Search

In order to make full use of video information, we transform the replay grounding problem into a video action location problem. We apply a unified network Faster-TAD proposed by us for temporal action detection to get the results of replay grounding. Finally, by observing the data distribution of the training data, we refine the output of the model to get the final submission.

The nature of the high-pressure plaquette-singlet (PS) phase of SrCu$_2$(BO$_3$)$_2$ remains enigmatic. In this work, we revisit the high-pressure $^{11}$B NMR study and identify two distinct coexisting gapped PS states within the NMR spectra. In addition to the previously reported full-plaquette phase, a second PS phase is discerned, characterized by a slightly lower resonance frequency and larger spin-lattice relaxation rates in its ordered phase. Notably, this second phase exhibits enhanced spin fluctuations in its precursor liquid state above the transition temperature. The volume fraction of this phase increases significantly with pressure, reaching approximately 70\% at 2.65~GPa. Furthermore, at 2.4~GPa, a field-induced quantum phase transition from the PS phase to an antiferromagnetic phase is observed around 5.5~T, with a scaling behavior of $1/T_1 \sim T^{0.6}$ near the transition field. This behavior suggests a continuous or nearly continuous nature for the field-induced transition. Our findings provide experimental evidence for the long-sought empty-plaquette singlet phase in SrCu$_2$(BO$_3$)$_2$ within the framework of the Shastry-Sutherland model, thus establishing a promising platform for future studies of deconfined quantum criticality in this model system., Comment: 6 pages, 5 figures

Softmax Loss (SL) is widely applied in recommender systems (RS) and has demonstrated effectiveness. This work analyzes SL from a pairwise perspective, revealing two significant limitations: 1) the relationship between SL and conventional ranking metrics like DCG is not sufficiently tight; 2) SL is highly sensitive to false negative instances. Our analysis indicates that these limitations are primarily due to the use of the exponential function. To address these issues, this work extends SL to a new family of loss functions, termed Pairwise Softmax Loss (PSL), which replaces the exponential function in SL with other appropriate activation functions. While the revision is minimal, we highlight three merits of PSL: 1) it serves as a tighter surrogate for DCG with suitable activation functions; 2) it better balances data contributions; and 3) it acts as a specific BPR loss enhanced by Distributionally Robust Optimization (DRO). We further validate the effectiveness and robustness of PSL through empirical experiments. The code is available at https://github.com/Tiny-Snow/IR-Benchmark.

We consider the problem of physically-based inverse rendering using 3D Gaussian Splatting (3DGS) representations. While recent 3DGS methods have achieved remarkable results in novel view synthesis (NVS), accurately capturing high-fidelity geometry, physically interpretable materials and lighting remains challenging, as it requires precise geometry modeling to provide accurate surface normals, along with physically-based rendering (PBR) techniques to ensure correct material and lighting disentanglement. Previous 3DGS methods resort to approximating surface normals, but often struggle with noisy local geometry, leading to inaccurate normal estimation and suboptimal material-lighting decomposition. In this paper, we introduce GeoSplatting, a novel hybrid representation that augments 3DGS with explicit geometric guidance and differentiable PBR equations. Specifically, we bridge isosurface and 3DGS together, where we first extract isosurface mesh from a scalar field, then convert it into 3DGS points and formulate PBR equations for them in a fully differentiable manner. In GeoSplatting, 3DGS is grounded on the mesh geometry, enabling precise surface normal modeling, which facilitates the use of PBR frameworks for material decomposition. This approach further maintains the efficiency and quality of NVS from 3DGS while ensuring accurate geometry from the isosurface. Comprehensive evaluations across diverse datasets demonstrate the superiority of GeoSplatting, consistently outperforming existing methods both quantitatively and qualitatively., Comment: Project page: https://pku-vcl-geometry.github.io/GeoSplatting/

Muons, which play a crucial role in both fundamental and applied physics, have traditionally been generated through proton accelerators or from cosmic rays. With the advent of ultra-short high-intensity lasers capable of accelerating electrons to GeV levels, it has become possible to generate muons in laser laboratories. In this work, we show the first proof of principle experiment for novel muon production with an ultra-short, high-intensity laser device through GeV electron beam bombardment on a lead converter target. The muon physical signal is confirmed by measuring its lifetime which is the first clear demonstration of laser-produced muons. Geant4 simulations were employed to investigate the photo-production, electro-production, and Bethe-Heitler processes response for muon generation and their subsequent detection. The results show that the dominant contributions of muons are attributed to the photo-production/electro-production and a significant yield of muons up to 0.01 $\mu$/$e^-$ out of the converter target could be achieved. This laser muon source features compact, ultra-short pulse and high flux. Moreover, its implementation in a small laser laboratory is relatively straightforward, significantly reducing the barriers to entry for research in areas such as muonic X-ray elemental analysis, muon spin spectroscopy and so on.

We discovered that a GPU kernel can have both idempotent and non-idempotent instances depending on the input. These kernels, called conditionally-idempotent, are prevalent in real-world GPU applications (490 out of 547 from six applications). Consequently, prior work that classifies GPU kernels as either idempotent or non-idempotent can severely compromise the correctness or efficiency of idempotence-based systems. This paper presents PICKER, the first system for instance-level idempotency validation. PICKER dynamically validates the idempotency of GPU kernel instances before their execution, by utilizing their launch arguments. Several optimizations are proposed to significantly reduce validation latency to microsecond-scale. Evaluations using representative GPU applications (547 kernels and 18,217 instances in total) show that PICKER can identify idempotent instances with no false positives and a false-negative rate of 18.54%, and can complete the validation within 5 us for all instances. Furthermore, by integrating PICKER, a fault-tolerant system can reduce the checkpoint cost to less than 4% and a scheduling system can reduce the preemption latency by 84.2%.

