Search

Modulation-enhanced localization microscopy (MELM) has demonstrated significant improvements in both lateral and axial localization precision compared to conventional single-molecule localization microscopy (SMLM). However, lateral modulated illumination based MELM (MELMxy) remains fundamentally limited to two-dimensional imaging. Here we present three-dimensional Single-Molecule Modulated Illumination Localization Estimator (SMILE) that synergistically integrates lateral illumination modulation with point spread function engineering. By simultaneously exploiting lateral modulation patterns and an accurate point spread function (PSF) model for 3D localization, SMILE achieves near-theoretical-minimum localization uncertainty, demonstrating an average 4-fold enhancement in lateral precision compared to conventional 3D-SMLM. Crucially, SMILE exhibits exceptional compatibility with diverse PSFs and different illumination patterns with various structures including 4Pi configurations, making it a versatile tool that can be easily adapted for different experimental setups. When integrated with 4Pi microscopy, 4Pi-SMILE shows particular promise for achieving sub-10 nm axial resolution and approaching isotropic resolution. From the simulations and proof-of-concept experiments, we verified the superiority of SMILE over 3D-SMLM and ordinary MELM. We highlight SMILE as a novel methodology and robust framework that holds great potential to significantly promote the development of MELM.

Large Language Models (LLMs) have become essential for offensive language detection, yet their ability to handle annotation disagreement remains underexplored. Disagreement samples, which arise from subjective interpretations, pose a unique challenge due to their ambiguous nature. Understanding how LLMs process these cases, particularly their confidence levels, can offer insight into their alignment with human annotators. This study systematically evaluates the performance of multiple LLMs in detecting offensive language at varying levels of annotation agreement. We analyze binary classification accuracy, examine the relationship between model confidence and human disagreement, and explore how disagreement samples influence model decision-making during few-shot learning and instruction fine-tuning. Our findings reveal that LLMs struggle with low-agreement samples, often exhibiting overconfidence in these ambiguous cases. However, utilizing disagreement samples in training improves both detection accuracy and model alignment with human judgment. These insights provide a foundation for enhancing LLM-based offensive language detection in real-world moderation tasks., Comment: 17 pages, submitted to the ACL 2025

Humor recognition aims to identify whether a specific speaker's text is humorous. Current methods for humor recognition mainly suffer from two limitations: (1) they solely focus on one aspect of humor commonalities, ignoring the multifaceted nature of humor; and (2) they typically overlook the critical role of speaker individuality, which is essential for a comprehensive understanding of humor expressions. To bridge these gaps, we introduce the Commonality and Individuality Incorporated Network for Humor Recognition (CIHR), a novel model designed to enhance humor recognition by integrating multifaceted humor commonalities with the distinctive individuality of speakers. The CIHR features a Humor Commonality Analysis module that explores various perspectives of multifaceted humor commonality within user texts, and a Speaker Individuality Extraction module that captures both static and dynamic aspects of a speaker's profile to accurately model their distinctive individuality. Additionally, Static and Dynamic Fusion modules are introduced to effectively incorporate the humor commonality with speaker's individuality in the humor recognition process. Extensive experiments demonstrate the effectiveness of CIHR, underscoring the importance of concurrently addressing both multifaceted humor commonality and distinctive speaker individuality in humor recognition., Comment: Accepted by NAACL 2025

In this paper, we propose and analyze a linear, structure-preserving scalar auxiliary variable (SAV) method for solving the Allen--Cahn equation based on the second-order backward differentiation formula (BDF2) with variable time steps. To this end, we first design a novel and essential auxiliary functional that serves twofold functions: (i) ensuring that a first-order approximation to the auxiliary variable, which is essentially important for deriving the unconditional energy dissipation law, does not affect the second-order temporal accuracy of the phase function $\phi$; and (ii) allowing us to develop effective stabilization terms that are helpful to establish the MBP-preserving linear methods. Together with this novel functional and standard central difference stencil, we then propose a linear, second-order variable-step BDF2 type stabilized exponential SAV scheme, namely BDF2-sESAV-I, which is shown to preserve both the discrete modified energy dissipation law under the temporal stepsize ratio $ 0 < r_{k} := \tau_{k}/\tau_{k-1} < 4.864 - \delta $ with a positive constant $\delta$ and the MBP under $ 0 < r_{k} < 1 + \sqrt{2} $. Moreover, an analysis of the approximation to the original energy by the modified one is presented. With the help of the kernel recombination technique, optimal $ H^{1}$- and $ L^{\infty}$-norm error estimates of the variable-step BDF2-sESAV-I scheme are rigorously established. Numerical examples are carried out to verify the theoretical results and demonstrate the effectiveness and efficiency of the proposed scheme., Comment: 25 pages,31 figures

