Search

Existing novel object 6D pose estimation methods typically rely on CAD models or dense reference views, which are both difficult to acquire. Using only a single reference view is more scalable, but challenging due to large pose discrepancies and limited geometric and spatial information. To address these issues, we propose a Single-Reference-based novel object 6D (SinRef-6D) pose estimation method. Our key idea is to iteratively establish point-wise alignment in the camera coordinate system based on state space models (SSMs). Specifically, iterative camera-space point-wise alignment can effectively handle large pose discrepancies, while our proposed RGB and Points SSMs can capture long-range dependencies and spatial information from a single view, offering linear complexity and superior spatial modeling capability. Once pre-trained on synthetic data, SinRef-6D can estimate the 6D pose of a novel object using only a single reference view, without requiring retraining or a CAD model. Extensive experiments on six popular datasets and real-world robotic scenes demonstrate that we achieve on-par performance with CAD-based and dense reference view-based methods, despite operating in the more challenging single reference setting. Code will be released at https://github.com/CNJianLiu/SinRef-6D., Comment: 17 pages, 12 figures (including supplementary material)

We report Raman forbidden layer-breathing modes (LBMs) in layered semiconductor materials (LSMs). The intensity distribution of all observed LBMs depends on layer number, incident light wavelength and refractive index mismatch between LSM and underlying substrate. These results are understood by a Raman scattering theory via the proposed spatial interference model, where the naturally occurring optical and phonon cavities in LSMs enable spatially coherent photon-phonon coupling mediated by the corresponding one-dimensional periodic electronic states. Our work reveals the spatial coherence of photon and phonon fields on the phonon excitation via photon/phonon cavity engineering., Comment: Please check the initial version on the website of Research Square at https://doi.org/10.21203/rs.3.rs-4156671/v1

To mitigate the negative impacts of online videos on teenagers, existing research and platforms have implemented various parental mediation mechanisms, such as Parent-Child Joint Media Engagement (JME). However, JME generally relies heavily on parents' time, knowledge, and experience. To fill this gap, we aim to design an automatic tool to help parents/children censor videos more effectively and efficiently in JME. For this goal, we first conducted a formative study to identify the needs and expectations of teenagers and parents for such a system. Based on the findings, we designed YouthCare, a personalized collaborative video censorship tool that supports parents and children to collaboratively filter out inappropriate content and select appropriate content in JME. An evaluation with 10 parent-child pairs demonstrated YouthCare's several strengths in supporting video censorship, while also highlighting some potential problems. These findings inspire us to propose several insights for the future design of parent-child collaborative JME systems.

In recent years, Diffusion Models (DMs) have demonstrated significant advances in the field of image generation. However, according to current research, DMs are vulnerable to backdoor attacks, which allow attackers to control the model's output by inputting data containing covert triggers, such as a specific patch or phrase. Existing defense strategies are well equipped to thwart such attacks through backdoor detection and trigger inversion because previous attack methods are constrained by limited input spaces and triggers defined by low-dimensional features. To bridge these gaps, we propose Gungnir, a novel method that enables attackers to activate the backdoor in DMs through hidden style triggers within input images. Our approach proposes using stylistic features as triggers for the first time and implements backdoor attacks successfully in image2image tasks by utilizing Reconstructing-Adversarial Noise (RAN) and Short-Term-Timesteps-Retention (STTR) of DMs. Meanwhile, experiments demonstrate that our method can easily bypass existing defense methods. Among existing DM main backdoor defense frameworks, our approach achieves a 0\% backdoor detection rate (BDR). Our codes are available at https://github.com/paoche11/Gungnir.

Urban overheating, exacerbated by climate change, threatens public health and urban sustainability. Traditional approaches, such as numerical simulations and field measurements, face challenges due to uncertainties in input data. This study integrates field measurements with machine learning models to predict the duration and severity of future urban overheating events, focusing on the role of urban greening under different global warming (GW) scenarios. Field measurements were conducted in summer 2024 at an office campus in Ottawa, a cold-climate city. Microclimate data were collected from four locations with varying levels of greenery: a large lawn without trees (Lawn), a parking lot without greenery (Parking), an area with sparsely distributed trees (Tree), and a fully covered forested area (Forest). Machine learning models, including Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) networks, were trained on local microclimate data, with LSTM achieving the best predictions. Four GW scenarios were analyzed, corresponding to different Shared Socioeconomic Pathways (SSP) for 2050 and 2090. Results show that the Universal Thermal Climate Index (UTCI) at the "Parking" location rises from about 27,\textdegree C under GW1.0 to 31,\textdegree C under GW3.5. Moreover, low health risk conditions (UTCI > 26,\textdegree C) increase across all locations due to climate change, regardless of greenery levels. However, tree-covered areas such as "Tree" and "Forest" effectively prevent extreme heat conditions (UTCI > 38.9,\textdegree C). These findings highlight the crucial role of urban greening in mitigating severe thermal stress and enhancing thermal comfort under future climate scenarios.

