Search

Recently, diffusion models have achieved great success in mono-channel audio generation. However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions. Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models. To the best of our knowledge, this work represents the first attempt to address these issues. We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions even including moving and multiple sources. Beyond text modality, we have also acquired a set of images and rationally paired stereo audios through retrieval to advance multimodal generation. Existing audio generation models tend to generate rather random and indistinct spatial audio. To provide accurate guidance for latent diffusion models, we introduce the SpatialSonic model utilizing spatial-aware encoders and azimuth state matrices to reveal reasonable spatial guidance. By leveraging spatial guidance, our unified model not only achieves the objective of generating immersive and controllable spatial audio from text and image but also enables interactive audio generation during inference. Finally, under fair settings, we conduct subjective and objective evaluations on simulated and real-world data to compare our approach with prevailing methods. The results demonstrate the effectiveness of our method, highlighting its capability to generate spatial audio that adheres to physical rules.

Recent advancements in generic 3D content generation from text prompts have been remarkable by fine-tuning text-to-image diffusion (T2I) models or employing these T2I models as priors to learn a general text-to-3D model. While fine-tuning-based methods ensure great alignment between text and generated views, i.e., semantic consistency, their ability to achieve multi-view consistency is hampered by the absence of 3D constraints, even in limited view. In contrast, prior-based methods focus on regressing 3D shapes with any view that maintains uniformity and coherence across views, i.e., multi-view consistency, but such approaches inevitably compromise visual-textual alignment, leading to a loss of semantic details in the generated objects. To achieve semantic and multi-view consistency simultaneously, we propose SeMv-3D, a novel framework for general text-to-3d generation. Specifically, we propose a Triplane Prior Learner (TPL) that learns triplane priors with 3D spatial features to maintain consistency among different views at the 3D level, e.g., geometry and texture. Moreover, we design a Semantic-aligned View Synthesizer (SVS) that preserves the alignment between 3D spatial features and textual semantics in latent space. In SVS, we devise a simple yet effective batch sampling and rendering strategy that can generate arbitrary views in a single feed-forward inference. Extensive experiments present our SeMv-3D's superiority over state-of-the-art performances with semantic and multi-view consistency in any view. Our code and more visual results are available at https://anonymous.4open.science/r/SeMv-3D-6425.

Everyone aspires to achieve personal goals. However, getting started is often complex and daunting, especially for large projects. AI has the potential to create plans and help jumpstart progress, but it often lacks sufficient personal context to be useful. We introduce JumpStarter, a system that uses AI-powered context curation to create action plans and draft personalized working solutions. JumpStarter assists users by posing questions to elicit relevant context, breaking down goals into manageable steps, and selecting appropriate context to draft working solutions for each step. A technical evaluation indicates that context curation results in plans and working solutions of higher quality. A user study demonstrates that compared to ChatGPT, JumpStarter significantly reduces users' mental load and increases their efficiency in kickstarting personal projects. We discuss the design implications of AI-powered context curation to facilitate the use of generative AI in complex problem-solving.

Recent advancements in large language models have significantly expedited the process of generating front-end code. This allows users to rapidly prototype user interfaces and ideate through code, a process known as exploratory programming. However, existing LLM code-generation tools focus more on technical implementation details rather than finding the right design given a particular problem. We present DynEx, an LLM-based method for design exploration in accelerated exploratory programming. DynEx uses LLMs to guide users through a structured Design Matrix to explore the design space before dynamic iterative implementation. It also introduces a technique to self-invoke generative AI, enabling the creation of a diverse suite of applications. A user study of 10 experts found that DynEx increased design exploration and enabled the creation of more complex and varied prototypes compared to a Claude Artifact baseline. We conclude with a discussion of the implications of design exploration for exploratory programming., Comment: 18 pages, 7 figures