Parkinson's disease (PD), a degenerative disorder of the central nervous system, is commonly diagnosed using functional medical imaging techniques such as single-photon emission computed tomography (SPECT). In this study, we utilized two SPECT data sets (n = 634 and n = 202) from different hospitals to develop a model capable of accurately predicting PD stages, a multiclass classification task. We used the entire three-dimensional (3D) brain images as input and experimented with various model architectures. Initially, we treated the 3D images as sequences of two-dimensional (2D) slices and fed them sequentially into 2D convolutional neural network (CNN) models pretrained on ImageNet, averaging the outputs to obtain the final predicted stage. We also applied 3D CNN models pretrained on Kinetics-400. Additionally, we incorporated an attention mechanism to account for the varying importance of different slices in the prediction process. To further enhance model efficacy and robustness, we simultaneously trained the two data sets using weight sharing, a technique known as cotraining. Our results demonstrated that 2D models pretrained on ImageNet outperformed 3D models pretrained on Kinetics-400, and models utilizing the attention mechanism outperformed both 2D and 3D models. The cotraining technique proved effective in improving model performance when the cotraining data sets were sufficiently large., Comment: 34 pages, 7 figures, and 4 tables

With a focus on natural language processing (NLP) and the role of large language models (LLMs), we explore the intersection of machine learning, deep learning, and artificial intelligence. As artificial intelligence continues to revolutionize fields from healthcare to finance, NLP techniques such as tokenization, text classification, and entity recognition are essential for processing and understanding human language. This paper discusses advanced data preprocessing techniques and the use of frameworks like Hugging Face for implementing transformer-based models. Additionally, it highlights challenges such as handling multilingual data, reducing bias, and ensuring model robustness. By addressing key aspects of data processing and model fine-tuning, this work aims to provide insights into deploying effective and ethically sound AI solutions., Comment: 255 pages

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.

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark)., Comment: accepted by NeurIPS 2024

Recent advancements in synthetic aperture radar (SAR) ship detection using deep learning have significantly improved accuracy and speed, yet effectively detecting small objects in complex backgrounds with fewer parameters remains a challenge. This letter introduces RSNet, a lightweight framework constructed to enhance ship detection in SAR imagery. To ensure accuracy with fewer parameters, we proposed Waveletpool-ContextGuided (WCG) as its backbone, guiding global context understanding through multi-scale wavelet features for effective detection in complex scenes. Additionally, Waveletpool-StarFusion (WSF) is introduced as the neck, employing a residual wavelet element-wise multiplication structure to achieve higher dimensional nonlinear features without increasing network width. The Lightweight-Shared (LS) module is designed as detect components to achieve efficient detection through lightweight shared convolutional structure and multi-format compatibility. Experiments on the SAR Ship Detection Dataset (SSDD) and High-Resolution SAR Image Dataset (HRSID) demonstrate that RSNet achieves a strong balance between lightweight design and detection performance, surpassing many state-of-the-art detectors, reaching 72.5\% and 67.6\% in \textbf{\(\mathbf{mAP_{.50:.95}}\) }respectively with 1.49M parameters. Our code will be released soon.

The widespread use of Large Language Models (LLMs) in software engineering has intensified the need for improved model and resource efficiency. In particular, for neural code generation, LLMs are used to translate function/method signature and DocString to executable code. DocStrings which capture user re quirements for the code and used as the prompt for LLMs, often contains redundant information. Recent advancements in prompt compression have shown promising results in Natural Language Processing (NLP), but their applicability to code generation remains uncertain. Our empirical study show that the state-of-the-art prompt compression methods achieve only about 10% reduction, as further reductions would cause significant performance degradation. In our study, we propose a novel compression method, ShortenDoc, dedicated to DocString compression for code generation. Our extensive experiments on six code generation datasets, five open-source LLMs (1B to 10B parameters), and one closed-source LLM GPT-4o confirm that ShortenDoc achieves 25-40% compression while preserving the quality of generated code, outperforming other baseline methods at similar compression levels. The benefit of this research is to improve efficiency and reduce the cost while maintaining the quality of the generated code, especially when calling third-party APIs, and is able to reduce the token processing cost by 25-40%., Comment: UNDER REVIEW

As the volume of image data grows, data-oriented cloud computing in Internet of Video Things (IoVT) systems encounters latency issues. Task-oriented edge computing addresses this by shifting data analysis to the edge. However, limited computational power of edge devices poses challenges for executing visual tasks. Existing methods struggle to balance high model performance with low resource consumption; lightweight neural networks often underperform, while device-specific models designed by Neural Architecture Search (NAS) fail to adapt to heterogeneous devices. For these issues, we propose a novel co-design framework to optimize neural network architecture and deployment strategies during inference for high-throughput. Specifically, it implements a dynamic model structure based on re-parameterization, coupled with a Roofline-based model partitioning strategy to enhance the computational performance of edge devices. We also employ a multi-objective co-optimization approach to balance throughput and accuracy. Additionally, we derive mathematical consistency and convergence of partitioned models. Experimental results demonstrate significant improvements in throughput (12.05\% on MNIST, 18.83\% on ImageNet) and superior classification accuracy compared to baseline algorithms. Our method consistently achieves stable performance across different devices, underscoring its adaptability. Simulated experiments further confirm its efficacy in high-accuracy, real-time detection for small objects in IoVT systems.

Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications. Despite the importance and recent progress, most existing works on personalized LLMs have focused either entirely on (a) personalized text generation or (b) leveraging LLMs for personalization-related downstream applications, such as recommendation systems. In this work, we bridge the gap between these two separate main directions for the first time by introducing a taxonomy for personalized LLM usage and summarizing the key differences and challenges. We provide a formalization of the foundations of personalized LLMs that consolidates and expands notions of personalization of LLMs, defining and discussing novel facets of personalization, usage, and desiderata of personalized LLMs. We then unify the literature across these diverse fields and usage scenarios by proposing systematic taxonomies for the granularity of personalization, personalization techniques, datasets, evaluation methods, and applications of personalized LLMs. Finally, we highlight challenges and important open problems that remain to be addressed. By unifying and surveying recent research using the proposed taxonomies, we aim to provide a clear guide to the existing literature and different facets of personalization in LLMs, empowering both researchers and practitioners.

Using $(10087\pm44)\times 10^{6}$ $J/\psi$ decays collected by the BESIII detector at the BEPCII collider, we search for baryon number violation via $\Lambda-\bar{\Lambda}$ oscillation in the decay $J/\psi \to \Lambda \bar{\Lambda}$. No evidence for $\Lambda-\bar\Lambda$ oscillation is observed. The upper limit on the time-integrated probability of $\Lambda-\bar{\Lambda}$ oscillation is estimated to be $1.4\times 10^{-6}$, corresponding to an oscillation parameter less than $2.1\times 10^{-18}~\mathrm{GeV}$ at $90\%$ confidence level., Comment: 8 pages, 2 figures

Sleep monitoring plays a crucial role in maintaining good health, with sleep staging serving as an essential metric in the monitoring process. Traditional methods, utilizing medical sensors like EEG and ECG, can be effective but often present challenges such as unnatural user experience, complex deployment, and high costs. Ballistocardiography~(BCG), a type of piezoelectric sensor signal, offers a non-invasive, user-friendly, and easily deployable alternative for long-term home monitoring. However, reliable BCG-based sleep staging is challenging due to the limited sleep monitoring data available for BCG. A restricted training dataset prevents the model from generalization across populations. Additionally, transferring to BCG faces difficulty ensuring model robustness when migrating from other data sources. To address these issues, we introduce SleepNetZero, a zero-shot learning based approach for sleep staging. To tackle the generalization challenge, we propose a series of BCG feature extraction methods that align BCG components with corresponding respiratory, cardiac, and movement channels in PSG. This allows models to be trained on large-scale PSG datasets that are diverse in population. For the migration challenge, we employ data augmentation techniques, significantly enhancing generalizability. We conducted extensive training and testing on large datasets~(12393 records from 9637 different subjects), achieving an accuracy of 0.803 and a Cohen's Kappa of 0.718. ZeroSleepNet was also deployed in real prototype~(monitoring pads) and tested in actual hospital settings~(265 users), demonstrating an accuracy of 0.697 and a Cohen's Kappa of 0.589. To the best of our knowledge, this work represents the first known reliable BCG-based sleep staging effort and marks a significant step towards in-home health monitoring., Comment: 25 pages

The thermalization of an isolated quantum system is described by quantum mechanics and thermodynamics, while these two subjects are still not fully consistent with each other. This leaves a less-explored region where both quantum and thermal effects cannot be neglected, and the ultracold atom platform provides a suitable and versatile testbed to experimentally investigate these complex phenomena. Here we perform experiments based on ultracold atoms in optical lattices and observe a divergence of thermalization rates of quantum matters when the temperature approaches zero. By ramping an external parameter in the Hamiltonian, we observe the time delay between the internal relaxation and the external ramping. This provides us with a direct comparison of the thermalization rates of different quantum phases. We find that the quantum coherence and bosonic stimulation of superfluid induces the divergence while the finite temperature and the many-body interactions are suppressing the divergence. The quantum coherence and the thermal effects are competing with each other in this isolated thermal quantum system, which leads to the transition of thermalization rate from divergence to convergence.

Temporal Knowledge Graph (TKG) representation learning aims to map temporal evolving entities and relations to embedded representations in a continuous low-dimensional vector space. However, existing approaches cannot capture the temporal evolution of high-order correlations in TKGs. To this end, we propose a Deep Evolutionary Clustering jointed temporal knowledge graph Representation Learning approach (DECRL). Specifically, a deep evolutionary clustering module is proposed to capture the temporal evolution of high-order correlations among entities. Furthermore, a cluster-aware unsupervised alignment mechanism is introduced to ensure the precise one-to-one alignment of soft overlapping clusters across timestamps, thereby maintaining the temporal smoothness of clusters. In addition, an implicit correlation encoder is introduced to capture latent correlations between any pair of clusters under the guidance of a global graph. Extensive experiments on seven real-world datasets demonstrate that DECRL achieves the state-of-the-art performances, outperforming the best baseline by an average of 9.53%, 12.98%, 10.42%, and 14.68% in MRR, Hits@1, Hits@3, and Hits@10, respectively., Comment: Accepted by NeurIPS 2024, 17 pages, and 3 figures

Nonlinear Hall effect (NLHE) offers a novel means of uncovering symmetry and topological properties in quantum materials, holding promise for exotic (opto)electronic applications such as microwave rectification and THz detection. The BCD-independent NLHE could exhibit a robust response even at room temperature, which is highly desirable for practical applications. However, in materials with bulk inversion symmetry, the coexistence of bulk and surface conducting channels often leads to a suppressed NLHE and complex thickness-dependent behavior. Here, we report the observation of room-temperature nonlinear transverse response in 3D topological insulator Bi2Te3 thin films, whose electrical transport properties are dominated by topological surface state (TSS). By varying the thickness of Bi2Te3 epitaxial films from 7 nm to 50 nm, we found that the nonlinear transverse response increases with thickness from 7 nm to 25 nm and remains almost constant above 25 nm. This is consistent with the thickness-dependent basic transport properties, including conductance, carrier density, and mobility, indicating a pure and robust TSS-dominated linear and nonlinear transport in thick (>25 nm) Bi2Te3 films. The weaker nonlinear transverse response in Bi2Te3 below 25 nm was attributed to Te deficiency and poorer crystallinity. By utilizing the TSS-dominated electrical second harmonic generation, we successfully achieved the microwave rectification from 0.01 to 16.6 GHz in 30 nm and bulk Bi2Te3. Our work demonstrated the room temperature nonlinear transverse response in a paradigm topological insulator, addressing the tunability of the topological second harmonic response by thickness engineering.