Serverless platforms typically adopt an early-binding approach for function sizing, requiring developers to specify an immutable size for each function within a workflow beforehand. Accounting for potential runtime variability, developers must size functions for worst-case scenarios to ensure service-level objectives (SLOs), resulting in significant resource inefficiency. To address this issue, we propose Janus, a novel resource adaptation framework for serverless platforms. Janus employs a late-binding approach, allowing function sizes to be dynamically adapted based on runtime conditions. The main challenge lies in the information barrier between the developer and the provider: developers lack access to runtime information, while providers lack domain knowledge about the workflow. To bridge this gap, Janus allows developers to provide hints containing rules and options for resource adaptation. Providers then follow these hints to dynamically adjust resource allocation at runtime based on real-time function execution information, ensuring compliance with SLOs. We implement Janus and conduct extensive experiments with real-world serverless workflows. Our results demonstrate that Janus enhances resource efficiency by up to 34.7% compared to the state-of-the-art., Comment: to be published in the 39th IEEE International Parallel & Distributed Processing Symposium (IPDPS)

Inspired by the work of Katznelson and Ornstein, we present a short way to achieve the almost optimal regularity in Moser's twist theorem. Specifically, for an integrable area-preserving twist map, the invariant circle with a given constant type frequency $\alpha$ persists under a small perturbation (dependent on $\alpha$) of class $C^{3+\epsilon}$. This result was initially established independently by Herman and R\"{u}ssmann in 1983. Our method differs essentially from their approaches.

Omnidirectional image (ODI) data is captured with a field-of-view of 360x180, which is much wider than the pinhole cameras and captures richer surrounding environment details than the conventional perspective images. In recent years, the availability of customer-level 360 cameras has made omnidirectional vision more popular, and the advance of deep learning (DL) has significantly sparked its research and applications. This paper presents a systematic and comprehensive review and analysis of the recent progress of DL for omnidirectional vision. It delineates the distinct challenges and complexities encountered in applying DL to omnidirectional images as opposed to traditional perspective imagery. Our work covers four main contents: (i) A thorough introduction to the principles of omnidirectional imaging and commonly explored projections of ODI; (ii) A methodical review of varied representation learning approaches tailored for ODI; (iii) An in-depth investigation of optimization strategies specific to omnidirectional vision; (iv) A structural and hierarchical taxonomy of the DL methods for the representative omnidirectional vision tasks, from visual enhancement (e.g., image generation and super-resolution) to 3D geometry and motion estimation (e.g., depth and optical flow estimation), alongside the discussions on emergent research directions; (v) An overview of cutting-edge applications (e.g., autonomous driving and virtual reality), coupled with a critical discussion on prevailing challenges and open questions, to trigger more research in the community., Comment: 37 pages, 24 figures, accepted by IJCV

Most recommendation systems typically follow a product-based paradigm utilizing user-product interactions to identify the most engaging items for users. However, this product-based paradigm has notable drawbacks for Xianyu~\footnote{Xianyu is China's largest online C2C e-commerce platform where a large portion of the product are post by individual sellers}. Most of the product on Xianyu posted from individual sellers often have limited stock available for distribution, and once the product is sold, it's no longer available for distribution. This result in most items distributed product on Xianyu having relatively few interactions, affecting the effectiveness of traditional recommendation depending on accumulating user-item interactions. To address these issues, we introduce \textbf{IU4Rec}, an \textbf{I}nterest \textbf{U}nit-based two-stage \textbf{Rec}ommendation system framework. We first group products into clusters based on attributes such as category, image, and semantics. These IUs are then integrated into the Recommendation system, delivering both product and technological innovations. IU4Rec begins by grouping products into clusters based on attributes such as category, image, and semantics, forming Interest Units (IUs). Then we redesign the recommendation process into two stages. In the first stage, the focus is on recommend these Interest Units, capturing broad-level interests. In the second stage, it guides users to find the best option among similar products within the selected Interest Unit. User-IU interactions are incorporated into our ranking models, offering the advantage of more persistent IU behaviors compared to item-specific interactions. Experimental results on the production dataset and online A/B testing demonstrate the effectiveness and superiority of our proposed IU-centric recommendation approach., Comment: Under review at KDD25 ADS. This work has already been deployed on the Xianyu platform in Alibaba. arXiv admin note: substantial text overlap with arXiv:2403.06747

Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual information. This integration has significantly enhanced performance across a diverse spectrum of applications, such as scene perception and robotics. However, the deployment of VLMs has also given rise to critical safety and security concerns, necessitating extensive research to assess the potential vulnerabilities these VLM systems may harbor. In this work, we present an in-depth survey of the attack strategies tailored for VLMs. We categorize these attacks based on their underlying objectives - namely jailbreak, camouflage, and exploitation - while also detailing the various methodologies employed for data manipulation of VLMs. Meanwhile, we outline corresponding defense mechanisms that have been proposed to mitigate these vulnerabilities. By discerning key connections and distinctions among the diverse types of attacks, we propose a compelling taxonomy for VLM attacks. Moreover, we summarize the evaluation metrics that comprehensively describe the characteristics and impact of different attacks on VLMs. Finally, we conclude with a discussion of promising future research directions that could further enhance the robustness and safety of VLMs, emphasizing the importance of ongoing exploration in this critical area of study. To facilitate community engagement, we maintain an up-to-date project page, accessible at: https://github.com/AobtDai/VLM_Attack_Paper_List.