Immunohistochemical (IHC) stains play a vital role in a pathologist's analysis of medical images, providing crucial diagnostic information for various diseases. Virtual staining from hematoxylin and eosin (H&E)-stained whole slide images (WSIs) allows the automatic production of other useful IHC stains without the expensive physical staining process. However, current virtual WSI generation methods based on tile-wise processing often suffer from inconsistencies in content, texture, and color at tile boundaries. These inconsistencies lead to artifacts that compromise image quality and potentially hinder accurate clinical assessment and diagnoses. To address this limitation, we propose a novel consistent WSI synthesis network, CC-WSI-Net, that extends GAN models to produce seamless synthetic whole slide images. Our CC-WSI-Net integrates a content- and color-consistency supervisor, ensuring consistency across tiles and facilitating the generation of seamless synthetic WSIs while ensuring Sox10 immunohistochemistry accuracy in melanocyte detection. We validate our method through extensive image-quality analyses, objective detection assessments, and a subjective survey with pathologists. By generating high-quality synthetic WSIs, our method opens doors for advanced virtual staining techniques with broader applications in research and clinical care.

Generative text-to-image models are disrupting the lives of creative professionals. Specifically, illustrators are threatened by models that claim to extract and reproduce their style. Yet, research on style transfer has rarely focused on their perspectives. We provided four illustrators with a model fine-tuned to their style and conducted semi-structured interviews about the model's successes, limitations, and potential uses. Evaluating their output, artists reported that style transfer successfully copies aesthetic fragments but is limited by content-style disentanglement and lacks the crucial emergent quality of their style. They also deemed the others' copies more successful. Understanding the results of style transfer as "boundary objects," we analyze how they can simultaneously be considered unsuccessful by artists and poised to replace their work by others. We connect our findings to critical HCI frameworks, demonstrating that style transfer, rather than merely a Creativity Support Tool, should also be understood as a supply chain optimization one.

This work considers the numerical computation of ground states of rotating Bose-Einstein condensates (BECs) which can exhibit a multiscale lattice of quantized vortices. This problem involves the minimization of an energy functional on a Riemannian manifold. For this we apply the framework of nonlinear conjugate gradient methods in combination with the paradigm of Sobolev gradients to investigate different metrics. Here we build on previous work that proposed to enhance the convergence of regular Riemannian gradients methods by an adaptively changing metric that is based on the current energy. In this work, we extend this approach to the branch of Riemannian conjugate gradient (CG) methods and investigate the arising schemes numerically. Special attention is given to the selection of the momentum parameter in search direction and how this affects the performance of the resulting schemes. As known from similar applications, we find that the choice of the momentum parameter plays a critical role, with certain parameters reducing the number of iterations required to achieve a specified tolerance by a significant factor. Besides the influence of the momentum parameters, we also investigate how the methods with adaptive metric compare to the corresponding realizations with a standard $H^1_0$-metric. As one of our main findings, the results of the numerical experiments show that the Riemannian CG method with the proposed adaptive metric along with a Polak-Ribi\'ere or Hestenes-Stiefel-type momentum parameter show the best performance and highest robustness compared to the other CG methods that were part of our numerical study.

With the rapid advancement of internet technology, the adaptability of adolescents to online learning has emerged as a focal point of interest within the educational sphere. However, the academic community's efforts to develop predictive models for adolescent online learning adaptability require further refinement and expansion. Utilizing data from the "Chinese Adolescent Online Education Survey" spanning the years 2014 to 2016, this study implements five machine learning algorithms - logistic regression, K-nearest neighbors, random forest, XGBoost, and CatBoost - to analyze the factors influencing adolescent online learning adaptability and to determine the model best suited for prediction. The research reveals that the duration of courses, the financial status of the family, and age are the primary factors affecting students' adaptability in online learning environments. Additionally, age significantly impacts students' adaptive capacities. Among the predictive models, the random forest, XGBoost, and CatBoost algorithms demonstrate superior forecasting capabilities, with the random forest model being particularly adept at capturing the characteristics of students' adaptability.

