Search

Dataset Distillation (DD) is an emerging technique that compresses large-scale datasets into significantly smaller synthesized datasets while preserving high test performance and enabling the efficient training of large models. However, current research primarily focuses on enhancing evaluation accuracy under limited compression ratios, often overlooking critical security concerns such as adversarial robustness. A key challenge in evaluating this robustness lies in the complex interactions between distillation methods, model architectures, and adversarial attack strategies, which complicate standardized assessments. To address this, we introduce BEARD, an open and unified benchmark designed to systematically assess the adversarial robustness of DD methods, including DM, IDM, and BACON. BEARD encompasses a variety of adversarial attacks (e.g., FGSM, PGD, C&W) on distilled datasets like CIFAR-10/100 and TinyImageNet. Utilizing an adversarial game framework, it introduces three key metrics: Robustness Ratio (RR), Attack Efficiency Ratio (AE), and Comprehensive Robustness-Efficiency Index (CREI). Our analysis includes unified benchmarks, various Images Per Class (IPC) settings, and the effects of adversarial training. Results are available on the BEARD Leaderboard, along with a library providing model and dataset pools to support reproducible research. Access the code at BEARD., Comment: 15 pages, 6 figures

This research focuses on real-time monitoring and analysis of track and field athletes, addressing the limitations of traditional monitoring systems in terms of real-time performance and accuracy. We propose an IoT-optimized system that integrates edge computing and deep learning algorithms. Traditional systems often experience delays and reduced accuracy when handling complex motion data, whereas our method, by incorporating a SAC-optimized deep learning model within the IoT architecture, achieves efficient motion recognition and real-time feedback. Experimental results show that this system significantly outperforms traditional methods in response time, data processing accuracy, and energy efficiency, particularly excelling in complex track and field events. This research not only enhances the precision and efficiency of athlete monitoring but also provides new technical support and application prospects for sports science research., Comment: 17 pages

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from labeled source domains to improve performance on the unlabeled target domains. While Convolutional Neural Networks (CNNs) have been dominant in previous UDA methods, recent research has shown promise in applying Vision Transformers (ViTs) to this task. In this study, we propose a novel Feature Fusion Transferability Aware Transformer (FFTAT) to enhance ViT performance in UDA tasks. Our method introduces two key innovations: First, we introduce a patch discriminator to evaluate the transferability of patches, generating a transferability matrix. We integrate this matrix into self-attention, directing the model to focus on transferable patches. Second, we propose a feature fusion technique to fuse embeddings in the latent space, enabling each embedding to incorporate information from all others, thereby improving generalization. These two components work in synergy to enhance feature representation learning. Extensive experiments on widely used benchmarks demonstrate that our method significantly improves UDA performance, achieving state-of-the-art (SOTA) results., Comment: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

Adversarial detection is designed to identify and reject maliciously crafted adversarial examples(AEs) which are generated to disrupt the classification of target models. Presently, various input transformation-based methods have been developed on adversarial example detection, which typically rely on empirical experience and lead to unreliability against new attacks. To address this issue, we propose and conduct a Dynamically Stable System (DSS), which can effectively detect the adversarial examples from normal examples according to the stability of input examples. Particularly, in our paper, the generation of adversarial examples is considered as the perturbation process of a Lyapunov dynamic system, and we propose an example stability mechanism, in which a novel control term is added in adversarial example generation to ensure that the normal examples can achieve dynamic stability while the adversarial examples cannot achieve the stability. Then, based on the proposed example stability mechanism, a Dynamically Stable System (DSS) is proposed, which can utilize the disruption and restoration actions to determine the stability of input examples and detect the adversarial examples through changes in the stability of the input examples. In comparison with existing methods in three benchmark datasets(MNIST, CIFAR10, and CIFAR100), our evaluation results show that our proposed DSS can achieve ROC-AUC values of 99.83%, 97.81% and 94.47%, surpassing the state-of-the-art(SOTA) values of 97.35%, 91.10% and 93.49% in the other 7 methods.

In this paper, we propose a novel framework for enhancing visual comprehension in autonomous driving systems by integrating visual language models (VLMs) with additional visual perception module specialised in object detection. We extend the Llama-Adapter architecture by incorporating a YOLOS-based detection network alongside the CLIP perception network, addressing limitations in object detection and localisation. Our approach introduces camera ID-separators to improve multi-view processing, crucial for comprehensive environmental awareness. Experiments on the DriveLM visual question answering challenge demonstrate significant improvements over baseline models, with enhanced performance in ChatGPT scores, BLEU scores, and CIDEr metrics, indicating closeness of model answer to ground truth. Our method represents a promising step towards more capable and interpretable autonomous driving systems. Possible safety enhancement enabled by detection modality is also discussed., Comment: accepted by SafeGenAI workshop of NeurIPS 2024

This paper examines how a firm's performance can decline despite consistently implementing successful A/B test innovations -- a phenomenon we term "seesaw experimentation." While these innovations improve the measured primary dimension, they create negative externalities in unmeasured secondary dimensions that exceed the gains. Using a multivariate normal distribution model, we identify the conditions for this decline and propose positive hurdle rates as a solution. Our analysis shows how to set optimal hurdle rates to best mitigate these negative externalities and provides practical guidance for experimental design by demonstrating how these rates should vary with underlying parameters., Comment: 15 pages, 1 figure

Building a robust underwater acoustic recognition system in real-world scenarios is challenging due to the complex underwater environment and the dynamic motion states of targets. A promising optimization approach is to leverage the intrinsic physical characteristics of targets, which remain invariable regardless of environmental conditions, to provide robust insights. However, our study reveals that while physical characteristics exhibit robust properties, they may lack class-specific discriminative patterns. Consequently, directly incorporating physical characteristics into model training can potentially introduce unintended inductive biases, leading to performance degradation. To utilize the benefits of physical characteristics while mitigating possible detrimental effects, we propose DEMONet in this study, which utilizes the detection of envelope modulation on noise (DEMON) to provide robust insights into the shaft frequency or blade counts of targets. DEMONet is a multi-expert network that allocates various underwater signals to their best-matched expert layer based on DEMON spectra for fine-grained signal processing. Thereinto, DEMON spectra are solely responsible for providing implicit physical characteristics without establishing a mapping relationship with the target category. Furthermore, to mitigate noise and spurious modulation spectra in DEMON features, we introduce a cross-temporal alignment strategy and employ a variational autoencoder (VAE) to reconstruct noise-resistant DEMON spectra to replace the raw DEMON features. The effectiveness of the proposed DEMONet with cross-temporal VAE was primarily evaluated on the DeepShip dataset and our proprietary datasets. Experimental results demonstrated that our approach could achieve state-of-the-art performance on both datasets.