In this paper, a Convolution-Based Converter (CBC) is proposed to develop a methodology for removing the strong or fixed priors in estimating the probability distribution of targets based on observations in the stochastic process. Traditional approaches, e.g., Markov-based and Gaussian process-based methods, typically leverage observations to estimate targets based on strong or fixed priors (such as Markov properties or Gaussian prior). However, the effectiveness of these methods depends on how well their prior assumptions align with the characteristics of the problem. When the assumed priors are not satisfied, these approaches may perform poorly or even become unusable. To overcome the above limitation, we introduce the Convolution-Based converter (CBC), which implicitly estimates the conditional probability distribution of targets without strong or fixed priors, and directly outputs the expected trajectory of the stochastic process that satisfies the constraints from observations. This approach reduces the dependence on priors, enhancing flexibility and adaptability in modeling stochastic processes when addressing different problems. Experimental results demonstrate that our method outperforms existing baselines across multiple metrics.

In this study, Disentanglement in Difference(DiD) is proposed to address the inherent inconsistency between the statistical independence of latent variables and the goal of semantic disentanglement in disentanglement representation learning. Conventional disentanglement methods achieve disentanglement representation by improving statistical independence among latent variables. However, the statistical independence of latent variables does not necessarily imply that they are semantically unrelated, thus, improving statistical independence does not always enhance disentanglement performance. To address the above issue, DiD is proposed to directly learn semantic differences rather than the statistical independence of latent variables. In the DiD, a Difference Encoder is designed to measure the semantic differences; a contrastive loss function is established to facilitate inter-dimensional comparison. Both of them allow the model to directly differentiate and disentangle distinct semantic factors, thereby resolving the inconsistency between statistical independence and semantic disentanglement. Experimental results on the dSprites and 3DShapes datasets demonstrate that the proposed DiD outperforms existing mainstream methods across various disentanglement metrics.

Two-dimensional van der Waals (vdW) ferromagnetic/semiconductor heterojunctions represent an ideal platform for studying and exploiting tunneling magnetoresistance (TMR) effects due to the versatile band structure of semiconductors and their high-quality interfaces. In the all-vdW magnetic tunnel junction (MTJ) devices, both the magnitude and sign of the TMR can be tuned by an applied voltage. Typically, as the bias voltage increases, first the amplitude of the TMR decreases, then the sign of the TMR reverses and/or oscillates. Here, we report on an unconventional bias-dependent TMR in the all-vdW Fe3GaTe2/GaSe/Fe3GaTe2 MTJs, where the TMR first increases, then decreases, and finally undergoes a sign reversal as the bias voltage increases. This dependence cannot be explained by traditional models of MTJs. We propose an in-plane electron momentum (k//) resolved tunneling model that considers both the coherent degree of k// and the decay of the electron wave function through the semiconductor spacer layer. This can explain well the conventional and unconventional bias-dependent TMR. Our results thus provide a deeper understanding of the bias-dependent spin-transport in semiconductor-based MTJs and offer new insights into semiconductor spintronics.

Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationship across samples with same class is often neglected. In this paper, we explore to redefine the knowledge in distillation, capturing the relationship between each sample and its corresponding in-context samples (a group of similar samples with the same or different classes), and perform KD from an in-context sample retrieval perspective. As KD is a type of learned label smoothing regularization (LSR), we first conduct a theoretical analysis showing that the teacher's knowledge from the in-context samples is a crucial contributor to regularize the student training with the corresponding samples. Buttressed by the analysis, we propose a novel in-context knowledge distillation (IC-KD) framework that shows its superiority across diverse KD paradigms (offline, online, and teacher-free KD). Firstly, we construct a feature memory bank from the teacher model and retrieve in-context samples for each corresponding sample through retrieval-based learning. We then introduce Positive In-Context Distillation (PICD) to reduce the discrepancy between a sample from the student and the aggregated in-context samples with the same class from the teacher in the logit space. Moreover, Negative In-Context Distillation (NICD) is introduced to separate a sample from the student and the in-context samples with different classes from the teacher in the logit space. Extensive experiments demonstrate that IC-KD is effective across various types of KD, and consistently achieves state-of-the-art performance on CIFAR-100 and ImageNet datasets.

Graph condensation reduces the size of large graphs while preserving performance, addressing the scalability challenges of Graph Neural Networks caused by computational inefficiencies on large datasets. Existing methods often rely on bi-level optimization, requiring extensive GNN training and limiting their scalability. To address these issues, this paper proposes Graph Condensation via Gaussian Process (GCGP), a novel and computationally efficient approach to graph condensation. GCGP utilizes a Gaussian Process (GP), with the condensed graph serving as observations, to estimate the posterior distribution of predictions. This approach eliminates the need for the iterative and resource-intensive training typically required by GNNs. To enhance the capability of the GCGP in capturing dependencies between function values, we derive a specialized covariance function that incorporates structural information. This covariance function broadens the receptive field of input nodes by local neighborhood aggregation, thereby facilitating the representation of intricate dependencies within the nodes. To address the challenge of optimizing binary structural information in condensed graphs, Concrete random variables are utilized to approximate the binary adjacency matrix in a continuous counterpart. This relaxation process allows the adjacency matrix to be represented in a differentiable form, enabling the application of gradient-based optimization techniques to discrete graph structures. Experimental results show that the proposed GCGP method efficiently condenses large-scale graph data while preserving predictive performance, addressing the scalability and efficiency challenges. The implementation of our method is publicly available at https://github.com/WANGLin0126/GCGP.