Large language models (LLMs) have excelled in various NLP tasks, including machine translation (MT), yet most studies focus on sentence-level translation. This work investigates the inherent capability of instruction-tuned LLMs for document-level translation (docMT). Unlike prior approaches that require specialized techniques, we evaluate LLMs by directly prompting them to translate entire documents in a single pass. Our results show that this method improves translation quality compared to translating sentences separately, even without document-level fine-tuning. However, this advantage is not reflected in BLEU scores, which often favor sentence-based translations. We propose using the LLM-as-a-judge paradigm for evaluation, where GPT-4 is used to assess document coherence, accuracy, and fluency in a more nuanced way than n-gram-based metrics. Overall, our work demonstrates that instruction-tuned LLMs can effectively leverage document context for translation. However, we caution against using BLEU scores for evaluating docMT, as they often provide misleading outcomes, failing to capture the quality of document-level translation. Code and data are available at https://github.com/EIT-NLP/BLEUless_DocMT

Recent studies have demonstrated that large language models (LLMs) exhibit significant biases in evaluation tasks, particularly in preferentially rating and favoring self-generated content. However, the extent to which this bias manifests in fact-oriented tasks, especially within retrieval-augmented generation (RAG) frameworks-where keyword extraction and factual accuracy take precedence over stylistic elements-remains unclear. Our study addresses this knowledge gap by simulating two critical phases of the RAG framework. In the first phase, we access the suitability of human-authored versus model-generated passages, emulating the pointwise reranking process. The second phase involves conducting pairwise reading comprehension tests to simulate the generation process. Contrary to previous findings indicating a self-preference in rating tasks, our results reveal no significant self-preference effect in RAG frameworks. Instead, we observe that factual accuracy significantly influences LLMs' output, even in the absence of prior knowledge. Our research contributes to the ongoing discourse on LLM biases and their implications for RAG-based system, offering insights that may inform the development of more robust and unbiased LLM systems., Comment: 15 pages, 14 tables, 5 figures

In this paper, we study an object synthesis task that combines an object text with an object image to create a new object image. However, most diffusion models struggle with this task, \textit{i.e.}, often generating an object that predominantly reflects either the text or the image due to an imbalance between their inputs. To address this issue, we propose a simple yet effective method called Adaptive Text-Image Harmony (ATIH) to generate novel and surprising objects. First, we introduce a scale factor and an injection step to balance text and image features in cross-attention and to preserve image information in self-attention during the text-image inversion diffusion process, respectively. Second, to better integrate object text and image, we design a balanced loss function with a noise parameter, ensuring both optimal editability and fidelity of the object image. Third, to adaptively adjust these parameters, we present a novel similarity score function that not only maximizes the similarities between the generated object image and the input text/image but also balances these similarities to harmonize text and image integration. Extensive experiments demonstrate the effectiveness of our approach, showcasing remarkable object creations such as colobus-glass jar. Project page: https://xzr52.github.io/ATIH/., Comment: NeurIPS2024

The massive population election simulation aims to model the preferences of specific groups in particular election scenarios. It has garnered significant attention for its potential to forecast real-world social trends. Traditional agent-based modeling (ABM) methods are constrained by their ability to incorporate complex individual background information and provide interactive prediction results. In this paper, we introduce ElectionSim, an innovative election simulation framework based on large language models, designed to support accurate voter simulations and customized distributions, together with an interactive platform to dialogue with simulated voters. We present a million-level voter pool sampled from social media platforms to support accurate individual simulation. We also introduce PPE, a poll-based presidential election benchmark to assess the performance of our framework under the U.S. presidential election scenario. Through extensive experiments and analyses, we demonstrate the effectiveness and robustness of our framework in U.S. presidential election simulations., Comment: 42 pages, 14 figures

We report the discovery of a peculiar X-ray transient, EP240408a, by Einstein Probe (EP) and follow-up studies made with EP, Swift, NICER, GROND, ATCA and other ground-based multi-wavelength telescopes. The new transient was first detected with Wide-field X-ray Telescope (WXT) on board EP on April 8th, 2024, manifested in an intense yet brief X-ray flare lasting for 12 seconds. The flare reached a peak flux of 3.9x10^(-9) erg/cm2/s in 0.5-4 keV, about 300 times brighter than the underlying X-ray emission detected throughout the observation. Rapid and more precise follow-up observations by EP/FXT, Swift and NICER confirmed the finding of this new transient. Its X-ray spectrum is non-thermal in 0.5-10 keV, with a power-law photon index varying within 1.8-2.5. The X-ray light curve shows a plateau lasting for about 4 days, followed by a steep decay till becoming undetectable about 10 days after the initial detection. Based on its temporal property and constraints from previous EP observations, an unusual timescale in the range of 7-23 days is found for EP240408a, which is intermediate between the commonly found fast and long-term transients. No counterparts have been found in optical and near-infrared, with the earliest observation at 17 hours after the initial X-ray detection, suggestive of intrinsically weak emission in these bands. We demonstrate that the remarkable properties of EP240408a are inconsistent with any of the transient types known so far, by comparison with, in particular, jetted tidal disruption events, gamma-ray bursts, X-ray binaries and fast blue optical transients. The nature of EP240408a thus remains an enigma. We suggest that EP240408a may represent a new type of transients with intermediate timescales of the order of about 10 days. The detection and follow-ups of more of such objects are essential for revealing their origin., Comment: 25 pages, 11 figures