Few-shot Class Incremental Learning (FSCIL) presents a challenging yet realistic scenario, which requires the model to continually learn new classes with limited labeled data (i.e., incremental sessions) while retaining knowledge of previously learned base classes (i.e., base sessions). Due to the limited data in incremental sessions, models are prone to overfitting new classes and suffering catastrophic forgetting of base classes. To tackle these issues, recent advancements resort to prototype-based approaches to constrain the base class distribution and learn discriminative representations of new classes. Despite the progress, the limited data issue still induces ill-divided feature space, leading the model to confuse the new class with old classes or fail to facilitate good separation among new classes. In this paper, we aim to mitigate these issues by directly constraining the span of each class distribution from a covariance perspective. In detail, we propose a simple yet effective covariance constraint loss to force the model to learn each class distribution with the same covariance matrix. In addition, we propose a perturbation approach to perturb the few-shot training samples in the feature space, which encourages the samples to be away from the weighted distribution of other classes. Regarding perturbed samples as new class data, the classifier is forced to establish explicit boundaries between each new class and the existing ones. Our approach is easy to integrate into existing FSCIL approaches to boost performance. Experiments on three benchmarks validate the effectiveness of our approach, achieving a new state-of-the-art performance of FSCIL., Comment: WACV2025,10 pages, 5 figures

Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effective and reduces the reliance on human supervision in LLMs' reasoning, but the performance soon plateaus. We delve into the process and find that models tend to over-sample on easy queries and under-sample on queries they have yet to master. As iterations proceed, this imbalance in sampling is exacerbated, leading to a long-tail distribution where solutions to difficult queries almost diminish. This phenomenon limits the performance gain of self-improving models. A straightforward solution is brute-force sampling to balance the distribution, which significantly raises computational costs. In this paper, we introduce Guided Self-Improvement (GSI), a strategy aimed at improving the efficiency of sampling challenging heavy-tailed data. It leverages Socratic-style guidance signals to help LLM reasoning with complex queries, reducing the exploration effort and minimizing computational overhead. Experiments on four models across diverse mathematical tasks show that GSI strikes a balance between performance and efficiency, while also being effective on held-out tasks., Comment: Codes are publicly available at https://github.com/Yiwen-Ding/Guided-Self-Improvement

Localization of mobile targets is a fundamental problem across various domains. One-way ranging-based downlink localization has gained significant attention due to its ability to support an unlimited number of targets and enable autonomous navigation by performing localization at the target side. Time-difference-of-arrival (TDOA)-based methods are particularly advantageous as they obviate the need for target-anchor synchronization, unlike time-of-arrival (TOA)-based approaches. However, existing TDOA estimation methods inherently rely on the quasi-static assumption (QSA), which assumes that targets remain stationary during the measurement period, thereby limiting their applicability in dynamic environments. In this paper, we propose a novel instantaneous TDOA estimation method for dynamic environments, termed Parameterized TDOA (P-TDOA). We first characterize the nonlinear, time-varying TDOA measurements using polynomial models and construct a system of linear equations for the model parameters through dedicated transformations, employing a novel successive time difference strategy (STDS). Subsequently, we solve the parameters with a weighted least squares (WLS) solution, thereby obtaining instantaneous TDOA estimates. Furthermore, we develop a mobile target localization approach that leverages instantaneous TDOA estimates from multiple anchor pairs at the same instant. Theoretical analysis shows that our proposed method can approach the Cramer-Rao lower bound (CRLB) of instantaneous TDOA estimation and localization in concurrent TOA scenarios, despite actual TOA measurements being obtained sequentially. Extensive numerical simulations validate our theoretical analysis and demonstrate the effectiveness of the proposed method, highlighting its superiority over state-of-the-art approaches across various scenarios., Comment: This work has been submitted to the IEEE for possible publication

The 3-hinge gyrus (3HG) is a newly defined folding pattern, which is the conjunction of gyri coming from three directions in cortical folding. Many studies demonstrated that 3HGs can be reliable nodes when constructing brain networks or connectome since they simultaneously possess commonality and individuality across different individual brains and populations. However, 3HGs are identified and validated within individual spaces, making it difficult to directly serve as the brain network nodes due to the absence of cross-subject correspondence. The 3HG correspondences represent the intrinsic regulation of brain organizational architecture, traditional image-based registration methods tend to fail because individual anatomical properties need to be fully respected. To address this challenge, we propose a novel self-supervised framework for anatomical feature embedding of the 3HGs to build the correspondences among different brains. The core component of this framework is to construct a structural similarity-enhanced multi-hop feature encoding strategy based on the recently developed Kolmogorov-Arnold network (KAN) for anatomical feature embedding. Extensive experiments suggest that our approach can effectively establish robust cross-subject correspondences when no one-to-one mapping exists.

