Search

Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve `state-of-the-art' performance in sequential recommendation. However, most of the baselines used for comparison are trained using a pointwise/pairwise loss function. This inconsistent experimental setting leads to the underestimation of traditional methods and further fosters over-confidence in the ranking capability of LLMs. In this study, we provide theoretical justification for the superiority of the cross-entropy loss by demonstrating its two desirable properties: tightness and coverage. Furthermore, this study sheds light on additional novel insights: 1) Taking into account only the recommendation performance, CE is not yet optimal as it is not a quite tight bound in terms of some ranking metrics. 2) In scenarios that full softmax cannot be performed, an effective alternative is to scale up the sampled normalizing term. These findings then help unleash the potential of traditional recommendation models, allowing them to surpass LLM-based counterparts. Given the substantial computational burden, existing LLM-based methods are not as effective as claimed for sequential recommendation. We hope that these theoretical understandings in conjunction with the empirical results will facilitate an objective evaluation of LLM-based recommendation in the future., Comment: 18 pages. arXiv admin note: substantial text overlap with arXiv:2402.06216

Machine anomalous sound detection (ASD) has emerged as one of the most promising applications in the Industrial Internet of Things (IIoT) due to its unprecedented efficacy in mitigating risks of malfunctions and promoting production efficiency. Previous works mainly investigated the machine ASD task under centralized settings. However, developing the ASD system under decentralized settings is crucial in practice, since the machine data are dispersed in various factories and the data should not be explicitly shared due to privacy concerns. To enable these factories to cooperatively develop a scalable ASD model while preserving their privacy, we propose a novel framework named CoopASD, where each factory trains an ASD model on its local dataset, and a central server aggregates these local models periodically. We employ a pre-trained model as the backbone of the ASD model to improve its robustness and develop specialized techniques to stabilize the model under a completely non-iid and domain shift setting. Compared with previous state-of-the-art (SOTA) models trained in centralized settings, CoopASD showcases competitive results with negligible degradation of 0.08%. We also conduct extensive ablation studies to demonstrate the effectiveness of CoopASD., Comment: Accepted by GLOBECOM 2024

Diffusion MRI (dMRI) is an advanced imaging technique characterizing tissue microstructure and white matter structural connectivity of the human brain. The demand for high-quality dMRI data is growing, driven by the need for better resolution and improved tissue contrast. However, acquiring high-quality dMRI data is expensive and time-consuming. In this context, deep generative modeling emerges as a promising solution to enhance image quality while minimizing acquisition costs and scanning time. In this study, we propose a novel generative approach to perform dMRI generation using deep diffusion models. It can generate high dimension (4D) and high resolution data preserving the gradients information and brain structure. We demonstrated our method through an image mapping task aimed at enhancing the quality of dMRI images from 3T to 7T. Our approach demonstrates highly enhanced performance in generating dMRI images when compared to the current state-of-the-art (SOTA) methods. This achievement underscores a substantial progression in enhancing dMRI quality, highlighting the potential of our novel generative approach to revolutionize dMRI imaging standards., Comment: 11 pages, 3 figures

To complete a complex task where a robot navigates to a goal object and fetches it, the robot needs to have a good understanding of the instructions and the surrounding environment. Large pre-trained models have shown capabilities to interpret tasks defined via language descriptions. However, previous methods attempting to integrate large pre-trained models with daily tasks are not competent in many robotic goal navigation tasks due to poor understanding of the environment. In this work, we present a visual scene representation built with large-scale visual language models to form a feature representation of the environment capable of handling natural language queries. Combined with large language models, this method can parse language instructions into action sequences for a robot to follow, and accomplish goal navigation with querying the scene representation. Experiments demonstrate that our method enables the robot to follow a wide range of instructions and complete complex goal navigation tasks.

This paper focuses on target-oriented grasping in occluded scenes, where the target object is specified by a binary mask and the goal is to grasp the target object with as few robotic manipulations as possible. Most existing methods rely on a push-grasping synergy to complete this task. To deliver a more powerful target-oriented grasping pipeline, we present MPGNet, a three-branch network for learning a synergy between moving, pushing, and grasping actions. We also propose a multi-stage training strategy to train the MPGNet which contains three policy networks corresponding to the three actions. The effectiveness of our method is demonstrated via both simulated and real-world experiments., Comment: Accepted to IROS 2024

Efficiently detecting target weld seams while ensuring sub-millimeter accuracy has always been an important challenge in autonomous welding, which has significant application in industrial practice. Previous works mostly focused on recognizing and localizing welding seams one by one, leading to inferior efficiency in modeling the workpiece. This paper proposes a novel framework capable of multiple weld seams extraction using both RGB images and 3D point clouds. The RGB image is used to obtain the region of interest by approximately localizing the weld seams, and the point cloud is used to achieve the fine-edge extraction of the weld seams within the region of interest using region growth. Our method is further accelerated by using a pre-trained deep learning model to ensure both efficiency and generalization ability. The performance of the proposed method has been comprehensively tested on various workpieces featuring both linear and curved weld seams and in physical experiment systems. The results showcase considerable potential for real-world industrial applications, emphasizing the method's efficiency and effectiveness. Videos of the real-world experiments can be found at https://youtu.be/pq162HSP2D4.