Wide-field surveys have markedly enhanced the discovery and study of solar system objects (SSOs). The 2.5-meter Wide Field Survey Telescope (WFST) represents the foremost facility dedicated to optical time-domain surveys in the northern hemisphere. To fully exploit WFST's capabilities for SSO detection, we have developed a heliocentric-orbiting objects processing system (HOPS) tailored for identifying these objects. This system integrates HelioLinC3D, an algorithm well suited for the WFST survey cadence, characterized by revisiting the same sky field twice on the majority of nights. In this paper, we outline the architecture and processing flow of our SSO processing system. The application of the system to the WFST pilot survey data collected between March and May 2024 demonstrates exceptional performance in terms of both temporal efficiency and completeness. A total of 658,489 observations encompassing 38,520 known asteroids have been documented, and 241 newly discovered asteroids have been assigned provisional designations. In particular, 27% of these new discoveries were achieved using merely two observations per night on three nights. The preliminary results not only illuminate the effectiveness of integrating HelioLinC3D within the SSO processing system, but also emphasize the considerable potential contributions of WFST to the field of solar system science., Comment: 23 pages, 6 figures, submitted to AAS journal

Convex clustering is a popular clustering model without requiring the number of clusters as prior knowledge. It can generate a clustering path by continuously solving the model with a sequence of regularization parameter values. This paper introduces {\it PyClustrPath}, a highly efficient Python package for solving the convex clustering model with GPU acceleration. {\it PyClustrPath} implements popular first-order and second-order algorithms with a clean modular design. Such a design makes {\it PyClustrPath} more scalable to incorporate new algorithms for solving the convex clustering model in the future. We extensively test the numerical performance of {\it PyClustrPath} on popular clustering datasets, demonstrating its superior performance compared to the existing solvers for generating the clustering path based on the convex clustering model. The implementation of {\it PyClustrPath} can be found at: https://github.com/D3IntOpt/PyClustrPath., Comment: 13 pages, 10 figures, 3 tables

The proliferation of hate speech has caused significant harm to society. The intensity and directionality of hate are closely tied to the target and argument it is associated with. However, research on hate speech detection in Chinese has lagged behind, and existing datasets lack span-level fine-grained annotations. Furthermore, the lack of research on Chinese hateful slang poses a significant challenge. In this paper, we provide a solution for fine-grained detection of Chinese hate speech. First, we construct a dataset containing Target-Argument-Hateful-Group quadruples (STATE ToxiCN), which is the first span-level Chinese hate speech dataset. Secondly, we evaluate the span-level hate speech detection performance of existing models using STATE ToxiCN. Finally, we conduct the first study on Chinese hateful slang and evaluate the ability of LLMs to detect such expressions. Our work contributes valuable resources and insights to advance span-level hate speech detection in Chinese.

As a class of nonlinear partial differential equations, the Keller-Segel system is widely used to model chemotaxis in biology. In this paper, we present the construction and analysis of a decoupled linear, mass-conservative, block-centered finite difference method for the classical Keller-Segel chemotaxis system. We show that the scheme is mass conservative for the cell density at the discrete level. In addition, second-order temporal and spatial convergence for both the cell density and the chemoattractant concentration are rigorously discussed, using the mathematical induction method, the discrete energy method and detailed analysis of the truncation errors. Our scheme is proposed and analyzed on non-uniform spatial grids, which leads to more accurate and efficient modeling results for the chemotaxis system with rapid blow-up phenomenon. Furthermore, the existence and uniqueness of solutions to the Keller-Segel chemotaxis system are also discussed. Numerical experiments are presented to verify the theoretical results and to show the robustness and accuracy of the scheme.

Collaborative perception significantly enhances individual vehicle perception performance through the exchange of sensory information among agents. However, real-world deployment faces challenges due to bandwidth constraints and inevitable calibration errors during information exchange. To address these issues, we propose mmCooper, a novel multi-agent, multi-stage, communication-efficient, and collaboration-robust cooperative perception framework. Our framework leverages a multi-stage collaboration strategy that dynamically and adaptively balances intermediate- and late-stage information to share among agents, enhancing perceptual performance while maintaining communication efficiency. To support robust collaboration despite potential misalignments and calibration errors, our framework captures multi-scale contextual information for robust fusion in the intermediate stage and calibrates the received detection results to improve accuracy in the late stage. We validate the effectiveness of mmCooper through extensive experiments on real-world and simulated datasets. The results demonstrate the superiority of our proposed framework and the effectiveness of each component.