The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC with missing data a critical challenge. To meet the needs of practical applications, we introduce DiffLight, a novel conditional diffusion model for TSC under data-missing scenarios in the offline setting. Specifically, we integrate two essential sub-tasks, i.e., traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards from interfering with the learning process. Meanwhile, to effectively capture the spatial-temporal dependencies among intersections, we design a Spatial-Temporal transFormer (STFormer) architecture. In addition, we propose a Diffusion Communication Mechanism (DCM) to promote better communication and control performance under data-missing scenarios. Extensive experiments on five datasets with various data-missing scenarios demonstrate that DiffLight is an effective controller to address TSC with missing data. The code of DiffLight is released at https://github.com/lokol5579/DiffLight-release., Comment: Accepted by NeurIPS 2024

Echocardiogram video plays a crucial role in analysing cardiac function and diagnosing cardiac diseases. Current deep neural network methods primarily aim to enhance diagnosis accuracy by incorporating prior knowledge, such as segmenting cardiac structures or lesions annotated by human experts. However, diagnosing the inconsistent behaviours of the heart, which exist across both spatial and temporal dimensions, remains extremely challenging. For instance, the analysis of cardiac motion acquires both spatial and temporal information from the heartbeat cycle. To address this issue, we propose a novel reconstruction-based approach named CardiacNet to learn a better representation of local cardiac structures and motion abnormalities through echocardiogram videos. CardiacNet is accompanied by the Consistency Deformation Codebook (CDC) and the Consistency Deformed-Discriminator (CDD) to learn the commonalities across abnormal and normal samples by incorporating cardiac prior knowledge. In addition, we propose benchmark datasets named CardiacNet-PAH and CardiacNet-ASD to evaluate the effectiveness of cardiac disease assessment. In experiments, our CardiacNet can achieve state-of-the-art results in three different cardiac disease assessment tasks on public datasets CAMUS, EchoNet, and our datasets. The code and dataset are available at: https://github.com/xmed-lab/CardiacNet., Comment: Paper Accepted by ECCV 2024 with Oral Presentation

This study introduces a novel multiagent ensemble method powered by LLMs to address a key challenge in ML - data labeling, particularly in large-scale EHR datasets. Manual labeling of such datasets requires domain expertise and is labor-intensive, time-consuming, expensive, and error-prone. To overcome this bottleneck, we developed an ensemble LLMs method and demonstrated its effectiveness in two real-world tasks: (1) labeling a large-scale unlabeled ECG dataset in MIMIC-IV; (2) identifying social determinants of health (SDOH) from the clinical notes of EHR. Trading off benefits and cost, we selected a pool of diverse open source LLMs with satisfactory performance. We treat each LLM's prediction as a vote and apply a mechanism of majority voting with minimal winning threshold for ensemble. We implemented an ensemble LLMs application for EHR data labeling tasks. By using the ensemble LLMs and natural language processing, we labeled MIMIC-IV ECG dataset of 623,566 ECG reports with an estimated accuracy of 98.2%. We applied the ensemble LLMs method to identify SDOH from social history sections of 1,405 EHR clinical notes, also achieving competitive performance. Our experiments show that the ensemble LLMs can outperform individual LLM even the best commercial one, and the method reduces hallucination errors. From the research, we found that (1) the ensemble LLMs method significantly reduces the time and effort required for labeling large-scale EHR data, automating the process with high accuracy and quality; (2) the method generalizes well to other text data labeling tasks, as shown by its application to SDOH identification; (3) the ensemble of a group of diverse LLMs can outperform or match the performance of the best individual LLM; and (4) the ensemble method substantially reduces hallucination errors. This approach provides a scalable and efficient solution to data-labeling challenges., Comment: 27 pages, 13 figures. Under journal review

An extreme ultraviolet (EUV) close-up view of the Sun offers unprecedented detail of heating events in the solar corona. Enhanced temporal and spatial images obtained by the Solar Orbiter during its first science perihelion enabled us to identify clustered EUV bright tadpoles (CEBTs) occurring near the footpoints of coronal loops. Combining SDO/AIA observations, we determine the altitudes of six distinct CEBTs by stereoscopy, ranging from $\sim$1300 to 3300 km. We then notice a substantial presence of dark, cooler filamentary structures seemingly beneath the CEBTs, displaying periodic up-and-down motions lasting 3 to 5 minutes. This periodic behavior suggests an association of the majority of CEBTs with Type I spicules. Out of the ten selected CEBTs with fast downward velocity, six exhibit corrected velocities close to or exceeding 50 km $s^{-1}$. These velocities notably surpass the typical speeds of Type I spicules. We explore the generation of such velocities. It indicates that due to the previous limited observations of spicules in the EUV wavelengths, they may reveal novel observational features beyond our current understanding. Gaining insights into these features contributes to a better comprehension of small-scale coronal heating dynamics., Comment: 17 pages, 10 figures, accepted for publication in RAA

Approximate Nearest Neighbor Search (ANNS), which enables efficient semantic similarity search in large datasets, has become a fundamental component of critical applications such as information retrieval and retrieval-augmented generation (RAG). However, ANNS is a well-known I/O-intensive algorithm with a low compute-to-I/O ratio, often requiring massive storage due to the large volume of high-dimensional data. This leads to I/O bottlenecks on CPUs and memory limitations on GPUs. DRAM-based Processing-in-Memory (DRAM-PIM) architecture, which offers high bandwidth, large-capacity memory, and the ability to perform efficient computation in or near the data, presents a promising solution for ANNS. In this work, we investigate the use of commercial DRAM-PIM for ANNS for the first time and propose DRIM-ANN, an optimized ANNS engine based on DRAM-PIMs from UPMEM. Notably, given that the target DRAM-PIM exhibits an even lower compute-to-I/O ratio than basic ANNS, we leverage lookup tables (LUTs) to replace more multiplications with I/O operations. We then systematically tune ANNS to search optimized configurations with lower computational load, aligning the compute-to-I/O ratio of ANNS with that of DRAM-PIMs while maintaining accuracy constraints. Building on this tuned ANNS algorithm, we further explore implementation optimizations to fully utilize the two thousand parallel processing units with private local memory in DRAM-PIMs. To address the load imbalance caused by ANNS requests distributed across different clusters of large datasets, we propose a load-balancing strategy that combines static data layout optimization with dynamic runtime request scheduling. Experimental results on representative datasets show that DRIM-ANN achieves an average performance speedup of 2.92x compared to a 32-thread CPU counterpart.