We study the task of language instruction-guided robotic manipulation, in which an embodied robot is supposed to manipulate the target objects based on the language instructions. In previous studies, the predicted manipulation regions of the target object typically do not change with specification from the language instructions, which means that the language perception and manipulation prediction are separate. However, in human behavioral patterns, the manipulation regions of the same object will change for different language instructions. In this paper, we propose Instruction-Guided Affordance Net (IGANet) for predicting affordance maps of instruction-guided robotic manipulation tasks by utilizing powerful priors from vision and language encoders pre-trained on large-scale datasets. We develop a Vison-Language-Models(VLMs)-based data augmentation pipeline, which can generate a large amount of data automatically for model training. Besides, with the help of Large-Language-Models(LLMs), actions can be effectively executed to finish the tasks defined by instructions. A series of real-world experiments revealed that our method can achieve better performance with generated data. Moreover, our model can generalize better to scenarios with unseen objects and language instructions., Comment: Accepted to ICARM 2024

This paper aims to establish the global well-posedness of the free boundary problem for the incompressible viscous resistive magnetohydrodynamic (MHD) equations. Under the framework of Lagrangian coordinates, a unique global solution exists in the half-space provided that the norm of the initial data in the critical homogeneous Besov space $\dot{B}_{p, 1}^{-1+N/p}(\mathbb{R}_{+}^N)$ is sufficiently small, where $p \in [N, 2N-1)$. Building upon prior work such as (Danchin and Mucha, J. Funct. Anal. 256 (2009) 881--927) and (Ogawa and Shimizu, J. Differ. Equations 274 (2021) 613--651) in the half-space setting, we establish maximal $L^{1}$-regularity for both the Stokes equations without surface stress and the linearized equations of the magnetic field with zero boundary condition. The existence and uniqueness of solutions to the nonlinear problems are proven using the Banach contraction mapping principle., Comment: 28 pages

Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video. In this year, LSVOS Challenge RVOS Track replaced the origin YouTube-RVOS benchmark with MeViS. MeViS focuses on referring the target object in a video through its motion descriptions instead of static attributes, posing a greater challenge to RVOS task. In this work, we integrate strengths of that leading RVOS and VOS models to build up a simple and effective pipeline for RVOS. Firstly, We finetune the state-of-the-art RVOS model to obtain mask sequences that are correlated with language descriptions. Secondly, based on a reliable and high-quality key frames, we leverage VOS model to enhance the quality and temporal consistency of the mask results. Finally, we further improve the performance of the RVOS model using semi-supervised learning. Our solution achieved 62.57 J&F on the MeViS test set and ranked 1st place for 6th LSVOS Challenge RVOS Track.

Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame. Recently, Segment Anything Model 2 (SAM 2) is proposed, which is a foundation model towards solving promptable visual segmentation in images and videos. SAM 2 builds a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. SAM 2 is a simple transformer architecture with streaming memory for real-time video processing, which trained on the date provides strong performance across a wide range of tasks. In this work, we evaluate the zero-shot performance of SAM 2 on the more challenging VOS datasets MOSE and LVOS. Without fine-tuning on the training set, SAM 2 achieved 75.79 J&F on the test set and ranked 4th place for 6th LSVOS Challenge VOS Track., Comment: arXiv admin note: substantial text overlap with arXiv:2408.00714

Relevance modeling is a critical component for enhancing user experience in search engines, with the primary objective of identifying items that align with users' queries. Traditional models only rely on the semantic congruence between queries and items to ascertain relevance. However, this approach represents merely one aspect of the relevance judgement, and is insufficient in isolation. Even powerful Large Language Models (LLMs) still cannot accurately judge the relevance of a query and an item from a semantic perspective. To augment LLMs-driven relevance modeling, this study proposes leveraging user interactions recorded in search logs to yield insights into users' implicit search intentions. The challenge lies in the effective prompting of LLMs to capture dynamic search intentions, which poses several obstacles in real-world relevance scenarios, i.e., the absence of domain-specific knowledge, the inadequacy of an isolated prompt, and the prohibitive costs associated with deploying LLMs. In response, we propose ProRBP, a novel Progressive Retrieved Behavior-augmented Prompting framework for integrating search scenario-oriented knowledge with LLMs effectively. Specifically, we perform the user-driven behavior neighbors retrieval from the daily search logs to obtain domain-specific knowledge in time, retrieving candidates that users consider to meet their expectations. Then, we guide LLMs for relevance modeling by employing advanced prompting techniques that progressively improve the outputs of the LLMs, followed by a progressive aggregation with comprehensive consideration of diverse aspects. For online serving, we have developed an industrial application framework tailored for the deployment of LLMs in relevance modeling. Experiments on real-world industry data and online A/B testing demonstrate our proposal achieves promising performance.

Orbital angular momentum (OAM), which is considered as a novel way to achieve high capacity, has been attracted much attention recently. OAM signals emitted by uniform circular array (UCA) are widely regarded to go through the Bessel-form channels. However, the channel gains corresponding to the Bessel-form channels are with low signal-to-noise-ratio (SNR) on OAM-modes and it is difficult to achieve high capacity using all OAM modes. To achieve maximum capacity offered by OAM multiplexing for wireless backhaul communications, in this paper we propose the optimal UCA design, which selects the optimal OAM-modes and radius of receive UCA. We formulate the capacity maximization problem and divide it into two subproblems for obtaining the corresponding optimal UCA design for OAM multiplexing based wireless backhaul communications. In particular, the optimal radius of the receive UCA is firstly derived. Then, we propose an mode selection scheme to choose appropriate OAM-modes for data transmission to maximize the capacity. Extensive simulations obtained validate that the capacity of OAM multiplexing can be significantly increased with our developed scheme.