Pulsar polarization profiles are critical for understanding their magnetospheric structures and radiation mechanisms. We present polarization profile measurements for 25 pulsars in globular clusters (GCs) from the observation of the Five-hundred-meter Aperture Spherical radio Telescope (FAST). The diversity of polarization profiles shows complex magnetic structure and emission pattern of pulsars. Among these, the polarization profiles of 15 pulsars were firstly measured. M53A present a 57\% linear polarization ratio, being highest among these 25 GC pulsars. M15H present a 42\% circular polarization ratio, which is the highest among these 25 pulsars. The average ratios of circular and absolute circular polarization of these GC pulsars are -1\% and 10\% respectively, lower than normal pulsars measured with Parkes (\citealt{Oswald2023}), which are 5\% and 32\%, respectively. The Rotation Measure (RM) values of each pulsar were measured, giving the range of pulsar(s) from M3, M5, M15, M71, M53, NGC6517, NGC6539, NGC6760 being 8(1) to 16(1) rad $m^{-2}$, -1(2) to -4(6) rad $m^{-2}$, -70(2) to -76(1) rad $m^{-2}$, -480(14) rad $m^{-2}$ (M71A only), -2(1) rad $m^{-2}$ (M53A only), 187(1) to 212(2) rad $m^{-2}$, 109(1) rad $m^{-2}$ (NGC6539A only), and 102(1) to 129(4) rad $m^{-2}$. The GCs closer to the Galactic plane (GP) tend to have larger RM. This is consistent with previous study (\citealt{Hutschenreuter2022})., Comment: 13 pages, 4 figues, 2 tables, submitted to RAA, comments are always welcomed!

Recommender systems play a pivotal role in modern content platforms, yet traditional behavior-based models often face challenges in addressing cold users with sparse interaction data. Engaging these users, however, remains critical for sustaining platform growth. To tackle this issue, we propose leveraging reconstructed social graph to complement interest representations derived from behavioral data. Despite the widespread availability of social graphs on content platforms, their utility is hindered by social-relation noise and inconsistencies between social and behavioral interests. To mitigate noise propagation in graph data and extract reliable social interests, we introduce a dual-view denoising framework. This approach first applies low-rank singular value decomposition (SVD) to the user-item interaction matrix, generating denoised user embeddings for reconstructing the social graph. It then employs contrastive learning to align the original and reconstructed social graphs. To address the discrepancy between social and behavioral interests, we utilize a mutual distillation mechanism that decomposes interests into four subcategories: aligned social/behavioral interests and social/behavioral-specific interests, enabling effective integration of the two. Empirical results demonstrate the efficacy of our method, particularly in improving recommendations for cold users, by combining social and behavioral data. The implementation of our approach is publicly available at https://github.com/WANGLin0126/CLSRec.

Graph neural network universal interatomic potentials (GNN-UIPs) have demonstrated remarkable generalization and transfer capabilities in material discovery and property prediction. These models can accelerate molecular dynamics (MD) simulation by several orders of magnitude while maintaining \textit{ab initio} accuracy, making them a promising new paradigm in material simulations. One notable example is Crystal Hamiltonian Graph Neural Network (CHGNet), pretrained on the energies, forces, stresses, and magnetic moments from the MPtrj dataset, representing a state-of-the-art GNN-UIP model for charge-informed MD simulations. However, training the CHGNet model is time-consuming(8.3 days on one A100 GPU) for three reasons: (i) requiring multi-layer propagation to reach more distant atom information, (ii) requiring second-order derivatives calculation to finish weights updating and (iii) the implementation of reference CHGNet does not fully leverage the computational capabilities. This paper introduces FastCHGNet, an optimized CHGNet, with three contributions: Firstly, we design innovative Force/Stress Readout modules to decompose Force/Stress prediction. Secondly, we adopt massive optimizations such as kernel fusion, redundancy bypass, etc, to exploit GPU computation power sufficiently. Finally, we extend CHGNet to support multiple GPUs and propose a load-balancing technique to enhance GPU utilization. Numerical results show that FastCHGNet reduces memory footprint by a factor of 3.59. The final training time of FastCHGNet can be decreased to \textbf{1.53 hours} on 32 GPUs without sacrificing model accuracy.