World models integrate raw data from various modalities, such as images and language to simulate comprehensive interactions in the world, thereby displaying crucial roles in fields like mixed reality and robotics. Yet, applying the world model for accurate video prediction is quite challenging due to the complex and dynamic intentions of the various scenes in practice. In this paper, inspired by the human rethinking process, we decompose the complex video prediction into four meta-tasks that enable the world model to handle this issue in a more fine-grained manner. Alongside these tasks, we introduce a new benchmark named Embodied Video Anticipation Benchmark (EVA-Bench) to provide a well-rounded evaluation. EVA-Bench focused on evaluating the video prediction ability of human and robot actions, presenting significant challenges for both the language model and the generation model. Targeting embodied video prediction, we propose the Embodied Video Anticipator (EVA), a unified framework aiming at video understanding and generation. EVA integrates a video generation model with a visual language model, effectively combining reasoning capabilities with high-quality generation. Moreover, to enhance the generalization of our framework, we tailor-designed a multi-stage pretraining paradigm that adaptatively ensembles LoRA to produce high-fidelity results. Extensive experiments on EVA-Bench highlight the potential of EVA to significantly improve performance in embodied scenes, paving the way for large-scale pre-trained models in real-world prediction tasks.

Open clusters (OCs) in the Galaxy are excellent probes for tracing the structure and evolution of the Galactic disk. We present an updated catalog of parameters for 1,145 OCs, estimated using the Gaia DR3 data earlier listed in Cantat-Gaudin et al. (2020). This sample is complemented by 3,677 OCs from the catalog by Hunt & Reffert (2023). Using the Galaxy potential and the space velocities, orbits of 4,006 OCs were computed. We provide a catalog with orbital parameters such as eccentricity, perigalactic and apogalactic distance, and the maximum vertical height traced by OCs from the Galactic disk. The OCs were found to be distributed between 5-16 kpc from the Galactic center, with older OCs showing a radially extended distribution. The low number of old OCs in the inner Solar circle region likely suggests their destruction in this area. We derive a quantitative expression for the dependency of the maximum vertical height (Z_max) OCs can reach with the cluster's age and Galactocentric radius for the first time. The young and intermediate-age OCs show similar values of Z_max till 9 kpc, with the latter group having higher values beyond. OCs older than 1 Gyr show larger values of Z_max at all Galactocentric radii and significantly larger values beyond 9 kpc. Higher values of Z_max are found in the third Galactic quadrant, suggesting a link between these higher values and the Galactic warp. This sample shows that young OCs are also involved in the diagonal ridge formation in the solar neighborhood.

The purpose of this article is to study the residual Monge-Amp\`{e}re mass of a plurisubharmonic function with an isolated unbounded locus. A general decomposition formula for the residual mass is obtained, under the Sasakian structure of the unit sphere. In complex dimension two, we further obtain an upper-bound estimate, provided with the uniform directional Lipschitz continuity. As an application, the zero mass conjecture is confirmed, if the function further has a single frequency on its alternating part.

Streamflow, vital for water resource management, is governed by complex hydrological systems involving intermediate processes driven by meteorological forces. While deep learning models have achieved state-of-the-art results of streamflow prediction, their end-to-end single-task learning approach often fails to capture the causal relationships within these systems. To address this, we propose Hierarchical Conditional Multi-Task Learning (HCMTL), a hierarchical approach that jointly models soil water and snowpack processes based on their causal connections to streamflow. HCMTL utilizes task embeddings to connect network modules, enhancing flexibility and expressiveness while capturing unobserved processes beyond soil water and snowpack. It also incorporates the Conditional Mini-Batch strategy to improve long time series modeling. We compare HCMTL with five baselines on a global dataset. HCMTL's superior performance across hundreds of drainage basins over extended periods shows that integrating domain-specific causal knowledge into deep learning enhances both prediction accuracy and interpretability. This is essential for advancing our understanding of complex hydrological systems and supporting efficient water resource management to mitigate natural disasters like droughts and floods.

Recent advancements in text-to-image (T2I) diffusion models have enabled the creation of high-quality images from text prompts, but they still struggle to generate images with precise control over specific visual concepts. Existing approaches can replicate a given concept by learning from reference images, yet they lack the flexibility for fine-grained customization of the individual component within the concept. In this paper, we introduce component-controllable personalization, a novel task that pushes the boundaries of T2I models by allowing users to reconfigure specific components when personalizing visual concepts. This task is particularly challenging due to two primary obstacles: semantic pollution, where unwanted visual elements corrupt the personalized concept, and semantic imbalance, which causes disproportionate learning of the concept and component. To overcome these challenges, we design MagicTailor, an innovative framework that leverages Dynamic Masked Degradation (DM-Deg) to dynamically perturb undesired visual semantics and Dual-Stream Balancing (DS-Bal) to establish a balanced learning paradigm for desired visual semantics. Extensive comparisons, ablations, and analyses demonstrate that MagicTailor not only excels in this challenging task but also holds significant promise for practical applications, paving the way for more nuanced and creative image generation., Comment: Project page: https://correr-zhou.github.io/MagicTailor

We study the problem of allocating $m$ indivisible chores to $n$ agents with additive cost functions under the fairness notion of maximin share (MMS). In this work, we propose a notion called $\alpha$-approximate all-but-one maximin share ($\alpha$-AMMS) which is a stronger version of $\alpha$-approximate MMS. An allocation is called $\alpha$-AMMS if $n-1$ agents are guaranteed their MMS values and the remaining agent is guaranteed $\alpha$-approximation of her MMS value. We show that there exist $\alpha$-AMMS allocations, with $\alpha = 9/8$ for three agents; $\alpha = 4/3$ for four agents; and $\alpha = (n+1)^2/4n$ for $n\geq 5$ agents., Comment: 18 pages, 7 figures