Self-supervised Pretrained Models (PTMs) have demonstrated remarkable performance in computer vision and natural language processing tasks. These successes have prompted researchers to design PTMs for time series data. In our experiments, most self-supervised time series PTMs were surpassed by simple supervised models. We hypothesize this undesired phenomenon may be caused by data scarcity. In response, we test six time series generation methods, use the generated data in pretraining in lieu of the real data, and examine the effects on classification performance. Our results indicate that replacing a real-data pretraining set with a greater volume of only generated samples produces noticeable improvement., Comment: To appear in CIKM 2024 as a short paper; the version here is the self-contained version that includes the non-mandatory supplementary material available on the paper's companion website

Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the underlying cause of alignment failures. In this paper, we propose Alignment-Enhanced Decoding (AED), a novel defense that employs adaptive decoding to address the root causes of jailbreak issues. We first define the Competitive Index to quantify alignment failures and utilize feedback from self-evaluation to compute post-alignment logits. Then, AED adaptively combines AED and post-alignment logits with the original logits to obtain harmless and helpful distributions. Consequently, our method enhances safety alignment while maintaining helpfulness. We conduct experiments across five models and four common jailbreaks, with the results validating the effectiveness of our approach. Code is available at https://github.com/GIGABaozi/AED.git., Comment: 15 pages, 5 figures

New particles beyond the Standard Model of particle physics, such as axions, can be effectively searched through their interactions with electrons. We use the large liquid xenon detector PandaX-4T to search for novel electronic recoil signals induced by solar axions, neutrinos with anomalous magnetic moment, axion-like particles, dark photons, and light fermionic dark matter. A detailed background model is established with the latest datasets with 1.54 $\rm tonne \cdot year$ exposure. No significant excess above the background has been observed, and we have obtained competitive constraints for axion couplings, neutrino magnetic moment, and fermionic dark matter interactions.

Kolmogorov-Arnold Networks (KAN) has recently attracted significant attention as a promising alternative to traditional Multi-Layer Perceptrons (MLP). Despite their theoretical appeal, KAN require validation on large-scale benchmark datasets. Time series data, which has become increasingly prevalent in recent years, especially univariate time series are naturally suited for validating KAN. Therefore, we conducted a fair comparison among KAN, MLP, and mixed structures. The results indicate that KAN can achieve performance comparable to, or even slightly better than, MLP across 128 time series datasets. We also performed an ablation study on KAN, revealing that the output is primarily determined by the base component instead of b-spline function. Furthermore, we assessed the robustness of these models and found that KAN and the hybrid structure MLP\_KAN exhibit significant robustness advantages, attributed to their lower Lipschitz constants. This suggests that KAN and KAN layers hold strong potential to be robust models or to improve the adversarial robustness of other models., Comment: 14 pages, 8 figs

We use a multi-phase transport (AMPT) model to study multi-pion and multi-kaon Hanbury Brown-Twiss (HBT) correlations for the partially coherent particle-emitting sources in relativistic heavy-ion collisions. A density-dependent longitudinal coherent emission length and density-dependent transverse coherent emission length are introduced in calculating the multi-boson HBT correlation functions of the partially coherent sources. We compare the model results of three- and four-pion HBT correlation functions with experimental data in Pb-Pb collisions at center-of-mass energy $\sqrt{s_{NN}}=$2.76 TeV, and investigate the influences of boson coherent emissions on the multi-pion and multi-kaon correlation functions, respectively. We find that all of the three- and four-pion correlation functions of the partially coherent sources are consistent with experimental data. Coherent emission leads to the intercept decreases of the multi-boson correlation functions. The intercepts of the multi-kaon correlation functions of the partially coherent source are higher than those of the multi-pion correlation functions, because low kaon densities lead to smaller kaon coherent emission lengths than pion emission lengths. The intercepts of multi-boson correlation functions of partially coherent sources in high transverse momentum intervals are higher than those in low transverse momentum intervals because particle de Broglie wavelengths are small at high momenta., Comment: 19 pages, 12 figures

Hybrid magnonic systems have emerged as a promising direction for information propagation with preserved coherence. Due to high tunability of magnons, their interactions with microwave photons can be engineered to probe novel phenomena based on strong photon-magnon coupling. Improving the photon-magnon coupling strength can be done by tuning the structure of microwave resonators to better interact with the magnon counterpart. Planar resonators have been explored due to their potential for on-chip integration, but only common modes from stripline-based resonators have been used. Here, we present a microwave spiral resonator supporting the spoof localized surface plasmons (LSPs) and implement it to the investigation of photon-magnon coupling for hybrid magnonic applications. We showcase strong magnon-LSP photon coupling using a ferrimagnetic yttrium iron garnet sphere. We discuss the dependence of the spiral resonator design to the engineering capacity of the photon mode frequency and spatial field distributions, via both experiment and simulation. By the localized photon mode profiles, the resulting magnetic field concentrates near the surface dielectrics, giving rise to an enhanced magnetic filling factor. The strong coupling and large engineering space render the spoof LSPs an interesting contender in developing novel hybrid magnonic systems and functionalities., Comment: 13 pages, 13 figures

Orbital angular momentum (OAM) has attracted much attention for radio vortex wireless communications due to the orthogonality among different OAM-modes. To maintain the orthogonality among different OAM modes at the receiver, the strict alignment between transmit and receive antennas is highly demanded. However, it is not practical to guarantee the transceiver alignment in wireless communications. The phase turbulence, resulting from the misaligned transceivers, leads to serious inter-mode interference among different OAM modes and therefore fail for signals detection of multiple OAM modes at the receiver. To achieve practical OAM based wireless communications, in this paper we investigate the radio vortex wireless communications with misaligned transmit and receive antennas. We propose a joint Beamforming and Pre-detection (BePre) scheme, which uses two unitary matrices to convert the channel matrix into the equivalent circulant matrix for keeping the orthogonality among OAM-modes at the receiver. Then, the OAM signals can be detected with the mode-decomposition scheme at the misaligned receiver. Extensive simulations obtained validate and evaluate that our developed joint BePre scheme can efficiently detect the signals of multiple OAM-modes for the misaligned transceiver and can significantly increase the spectrum efficiency.