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal representation. Our MAE includes an encoder and a decoder. A certain proportion of input EEG signals are randomly masked and sent to our MAE. The goal is to recover these masked signals. After this self-supervised pre-training, the encoder is fine-tuned on downstream tasks. We evaluate our MAE on EEGEyeNet gaze estimation task. We find that the MAE is an effective brain signal learner. It also significantly improves learning efficiency. Compared to the model without MAE pre-training, the pre-trained one achieves equal performance with 1/3 the time of training and outperforms it in half the training time. Our study shows that self-supervised learning is a promising research direction for EEG-based applications as other fields (natural language processing, computer vision, robotics, etc.), and thus we expect foundation models to be successful in EEG domain.

This paper advances a novel architectural schema anchored upon the Transformer paradigm and innovatively amalgamates the K-means categorization algorithm to augment the contextual apprehension capabilities of the schema. The transformer model performs well in machine translation tasks due to its parallel computing power and multi-head attention mechanism. However, it may encounter contextual ambiguity or ignore local features when dealing with highly complex language structures. To circumvent this constraint, this exposition incorporates the K-Means algorithm, which is used to stratify the lexis and idioms of the input textual matter, thereby facilitating superior identification and preservation of the local structure and contextual intelligence of the language. The advantage of this combination is that K-Means can automatically discover the topic or concept regions in the text, which may be directly related to translation quality. Consequently, the schema contrived herein enlists K-Means as a preparatory phase antecedent to the Transformer and recalibrates the multi-head attention weights to assist in the discrimination of lexis and idioms bearing analogous semantics or functionalities. This ensures the schema accords heightened regard to the contextual intelligence embodied by these clusters during the training phase, rather than merely focusing on locational intelligence.

Interactive point cloud segmentation has become a pivotal task for understanding 3D scenes, enabling users to guide segmentation models with simple interactions such as clicks, therefore significantly reducing the effort required to tailor models to diverse scenarios and new categories. However, in the realm of interactive segmentation, the meaning of instance diverges from that in instance segmentation, because users might desire to segment instances of both thing and stuff categories that vary greatly in scale. Existing methods have focused on thing categories, neglecting the segmentation of stuff categories and the difficulties arising from scale disparity. To bridge this gap, we propose ClickFormer, an innovative interactive point cloud segmentation model that accurately segments instances of both thing and stuff categories. We propose a query augmentation module to augment click queries by a global query sampling strategy, thus maintaining consistent performance across different instance scales. Additionally, we employ global attention in the query-voxel transformer to mitigate the risk of generating false positives, along with several other network structure improvements to further enhance the model's segmentation performance. Experiments demonstrate that ClickFormer outperforms existing interactive point cloud segmentation methods across both indoor and outdoor datasets, providing more accurate segmentation results with fewer user clicks in an open-world setting., Comment: Accepted by 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems

Large language models (LLMs) are remarkably good at writing code. A particularly valuable case of human-LLM collaboration is code-based UI prototyping, a method for creating interactive prototypes that allows users to view and fully engage with a user interface. We conduct a formative study of GPT Pilot, a leading LLM-generated code-prototyping system, and find that its inflexibility towards change once development has started leads to weaknesses in failure prevention and dynamic planning; it closely resembles the linear workflow of the waterfall model. We introduce DIDUP, a system for code-based UI prototyping that follows an iterative spiral model, which takes changes and iterations that come up during the development process into account. We propose three novel mechanisms for LLM-generated code-prototyping systems: (1) adaptive planning, where plans should be dynamic and reflect changes during implementation, (2) code injection, where the system should write a minimal amount of code and inject it instead of rewriting code so users have a better mental model of the code evolution, and (3) lightweight state management, a simplified version of source control so users can quickly revert to different working states. Together, this enables users to rapidly develop and iterate on prototypes., Comment: 5 pages, 3 figures