The rapid evolution of Brain-Computer Interfaces (BCIs) has significantly influenced the domain of human-computer interaction, with Steady-State Visual Evoked Potentials (SSVEP) emerging as a notably robust paradigm. This study explores advanced classification techniques leveraging interpretable fuzzy transfer learning (iFuzzyTL) to enhance the adaptability and performance of SSVEP-based systems. Recent efforts have strengthened to reduce calibration requirements through innovative transfer learning approaches, which refine cross-subject generalizability and minimize calibration through strategic application of domain adaptation and few-shot learning strategies. Pioneering developments in deep learning also offer promising enhancements, facilitating robust domain adaptation and significantly improving system responsiveness and accuracy in SSVEP classification. However, these methods often require complex tuning and extensive data, limiting immediate applicability. iFuzzyTL introduces an adaptive framework that combines fuzzy logic principles with neural network architectures, focusing on efficient knowledge transfer and domain adaptation. iFuzzyTL refines input signal processing and classification in a human-interpretable format by integrating fuzzy inference systems and attention mechanisms. This approach bolsters the model's precision and aligns with real-world operational demands by effectively managing the inherent variability and uncertainty of EEG data. The model's efficacy is demonstrated across three datasets: 12JFPM (89.70% accuracy for 1s with an information transfer rate (ITR) of 149.58), Benchmark (85.81% accuracy for 1s with an ITR of 213.99), and eldBETA (76.50% accuracy for 1s with an ITR of 94.63), achieving state-of-the-art results and setting new benchmarks for SSVEP BCI performance.

Despite efforts from cloud and content providers to lower latency to acceptable levels for current and future services (e.g., augmented reality or cloud gaming), there are still opportunities for improvement. A major reason that traffic engineering efforts are challenged to lower latency is that the Internet's inter-domain routing protocol, the Border Gateway Protocol, is oblivious to any performance metric, and circuitous routing is still pervasive. In this work, we propose two implementation modifications that networks can leverage to make BGP latency-aware and reduce excessive latency inflation. These proposals, latency-proportional AS prepending and local preference neutralization, show promise towards providing a method for propagating abstract latency information with a reasonable increase in routing overhead.

The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of purely data-driven methods. Current LLM-based agents require lengthy inference times and face challenges in interacting with real-time autonomous driving environments. A key open question is whether we can effectively leverage the knowledge from LLMs to train an efficient and robust Reinforcement Learning (RL) agent. This paper introduces RAPID, a novel \underline{\textbf{R}}obust \underline{\textbf{A}}daptive \underline{\textbf{P}}olicy \underline{\textbf{I}}nfusion and \underline{\textbf{D}}istillation framework, which trains specialized mix-of-policy RL agents using data synthesized by an LLM-based driving agent and online adaptation. RAPID features three key designs: 1) utilization of offline data collected from an LLM agent to distil expert knowledge into RL policies for faster real-time inference; 2) introduction of robust distillation in RL to inherit both performance and robustness from LLM-based teacher; and 3) employment of a mix-of-policy approach for joint decision decoding with a policy adapter. Through fine-tuning via online environment interaction, RAPID reduces the forgetting of LLM knowledge while maintaining adaptability to different tasks. Extensive experiments demonstrate RAPID's capability to effectively integrate LLM knowledge into scaled-down RL policies in an efficient, adaptable, and robust way. Code and checkpoints will be made publicly available upon acceptance.

Accurate long-term predictions are the foundations for many machine learning applications and decision-making processes. Traditional time series approaches for prediction often focus on either autoregressive modeling, which relies solely on past observations of the target ``endogenous variables'', or forward modeling, which considers only current covariate drivers ``exogenous variables''. However, effectively integrating past endogenous and past exogenous with current exogenous variables remains a significant challenge. In this paper, we propose ExoTST, a novel transformer-based framework that effectively incorporates current exogenous variables alongside past context for improved time series prediction. To integrate exogenous information efficiently, ExoTST leverages the strengths of attention mechanisms and introduces a novel cross-temporal modality fusion module. This module enables the model to jointly learn from both past and current exogenous series, treating them as distinct modalities. By considering these series separately, ExoTST provides robustness and flexibility in handling data uncertainties that arise from the inherent distribution shift between historical and current exogenous variables. Extensive experiments on real-world carbon flux datasets and time series benchmarks demonstrate ExoTST's superior performance compared to state-of-the-art baselines, with improvements of up to 10\% in prediction accuracy. Moreover, ExoTST exhibits strong robustness against missing values and noise in exogenous drivers, maintaining consistent performance in real-world situations where these imperfections are common., Comment: Accepted at ICDM 2024

Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or 4-bit weight-only quantization, achieve limited performance improvements due to poor support for low-precision (e.g., 4-bit) activation. This work, for the first time, realizes practical W4A4KV4 serving for LLMs, fully utilizing the INT4 tensor cores on modern GPUs and reducing the memory bottleneck caused by the KV cache. Specifically, we propose a novel fine-grained mixed-precision quantization algorithm (FMPQ) that compresses most activations into 4-bit with negligible accuracy loss. To support mixed-precision matrix multiplication for W4A4 and W4A8, we develop a highly optimized W4Ax kernel. Our approach introduces a novel mixed-precision data layout to facilitate access and fast dequantization for activation and weight tensors, utilizing the GPU's software pipeline to hide the overhead of data loading and conversion. Additionally, we propose fine-grained streaming multiprocessor (SM) scheduling to achieve load balance across different SMs. We integrate the optimized W4Ax kernel into our inference framework, COMET, and provide efficient management to support popular LLMs such as LLaMA-3-70B. Extensive evaluations demonstrate that, when running LLaMA family models on a single A100-80G-SMX4, COMET achieves a kernel-level speedup of \textbf{$2.88\times$} over cuBLAS and a \textbf{$2.02 \times$} throughput improvement compared to TensorRT-LLM from an end-to-end framework perspective., Comment: 14 pages, 12 figures