Multiple-input-multiple-output (MIMO) has been proved its success for the fourth generation (4G) long term evolution (LTE) and is one of the key technical enablers for evolved mobile broadband (eMBB) in the fifth generation (5G) wireless communications. However, along with the number of antennas eventually increased to be extremely large and one-hop communication distance gradually reduced, how to significantly increase the capacity for line-of-sight (LOS) MIMO becomes more and more urgent. In this article, we introduce the quasi-fractal uniform circular array (QF-UCA) antenna structure based MIMO wireless communications, which can adequately exploit the potential of MIMO in LOS channel and greatly increase the capacity with low complexity demodulation schemes. Specifically, three advantages regarding QF-UCA based LOS MIMO are reviewed. Then, research challenges on transceiver alignment, low-rank channel matrix, extended dimensions of QF-UCA, maximum number of orthogonal streams, and the corresponding potential solutions are discussed. Compared with traditional scattering-depended MIMO communications, the QF-UCA based LOS MIMO wireless communication can achieve high-efficient transmission in LOS channel.

Whisper and other large-scale automatic speech recognition models have made significant progress in performance. However, their performance on many low-resource languages, such as Kazakh, is not satisfactory. It is worth researching how to utilize low-cost data to improve the performance of Whisper on under-represented languages. In this study, we utilized easily accessible unpaired speech and text data and combined the language model GPT with Whisper on Kazakh. We implemented end of transcript (EOT) judgment modification and hallucination penalty to improve the performance of speech recognition. Further, we employed the decoding average token log probability as a criterion to select samples from unlabeled speech data and used pseudo-labeled data to fine-tune the model to further improve its performance. Ultimately, we achieved more than 10\% absolute WER reduction in multiple experiments, and the whole process has the potential to be generalized to other under-represented languages., Comment: Accepted by INTERSPEECH 2024;Minor typo correction

The development of orbital angular momentum (OAM)-based radio vortex transmission presents a promising opportunity for increasing the capacity of wireless communication in correlated channels due to its inherent orthogonality among different OAM modes. One of the most popular schemes for high-efficient OAM transmission is the digital baseband associated with uniform circular array (UCA) based transceiver. However, the periodicity of complex-exponential feed makes the maximum number of orthogonal signals carried by multiple OAM modes generally restricted to the array-element number of UCA antenna, which poses an open question of how to employ more OAM modes given a fixed number of array elements. Furthermore, signals modulated with high-order OAM modes are difficult to be captured by the receiver due to their serious divergence as propagating in free space, thus severely limiting the capacity of radio vortex communications. To overcome the above challenges, in this paper based on the partly element-overlapped fractal geometry layout and effectively using low-order OAM modes, we propose the quasi-fractal UCA (QF-UCA) antenna based OAM multiplexing transmission. We perform the two-dimension OAM modulation (TOM) and demodulation (TOD) schemes with the orthogonal OAM mode number exceeding the array-element number, which is beyond the traditional concept of multiple antennas based wireless communications. Simulation results show that our proposed scheme can achieve more number of orthogonal multiplexing streams than the maximum number of orthogonal multiplexing corresponding to traditional multiple antenna systems.

With the exponential surge in traffic data and the pressing need for ultra-low latency in emerging intelligence applications, it is envisioned that 6G networks will demand disruptive communication technologies to foster ubiquitous intelligence and succinctness within the human society. Semantic communication, a novel paradigm, holds the promise of significantly curtailing communication overhead and latency by transmitting only task-relevant information. Despite numerous efforts in both theoretical frameworks and practical implementations of semantic communications, a substantial theory-practice gap complicates the theoretical analysis and interpretation, particularly when employing black-box machine learning techniques. This article initially delves into information-theoretic metrics such as semantic entropy, semantic distortions, and semantic communication rate to characterize the information flow in semantic communications. Subsequently, it provides a guideline for implementing semantic communications to ensure both theoretical interpretability and communication effectiveness., Comment: This paper has been accepted by IEEE Network Magazine

Accurate traffic Flow Prediction can assist in traffic management, route planning, and congestion mitigation, which holds significant importance in enhancing the efficiency and reliability of intelligent transportation systems (ITS). However, existing traffic flow prediction models suffer from limitations in capturing the complex spatial-temporal dependencies within traffic networks. In order to address this issue, this study proposes a multi-segment fusion tensor graph convolutional network (MS-FTGCN) for traffic flow prediction with the following three-fold ideas: a) building a unified spatial-temporal graph convolutional framework based on Tensor M-product, which capture the spatial-temporal patterns simultaneously; b) incorporating hourly, daily, and weekly components to model multi temporal properties of traffic flows, respectively; c) fusing the outputs of the three components by attention mechanism to obtain the final traffic flow prediction results. The results of experiments conducted on two traffic flow datasets demonstrate that the proposed MS-FTGCN outperforms the state-of-the-art models.

Large-scale multi-session LiDAR mapping is essential for a wide range of applications, including surveying, autonomous driving, crowdsourced mapping, and multi-agent navigation. However, existing approaches often struggle with data redundancy, robustness, and accuracy in complex environments. To address these challenges, we present MS-Mapping, an novel multi-session LiDAR mapping system that employs an incremental mapping scheme for robust and accurate map assembly in large-scale environments. Our approach introduces three key innovations: 1) A distribution-aware keyframe selection method that captures the subtle contributions of each point cloud frame to the map by analyzing the similarity of map distributions. This method effectively reduces data redundancy and pose graph size, while enhancing graph optimization speed; 2) An uncertainty model that automatically performs least-squares adjustments according to the covariance matrix during graph optimization, improving mapping precision, robustness, and flexibility without the need for scene-specific parameter tuning. This uncertainty model enables our system to monitor pose uncertainty and avoid ill-posed optimizations, thereby increasing adaptability to diverse and challenging environments. 3) To ensure fair evaluation, we redesign baseline comparisons and the evaluation benchmark. Direct assessment of map accuracy demonstrates the superiority of the proposed MS-Mapping algorithm compared to state-of-the-art methods. In addition to employing public datasets such as Urban-Nav, FusionPortable, and Newer College, we conducted extensive experiments on such a large \SI{855}{m}$\times$\SI{636}{m} ground truth map, collecting over \SI{20}{km} of indoor and outdoor data across more than ten sequences..., Comment: 18 pages, 22 figures