Visual place recognition (VPR) enables autonomous robots to identify previously visited locations, which contributes to tasks like simultaneous localization and mapping (SLAM). VPR faces challenges such as accurate image neighbor retrieval and appearance change in scenery. Event cameras, also known as dynamic vision sensors, are a new sensor modality for VPR and offer a promising solution to the challenges with their unique attributes: high temporal resolution (1MHz clock), ultra-low latency (in {\mu}s), and high dynamic range (>120dB). These attributes make event cameras less susceptible to motion blur and more robust in variable lighting conditions, making them suitable for addressing VPR challenges. However, the scarcity of event-based VPR datasets, partly due to the novelty and cost of event cameras, hampers their adoption. To fill this data gap, our paper introduces the NYC-Event-VPR dataset to the robotics and computer vision communities, featuring the Prophesee IMX636 HD event sensor (1280x720 resolution), combined with RGB camera and GPS module. It encompasses over 13 hours of geotagged event data, spanning 260 kilometers across New York City, covering diverse lighting and weather conditions, day/night scenarios, and multiple visits to various locations. Furthermore, our paper employs three frameworks to conduct generalization performance assessments, promoting innovation in event-based VPR and its integration into robotics applications.

This paper proposes a double Y-configuration multi active bridge converter (DYAB) capable of single stage bidirectional AC-DC isolated power conversion with a simple sinusoidal phase shift modulation. Compared to other dual active bridge (DAB) based AC-DC converters, the DYAB achieves power factor correction (PFC) with a simpler control method while maintaining nearly full-range zero-voltage switching (ZVS) and relatively low circulating current, resulting in high efficiency. The paper details the equivalent model and modulation method. A steady-state analysis tool based on the fast fourier transform (FFT) is developed to calculate the ZVS range, PFC performance, and loss breakdown. A 2.66kW hardware test demonstrating an efficiency of 97.14% is implemented to verify the proposed circuit and the steady state model.

Since the release of ChatGPT, large language models (LLMs) have demonstrated remarkable capabilities across various domains. A key challenge in developing these general capabilities is efficiently sourcing diverse, high-quality data. This becomes especially critical in reasoning-related tasks with sandbox checkers, such as math or code, where the goal is to generate correct solutions to specific problems with higher probability. In this work, we introduce Flaming-hot Initiation with Regular Execution (FIRE) sampling, a simple yet highly effective method to efficiently find good responses. Our empirical findings show that FIRE sampling enhances inference-time generation quality and also benefits training in the alignment stage. Furthermore, we explore how FIRE sampling improves performance by promoting diversity and analyze the impact of employing FIRE at different positions within a response.

Measurements of $CP$ observables and the CKM angle $\gamma$ are performed in $B^{\pm} \to D K^*(892)^{\pm}$ decays, where $D$ represents a superposition of $D^0$ and $\overline{D}{}^0$ states, using the LHCb dataset collected during Run 1 (2011-2012) and Run 2 (2015-2018). A comprehensive study of this channel is presented with the $D$ meson reconstructed in two-body final states $K^{\pm}\pi^{\mp}$, $K^+K^-$ and $\pi^+\pi^-$; four-body final states $K^{\pm}\pi^{\mp}\pi^{\pm}\pi^{\mp}$ and $\pi^+\pi^-\pi^+\pi^-$; and three-body final states $K^0_{S} \pi^+\pi^-$ and $K^0_{S} K^+ K^-$. This analysis includes the first observation of the suppressed $B^{\pm} \to [\pi^+K^-]_D K^{*\pm}$ and $B^{\pm} \to [\pi^+K^-\pi^+\pi^-]_D K^{*\pm}$ decays. The combined result gives $\gamma=(63\pm 13)^\circ$., Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3180/ (LHCb public pages)

In semiconducting monolayer transition metal dichalcogenides (ML-TMDs), broken inversion symmetry and strong spin-orbit coupling result in spin-valley lock-in effects so that the valley degeneracy may be lifted by external magnetic fields, potentially leading to real-space structural transformation. Here, we report magnetic field (B)-induced giant electric hysteretic responses to back-gate voltages in ML-MoS2 field-effect transistors (FETs) on SiO2/Si at temperatures < 20 K. The observed hysteresis increases with |B| up to 12 T and is tunable by varying the temperature. Raman spectroscopic and scanning tunneling microscopic studies reveal significant lattice expansion with increasing |B| at 4.2 K, and this lattice expansion becomes asymmetric in ML-MoS2 FETs on rigid SiO2/Si substrates, leading to out-of-plane mirror symmetry breaking and the emergence of a tunable out-of-plane ferroelectric-like polar order. This broken symmetry-induced polarization in ML-MoS2 shows typical ferroelectric butterfly hysteresis in piezo-response force microscopy, adding ML-MoS2 to the single-layer material family that exhibit out-of-plane polar order-induced ferroelectricity, which is promising for such technological applications as cryo-temperature ultracompact non-volatile memories, memtransistors, and ultrasensitive magnetic field sensors. Moreover, the polar effect induced by asymmetric lattice expansion may be further generalized to other ML-TMDs and achieved by nanoscale strain engineering of the substrate without magnetic fields.

High-energy vortex $\gamma$ photons have significant applications in many fields, however, their generation and angular momentum manipulation are still great challenges. Here, we first investigated the generation of vortex $\gamma$ photons with controllable spin and orbital angular momenta via nonlinear Compton scattering of two-color counter-rotating circularly polarized (CP) laser fields. The radiation probability of vortex photons are calculated using the semiclassical approach that resolves angular momenta of emitted photons. We find that the angular momenta transferred to emitted photons are determined by the dominating photon absorption channel, leading to a structured spectrum with alternations in chirality and twisted direction. By tuning the relative intensity ratio of the two-color CP laser fields, the polarization and vortex charge of the emitted $\gamma$ photons can be controlled, enabling the generation of circularly polarized vortex $\gamma$ photons with a user-defined polarization and topological charge, which may have a plenty of applications in nuclear physics, astrophysics, particle physics, etc.

Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-explored. To fill this gap, this work aims to investigate the research question: "What factors affect the performance of MM-ICL?'' To this end, we investigate extensive experiments on the three core steps of MM-ICL including demonstration retrieval, demonstration ordering, and prompt construction using 6 vision large language models and 20 strategies. Our findings highlight (1) the necessity of a multi-modal retriever for demonstration retrieval, (2) the importance of intra-demonstration ordering over inter-demonstration ordering, and (3) the enhancement of task comprehension through introductory instructions in prompts. We hope this study can serve as a foundational guide for optimizing MM-ICL strategies in future research., Comment: Accepted at NeurIPS 2024

Multi-dimensional time series data, such as matrix and tensor-variate time series, are increasingly prevalent in fields such as economics, finance, and climate science. Traditional Transformer models, though adept with sequential data, do not effectively preserve these multi-dimensional structures, as their internal operations in effect flatten multi-dimensional observations into vectors, thereby losing critical multi-dimensional relationships and patterns. To address this, we introduce the Tensor-Augmented Transformer (TEAFormer), a novel method that incorporates tensor expansion and compression within the Transformer framework to maintain and leverage the inherent multi-dimensional structures, thus reducing computational costs and improving prediction accuracy. The core feature of the TEAFormer, the Tensor-Augmentation (TEA) module, utilizes tensor expansion to enhance multi-view feature learning and tensor compression for efficient information aggregation and reduced computational load. The TEA module is not just a specific model architecture but a versatile component that is highly compatible with the attention mechanism and the encoder-decoder structure of Transformers, making it adaptable to existing Transformer architectures. Our comprehensive experiments, which integrate the TEA module into three popular time series Transformer models across three real-world benchmarks, show significant performance enhancements, highlighting the potential of TEAFormers for cutting-edge time series forecasting.

This material introduces the D-Subspace algorithm derived on the basis of the centralized algorithm [1], which originally addresses parameter estimation problems under a subspace constraint.

Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e.g., bounding boxes). To address this gap, this paper introduces R-LLaVA, designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual regions of interest are then fed into the LLaVA model during training, aiming to enrich the model's understanding of biomedical queries. Experimental evaluation on four standard Med-VQA datasets demonstrates R-LLaVA's superiority over existing state-of-the-art (SoTA) methods. Additionally, to verify the model's capability in visual comprehension, a novel multiple-choice medical visual understanding dataset is introduced, confirming the positive impact of focusing on visual regions of interest in advancing biomedical VQA understanding., Comment: 11 pages, 7 figures

Digital Signal Processing (DSP) and Digital Image Processing (DIP) with Machine Learning (ML) and Deep Learning (DL) are popular research areas in Computer Vision and related fields. We highlight transformative applications in image enhancement, filtering techniques, and pattern recognition. By integrating frameworks like the Discrete Fourier Transform (DFT), Z-Transform, and Fourier Transform methods, we enable robust data manipulation and feature extraction essential for AI-driven tasks. Using Python, we implement algorithms that optimize real-time data processing, forming a foundation for scalable, high-performance solutions in computer vision. This work illustrates the potential of ML and DL to advance DSP and DIP methodologies, contributing to artificial intelligence, automated feature extraction, and applications across diverse domains., Comment: 293 pages

Diffusion models, which can be viewed as a special case of hierarchical variational autoencoders (HVAEs), have shown profound success in generating photo-realistic images. In contrast, standard HVAEs often produce images of inferior quality compared to diffusion models. In this paper, we hypothesize that the success of diffusion models can be partly attributed to the additional self-supervision information for their intermediate latent states provided by corrupted images, which along with the original image form a pseudo video. Based on this hypothesis, we explore the possibility of improving other types of generative models with such pseudo videos. Specifically, we first extend a given image generative model to their video generative model counterpart, and then train the video generative model on pseudo videos constructed by applying data augmentation to the original images. Furthermore, we analyze the potential issues of first-order Markov data augmentation methods, which are typically used in diffusion models, and propose to use more expressive data augmentation to construct more useful information in pseudo videos. Our empirical results on the CIFAR10 and CelebA datasets demonstrate that improved image generation quality can be achieved with additional self-supervised information from pseudo videos., Comment: 18 pages, 7 figures

By analyzing $e^{+}e^{-}$ collision data with an integrated luminosity of 7.9~fb$^{-1}$ collected with the BESIII detector at the center-of-mass energy of 3.773~GeV, the branching fraction of $D^+\to\tau^+\nu_{\tau}$ is determined as $\mathcal{B}=(9.9\pm 1.1_\mathrm{stat}\pm 0.5_\mathrm{syst})\times10^{-4}$. Taking the most precise result $\mathcal{B}(D^+\to\mu^+\nu_{\mu})=(3.981\pm 0.079_\mathrm{stat}\pm0.040_\mathrm{syst})\times10^{-4}$, we determine $R_{\tau/\mu} = \Gamma(D^+\to\tau^+\nu_{\tau})/\Gamma(D^+\to\mu^+\nu_{\mu})= 2.49\pm0.31$, achieving a factor of two improvement in precision compared to the previous BESIII result. This measurement is in agreement with the standard model prediction of lepton flavor universality within one standard deviation.