Accurate perception of the dynamic environment is a fundamental task for autonomous driving and robot systems. This paper introduces Let Occ Flow, the first self-supervised work for joint 3D occupancy and occupancy flow prediction using only camera inputs, eliminating the need for 3D annotations. Utilizing TPV for unified scene representation and deformable attention layers for feature aggregation, our approach incorporates a novel attention-based temporal fusion module to capture dynamic object dependencies, followed by a 3D refine module for fine-gained volumetric representation. Besides, our method extends differentiable rendering to 3D volumetric flow fields, leveraging zero-shot 2D segmentation and optical flow cues for dynamic decomposition and motion optimization. Extensive experiments on nuScenes and KITTI datasets demonstrate the competitive performance of our approach over prior state-of-the-art methods. Our project page is available at https://eliliu2233.github.io/letoccflow/, Comment: Accepted to CoRL 2024

Panoptic reconstruction is a challenging task in 3D scene understanding. However, most existing methods heavily rely on pre-trained semantic segmentation models and known 3D object bounding boxes for 3D panoptic segmentation, which is not available for in-the-wild scenes. In this paper, we propose a novel zero-shot panoptic reconstruction method from RGB-D images of scenes. For zero-shot segmentation, we leverage open-vocabulary instance segmentation, but it has to face partial labeling and instance association challenges. We tackle both challenges by propagating partial labels with the aid of dense generalized features and building a 3D instance graph for associating 2D instance IDs. Specifically, we exploit partial labels to learn a classifier for generalized semantic features to provide complete labels for scenes with dense distilled features. Moreover, we formulate instance association as a 3D instance graph segmentation problem, allowing us to fully utilize the scene geometry prior and all 2D instance masks to infer global unique pseudo 3D instance ID. Our method outperforms state-of-the-art methods on the indoor dataset ScanNet V2 and the outdoor dataset KITTI-360, demonstrating the effectiveness of our graph segmentation method and reconstruction network.

The emergence of Large Language Models (LLMs) has improved the prospects for robotic tasks. However, existing benchmarks are still limited to single tasks with limited generalization capabilities. In this work, we introduce a comprehensive benchmark and an autonomous learning framework, RoboCoder aimed at enhancing the generalization capabilities of robots in complex environments. Unlike traditional methods that focus on single-task learning, our research emphasizes the development of a general-purpose robotic coding algorithm that enables robots to leverage basic skills to tackle increasingly complex tasks. The newly proposed benchmark consists of 80 manually designed tasks across 7 distinct entities, testing the models' ability to learn from minimal initial mastery. Initial testing revealed that even advanced models like GPT-4 could only achieve a 47% pass rate in three-shot scenarios with humanoid entities. To address these limitations, the RoboCoder framework integrates Large Language Models (LLMs) with a dynamic learning system that uses real-time environmental feedback to continuously update and refine action codes. This adaptive method showed a remarkable improvement, achieving a 36% relative improvement. Our codes will be released.

In this study, we successfully developed two-dimensional paper-based analytical devices using a hybrid technique of injection molding and embossing. This innovative approach involves passive or active delivery of molten wax onto a glass substrate through a sealed chip, facilitating wax stamp creation.

Although visual navigation has been extensively studied using deep reinforcement learning, online learning for real-world robots remains a challenging task. Recent work directly learned from offline dataset to achieve broader generalization in the real-world tasks, which, however, faces the out-of-distribution (OOD) issue and potential robot localization failures in a given map for unseen observation. This significantly drops the success rates and even induces collision. In this paper, we present a self-correcting visual navigation method, SCALE, that can autonomously prevent the robot from the OOD situations without human intervention. Specifically, we develop an image-goal conditioned offline reinforcement learning method based on implicit Q-learning (IQL). When facing OOD observation, our novel localization recovery method generates the potential future trajectories by learning from the navigation affordance, and estimates the future novelty via random network distillation (RND). A tailored cost function searches for the candidates with the least novelty that can lead the robot to the familiar places. We collect offline data and conduct evaluation experiments in three real-world urban scenarios. Experiment results show that SCALE outperforms the previous state-of-the-art methods for open-world navigation with a unique capability of localization recovery, significantly reducing the need for human intervention. Code is available at https://github.com/KubeEdge4Robotics/ScaleNav., Comment: 7 pages, 5 figures, 2024 IEEE International Conference on Robotics and Automation