Fusing small resource states into a larger, fully connected graph-state is essential for scalable photonic quantum computing. Theoretical analysis reveals that this can only be achieved when the success probability of the fusion gate surpasses a specific percolation threshold of 58.98% by using three-photon GHZ states as resource states. However, such an implementation of a fusion gate has never been experimentally realized before. Here, we successfully demonstrate a boosted fusion gate with a theoretical success probability of 75%, using deterministically generated auxiliary states. The success probability is experimentally measured to be 71.0(7)%. We further demonstrate the effectiveness of the boosted fusion gate by fusing two Bell states with a fidelity of 67(2)%. Our work paves a crucial path toward scalable linear optical quantum computing., Comment: 5 pages, 4 figures

In this paper, we address the challenging modality-agnostic semantic segmentation (MaSS), aiming at centering the value of every modality at every feature granularity. Training with all available visual modalities and effectively fusing an arbitrary combination of them is essential for robust multi-modal fusion in semantic segmentation, especially in real-world scenarios, yet remains less explored to date. Existing approaches often place RGB at the center, treating other modalities as secondary, resulting in an asymmetric architecture. However, RGB alone can be limiting in scenarios like nighttime, where modalities such as event data excel. Therefore, a resilient fusion model must dynamically adapt to each modality's strengths while compensating for weaker inputs.To this end, we introduce the MAGIC++ framework, which comprises two key plug-and-play modules for effective multi-modal fusion and hierarchical modality selection that can be equipped with various backbone models. Firstly, we introduce a multi-modal interaction module to efficiently process features from the input multi-modal batches and extract complementary scene information with channel-wise and spatial-wise guidance. On top, a unified multi-scale arbitrary-modal selection module is proposed to utilize the aggregated features as the benchmark to rank the multi-modal features based on the similarity scores at hierarchical feature spaces. This way, our method can eliminate the dependence on RGB modality at every feature granularity and better overcome sensor failures and environmental noises while ensuring the segmentation performance. Under the common multi-modal setting, our method achieves state-of-the-art performance on both real-world and synthetic benchmarks. Moreover, our method is superior in the novel modality-agnostic setting, where it outperforms prior arts by a large margin.

Large Automatic Speech Recognition (ASR) models demand a vast number of parameters, copious amounts of data, and significant computational resources during the training process. However, such models can merely be deployed on high-compute cloud platforms and are only capable of performing speech recognition tasks. This leads to high costs and restricted capabilities. In this report, we initially propose the elastic mixture of the expert (eMoE) model. This model can be trained just once and then be elastically scaled in accordance with deployment requirements. Secondly, we devise an unsupervised data creation and validation procedure and gather millions of hours of audio data from diverse domains for training. Using these two techniques, our system achieves elastic deployment capabilities while reducing the Character Error Rate (CER) on the SpeechIO testsets from 4.98\% to 2.45\%. Thirdly, our model is not only competent in Mandarin speech recognition but also proficient in multilingual, multi-dialect, emotion, gender, and sound event perception. We refer to this as Automatic Speech Perception (ASP), and the perception results are presented in the experimental section., Comment: Technical Report

Recent studies have highlighted the limitations of large language models in mathematical reasoning, particularly their inability to capture the underlying logic. Inspired by meta-learning, we propose that models should acquire not only task-specific knowledge but also transferable problem-solving skills. We introduce MetaRuleGPT, a novel Transformer-based architecture that performs precise numerical calculations and complex logical operations by learning and combining different rules. In contrast with traditional training sets, which are heavily composed of massive raw instance data, MetaRuleGPT is pre-trained on much less abstract datasets containing basic, compound, and iterative rules for mathematical reasoning. Extensive experimental results demonstrate MetaRuleGPT can mimic human's rule-following capabilities, break down complexity, and iteratively derive accurate results for complex mathematical problems. These findings prove the potential of rule learning to enhance the numerical reasoning abilities of language models., Comment: 8 pages, 6 figures

Distilling 3D representations from pretrained 2D diffusion models is essential for 3D creative applications across gaming, film, and interior design. Current SDS-based methods are hindered by inefficient information distillation from diffusion models, which prevents the creation of photorealistic 3D contents. Our research reevaluates the SDS approach by analyzing its fundamental nature as a basic image editing process that commonly results in over-saturation, over-smoothing and lack of rich content due to the poor-quality single-step denoising. To address these limitations, we propose GE3D (3D Generation by Editing). Each iteration of GE3D utilizes a 2D editing framework that combines a noising trajectory to preserve the information of the input image, alongside a text-guided denoising trajectory. We optimize the process by aligning the latents across both trajectories. This approach fully exploits pretrained diffusion models to distill multi-granularity information through multiple denoising steps, resulting in photorealistic 3D outputs. Both theoretical and experimental results confirm the effectiveness of our approach, which not only advances 3D generation technology but also establishes a novel connection between 3D generation and 2D editing. This could potentially inspire further research in the field. Code and demos are released at https://jahnsonblack.github.io/GE3D/.

Linear Text Segmentation is the task of automatically tagging text documents with topic shifts, i.e. the places in the text where the topics change. A well-established area of research in Natural Language Processing, drawing from well-understood concepts in linguistic and computational linguistic research, the field has recently seen a lot of interest as a result of the surge of text, video, and audio available on the web, which in turn require ways of summarising and categorizing the mole of content for which linear text segmentation is a fundamental step. In this survey, we provide an extensive overview of current advances in linear text segmentation, describing the state of the art in terms of resources and approaches for the task. Finally, we highlight the limitations of available resources and of the task itself, while indicating ways forward based on the most recent literature and under-explored research directions.