3D models are favored over 2D for 3D medical image segmentation tasks due to their ability to leverage inter-slice relationship, yielding higher segmentation accuracy. However, 3D models demand significantly more GPU memory with increased model size and intermediate tensors. A common solution is to use patch-based training and make whole-volume predictions with sliding window (SW) inference. SW inference reduces memory usage but is slower due to equal resource allocation across patches and less accurate as it overlooks global features beyond patches. We propose NMSW-Net (No-More-Sliding-Window-Net), a novel framework that enhances efficiency and accuracy of any given 3D segmentation model by eliminating SW inference and incorporating global predictions when necessary. NMSW-Net incorporates a differentiable Top-k module to sample only the relevant patches that enhance segmentation accuracy, thereby minimizing redundant computations. Additionally, it learns to leverage coarse global predictions when patch prediction alone is insufficient. NMSW-Net is model-agnostic, making it compatible with any 3D segmentation model that previously relied on SW inference. Evaluated across 3 tasks with 3 segmentation backbones, NMSW-Net achieves competitive or sometimes superior accuracy compared to SW, while reducing computational complexity by 90% (87.5 to 7.95 TFLOPS), delivering 4x faster inference on the H100 GPU (19.0 to 4.3 sec), and 7x faster inference on the Intel Xeon Gold CPU (1710 to 230 seconds).

Recent advancements in 3D human pose estimation from single-camera images and videos have relied on parametric models, like SMPL. However, these models oversimplify anatomical structures, limiting their accuracy in capturing true joint locations and movements, which reduces their applicability in biomechanics, healthcare, and robotics. Biomechanically accurate pose estimation, on the other hand, typically requires costly marker-based motion capture systems and optimization techniques in specialized labs. To bridge this gap, we propose BioPose, a novel learning-based framework for predicting biomechanically accurate 3D human pose directly from monocular videos. BioPose includes three key components: a Multi-Query Human Mesh Recovery model (MQ-HMR), a Neural Inverse Kinematics (NeurIK) model, and a 2D-informed pose refinement technique. MQ-HMR leverages a multi-query deformable transformer to extract multi-scale fine-grained image features, enabling precise human mesh recovery. NeurIK treats the mesh vertices as virtual markers, applying a spatial-temporal network to regress biomechanically accurate 3D poses under anatomical constraints. To further improve 3D pose estimations, a 2D-informed refinement step optimizes the query tokens during inference by aligning the 3D structure with 2D pose observations. Experiments on benchmark datasets demonstrate that BioPose significantly outperforms state-of-the-art methods. Project website: \url{https://m-usamasaleem.github.io/publication/BioPose/BioPose.html}.

Human mesh recovery (HMR) is crucial in many computer vision applications; from health to arts and entertainment. HMR from monocular images has predominantly been addressed by deterministic methods that output a single prediction for a given 2D image. However, HMR from a single image is an ill-posed problem due to depth ambiguity and occlusions. Probabilistic methods have attempted to address this by generating and fusing multiple plausible 3D reconstructions, but their performance has often lagged behind deterministic approaches. In this paper, we introduce GenHMR, a novel generative framework that reformulates monocular HMR as an image-conditioned generative task, explicitly modeling and mitigating uncertainties in the 2D-to-3D mapping process. GenHMR comprises two key components: (1) a pose tokenizer to convert 3D human poses into a sequence of discrete tokens in a latent space, and (2) an image-conditional masked transformer to learn the probabilistic distributions of the pose tokens, conditioned on the input image prompt along with randomly masked token sequence. During inference, the model samples from the learned conditional distribution to iteratively decode high-confidence pose tokens, thereby reducing 3D reconstruction uncertainties. To further refine the reconstruction, a 2D pose-guided refinement technique is proposed to directly fine-tune the decoded pose tokens in the latent space, which forces the projected 3D body mesh to align with the 2D pose clues. Experiments on benchmark datasets demonstrate that GenHMR significantly outperforms state-of-the-art methods. Project website can be found at https://m-usamasaleem.github.io/publication/GenHMR/GenHMR.html

Since the debut of DPO, it has been shown that aligning a target LLM with human preferences via the KL-constrained RLHF loss is mathematically equivalent to a special kind of reward modeling task. Concretely, the task requires: 1) using the target LLM to parameterize the reward model, and 2) tuning the reward model so that it has a 1:1 linear relationship with the true reward. However, we identify a significant issue: the DPO loss might have multiple minimizers, of which only one satisfies the required linearity condition. The problem arises from a well-known issue of the underlying Bradley-Terry preference model: it does not always have a unique maximum likelihood estimator (MLE). Consequently,the minimizer of the RLHF loss might be unattainable because it is merely one among many minimizers of the DPO loss. As a better alternative, we propose an energy-based model (EBM) that always has a unique MLE, inherently satisfying the linearity requirement. To approximate the MLE in practice, we propose a contrastive loss named Energy Preference Alignment (EPA), wherein each positive sample is contrasted against one or more strong negatives as well as many free weak negatives. Theoretical properties of our EBM enable the approximation error of EPA to almost surely vanish when a sufficient number of negatives are used. Empirically, we demonstrate that EPA consistently delivers better performance on open benchmarks compared to DPO, thereby showing the superiority of our EBM.