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through a large community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension) by systematically reviewing 115 papers. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants., Comment: Published as a conference paper at CHI 2024

Emotion is vital to information and message processing, playing a key role in attitude formation. Consequently, creating a mood that evokes an emotional response is essential to any compelling piece of outreach communication. Many nonprofits and charities, despite having established messages, face challenges in creating advocacy campaign videos for social media. It requires significant creative and cognitive efforts to ensure that videos achieve the desired mood across multiple dimensions: script, visuals, and audio. We introduce MoodSmith, an AI-powered system that helps users explore mood possibilities for their message and create advocacy campaigns that are mood-consistent across dimensions. To achieve this, MoodSmith uses emotive language and plotlines for scripts, artistic style and color palette for visuals, and positivity and energy for audio. Our studies show that MoodSmith can effectively achieve a variety of moods, and the produced videos are consistent across media dimensions., Comment: 8 pages, 8 figures

Deploying machine learning in open environments presents the challenge of encountering diverse test inputs that differ significantly from the training data. These out-of-distribution samples may exhibit shifts in local or global features compared to the training distribution. The machine learning (ML) community has responded with a number of methods aimed at distinguishing anomalous inputs from original training data. However, the majority of previous studies have primarily focused on the output layer or penultimate layer of pre-trained deep neural networks. In this paper, we propose a novel framework, Multitesting-based Layer-wise Out-of-Distribution (OOD) Detection (MLOD), to identify distributional shifts in test samples at different levels of features through rigorous multiple testing procedure. Our approach distinguishes itself from existing methods as it does not require modifying the structure or fine-tuning of the pre-trained classifier. Through extensive experiments, we demonstrate that our proposed framework can seamlessly integrate with any existing distance-based inspection method while efficiently utilizing feature extractors of varying depths. Our scheme effectively enhances the performance of out-of-distribution detection when compared to baseline methods. In particular, MLOD-Fisher achieves superior performance in general. When trained using KNN on CIFAR10, MLOD-Fisher significantly lowers the false positive rate (FPR) from 24.09% to 7.47% on average compared to merely utilizing the features of the last layer.

Exploring and mining subtle yet distinctive features between sub-categories with similar appearances is crucial for fine-grained visual categorization (FGVC). However, less effort has been devoted to assessing the quality of extracted visual representations. Intuitively, the network may struggle to capture discriminative features from low-quality samples, which leads to a significant decline in FGVC performance. To tackle this challenge, we propose a weakly supervised Context-Semantic Quality Awareness Network (CSQA-Net) for FGVC. In this network, to model the spatial contextual relationship between rich part descriptors and global semantics for capturing more discriminative details within the object, we design a novel multi-part and multi-scale cross-attention (MPMSCA) module. Before feeding to the MPMSCA module, the part navigator is developed to address the scale confusion problems and accurately identify the local distinctive regions. Furthermore, we propose a generic multi-level semantic quality evaluation module (MLSQE) to progressively supervise and enhance hierarchical semantics from different levels of the backbone network. Finally, context-aware features from MPMSCA and semantically enhanced features from MLSQE are fed into the corresponding quality probing classifiers to evaluate their quality in real-time, thus boosting the discriminability of feature representations. Comprehensive experiments on four popular and highly competitive FGVC datasets demonstrate the superiority of the proposed CSQA-Net in comparison with the state-of-the-art methods.