Neural network force field models such as DeePMD have enabled highly efficient large-scale molecular dynamics simulations with ab initio accuracy. However, building such models heavily depends on the training data obtained by costly electronic structure calculations, thereby it is crucial to carefully select and label the most representative configurations during model training to improve both extrapolation capability and training efficiency. To address this challenge, based on the Kalman filter theory we propose the Kalman Prediction Uncertainty (KPU) to quantify uncertainty of the model's prediction. With KPU we design the Active Learning by KPU (ALKPU) method, which can efficiently select representative configurations that should be labelled during model training. We prove that ALKPU locally leads to the fastest reduction of model's uncertainty, which reveals its rationality as a general active learning method. We test the ALKPU method using various physical system simulations and demonstrate that it can efficiently coverage the system's configuration space. Our work demonstrates the benefits of ALKPU as a novel active learning method, enhancing training efficiency and reducing computational resource demands.

Generating realistic and diverse road scenarios is essential for autonomous vehicle testing and validation. Nevertheless, owing to the complexity and variability of real-world road environments, creating authentic and varied scenarios for intelligent driving testing is challenging. In this paper, we propose DiffRoad, a novel diffusion model designed to produce controllable and high-fidelity 3D road scenarios. DiffRoad leverages the generative capabilities of diffusion models to synthesize road layouts from white noise through an inverse denoising process, preserving real-world spatial features. To enhance the quality of generated scenarios, we design the Road-UNet architecture, optimizing the balance between backbone and skip connections for high-realism scenario generation. Furthermore, we introduce a road scenario evaluation module that screens adequate and reasonable scenarios for intelligent driving testing using two critical metrics: road continuity and road reasonableness. Experimental results on multiple real-world datasets demonstrate DiffRoad's ability to generate realistic and smooth road structures while maintaining the original distribution. Additionally, the generated scenarios can be fully automated into the OpenDRIVE format, facilitating generalized autonomous vehicle simulation testing. DiffRoad provides a rich and diverse scenario library for large-scale autonomous vehicle testing and offers valuable insights for future infrastructure designs that are better suited for autonomous vehicles., Comment: 14 pages, 9 figures

In the field of big data analytics, the search for efficient subdata selection methods that enable robust statistical inferences with minimal computational resources is of high importance. A procedure prior to subdata selection could perform variable selection, as only a subset of a large number of variables is active. We propose an approach when both the size of the full dataset and the number of variables are large. This approach firstly identifies the active variables by applying a procedure inspired by random LASSO (Least Absolute Shrinkage and Selection Operator) and then selects subdata based on leverage scores to build a predictive model. Our proposed approach outperforms approaches that already exists in the current literature, including the usage of the full dataset, in both variable selection and prediction, while also exhibiting significant improvements in computing time. Simulation experiments as well as a real data application are provided.

We explore probabilistic approaches to the deterministic energy equality for the forced Surface Quasi-Geostrophic (SQG) equation on a torus. First, we prove the zero-noise dynamical large deviations for a corresponding stochastic SQG equation, where the lower bound matches the upper bound on a certain closure of the weak-strong uniqueness class for the deterministic forced SQG equation. Furthermore, we show that the energy equality for the deterministic SQG equation holds on arbitrary time-reversible subsets of the domain, where we match the upper bound and the lower bound. Conversely, the violation of the deterministic energy equality breaks the lower bound of large deviations. These results extend the existing techniques in Gess, Heydecker, and the second author \cite{arXiv:2311.02223} to generalized Sobolev spaces with negative indices. Finally, we provide an analysis of the restricted quasi-potential and prove a conditional equivalence compared to the rate function of large deviations for the Gaussian distribution. This suggests a potential connection between non-Gaussian large deviations in equilibrium for the stochastic SQG equation and the open problem regarding the uniqueness of the deterministic SQG equation., Comment: 42 pages

Multimodal conversation, a crucial form of human communication, carries rich emotional content, making the exploration of the causes of emotions within it a research endeavor of significant importance. However, existing research on the causes of emotions typically uses clause selection methods to locate the reason utterance, without providing a detailed explanation of the emotional causes. In this paper, we propose a new task, \textbf{M}ultimodal \textbf{C}onversation \textbf{E}motion \textbf{C}ause \textbf{E}xplanation (MCECE), aiming to generate a detailed explanation of the emotional cause to the target utterance within a multimodal conversation scenario. Building upon the MELD dataset, we develop a new dataset (ECEM) that integrates video clips with detailed explanations of character emotions, facilitating an in-depth examination of the causal factors behind emotional expressions in multimodal conversations.A novel approach, FAME-Net, is further proposed, that harnesses the power of Large Language Models (LLMs) to analyze visual data and accurately interpret the emotions conveyed through facial expressions in videos. By exploiting the contagion effect of facial emotions, FAME-Net effectively captures the emotional causes of individuals engaged in conversations. Our experimental results on the newly constructed dataset show that FAME-Net significantly outperforms several excellent large language model baselines. Code and dataset are available at \url{https://github.com/3222345200/ECEMdataset.git}

The increasing concern for data privacy has driven the rapid development of federated learning (FL), a privacy-preserving collaborative paradigm. However, the statistical heterogeneity among clients in FL results in inconsistent performance of the server model across various clients. Server model may show favoritism towards certain clients while performing poorly for others, heightening the challenge of fairness. In this paper, we reconsider the inconsistency in client performance distribution and introduce the concept of adversarial multi-armed bandit to optimize the proposed objective with explicit constraints on performance disparities. Practically, we propose a novel multi-armed bandit-based allocation FL algorithm (FedMABA) to mitigate performance unfairness among diverse clients with different data distributions. Extensive experiments, in different Non-I.I.D. scenarios, demonstrate the exceptional performance of FedMABA in enhancing fairness.