Third-party web cookies are often used for privacy-invasive behavior tracking. Partly due to privacy concerns, browser vendors have started to block all third-party cookies in recent years. To understand the effects of such third-party cookieless browsing, we crawled and measured the top 10,000 Tranco websites. We developed a framework to remove third-party cookies and analyze the differences between the appearance of web pages with and without these cookies. We find that disabling third-party cookies has no substantial effect on website appearance including layouts, text, and images. This validates the industry-wide shift towards cookieless browsing as a way to protect user privacy without compromising on the user experience., Comment: To appear in IMC '24

The Gum Nebula is a faint supernova remnant extending about 40 degrees across the southern sky, potentially affecting tens of background pulsars. Though the view that the Gum Nebula acts as a potential scattering screen for background pulsars has been recurrently mentioned over the past five decades, it has not been directly confirmed. We chose the strong background pulsar PSR~B0740$-$28 as a probe and monitored its diffractive interstellar scintillation (DISS) at 2.25~$\&$~8.60~GHz simultaneously for about two years using the Shanghai Tian Ma Radio Telescope (TMRT). DISS was detected at both frequencies and quantified by two-dimensional autocorrelation analysis. We calculated their scattering spectral index $\alpha$ and found that 9/21 of the observations followed the theoretical predictions, while 4/21 of them clearly showed $\alpha < 4$. This finding provides strong support for anomalous scattering along the pulsar line of sight, due to the large frequency lever arm and the simultaneous features of our dual-frequency observations. In comparison to the 2.25~GHz observations, scintillation arcs were observed in 10/21 of the secondary spectrum plots for 8.60~GHz observations. Consequently, the highest frequency record for pulsar scintillation arc detection was updated to 8.60~GHz. Our fitting results were the most direct evidence for the view that the Gum Nebula acts as the scattering screen for background pulsars, because both the distance ($245^{+69}_{-72}$~pc) and transverse speed ($22.4^{+4.1}_{-4.2}$~km/s) of the scintillation screen are comparable with related parameters of the Gum Nebula. Our findings indicated that anisotropic scattering provides a superior explanation for the annual modulation of scintillation arcs than isotropic scattering. Additionally, the orientation of its long axis was also fitted., Comment: Accepted by SCIENCE CHINA Physics, Mechanics & Astronomy

Ego-centric queries, focusing on a target vertex and its direct neighbors, are essential for various applications. Enabling such queries on graphs owned by mutually distrustful data providers, without breaching privacy, holds promise for more comprehensive results. In this paper, we propose GORAM, a graph-oriented data structure that enables efficient ego-centric queries on federated graphs with strong privacy guarantees. GORAM is built upon secure multi-party computation (MPC) and ensures that no single party can learn any sensitive information about the graph data or the querying keys during the process. However, achieving practical performance with privacy guaranteed presents a challenge. To overcome this, GORAM is designed to partition the federated graph and construct an Oblivious RAM(ORAM)-inspired index atop these partitions. This design enables each ego-centric query to process only a single partition, which can be accessed fast and securely. To evaluate the performance of GORAM, we developed a prototype querying engine on a real-world MPC framework. We conduct a comprehensive evaluation with five commonly used queries on both synthetic and real-world graphs. Our evaluation shows that all benchmark queries can be completed in just 58.1 milliseconds to 35.7 seconds, even on graphs with up to 41.6 million vertices and 1.4 billion edges. To the best of our knowledge, this represents the first instance of processing billion-scale graphs with practical performance on MPC.

Recent advancements in humanoid robotics, including the integration of hierarchical reinforcement learning-based control and the utilization of LLM planning, have significantly enhanced the ability of robots to perform complex tasks. In contrast to the highly developed humanoid robots, the human factors involved remain relatively unexplored. Directly controlling humanoid robots with the brain has already appeared in many science fiction novels, such as Pacific Rim and Gundam. In this work, we present E2H (EEG-to-Humanoid), an innovative framework that pioneers the control of humanoid robots using high-frequency non-invasive neural signals. As the none-invasive signal quality remains low in decoding precise spatial trajectory, we decompose the E2H framework in an innovative two-stage formation: 1) decoding neural signals (EEG) into semantic motion keywords, 2) utilizing LLM facilitated motion generation with a precise motion imitation control policy to realize humanoid robotics control. The method of directly driving robots with brainwave commands offers a novel approach to human-machine collaboration, especially in situations where verbal commands are impractical, such as in cases of speech impairments, space exploration, or underwater exploration, unlocking significant potential. E2H offers an exciting glimpse into the future, holding immense potential for human-computer interaction.

This paper examines how AI persuades doctors when their diagnoses differ. Disagreements arise from two sources: attention differences, which are objective and play a complementary role to the doctor, and comprehension differences, which are subjective and act as substitutes. AI's interpretability influences how doctors attribute these sources and their willingness to change their minds. Surprisingly, uninterpretable AI can be more persuasive by allowing doctors to partially attribute disagreements to attention differences. This effect is stronger when doctors have low abnormality detection skills. Additionally, uninterpretable AI can improve diagnostic accuracy when doctors have career concerns.

NOAA Active Region (AR) 13664/8 produced the most intense geomagnetic effects since the ``Halloween'' event of 2003. The resulting extreme solar storm is believed to be the consequence of multiple interacting coronal mass ejections (CMEs). Notably, this AR exhibites an exceptionally rapid magnetic flux emergence. The eruptions we are focusing on all occurred along collisional polarity inversion lines (PILs) through ``collisional shearing'' during a three-day period of extraordinarily high flux emergence ($\sim$10$^{21}$ Mx hr$^{-1}$). Our key findings reveal how photospheric magnetic configurations in eruption sources influence solar superstorm formation and geomagnetic responses, and link exceptionally strong flux emergence to sequential homologous eruptions: (1) We identified the source regions of seven halo CMEs, distributed primarily along two distinct PILs, suggesting the presence of two groups of homologous CMEs. (2) The variations in magnetic flux emergence rates at the source regions correlate with CME intensities, potentially explaining the two contrasting cases of complex ejecta observed at Earth. (3) Calculations of magnetic field gradients around CME source regions show strong correlations with eruptions, providing crucial insights into solar eruption mechanisms and enhancing future prediction capabilities., Comment: 4 figures, accepted for publication in A&A