Graph matching is a commonly used technique in computer vision and pattern recognition. Recent data-driven approaches have improved the graph matching accuracy remarkably, whereas some traditional algorithm-based methods are more robust to feature noises, outlier nodes, and global transformation (e.g.~rotation). In this paper, we propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods. In the GNN framework, we transform traditional graph-matching solvers as single-channel GNNs on the association graph and extend the single-channel architecture to the multi-channel network. The proposed model can be seen as an ensemble method that fuses multiple algorithms at every iteration. Instead of averaging the estimates at the end of the ensemble, in our approach, the independent iterations of the ensembled algorithms exchange their information after each iteration via a 1x1 channel-wise convolution layer. Experiments show that our model improves the performance of traditional algorithms significantly. In addition, we propose a random sampling strategy to reduce the computational complexity and GPU memory usage, so the model applies to matching graphs with thousands of nodes. We evaluate the performance of our method on three tasks: geometric graph matching, semantic feature matching, and few-shot 3D shape classification. The proposed model performs comparably or outperforms the best existing GNN-based methods., Comment: Accepted by IJCV in 2024

This is the first paper in a series on hyper-realist rendering. In this paper, we introduce the concept of hyper-realist rendering and present a theoretical framework to obtain hyper-realist images. We are using the term Hyper-realism as an umbrella word that captures all types of visual artifacts that can evoke an impression of reality. The hyper-realist artifacts are visual representations that are not necessarily created by following logical and physical principles and can still be perceived as representations of reality. This idea stems from the principles of representational arts, which attain visually acceptable renderings of scenes without implementing strict physical laws of optics and materials. The objective of this work is to demonstrate that it is possible to obtain visually acceptable illusions of reality by employing such artistic approaches. With representational art methods, we can even obtain an alternate illusion of reality that looks more real even when it is not real. This paper demonstrates that it is common to create illusions of reality in visual arts with examples of paintings by representational artists. We propose an approach to obtain expressive local and global illuminations to obtain these stylistic illusions with a set of well-defined and formal methods., Comment: 20 pages

Natural language explanation in visual question answer (VQA-NLE) aims to explain the decision-making process of models by generating natural language sentences to increase users' trust in the black-box systems. Existing post-hoc methods have achieved significant progress in obtaining a plausible explanation. However, such post-hoc explanations are not always aligned with human logical inference, suffering from the issues on: 1) Deductive unsatisfiability, the generated explanations do not logically lead to the answer; 2) Factual inconsistency, the model falsifies its counterfactual explanation for answers without considering the facts in images; and 3) Semantic perturbation insensitivity, the model can not recognize the semantic changes caused by small perturbations. These problems reduce the faithfulness of explanations generated by models. To address the above issues, we propose a novel self-supervised \textbf{M}ulti-level \textbf{C}ontrastive \textbf{L}earning based natural language \textbf{E}xplanation model (MCLE) for VQA with semantic-level, image-level, and instance-level factual and counterfactual samples. MCLE extracts discriminative features and aligns the feature spaces from explanations with visual question and answer to generate more consistent explanations. We conduct extensive experiments, ablation analysis, and case study to demonstrate the effectiveness of our method on two VQA-NLE benchmarks., Comment: AAAI 2024

In this work, we present a method for turning Chinese still-life paintings with global illumination effects into dynamic paintings with moving lights. Our goal is to preserve the original look and feel of still-life paintings with moving lights and objects. We have developed a deceptively simple method that can be computed as a composite of two animated texture images using an animated rendering. The compositing process can be implemented directly in an animation system such as AfterEffect, which allows for the basic compositing operation over animations. It is also possible to control the colors by changing the material colors in animated rendering. We have provided a proof-of-concept based on an original digital Still-Life painting that is in realist Chinese style. This approach can be used to turn almost any still-life painting into a dynamic painting., Comment: 14 pages