Blind face restoration (BFR) is a fundamental and challenging problem in computer vision. To faithfully restore high-quality (HQ) photos from poor-quality ones, recent research endeavors predominantly rely on facial image priors from the powerful pretrained text-to-image (T2I) diffusion models. However, such priors often lead to the incorrect generation of non-facial features and insufficient facial details, thus rendering them less practical for real-world applications. In this paper, we propose a novel framework, namely AuthFace that achieves highly authentic face restoration results by exploring a face-oriented generative diffusion prior. To learn such a prior, we first collect a dataset of 1.5K high-quality images, with resolutions exceeding 8K, captured by professional photographers. Based on the dataset, we then introduce a novel face-oriented restoration-tuning pipeline that fine-tunes a pretrained T2I model. Identifying key criteria of quality-first and photography-guided annotation, we involve the retouching and reviewing process under the guidance of photographers for high-quality images that show rich facial features. The photography-guided annotation system fully explores the potential of these high-quality photographic images. In this way, the potent natural image priors from pretrained T2I diffusion models can be subtly harnessed, specifically enhancing their capability in facial detail restoration. Moreover, to minimize artifacts in critical facial areas, such as eyes and mouth, we propose a time-aware latent facial feature loss to learn the authentic face restoration process. Extensive experiments on the synthetic and real-world BFR datasets demonstrate the superiority of our approach., Comment: Codes and datasets will be available at https://github.com/EthanLiang99/AuthFace

Panoramic images provide comprehensive scene information and are suitable for VR applications. Obtaining corresponding depth maps is essential for achieving immersive and interactive experiences. However, panoramic depth estimation presents significant challenges due to the severe distortion caused by equirectangular projection (ERP) and the limited availability of panoramic RGB-D datasets. Inspired by the recent success of neural rendering, we propose a novel method, named $\mathbf{CUBE360}$, that learns a cubic field composed of multiple MPIs from a single panoramic image for $\mathbf{continuous}$ depth estimation at any view direction. Our CUBE360 employs cubemap projection to transform an ERP image into six faces and extract the MPIs for each, thereby reducing the memory consumption required for MPI processing of high-resolution data. Additionally, this approach avoids the computational complexity of handling the uneven pixel distribution inherent to equirectangular projectio. An attention-based blending module is then employed to learn correlations among the MPIs of cubic faces, constructing a cubic field representation with color and density information at various depth levels. Furthermore, a novel sampling strategy is introduced for rendering novel views from the cubic field at both cubic and planar scales. The entire pipeline is trained using photometric loss calculated from rendered views within a self-supervised learning approach, enabling training on 360 videos without depth annotations. Experiments on both synthetic and real-world datasets demonstrate the superior performance of CUBE360 compared to prior SSL methods. We also highlight its effectiveness in downstream applications, such as VR roaming and visual effects, underscoring CUBE360's potential to enhance immersive experiences.

Quantum emitters trapped near photonic crystal waveguides have recently emerged as an exciting platform for realizing novel quantum matter-light interfaces. Here we study tunable photon scattering in a photonic crystal waveguide coupled to an atom dimer with an arbitrary spatial separation. In the weak-excitation regime, we give the energy levels and their decay rates into the waveguide modes in the dressed basis, which both depend on the distance between the two atoms. We focus on the Bragg case and anti-Bragg case, where subradiant and superradiant states are produced and perfect transmission with a $\pi$ phase shift may occur on resonance. We observe quantum beats in the photon-photon correlation function of the reflected field in the anti-Bragg case. Moreover, the frequencies of quantum beats can be controlled due to the tunability of the bound states via the dispersion engineering of the structure. We also observe directional photon emission in the anti-Bragg case and give the dynamic mechanism of the perfect transmission. We quantify the effects of the system imperfections, including the deviation in the distance between the two atoms and the asymmetry in the atomic decay rates into the waveguide modes. With recent experimental advances in the superconducting microwave transmission lines, our results should soon be realizable., Comment: 14 pages, 8 figures, Comments are welcome

We present a workflow that iteratively combines \textit{ab-initio} calculations with a machine-learning (ML) guided search for superconducting compounds with both dynamical stability and instability from imaginary phonon modes, the latter of which have been largely overlooked in previous studies. Electron-phonon coupling (EPC) properties and critical temperature (T$_c$) of 417 boron, carbon, and borocarbide compounds have been calculated with density functional perturbation theory (DFPT) and isotropic Eliashberg approximation. Our study addresses T$_c$ convergence of Brillouin zone sampling with an ansatz test, stabilizing imaginary phonon modes for significant EPC contributions and comparing performance of two ML models especially when including compounds of dynamical instability. We predict a few promising superconducting compounds with formation energy just above the ground state convex hull, such as Ca$_5$B$_3$N$_6$ (35 K), TaNbC$_2$ (28.4 K), Nb$_3$B$_3$C (16.4 K), Y$_2$B$_3$C$_2$ (4.0 K), Pd$_3$CaB (7.0 K), MoRuB$_2$ (15.6 K), RuVB$_2$ (15.0 K), RuSc$_3$C$_4$ (6.6 K) among others.