The emergence of learned indexes has caused a paradigm shift in our perception of indexing by considering indexes as predictive models that estimate keys' positions within a data set, resulting in notable improvements in key search efficiency and index size reduction; however, a significant challenge inherent in learned index modeling is its constrained support for update operations, necessitated by the requirement for a fixed distribution of records. Previous studies have proposed various approaches to address this issue with the drawback of high overhead due to multiple model retraining. In this paper, we present UpLIF, an adaptive self-tuning learned index that adjusts the model to accommodate incoming updates, predicts the distribution of updates for performance improvement, and optimizes its index structure using reinforcement learning. We also introduce the concept of balanced model adjustment, which determines the model's inherent properties (i.e. bias and variance), enabling the integration of these factors into the existing index model without the need for retraining with new data. Our comprehensive experiments show that the system surpasses state-of-the-art indexing solutions (both traditional and ML-based), achieving an increase in throughput of up to 3.12 times with 1000 times less memory usage., Comment: 20 pages, ACM IDEAS 2024

We consider the problem of Gaussian approximation for the $\kappa$th coordinate of a sum of high-dimensional random vectors. Such a problem has been studied previously for $\kappa=1$ (i.e., maxima). However, in many applications, a general $\kappa\geq1$ is of great interest, which is addressed in this paper. We make four contributions: 1) we first show that the distribution of the $\kappa$th coordinate of a sum of random vectors, $\boldsymbol{X}= (X_{1},\cdots,X_{p})^{\sf T}= n^{-1/2}\sum_{i=1}^n \boldsymbol{x}_{i}$, can be approximated by that of Gaussian random vectors and derive their Kolmogorov's distributional difference bound; 2) we provide the theoretical justification for estimating the distribution of the $\kappa$th coordinate of a sum of random vectors using a Gaussian multiplier procedure, which multiplies the original vectors with i.i.d. standard Gaussian random variables; 3) we extend the Gaussian approximation result and Gaussian multiplier bootstrap procedure to a more general case where $\kappa$ diverges; 4) we further consider the Gaussian approximation for a square sum of the first $d$ largest coordinates of $\boldsymbol{X}$. All these results allow the dimension $p$ of random vectors to be as large as or much larger than the sample size $n$.

The expanding applications of legged robots require their mastery of versatile motion skills. Correspondingly, researchers must address the challenge of integrating multiple diverse motion skills into controllers. While existing reinforcement learning (RL)-based approaches have achieved notable success in multi-skill integration for legged robots, these methods often require intricate reward engineering or are restricted to integrating a predefined set of motion skills constrained by specific task objectives, resulting in limited flexibility. In this work, we introduce a flexible multi-skill integration framework named Controllable Skills Integration (CSI). CSI enables the integration of a diverse set of motion skills with varying styles into a single policy without the need for complex reward tuning. Furthermore, in a hierarchical control manner, the trained low-level policy can be coupled with a high-level Natural Language Inference (NLI) module to enable preliminary language-directed skill control. Our experiments demonstrate that CSI can flexibly integrate a diverse array of motion skills more comprehensively and facilitate the transitions between different skills. Additionally, CSI exhibits good scalability as the number of motion skills to be integrated increases significantly.

Long-term time series forecasting (LTSF) has been widely applied in finance, traffic prediction, and other domains. Recently, patch-based transformers have emerged as a promising approach, segmenting data into sub-level patches that serve as input tokens. However, existing methods mostly rely on predetermined patch lengths, necessitating expert knowledge and posing challenges in capturing diverse characteristics across various scales. Moreover, time series data exhibit diverse variations and fluctuations across different temporal scales, which traditional approaches struggle to model effectively. In this paper, we propose a dynamic tokenizer with a dynamic sparse learning algorithm to capture diverse receptive fields and sparse patterns of time series data. In order to build hierarchical receptive fields, we develop a multi-scale Transformer model, coupled with multi-scale sequence extraction, capable of capturing multi-resolution features. Additionally, we introduce a group-aware rotary position encoding technique to enhance intra- and inter-group position awareness among representations across different temporal scales. Our proposed model, named DRFormer, is evaluated on various real-world datasets, and experimental results demonstrate its superiority compared to existing methods. Our code is available at: https://github.com/ruixindingECNU/DRFormer.

In an era defined by the explosive growth of data and rapid technological advancements, Multimodal Large Language Models (MLLMs) stand at the forefront of artificial intelligence (AI) systems. Designed to seamlessly integrate diverse data types-including text, images, videos, audio, and physiological sequences-MLLMs address the complexities of real-world applications far beyond the capabilities of single-modality systems. In this paper, we systematically sort out the applications of MLLM in multimodal tasks such as natural language, vision, and audio. We also provide a comparative analysis of the focus of different MLLMs in the tasks, and provide insights into the shortcomings of current MLLMs, and suggest potential directions for future research. Through these discussions, this paper hopes to provide valuable insights for the further development and application of MLLM.