Story Visualization aims to generate images aligned with story prompts, reflecting the coherence of storybooks through visual consistency among characters and scenes.Whereas current approaches exclusively concentrate on characters and neglect the visual consistency among contextually correlated scenes, resulting in independent character images without inter-image coherence.To tackle this issue, we propose a new presentation form for Story Visualization called Storyboard, inspired by film-making, as illustrated in Fig.1.Specifically, a Storyboard unfolds a story into visual representations scene by scene. Within each scene in Storyboard, characters engage in activities at the same location, necessitating both visually consistent scenes and characters.For Storyboard, we design a general framework coined as Make-A-Storyboard that applies disentangled control over the consistency of contextual correlated characters and scenes and then merge them to form harmonized images.Extensive experiments demonstrate 1) Effectiveness.the effectiveness of the method in story alignment, character consistency, and scene correlation; 2) Generalization. Our method could be seamlessly integrated into mainstream Image Customization methods, empowering them with the capability of story visualization.

Recently Text-to-Video (T2V) synthesis has undergone a breakthrough by training transformers or diffusion models on large-scale datasets. Nevertheless, inferring such large models incurs huge costs.Previous inference acceleration works either require costly retraining or are model-specific.To address this issue, instead of retraining we explore the inference process of two mainstream T2V models using transformers and diffusion models.The exploration reveals the redundancy in temporal attention modules of both models, which are commonly utilized to establish temporal relations among frames.Consequently, we propose a training-free and generalized pruning strategy called F3-Pruning to prune redundant temporal attention weights.Specifically, when aggregate temporal attention values are ranked below a certain ratio, corresponding weights will be pruned.Extensive experiments on three datasets using a classic transformer-based model CogVideo and a typical diffusion-based model Tune-A-Video verify the effectiveness of F3-Pruning in inference acceleration, quality assurance and broad applicability.

The generalized stacking-fault energy (GSFE) is the fundamental but key parameter for the plastic deformation of materials. We perform first-principles calculations by full-potential linearized augmented planewave (FLAPW) method to evaluate the GSFE based on the single-shift and triple-shift supercell models. Different degrees of defects are introduced in the two models, thereby affecting the convergence of the self-consistent field (SCF) iterations. We present an adaptive preconditioning scheme which can identify the long-wavelength divergence behavior of the Jacobian during the SCF iteration and automatically switch on the Kerker preconditioning to accelerate the convergence. We implement this algorithm in Elk-7.2.42 package and calculate the GSFE curves for Al, Cu, and Si (111) plane <-1-12> direction. We found that the single-shift and triple-shift supercell models have equivalent calculation accuracy and are within the experimental data uncertainty. For computational efficiency, the triple-shift supercell model is preferable due to its better convergence, exhibiting lower degree of defect compared to the single-shift supercell model., Comment: 10 pages, 8 figures

Video podcast teasers are short videos that can be shared on social media platforms to capture interest in the full episodes of a video podcast. These teasers enable long-form podcasters to reach new audiences and gain new followers. However, creating a compelling teaser from an hour-long episode is challenging. Selecting interesting clips requires significant mental effort; editing the chosen clips into a cohesive, well-produced teaser is time-consuming. To support the creation of video podcast teasers, we first investigate what makes a good teaser. We combine insights from both audience comments and creator interviews to determine a set of essential ingredients. We also identify a common workflow shared by creators during the process. Based on these findings, we introduce a human-AI co-creative tool called PodReels to assist video podcasters in creating teasers. Our user study shows that PodReels significantly reduces creators' mental demand and improves their efficiency in producing video podcast teasers.