On-demand Food Delivery (OFD) services have become very common around the world. For example, on the Ele.me platform, users place more than 15 million food orders every day. Predicting the Real-time Pressure Signal (RPS) is crucial for OFD services, as it is primarily used to measure the current status of pressure on the logistics system. When RPS rises, the pressure increases, and the platform needs to quickly take measures to prevent the logistics system from being overloaded. Usually, the average delivery time for all orders within a business district is used to represent RPS. Existing research on OFD services primarily focuses on predicting the delivery time of orders, while relatively less attention has been given to the study of the RPS. Previous research directly applies general models such as DeepFM, RNN, and GNN for prediction, but fails to adequately utilize the unique temporal and spatial characteristics of OFD services, and faces issues with insufficient sensitivity during sudden severe weather conditions or peak periods. To address these problems, this paper proposes a new method based on Spatio-Temporal Transformer and Memory Network (STTM). Specifically, we use a novel Spatio-Temporal Transformer structure to learn logistics features across temporal and spatial dimensions and encode the historical information of a business district and its neighbors, thereby learning both temporal and spatial information. Additionally, a Memory Network is employed to increase sensitivity to abnormal events. Experimental results on the real-world dataset show that STTM significantly outperforms previous methods in both offline experiments and the online A/B test, demonstrating the effectiveness of this method.

This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: -83.3% success rate in solving complex competitive programming problems, surpassing many human experts. -Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. -100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. -Advanced natural language inference capabilities across general and specialized domains like medicine. -Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. -Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. -Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. -Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence.

Text-to-Image (T2I) Diffusion Models (DMs) have garnered widespread attention for their impressive advancements in image generation. However, their growing popularity has raised ethical and social concerns related to key non-functional properties of trustworthiness, such as robustness, fairness, security, privacy, factuality, and explainability, similar to those in traditional deep learning (DL) tasks. Conventional approaches for studying trustworthiness in DL tasks often fall short due to the unique characteristics of T2I DMs, e.g., the multi-modal nature. Given the challenge, recent efforts have been made to develop new methods for investigating trustworthiness in T2I DMs via various means, including falsification, enhancement, verification \& validation and assessment. However, there is a notable lack of in-depth analysis concerning those non-functional properties and means. In this survey, we provide a timely and focused review of the literature on trustworthy T2I DMs, covering a concise-structured taxonomy from the perspectives of property, means, benchmarks and applications. Our review begins with an introduction to essential preliminaries of T2I DMs, and then we summarise key definitions/metrics specific to T2I tasks and analyses the means proposed in recent literature based on these definitions/metrics. Additionally, we review benchmarks and domain applications of T2I DMs. Finally, we highlight the gaps in current research, discuss the limitations of existing methods, and propose future research directions to advance the development of trustworthy T2I DMs. Furthermore, we keep up-to-date updates in this field to track the latest developments and maintain our GitHub repository at: https://github.com/wellzline/Trustworthy_T2I_DMs, Comment: under review

The paper introduces a Fuzzy-based Attention (Fuzzy Attention Layer) mechanism, a novel computational approach to enhance the interpretability and efficacy of neural models in psychological research. The proposed Fuzzy Attention Layer mechanism is integrated as a neural network layer within the Transformer Encoder model to facilitate the analysis of complex psychological phenomena through neural signals, such as those captured by functional Near-Infrared Spectroscopy (fNIRS). By leveraging fuzzy logic, the Fuzzy Attention Layer is capable of learning and identifying interpretable patterns of neural activity. This capability addresses a significant challenge when using Transformer: the lack of transparency in determining which specific brain activities most contribute to particular predictions. Our experimental results demonstrated on fNIRS data from subjects engaged in social interactions involving handholding reveal that the Fuzzy Attention Layer not only learns interpretable patterns of neural activity but also enhances model performance. Additionally, the learned patterns provide deeper insights into the neural correlates of interpersonal touch and emotional exchange. The application of our model shows promising potential in deciphering the subtle complexities of human social behaviors, thereby contributing significantly to the fields of social neuroscience and psychological AI.

The importance of Very Long Baseline Interferometry (VLBI) for pulsar research is becoming increasingly prominent and receiving more and more attention. In this paper, we present pathfinding pulsar observation results with the Chinese VLBI Network (CVN) incorporating the Five-hundred-meter Aperture Spherical radio Telescope (FAST). On MJD 60045 (April 11th, 2023), PSRs B0919+06 and B1133+16 were observed with the phase-referencing mode in the L-band using four radio telescopes (FAST, TianMa, Haoping and Nanshan) and correlated with the pulsar binning mode of the distributed FX-style software correlator in Shanghai. After further data processing with the NRAO Astronomical Image Processing System (AIPS), we detected these two pulsars and fitted their current positions with accuracy at the milliarcsecond level. By comparison, our results show significantly better agreement with predicted values based on historical VLBI observations than that with previous timing observations, as pulsar astrometry with the VLBI provides a more direct and model-independent method for accurately obtaining related parameters., Comment: Accepted by the Chinese Physics Letters