Conventional multiple-input multiple-out (MIMO) technologies have encountered bottlenecks of significantly increasing spectrum efficiencies of wireless communications due to the low degrees of freedom in practical line-of-sight scenarios and severe path loss of high frequency carriers. Orbital angular momentum (OAM) has shown the potential for high spectrum efficiencies in radio frequency domains. To investigate the advantage of OAM in multiuser communications, in this paper we propose the reconfigurable intelligence surface (RIS) assisted OAM multiuser (MU) wireless communication schemes, where RIS is deployed to establish the direct links blocked by obstacles between the OAM transmitter and users, to significantly increase the achievable sum rate (ASR) of MU systems. To maximize the ASR, we develop the alternative optimization algorithm to jointly optimize the transmit power and phase shifts of RIS. The numerical outcomes demonstrate the superiority of our proposed scheme compared to existing methods in terms of ASR., Comment: 5 pages, 5 figures and accepted by UCom 2024

In this letter, we report the dark matter search results from the commissioning run and the first science run of the PandaX-4T experiment. A blind analysis is carried out on the entire data set. The data processing is improved compared to previous work, unifying the low-level signal reconstruction in a wide energy range up to 120 keV. With a total exposure of 1.54 tonne$\cdot$year, no significant excess of nuclear recoil events is found. The lowest 90% confidence level exclusion on the spin-independent cross section is $1.6 \times 10^{-47} \mathrm{cm}^2$ at a dark matter mass of 40 GeV$/c^2$. Our results represent the most stringent constraint for a dark matter mass above 100 GeV$/c^2$.

Some companies(e.g., Microsoft Research and Google DeepMind) have discovered some of the limitations of GPTs autoregressive paradigm next-word prediction, manifested in the model lack of planning, working memory, backtracking, and reasoning skills. GPTs rely on a local and greedy process of generating the next word, without a global understanding of the task or the output.We have confirmed the above limitations through specialized empirical studies of code comprehension. Although GPT4 is good at producing fluent and coherent text, it cannot handle complex logic and generate new code that haven not been seen, and it relies too much on the formatting of the prompt to generate the correct code.We propose a new paradigm for code understanding that goes beyond the next-word prediction paradigm, inspired by the successful application of diffusion techniques to image generation(Dalle2, Sora) and protein structure generation(AlphaFold3), which have no autoregressive constraints.Instead of encoding the code in a form that mimics natural language, we encode the code as a heterogeneous image paradigm with a memory of global information that mimics both images and protein structures.We then refer to Sora's CLIP upstream text-to-image encoder model to design a text-to-code encoder model that can be applied to various downstream code understanding tasks.The model learns the global understanding of code under the new paradigm heterogeneous image, connects the encoding space of text and code, and encodes the input of text into the vector of code most similar to it.Using self-supervised comparative learning on 456,360 text-code pairs, the model achieved a zero-shot prediction of new data. This work is the basis for future work on code generation using diffusion techniques under a new paradigm to avoid autoregressive limitations., Comment: 10 page, 14 figures

Accurate diagnosis of depression is crucial for timely implementation of optimal treatments, preventing complications and reducing the risk of suicide. Traditional methods rely on self-report questionnaires and clinical assessment, lacking objective biomarkers. Combining fMRI with artificial intelligence can enhance depression diagnosis by integrating neuroimaging indicators. However, the specificity of fMRI acquisition for depression often results in unbalanced and small datasets, challenging the sensitivity and accuracy of classification models. In this study, we propose the Spatio-Temporal Aggregation Network (STANet) for diagnosing depression by integrating CNN and RNN to capture both temporal and spatial features of brain activity. STANet comprises the following steps:(1) Aggregate spatio-temporal information via ICA. (2) Utilize multi-scale deep convolution to capture detailed features. (3) Balance data using the SMOTE to generate new samples for minority classes. (4) Employ the AFGRU classifier, which combines Fourier transformation with GRU, to capture long-term dependencies, with an adaptive weight assignment mechanism to enhance model generalization. The experimental results demonstrate that STANet achieves superior depression diagnostic performance with 82.38% accuracy and a 90.72% AUC. The STFA module enhances classification by capturing deeper features at multiple scales. The AFGRU classifier, with adaptive weights and stacked GRU, attains higher accuracy and AUC. SMOTE outperforms other oversampling methods. Additionally, spatio-temporal aggregated features achieve better performance compared to using only temporal or spatial features. STANet outperforms traditional or deep learning classifiers, and functional connectivity-based classifiers, as demonstrated by ten-fold cross-validation.

In the past decade, significant strides in deep learning have led to numerous groundbreaking applications. Despite these advancements, the understanding of the high generalizability of deep learning, especially in such an over-parametrized space, remains limited. Successful applications are often considered as empirical rather than scientific achievements. For instance, deep neural networks' (DNNs) internal representations, decision-making mechanism, absence of overfitting in an over-parametrized space, high generalizability, etc., remain less understood. This paper delves into the loss landscape of DNNs through the lens of spin glass in statistical physics, i.e. a system characterized by a complex energy landscape with numerous metastable states, to better understand how DNNs work. We investigated a single hidden layer Rectified Linear Unit (ReLU) neural network model, and introduced several protocols to examine the analogy between DNNs (trained with datasets including MNIST and CIFAR10) and spin glass. Specifically, we used (1) random walk in the parameter space of DNNs to unravel the structures in their loss landscape; (2) a permutation-interpolation protocol to study the connection between copies of identical regions in the loss landscape due to the permutation symmetry in the hidden layers; (3) hierarchical clustering to reveal the hierarchy among trained solutions of DNNs, reminiscent of the so-called Replica Symmetry Breaking (RSB) phenomenon (i.e. the Parisi solution) in analogy to spin glass; (4) finally, we examine the relationship between the degree of the ruggedness of the loss landscape of the DNN and its generalizability, showing an improvement of flattened minima., Comment: 21 pages, 10 figures