Event cameras are bio-inspired sensors that capture the intensity changes asynchronously and output event streams with distinct advantages, such as high temporal resolution. To exploit event cameras for object/action recognition, existing methods predominantly sample and aggregate events in a second-level duration at every fixed temporal interval (or frequency). However, they often face difficulties in capturing the spatiotemporal relationships for longer, e.g., minute-level, events and generalizing across varying temporal frequencies. To fill the gap, we present a novel framework, dubbed PAST-SSM, exhibiting superior capacity in recognizing events with arbitrary duration (e.g., 0.1s to 4.5s) and generalizing to varying inference frequencies. Our key insight is to learn the spatiotemporal relationships from the encoded event features via the state space model (SSM) -- whose linear complexity makes it ideal for modeling high temporal resolution events with longer sequences. To achieve this goal, we first propose a Path-Adaptive Event Aggregation and Scan (PEAS) module to encode events of varying duration into features with fixed dimensions by adaptively scanning and selecting aggregated event frames. On top of PEAS, we introduce a novel Multi-faceted Selection Guiding (MSG) loss to minimize the randomness and redundancy of the encoded features. This subtly enhances the model generalization across different inference frequencies. Lastly, the SSM is employed to better learn the spatiotemporal properties from the encoded features. Moreover, we build a minute-level event-based recognition dataset, named ArDVS100, with arbitrary duration for the benefit of the community. Extensive experiments prove that our method outperforms prior arts by +3.45%, +0.38% and +8.31% on the DVS Action, SeAct and HARDVS datasets, respectively., Comment: First version

EuAl$_4$ is proposed to host a topological Hall state. This material also undergoes four consecutive antiferromagnetic (AFM) transitions upon cooling below TN1 = 15.4 K in the presence of charge density wave (CDW) order that sets in below TCDW = 140 K. We use angle-resolved photoemission spectroscopy and density-functional-theory calculations to study how magnetic ordering affects the electronic properties in EuAl$_4$. We found changes in the band structure upon each of the four consecutive AFM transitions including band splitting, renormalizations, and appearance of new bands forming additional Fermi sheets. In addition we also found significant enhancement of the quasiparticles' lifetime due to suppression of spin flip scattering, similar to what was previously reported for ferromagnetic EuCd$_2$As$_2$. Surprisingly, we observe that most significant changes in electronic properties occur not at TN1, but instead at the AFM3 to AFM4 transition, which coincides with the largest drop in resistivity.

Recent years have witnessed tremendous progress in the 3D reconstruction of dynamic humans from a monocular video with the advent of neural rendering techniques. This task has a wide range of applications, including the creation of virtual characters for virtual reality (VR) environments. However, it is still challenging to reconstruct clear humans when the monocular video is affected by motion blur, particularly caused by rapid human motion (e.g., running, dancing), as often occurs in the wild. This leads to distinct inconsistency of shape and appearance for the rendered 3D humans, especially in the blurry regions with rapid motion, e.g., hands and legs. In this paper, we propose ExFMan, the first neural rendering framework that unveils the possibility of rendering high-quality humans in rapid motion with a hybrid frame-based RGB and bio-inspired event camera. The ``out-of-the-box'' insight is to leverage the high temporal information of event data in a complementary manner and adaptively reweight the effect of losses for both RGB frames and events in the local regions, according to the velocity of the rendered human. This significantly mitigates the inconsistency associated with motion blur in the RGB frames. Specifically, we first formulate a velocity field of the 3D body in the canonical space and render it to image space to identify the body parts with motion blur. We then propose two novel losses, i.e., velocity-aware photometric loss and velocity-relative event loss, to optimize the neural human for both modalities under the guidance of the estimated velocity. In addition, we incorporate novel pose regularization and alpha losses to facilitate continuous pose and clear boundary. Extensive experiments on synthetic and real-world datasets demonstrate that ExFMan can reconstruct sharper and higher quality humans.

Can we directly visualize what we imagine in our brain together with what we describe? The inherent nature of human perception reveals that, when we think, our body can combine language description and build a vivid picture in our brain. Intuitively, generative models should also hold such versatility. In this paper, we introduce BrainDreamer, a novel end-to-end language-guided generative framework that can mimic human reasoning and generate high-quality images from electroencephalogram (EEG) brain signals. Our method is superior in its capacity to eliminate the noise introduced by non-invasive EEG data acquisition and meanwhile achieve a more precise mapping between the EEG and image modality, thus leading to significantly better-generated images. Specifically, BrainDreamer consists of two key learning stages: 1) modality alignment and 2) image generation. In the alignment stage, we propose a novel mask-based triple contrastive learning strategy to effectively align EEG, text, and image embeddings to learn a unified representation. In the generation stage, we inject the EEG embeddings into the pre-trained Stable Diffusion model by designing a learnable EEG adapter to generate high-quality reasoning-coherent images. Moreover, BrainDreamer can accept textual descriptions (e.g., color, position, etc.) to achieve controllable image generation. Extensive experiments show that our method significantly outperforms prior arts in terms of generating quality and quantitative performance.