Deep learning is widely used to predict complex dynamical systems in many scientific and engineering areas. However, the black-box nature of these deep learning models presents significant challenges for carrying out simultaneous data assimilation (DA), which is a crucial technique for state estimation, model identification, and reconstructing missing data. Integrating ensemble-based DA methods with nonlinear deep learning models is computationally expensive and may suffer from large sampling errors. To address these challenges, we introduce a deep learning framework designed to simultaneously provide accurate forecasts and efficient DA. It is named Conditional Gaussian Koopman Network (CGKN), which transforms general nonlinear systems into nonlinear neural differential equations with conditional Gaussian structures. CGKN aims to retain essential nonlinear components while applying systematic and minimal simplifications to facilitate the development of analytic formulae for nonlinear DA. This allows for seamless integration of DA performance into the deep learning training process, eliminating the need for empirical tuning as required in ensemble methods. CGKN compensates for structural simplifications by lifting the dimension of the system, which is motivated by Koopman theory. Nevertheless, CGKN exploits special nonlinear dynamics within the lifted space. This enables the model to capture extreme events and strong non-Gaussian features in joint and marginal distributions with appropriate uncertainty quantification. We demonstrate the effectiveness of CGKN for both prediction and DA on three strongly nonlinear and non-Gaussian turbulent systems: the projected stochastic Burgers--Sivashinsky equation, the Lorenz 96 system, and the El Ni\~no-Southern Oscillation. The results justify the robustness and computational efficiency of CGKN.

Small Language Models (SLMs) have become increasingly important due to their efficiency and performance to perform various language tasks with minimal computational resources, making them ideal for various settings including on-device, mobile, edge devices, among many others. In this article, we present a comprehensive survey on SLMs, focusing on their architectures, training techniques, and model compression techniques. We propose a novel taxonomy for categorizing the methods used to optimize SLMs, including model compression, pruning, and quantization techniques. We summarize the benchmark datasets that are useful for benchmarking SLMs along with the evaluation metrics commonly used. Additionally, we highlight key open challenges that remain to be addressed. Our survey aims to serve as a valuable resource for researchers and practitioners interested in developing and deploying small yet efficient language models.

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

This study focuses on transforming galaxy images between astronomical surveys, specifically enhancing images from the Sloan Digital Sky Survey (SDSS) and the Dark Energy Camera Legacy Survey (DECaLS) to achieve quality comparable to the Hyper Suprime-Cam survey (HSC). We proposed a hybrid model called Pix2WGAN, which integrates the pix2pix framework with the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) to convert low-quality observational images into high-quality counterparts. Our model successfully transformed DECaLS images into pseudo-HSC images, yielding impressive results and significantly enhancing the identification of complex structures, such as galaxy spiral arms and tidal tails, which may have been overlooked in the original DECaLS images. Moreover, Pix2WGAN effectively addresses issues like artifacts, noise, and blurriness in both source and target images. In addition to the basic Pix2WGAN model, we further developed an advanced architecture called Cascaded Pix2WGAN, which incorporates a multi-stage training mechanism designed to bridge the quality gap between SDSS and HSC images, demonstrating similarly promising outcomes. We systematically assessed the similarity between the model-generated pseudo-HSC images and actual HSC images using various metrics, including Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM), along with perceptual metrics such as Learned Perceptual Image Patch Similarity (LPIPS) and Fr\'echet Inception Distance (FID). The results indicate that images transformed by our model outperform both the original SDSS and DECaLS images across nearly all evaluation metrics. Our research is expected to provide significant technical support for astronomical data analysis, cross-survey image integration, and high-precision astrometry.

Two-dimensional (2D) superconductors that reside on substrates must be influenced by Rashba spin-orbit coupling (SOC). The intriguing effect of Rashba-type SOCs on iron-based superconductors (IBSs) has remained largely a mystery. In this work, we unveil modified Landau-level spectroscopy and the intricate band splitting of FeSe monolayers through the precision of scanning tunneling spectroscopy, which unequivocally demonstrates the presence of Rashba SOC. The discovery sheds light on a nonparabolic electron band at the X/Y point, displaying a distinctive Landau quantization behavior characterized by $E_n\propto(nB)^{4/3}$. The theoretical model aligns with our experimental insights, positing that the k$^4$-term of the electron band becomes predominant and profoundly reshapes the band structure. Our research underscores the pivotal role of the Rashba SOC effect on 2D superconductors and sets the stage to probe new quantum states in systems with remarkably low carrier concentrations., Comment: 21 pages, 5 figures

Isolated Sign Language Recognition (ISLR) focuses on identifying individual sign language glosses. Considering the diversity of sign languages across geographical regions, developing region-specific ISLR datasets is crucial for supporting communication and research. Auslan, as a sign language specific to Australia, still lacks a dedicated large-scale word-level dataset for the ISLR task. To fill this gap, we curate \underline{\textbf{the first}} large-scale Multi-view Multi-modal Word-Level Australian Sign Language recognition dataset, dubbed MM-WLAuslan. Compared to other publicly available datasets, MM-WLAuslan exhibits three significant advantages: (1) the largest amount of data, (2) the most extensive vocabulary, and (3) the most diverse of multi-modal camera views. Specifically, we record 282K+ sign videos covering 3,215 commonly used Auslan glosses presented by 73 signers in a studio environment. Moreover, our filming system includes two different types of cameras, i.e., three Kinect-V2 cameras and a RealSense camera. We position cameras hemispherically around the front half of the model and simultaneously record videos using all four cameras. Furthermore, we benchmark results with state-of-the-art methods for various multi-modal ISLR settings on MM-WLAuslan, including multi-view, cross-camera, and cross-view. Experiment results indicate that MM-WLAuslan is a challenging ISLR dataset, and we hope this dataset will contribute to the development of Auslan and the advancement of sign languages worldwide. All datasets and benchmarks are available at MM-WLAuslan.