Cloud key-value (KV) stores provide businesses with a cost-effective and adaptive alternative to traditional on-premise data management solutions. KV stores frequently consist of heterogeneous clusters, characterized by varying hardware specifications of the deployment nodes, with each node potentially running a distinct version of the KV store software. This heterogeneity is accompanied by the diverse metadata that they need to manage. In this study, we introduce MetaHive, a cache-optimized approach to managing metadata in heterogeneous KV store clusters. MetaHive disaggregates the original data from its associated metadata to promote independence between them, while maintaining their interconnection during usage. This makes the metadata opaque from the downstream processes and the other KV stores in the cluster. MetaHive also ensures that the KV and metadata entries are stored in the vicinity of each other in memory and storage. This allows MetaHive to optimally utilize the caching mechanism without extra storage read overhead for metadata retrieval. We deploy MetaHive to ensure data integrity in RocksDB and demonstrate its rapid data validation with minimal effect on performance., Comment: Cloud Databases

In this letter, we investigate the channel estimation problem for MIMO wireless communication systems with movable antennas (MAs) at both the transmitter (Tx) and receiver (Rx). To achieve high channel estimation accuracy with low pilot training overhead, we propose a tensor decomposition-based method for estimating the parameters of multi-path channel components, including their azimuth and elevation angles, as well as complex gain coefficients, thereby reconstructing the wireless channel between any pair of Tx and Rx MA positions in the Tx and Rx regions. First, we introduce a two-stage Tx-Rx successive antenna movement pattern for pilot training, such that the received pilot signals in both stages can be expressed as a third-order tensor. Then, we obtain the factor matrices of the tensor via the canonical polyadic decomposition, and thereby estimate the angle/gain parameters for enabling the channel reconstruction between arbitrary Tx/Rx MA positions. In addition, we analyze the uniqueness condition of the tensor decomposition, which ensures the complete channel reconstruction between the whole Tx and Rx regions based on the channel measurements at only a finite number of Tx/Rx MA positions. Finally, simulation results are presented to evaluate the proposed tensor decomposition-based method as compared to existing methods, in terms of channel estimation accuracy and pilot overhead., Comment: 5 pages, 3 figures

For unforeseen natural disasters, such as earthquakes, hurricanes, and floods, etc., the traditional communication infrastructure is unavailable or seriously disrupted along with persistent secondary disasters. Under such circumstances, it is highly demanded to deploy emergency wireless communication (EWC) networks to restore connectivity in accident/incident areas. The emerging fifth-generation (5G)/beyond-5G (B5G) wireless communication system, like unmanned aerial vehicle (UAV) assisted networks and intelligent reflecting surface (IRS) based communication systems, are expected to be designed or re-farmed for supporting temporary high quality communications in post-disaster areas. However, the channel characteristics of post-disaster areas quickly change as the secondary disaster resulted topographical changes, imposing new but critical challenges for EWC networks. In this paper, we propose a novel heterogeneous $\mathcal{F}$ composite fading channel model for EWC networks which accurately models and characterizes the composite fading channel with reflectors, path-loss exponent, fading, and shadowing parameters in 5G-UAV based EWC networks. Based on the model, we develop the optimal power allocation scheme with the simple closed-form expression and the numerical results based optimal joint bandwidth-power allocation scheme. We derive the corresponding capacities and compare the energy efficiency between IRS and traditional relay based 5G-UAVs. Numerical results show that the new heterogeneous Fisher-Snedecor $\mathcal{F}$ composite fading channel adapted resource allocation schemes can achieve higher capacity and energy efficiency than those of traditional channel model adapted resource allocation schemes, thus providing better communications service for post-disaster areas.

For unforeseen emergencies, such as natural disasters and pandemic events, it is highly demanded to cope with the explosive growth of mobile data traffic in extremely critical environments. An Unmanned aerial vehicle (UAV) fleet is an effective way to facilitate the Emergency wireless COmmunication NETwork (EcoNet). In this article, a MUlti-tier Heterogeneous UAV Network (MuHun), which is with different UAV fleets in different altitudes, is proposed to flexibly serve various emergencies. We refresh the key performance indicators of full coverage, network capacity, low latency, and energy efficiency in harsh environments. Then, we present the special challenges regarding shadowing-dominated complex channel model, energy supply limited short-endurance, various communication mechanisms coexistence, and communication island for underground users in UAV-based EcoNet, followed by the MuHun-based EcoNet architecture and its advantages. Furthermore, some potential solutions such as the new hybrid-channel adapted resource allocation, reconfigurable intelligent surface assisted UAV communications, competitive heterogenous-networks, and magnetic induction based air-to-ground/underground communications are discussed to effectively achieve full coverage, high capacity, high energy efficiency, and diverse qualities of services for EcoNets in harsh environments.

When reading long-form text, human cognition is complex and structurized. While large language models (LLMs) process input contexts through a causal and sequential perspective, this approach can potentially limit their ability to handle intricate and complex inputs effectively. To enhance LLM's cognition capability, this paper presents a novel concept of context structurization. Specifically, we transform the plain, unordered contextual sentences into well-ordered and hierarchically structurized elements. By doing so, LLMs can better grasp intricate and extended contexts through precise attention and information-seeking along the organized structures. Extensive evaluations are conducted across various model architectures and sizes (including several 7B- to 72B-size auto-regressive LLMs as well as BERT-like masking models) on a diverse set of NLP tasks (e.g., context-based question-answering, exhaustive hallucination evaluation, and passage-level dense retrieval). Empirical results show consistent and significant performance gains afforded by a single-round structurization. In particular, we boost a 72B-parameter open-source model to achieve comparable performance against GPT-3.5-Turbo as the hallucination evaluator. Besides, we show the feasibility of distilling advanced LLMs' language processing abilities to a smaller yet effective StruXGPT-7B to execute structurization, addressing the practicality of our approach. Code will be made public soon., Comment: N/A