In this paper, we propose a novel data-pruning approach called moving-one-sample-out (MoSo), which aims to identify and remove the least informative samples from the training set. The core insight behind MoSo is to determine the importance of each sample by assessing its impact on the optimal empirical risk. This is achieved by measuring the extent to which the empirical risk changes when a particular sample is excluded from the training set. Instead of using the computationally expensive leaving-one-out-retraining procedure, we propose an efficient first-order approximator that only requires gradient information from different training stages. The key idea behind our approximation is that samples with gradients that are consistently aligned with the average gradient of the training set are more informative and should receive higher scores, which could be intuitively understood as follows: if the gradient from a specific sample is consistent with the average gradient vector, it implies that optimizing the network using the sample will yield a similar effect on all remaining samples. Experimental results demonstrate that MoSo effectively mitigates severe performance degradation at high pruning ratios and achieves satisfactory performance across various settings., Comment: Accepted by the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)

Alzheimer's Disease (AD) and related dementia are a growing global health challenge due to the aging population. In this paper, we present ADMarker, the first end-to-end system that integrates multi-modal sensors and new federated learning algorithms for detecting multidimensional AD digital biomarkers in natural living environments. ADMarker features a novel three-stage multi-modal federated learning architecture that can accurately detect digital biomarkers in a privacy-preserving manner. Our approach collectively addresses several major real-world challenges, such as limited data labels, data heterogeneity, and limited computing resources. We built a compact multi-modality hardware system and deployed it in a four-week clinical trial involving 91 elderly participants. The results indicate that ADMarker can accurately detect a comprehensive set of digital biomarkers with up to 93.8% accuracy and identify early AD with an average of 88.9% accuracy. ADMarker offers a new platform that can allow AD clinicians to characterize and track the complex correlation between multidimensional interpretable digital biomarkers, demographic factors of patients, and AD diagnosis in a longitudinal manner.

The Internet inter-domain routing system is vulnerable. On the control plane, the de facto Border Gateway Protocol (BGP) does not have built-in mechanisms to authenticate routing announcements, so an adversary can announce virtually arbitrary paths to hijack network traffic; on the data plane, it is difficult to ensure that actual forwarding path complies with the control plane decisions. The community has proposed significant research to secure the routing system. Yet, existing secure BGP protocols (e.g., BGPsec) are not incrementally deployable, and existing path authorization protocols are not compatible with the current Internet routing infrastructure. In this paper, we propose FC-BGP, the first secure Internet inter-domain routing system that can simultaneously authenticate BGP announcements and validate data plane forwarding in an efficient and incrementally-deployable manner. FC-BGP is built upon a novel primitive, name Forwarding Commitment, to certify an AS's routing intent on its directly connected hops. We analyze the security benefits of FC-BGP in the Internet at different deployment rates. Further, we implement a prototype of FC-BGP and extensively evaluate it over a large-scale overlay network with 100 virtual machines deployed globally. The results demonstrate that FC-BGP saves roughly 55% of the overhead required to validate BGP announcements compared with BGPsec, and meanwhile FC-BGP introduces a small overhead for building a globally-consistent view on the desirable forwarding paths., Comment: 16 pages, 17 figures

Single fiber imaging technology offers unique insights for research and inspection in difficult to reach and narrow spaces. In particular, ultra-compact multimode fiber (MMF) imaging, has received increasing interest over the past decade. However, MMF imaging will be seriously distorted when subjected to dynamic perturbations due to time-varying mode coupling, and the imaging of space objects via Gaussian beam will be relatively degraded at the edge due to insufficient contrast. Here, a robust super-resolution imaging method based on a ring core fiber (RCF) with orbital angular momentum (OAM) has been proposed and experimentally demonstrated. The OAM modes propagating in the RCF form a series of weakly-coupled mode groups, making our imaging system robust to external perturbations. In addition, a spiral phase plate is used as a vortex filter to produce OAM for edge enhancement, thus improving the image resolution. Furthermore, a few-shot U-Transformer neural network is proposed to enhance the resilience of the developed RCF-OAM imaging system against environmental perturbations. Finally, the developed RCF-OAM imaging system achieves biological image transmission, demonstrating the practicality of our scheme. This pioneering RCF OAM imaging system may have broad applications, potentially revolutionising fields such as biological imaging and industrial non-destructive testing.