skill library. We divide tasks into subtasks using the Vision-Language-Planning (VLP). Then, atomic skill definitions are formed by abstracting the subtasks. Finally, an atomic skill library is constructed via data collection and Vision-Language-Action (VLA) fine-tuning. As the atomic skill library expands dynamically with the three-wheel update strategy, the range of tasks it can cover grows naturally. In this way, our method shifts focus from end-to-end tasks to atomic skills, significantly reducing data costs while maintaining high performance and enabling efficient adaptation to new tasks. Extensive experiments in real-world settings demonstrate the effectiveness and efficiency of our approach.

Respiratory rate (RR) is a critical health indicator often monitored under inconvenient scenarios, limiting its practicality for continuous monitoring. Photoplethysmography (PPG) sensors, increasingly integrated into wearable devices, offer a chance to continuously estimate RR in a portable manner. In this paper, we propose RespDiff, an end-to-end multi-scale RNN diffusion model for respiratory waveform estimation from PPG signals. RespDiff does not require hand-crafted features or the exclusion of low-quality signal segments, making it suitable for real-world scenarios. The model employs multi-scale encoders, to extract features at different resolutions, and a bidirectional RNN to process PPG signals and extract respiratory waveform. Additionally, a spectral loss term is introduced to optimize the model further. Experiments conducted on the BIDMC dataset demonstrate that RespDiff outperforms notable previous works, achieving a mean absolute error (MAE) of 1.18 bpm for RR estimation while others range from 1.66 to 2.15 bpm, showing its potential for robust and accurate respiratory monitoring in real-world applications.

In recent years, diffusion-based text-to-music (TTM) generation has gained prominence, offering a novel approach to synthesizing musical content from textual descriptions. Achieving high accuracy and diversity in this generation process requires extensive, high-quality data, which often constitutes only a fraction of available datasets. Within open-source datasets, the prevalence of issues like mislabeling, weak labeling, unlabeled data, and low-quality music waveform significantly hampers the development of music generation models. To overcome these challenges, we introduce a novel quality-aware masked diffusion transformer (QA-MDT) approach that enables generative models to discern the quality of input music waveform during training. Building on the unique properties of musical signals, we have adapted and implemented a MDT model for TTM task, while further unveiling its distinct capacity for quality control. Moreover, we address the issue of low-quality captions with a caption refinement data processing approach. Our demo page is shown in https://qa-mdt.github.io/.

With the increasing importance of machine learning, the privacy and security of training data have become critical. Federated learning, which stores data in distributed nodes and shares only model parameters, has gained significant attention for addressing this concern. However, a challenge arises in federated learning due to the Byzantine Attack Problem, where malicious local models can compromise the global model's performance during aggregation. This article proposes the Blockchain-based Byzantine-Robust Federated Learning (BRLF) model that combines federated learning with blockchain technology. This integration enables traceability of malicious models and provides incentives for locally trained clients. Our approach involves selecting the aggregation node based on Pearson's correlation coefficient, and we perform spectral clustering and calculate the average gradient within each cluster, validating its accuracy using local dataset of the aggregation nodes. Experimental results on public datasets demonstrate the superior byzantine robustness of our secure aggregation algorithm compared to other baseline byzantine robust aggregation methods, and proved our proposed model effectiveness in addressing the resource consumption problem.

Automated machine learning (AutoML) seeks to build ML models with minimal human effort. While considerable research has been conducted in the area of AutoML in general, aiming to take humans out of the loop when building artificial intelligence (AI) applications, scant literature has focused on how AutoML works well in open-environment scenarios such as the process of training and updating large models, industrial supply chains or the industrial metaverse, where people often face open-loop problems during the search process: they must continuously collect data, update data and models, satisfy the requirements of the development and deployment environment, support massive devices, modify evaluation metrics, etc. Addressing the open-environment issue with pure data-driven approaches requires considerable data, computing resources, and effort from dedicated data engineers, making current AutoML systems and platforms inefficient and computationally intractable. Human-computer interaction is a practical and feasible way to tackle the problem of open-environment AI. In this paper, we introduce OmniForce, a human-centered AutoML (HAML) system that yields both human-assisted ML and ML-assisted human techniques, to put an AutoML system into practice and build adaptive AI in open-environment scenarios. Specifically, we present OmniForce in terms of ML version management; pipeline-driven development and deployment collaborations; a flexible search strategy framework; and widely provisioned and crowdsourced application algorithms, including large models. Furthermore, the (large) models constructed by OmniForce can be automatically turned into remote services in a few minutes; this process is dubbed model as a service (MaaS). Experimental results obtained in multiple search spaces and real-world use cases demonstrate the efficacy and efficiency of OmniForce.

Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation. As an essential component of the architecture, graph pooling is indispensable for obtaining a holistic graph-level representation of the whole graph. Although a great variety of methods have been proposed in this promising and fast-developing research field, to the best of our knowledge, little effort has been made to systematically summarize these works. To set the stage for the development of future works, in this paper, we attempt to fill this gap by providing a broad review of recent methods for graph pooling. Specifically, 1) we first propose a taxonomy of existing graph pooling methods with a mathematical summary for each category; 2) then, we provide an overview of the libraries related to graph pooling, including the commonly used datasets, model architectures for downstream tasks, and open-source implementations; 3) next, we further outline the applications that incorporate the idea of graph pooling in a variety of domains; 4) finally, we discuss certain critical challenges facing current studies and share our insights on future potential directions for research on the improvement of graph pooling.

Higher-Order Influence Functions (HOIFs) provide a unified theory for constructing rate-optimal estimators for a large class of low-dimensional (smooth) statistical functionals/parameters (and sometimes even infinite-dimensional functions) that arise in substantive fields including epidemiology, economics, and the social sciences. Since the introduction of HOIFs by Robins et al. (2008), they have been viewed mostly as a theoretical benchmark rather than a useful tool for statistical practice. Works aimed to flip the script are scant, but a few recent papers Liu et al. (2017, 2021b) make some partial progress. In this paper, we take a fresh attempt at achieving this goal by constructing new, numerically stable HOIF estimators (or sHOIF estimators for short with ``s'' standing for ``stable'') with provable statistical, numerical, and computational guarantees. This new class of sHOIF estimators (up to the 2nd order) was foreshadowed in synthetic experiments conducted by Liu et al. (2020a).

With the growing utility of today's conversational virtual assistants, the importance of user motivation in human-AI interaction is becoming more obvious. However, previous studies in this and related fields, such as human-computer interaction and human-robot interaction, scarcely discussed intrinsic motivation and its affecting factors. Those studies either treated motivation as an inseparable concept or focused on non-intrinsic motivation. The current study aims to cover intrinsic motivation by taking an affective-engineering approach. A novel motivation model is proposed, in which intrinsic motivation is affected by two factors that derive from user interactions with virtual assistants: expectation of capability and uncertainty. Experiments are conducted where these two factors are manipulated by making participants believe they are interacting with the smart speaker "Amazon Echo". Intrinsic motivation is measured both by using questionnaires and by covertly monitoring a five-minute free-choice period in the experimenter's absence, during which the participants could decide for themselves whether to interact with the virtual assistants. Results of the first experiment showed that high expectation engenders more intrinsically motivated interaction compared with low expectation. The results also suggested suppressive effects by uncertainty on intrinsic motivation, though we had not hypothesized before experiments. We then revised our hypothetical model of action selection accordingly and conducted a verification experiment of uncertainty's effects. Results of the verification experiment showed that reducing uncertainty encourages more interactions and causes the motivation behind these interactions to shift from non-intrinsic to intrinsic.

Non-stationarity appears in many online applications such as web search and advertising. In this paper, we study the online learning to rank problem in a non-stationary environment where user preferences change abruptly at an unknown moment in time. We consider the problem of identifying the K most attractive items and propose cascading non-stationary bandits, an online learning variant of the cascading model, where a user browses a ranked list from top to bottom and clicks on the first attractive item. We propose two algorithms for solving this non-stationary problem: CascadeDUCB and CascadeSWUCB. We analyze their performance and derive gap-dependent upper bounds on the n-step regret of these algorithms. We also establish a lower bound on the regret for cascading non-stationary bandits and show that both algorithms match the lower bound up to a logarithmic factor. Finally, we evaluate their performance on a real-world web search click dataset.