In this paper, we propose a virtual full-duplex (VFD) technique with zero-interval modulation and sampling (ZIMS), where two half-duplex (HD) transceivers can simultaneously transmit signals and each transceiver can effectively receive the desired information. In ZIMS-VFD, the transceiver inserts a zero-interval for each symbol in the transmit signal and provides self-interference (SI)-free intervals for itself. Meanwhile, it samples the receive signal in the provided SI-free intervals and restores the desired symbols. Based on orthogonal frequency division multiplexing (OFDM), we formulate the system model and show the transmit signal structure. Then, we give the transceiver design for single input single output (SISO) ZIMS-VFD and extend it to multiple input multiple output (MIMO) communications. Numerical results verify our theoretical analyses and show that ZIMS-VFD can effectively increase the capacity and approach the FD without SI.

Affective Behavior Analysis aims to develop emotionally intelligent technology that can recognize and respond to human emotions. To advance this, the 7th Affective Behavior Analysis in-the-wild (ABAW) competition establishes two tracks: i.e., the Multi-task Learning (MTL) Challenge and the Compound Expression (CE) challenge based on Aff-Wild2 and C-EXPR-DB datasets. In this paper, we present our methods and experimental results for the two competition tracks. Specifically, it can be summarized in the following four aspects: 1) To attain high-quality facial features, we train a Masked-Auto Encoder in a self-supervised manner. 2) We devise a temporal convergence module to capture the temporal information between video frames and explore the impact of window size and sequence length on each sub-task. 3) To facilitate the joint optimization of various sub-tasks, we explore the impact of sub-task joint training and feature fusion from individual tasks on each task performance improvement. 4) We utilize curriculum learning to transition the model from recognizing single expressions to recognizing compound expressions, thereby improving the accuracy of compound expression recognition. Extensive experiments demonstrate the superiority of our designs., Comment: Techical Report for 7th ABAW Competition

Facial Expression Analysis remains a challenging task due to unexpected task-irrelevant noise, such as identity, head pose, and background. To address this issue, this paper proposes a novel framework, called Norface, that is unified for both Action Unit (AU) analysis and Facial Emotion Recognition (FER) tasks. Norface consists of a normalization network and a classification network. First, the carefully designed normalization network struggles to directly remove the above task-irrelevant noise, by maintaining facial expression consistency but normalizing all original images to a common identity with consistent pose, and background. Then, these additional normalized images are fed into the classification network. Due to consistent identity and other factors (e.g. head pose, background, etc.), the normalized images enable the classification network to extract useful expression information more effectively. Additionally, the classification network incorporates a Mixture of Experts to refine the latent representation, including handling the input of facial representations and the output of multiple (AU or emotion) labels. Extensive experiments validate the carefully designed framework with the insight of identity normalization. The proposed method outperforms existing SOTA methods in multiple facial expression analysis tasks, including AU detection, AU intensity estimation, and FER tasks, as well as their cross-dataset tasks. For the normalized datasets and code please visit {https://norface-fea.github.io/}., Comment: Accepted by ECCV2024

Most multi-agent reinforcement learning approaches adopt two types of policy optimization methods that either update policy simultaneously or sequentially. Simultaneously updating policies of all agents introduces non-stationarity problem. Although sequentially updating policies agent-by-agent in an appropriate order improves policy performance, it is prone to low efficiency due to sequential execution, resulting in longer model training and execution time. Intuitively, partitioning policies of all agents according to their interdependence and updating joint policy batch-by-batch can effectively balance performance and efficiency. However, how to determine the optimal batch partition of policies and batch updating order are challenging problems. Firstly, a sequential batched policy updating scheme, B2MAPO (Batch by Batch Multi-Agent Policy Optimization), is proposed with a theoretical guarantee of the monotonic incrementally tightened bound. Secondly, a universal modulized plug-and-play B2MAPO hierarchical framework, which satisfies CTDE principle, is designed to conveniently integrate any MARL models to fully exploit and merge their merits, including policy optimality and inference efficiency. Next, a DAG-based B2MAPO algorithm is devised, which is a carefully designed implementation of B2MAPO framework. Comprehensive experimental results conducted on StarCraftII Multi-agent Challenge and Google Football Research demonstrate the performance of DAG-based B2MAPO algorithm outperforms baseline methods. Meanwhile, compared with A2PO, our algorithm reduces the model training and execution time by 60.4% and 78.7%, respectively.

Recent advances in visual prompting in the natural image area have allowed users to interact with artificial intelligence (AI) tools through various visual marks such as box, point, and free-form shapes. However, due to the significant difference between the natural and remote sensing (RS) images, existing visual prompting models face challenges in RS scenarios. Moreover, RS MLLMs mainly focus on interpreting image-level RS data and only support interaction with language instruction, restricting flexibility applications in the real world. To address those limitations, the first visual prompting model named EarthMarker is proposed, which excels in image-level, region-level, and point-level RS imagery interpretation. Specifically, the visual prompts alongside images and text instruction input into the large language model (LLM), adapt models toward specific predictions and tasks. Subsequently, a sharing visual encoding method is introduced to refine multi-scale image features and visual prompt information uniformly. Furthermore, to endow the EarthMarker with versatile multi-granularity visual perception abilities, the cross-domain phased learning strategy is developed, and the disjoint parameters are optimized in a lightweight manner by leveraging both the natural and RS domain-specific knowledge. In addition, to tackle the lack of RS visual prompting data, a dataset named RSVP featuring multi-modal fine-grained visual prompting instruction is constructed. Extensive experiments are conducted to demonstrate the proposed EarthMarker's competitive performance, representing a significant advance in multi-granularity RS imagery interpretation under the visual prompting learning framework.