This paper explores the application of prompt engineering to enhance the performance of large language models (LLMs) in the domain of Traditional Chinese Medicine (TCM). We propose TCM-Prompt, a framework that integrates various pre-trained language models (PLMs), templates, tokenization, and verbalization methods, allowing researchers to easily construct and fine-tune models for specific TCM-related tasks. We conducted experiments on disease classification, syndrome identification, herbal medicine recommendation, and general NLP tasks, demonstrating the effectiveness and superiority of our approach compared to baseline methods. Our findings suggest that prompt engineering is a promising technique for improving the performance of LLMs in specialized domains like TCM, with potential applications in digitalization, modernization, and personalized medicine.

We have investigated the structures and electronic properties of ultra-thin Bi(110) films grown on an s-wave superconductor substrate using low-temperature scanning tunneling microscopy and spectroscopy. Remarkably, our experimental results validate the theoretical predictions that the manipulation of Bi(110) surface atom buckling can control the topological phase transition. Notably, we have observed robust unreconstructed edge states at the edges of both 3-bilayer (BL) and 4-BL Bi(110) films, with the 4-BL film displaying stronger edge state intensity and a smaller degree of atomic buckling. First-principle calculations further substantiate these findings, demonstrating a gradual reduction in buckling as the film thickness increases, with average height differences between two Bi atoms of approximately 0.19 {\AA}, 0.10 {\AA}, 0.05 {\AA}, and 0.00 {\AA} for the 1-BL, 2-BL, 3-BL, and 4-BL Bi(110) films, respectively. When Bi films are larger than 2 layers, the system changes from a trivial to a non-trivial phase. This research sets the stage for the controlled realization of topological superconductors through the superconducting proximity effect, providing a significant platform for investigating Majorana zero modes and fabricating quantum devices.

Multi-modal fusion is imperative to the implementation of reliable object detection and tracking in complex environments. Exploiting the synergy of heterogeneous modal information endows perception systems the ability to achieve more comprehensive, robust, and accurate performance. As a nucleus concern in wireless-vision collaboration, radar-camera fusion has prompted prospective research directions owing to its extensive applicability, complementarity, and compatibility. Nonetheless, there still lacks a systematic survey specifically focusing on deep fusion of radar and camera for object detection and tracking. To fill this void, we embark on an endeavor to comprehensively review radar-camera fusion in a holistic way. First, we elaborate on the fundamental principles, methodologies, and applications of radar-camera fusion perception. Next, we delve into the key techniques concerning sensor calibration, modal representation, data alignment, and fusion operation. Furthermore, we provide a detailed taxonomy covering the research topics related to object detection and tracking in the context of radar and camera technologies.Finally, we discuss the emerging perspectives in the field of radar-camera fusion perception and highlight the potential areas for future research.

The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena, offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard Model. Utilizing a high-intensity muon beam, a Michel electron magnetic spectrometer and a positron transport solenoid together with a positron detection system, MACE aims to discover or constrain this rare process at the conversion probability beyond the level of $10^{-13}$. This report provides an overview of the theoretical framework and detailed experimental design in the search for the muonium-to-antimuonium conversion., Comment: 115 pages, 59 figures

We present a new method for the verification of quantum circuits based on a novel symbolic representation of sets of quantum states using level-synchronized tree automata (LSTAs). LSTAs extend classical tree automata by labeling each transition with a set of choices, which are then used to synchronize subtrees of an accepted tree. Compared to the traditional tree automata, LSTAs have an incomparable expressive power while maintaining important properties, such as closure under union and intersection, and decidable language emptiness and inclusion. We have developed an efficient and fully automated symbolic verification algorithm for quantum circuits based on LSTAs. The complexity of supported gate operations is at most quadratic, dramatically improving the exponential worst-case complexity of an earlier tree automata-based approach. Furthermore, we show that LSTAs are a promising model for parameterized verification, i.e., verifying the correctness of families of circuits with the same structure for any number of qubits involved, which principally lies beyond the capabilities of previous automated approaches. We implemented this method as a C++ tool and compared it with three symbolic quantum circuit verifiers and two simulators on several benchmark examples. The results show that our approach can solve problems with sizes orders of magnitude larger than the state of the art.

Using $(27.12\pm0.14) \times 10^{8}$ $\psi(2S)$ events collected by the BESIII detector operating at BEPCII, we search for the decay $\eta_c(2S)\to p\bar{p}$ via the process $\psi(2S)\to \gamma\eta_c(2S)$, and only find a signal with a significance of $1.7\,\sigma$. The upper limit of the product branching fraction at the 90% confidence level is determined to be $\mathcal{B}(\psi(2S)\to \gamma\eta_c(2S))\times \mathcal{B}(\eta_c(2S)\to p\bar{p})<2.4\times 10^{-7}$. The branching fractions of $\chi_{cJ}\to p\bar{p}~(J=0,1,2)$ are also measured to be $\mathcal{B}(\chi_{c0}\to p\bar{p})=(2.51\pm0.02\pm0.08)\times 10^{-4}$, $\mathcal{B}(\chi_{c1}\to p\bar{p})=(8.16\pm0.09\pm0.25)\times 10^{-4}$, and $\mathcal{B}(\chi_{c2}\to p\bar{p})=(8.33\pm0.09\pm0.22)\times 10^{-4}$, where the first uncertainty is statistical and the second systematic.

The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts for more than 80\% of this memory consumption. Nowadays, most existing KV cache compression methods focus on intra-layer compression within a single Transformer layer but few works consider layer-wise compression. In this paper, we propose a plug-and-play method called \textit{KVSharer}, which shares the KV cache between layers to achieve layer-wise compression. Rather than intuitively sharing based on higher similarity, we discover a counterintuitive phenomenon: sharing dissimilar KV caches better preserves the model performance. Experiments show that \textit{KVSharer} can reduce KV cache computation by 30\%, thereby lowering memory consumption without significantly impacting model performance and it can also achieve at least 1.3 times generation acceleration. Additionally, we verify that \textit{KVSharer} is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory., Comment: Under Review by ICLR2025