We select and investigate six global solar extreme ultraviolet (EUV) wave events using data from the Solar Dynamics Observatory (SDO) and the Solar and Heliospheric Observatory (SOHO). These eruptions are all on the limb but recorded as halo coronal mass ejections (CMEs) because the CME-driven shocks have expanded laterally to the opposite side. With the limb observations avoiding the projection effect, we have measured the inclination and speed of the EUV wavefront from 1.05 to 1.25 $R_\odot$. We also investigate the coupling and connection of the EUV wavefront with the CME boundary and the CME-driven shock, respectively. The major findings in the six events are: (1) the forward inclination of the primary and coronal-hole transmitted EUV wavefronts is estimated, respectively, and the origins of these inclinations and their effects on the estimate of actual wavefront speed are investigated; (2) the wavefront speed can be elevated by loop systems near the coronal base, and the average speed in the low corona has no clear correlation with the lateral expansion of the CME-driven shock in the high corona; (3) the fast magnetosonic Mach number of the wavefront is larger than unity from the coronal base; (4) the EUV wavefront is coupled with the CME driver throughout the propagation in two events; (5) after the EUV wavefront vanishes, the CME-driven shock continues traveling on the opposite side and disconnects from the EUV wavefront in four events. These results and their implications are discussed, which provide insight into the properties of global EUV waves., Comment: 32 pages, 10 figures, 2 tables; accepted by ApJ; added necessary revisions according to proof

Gamma-ray bursts (GRBs) are the most luminous transients in the universe. The interaction of the relativistic jet with the circumburst medium produces an afterglow and generates multiwavelength emission. In this work, we present simultaneous multiband photometry of GRB~240825A with the Multi-channel Photometric Survey Telescope (Mephisto) and analyze its temporal and spectral properties. The measurement began 128 seconds after the GRB trigger and continued until the fourth day when the afterglow essentially diminished and the measured brightness was close to that of the host galaxy. Based on the multiband light curves in the $uvgriz$ bands, we find that the optical flux density satisfies $F_{\nu,{\rm obs}}\propto t^{-1.34}\nu^{-2.48}$ with a spectral index of $2.48$ much larger than those of most other GRBs. To reconcile the measured much softer spectral energy distribution (SED) with that predicted by the standard afterglow model, an extra host-galaxy extinction of $E_{B-V}\sim(0.37-0.57)$ mag is required. We interpreted this excess as arising from a dense circumburst medium. We further find that the SED of the optical afterglow hardened as the afterglow decayed and the color excess $E_{B-V}$ decreased $\sim0.21$ mag in the first 3000 seconds. Finally, we analyze the properties of the host galaxy of GRB~240825A based on data from the SDSS, PanSTARRS and HSC-SSP surveys. For a host redshift of $z=0.659$, the stellar mass and star formation rate of the host galaxy are estimated to be $\log(M_*/M_\odot)=10.0^{+0.3}_{-0.3}$ and $\log({\rm SFR}/M_{\odot}{\rm yr}^{-1})= 0.6^{+0.8}_{-3.3}$, respectively, pointing to a gas-rich, star-forming, medium-size galaxy., Comment: 15 pages, 5 figures, 1 table. Comments welcome!

The early time observations of Type Ia supernovae (SNe Ia) play a crucial role in investigating and resolving longstanding questions about progenitor stars and the explosion mechanisms of these events. Colors of supernovae (SNe) in the initial days after the explosion can help differentiate between different types of SNe. However, the use of true color information to identify SNe Ia at the early-time explosion is still in its infancy. The Multi-channel Photometric Survey Telescope (Mephisto) is a photometric survey telescope equipped with three CCD cameras, capable of simultaneously imaging the same patch of sky in three bands (\emph{u, g, i} or \emph{v, r, z}), yielding real-time colors of astronomical objects. In this paper, we introduce a new time-series classification tool named Mephisto Early Supernovae Ia Rapid Identifier (\emph{\texttt{Mesiri}}), which for the first time, utilizes real-time color information to distinguish early-time SNe Ia from core-collapse supernovae (CCSNe). \emph{\texttt{Mesiri}} is based on the deep learning approach and can achieve an accuracy of $96.75\pm0.79$\%, and AUC of $98.87\pm0.53$\% in case of single epoch random observation before the peak brightness. These values reach towards perfectness if additional data points on several night observations are considered. The classification with real-time color significantly outperforms that with pseudo-color, especially at the early time, i.e., with only a few points of observations. The architecture of BiLSTM shows the best performance than the others that have been tested in this work., Comment: 30 pages, 17 figures, 4 tables, accepted for publication in RAA

In this paper, we adopt constrastive explanations within an end-user application for temporal planning of smart homes. In this application, users have requirements on the execution of appliance tasks, pay for energy according to dynamic energy tariffs, have access to high-capacity battery storage, and are able to sell energy to the grid. The concurrent scheduling of devices makes this a multi-effector planning problem, while the dynamic tariffs yield costs that are non-stationary (alternatively, costs that are stationary but depend on exogenous events). These characteristics are such that the planning problems are generally not supported by existing PDDL-based planners, so we instead design a custom domain-dependent planner that scales to reasonable appliance numbers and time horizons. We conduct a controlled user study with 128 participants using an online crowd-sourcing platform based on two user stories. Our results indicate that users provided with contrastive questions and explanations have higher levels of satisfaction, tend to gain improved understanding, and rate the helpfulness more favourably with the recommended AI schedule compared to those without access to these features.

The largest geomagnetic storm in two decades occurred in 2024 May with a minimum $D_{\rm st}$ of $-412$ nT. We examine its solar and interplanetary origins by combining multipoint imaging and in situ observations. The source active region, NOAA AR 13664, exhibited extraordinary activity and produced successive halo eruptions, which were responsible for two complex ejecta observed at the Earth. In situ measurements from STEREO A, which was $12.6^{\circ}$ apart, allow us to compare the ``geo-effectiveness" at the Earth and STEREO A. We obtain key findings concerning the formation of solar superstorms and how mesoscale variations of coronal mass ejections affect geo-effectiveness: (1) the 2024 May storm supports the hypothesis that solar superstorms are ``perfect storms" in nature, i.e., a combination of circumstances resulting in an event of an unusual magnitude; (2) the first complex ejecta, which caused the geomagnetic superstorm, shows considerable differences in the magnetic field and associated ``geo-effectiveness" between the Earth and STEREO A, despite a mesoscale separation; and (3) two contrasting cases of complex ejecta are found in terms of the geo-effectiveness at the Earth, which is largely due to different magnetic field configurations within the same active region., Comment: Accepted for publication in ApJL