Fuel efficiency is a crucial aspect of long-distance cargo transportation by oil-powered trucks that economize on costs and decrease carbon emissions. Current predictive control methods depend on an accurate model of vehicle dynamics and engine, including weight, drag coefficient, and the Brake-specific Fuel Consumption (BSFC) map of the engine. We propose a pure data-driven method, Neural Predictive Control (NPC), which does not use any physical model for the vehicle. After training with over 20,000 km of historical data, the novel proposed NVFormer implicitly models the relationship between vehicle dynamics, road slope, fuel consumption, and control commands using the attention mechanism. Based on the online sampled primitives from the past of the current freight trip and anchor-based future data synthesis, the NVFormer can infer optimal control command for reasonable fuel consumption. The physical model-free NPC outperforms the base PCC method with 2.41% and 3.45% more significant fuel saving in simulation and open-road highway testing, respectively., Comment: 7 pages, 6 figures, for associated mpeg file, see https://www.youtube.com/watch?v=hqgpj7LhiL4

As the time-domain survey telescope of the highest survey power in the northern hemisphere currently, Wide Field Survey Telescope (WFST) is scheduled to hourly/daily/semi-weekly scan northern sky up to ~23 mag in four optical (ugri) bands. Unlike the observation cadences in the forthcoming regular survey missions, WFST performed "staring" observations toward Galactic plane in a cadence of $\approx$1 minute for a total on-source time of about 13 hours, during the commissioning and pilot observation phases. Such an observation cadence is well applied in producing densely sampling light curves and hunting for stars exhibiting fast stellar variabilities. Here we introduce the primary methodologies in detecting variability, periodicity, and stellar flares among a half million sources from the minute-cadence observations, and present the WFST g-/r-band light curves generated from periodic variable stars and flaring stars. Benefit from high photometric precisions and deep detection limits of WFST, the observations have captured several rare variable stars, such as a variable hot white dwarf (WD) and an ellipsoidal WD binary candidate. By surveying the almost unexplored parameter spaces for variables, WFST will lead to new opportunities in discovering unique variable stars in the northern sky., Comment: 19 pages, 12 figures, submitted

Reconstructing a 3D hand mesh from a single RGB image is challenging due to complex articulations, self-occlusions, and depth ambiguities. Traditional discriminative methods, which learn a deterministic mapping from a 2D image to a single 3D mesh, often struggle with the inherent ambiguities in 2D-to-3D mapping. To address this challenge, we propose MMHMR, a novel generative masked model for hand mesh recovery that synthesizes plausible 3D hand meshes by learning and sampling from the probabilistic distribution of the ambiguous 2D-to-3D mapping process. MMHMR consists of two key components: (1) a VQ-MANO, which encodes 3D hand articulations as discrete pose tokens in a latent space, and (2) a Context-Guided Masked Transformer that randomly masks out pose tokens and learns their joint distribution, conditioned on corrupted token sequences, image context, and 2D pose cues. This learned distribution facilitates confidence-guided sampling during inference, producing mesh reconstructions with low uncertainty and high precision. Extensive evaluations on benchmark and real-world datasets demonstrate that MMHMR achieves state-of-the-art accuracy, robustness, and realism in 3D hand mesh reconstruction. Project website: https://m-usamasaleem.github.io/publication/MMHMR/mmhmr.html

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling typically with a cross-entropy objective, requiring a large amount of high-quality instruction-response pairs. However, the quality of widely used SFT datasets can not be guaranteed due to the high cost and intensive labor for the creation and maintenance in practice. To overcome the limitations associated with the quality of SFT datasets, we introduce a novel \textbf{p}reference-\textbf{o}riented supervised \textbf{f}ine-\textbf{t}uning approach, namely PoFT. The intuition is to boost SFT by imposing a particular preference: \textit{favoring the target model over aligned LLMs on the same SFT data.} This preference encourages the target model to predict a higher likelihood than that predicted by the aligned LLMs, incorporating assessment information on data quality (i.e., predicted likelihood by the aligned LLMs) into the training process. Extensive experiments are conducted, and the results validate the effectiveness of the proposed method. PoFT achieves stable and consistent improvements over the SFT baselines across different training datasets and base models. Moreover, we prove that PoFT can be integrated with existing SFT data filtering methods to achieve better performance, and further improved by following preference optimization procedures, such as DPO., Comment: AAAI2025, 12 pages, 9 figures

In recent years, Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) have significantly enhanced the adaptability of large-scale pre-trained models. Weight-Decomposed Low-Rank Adaptation (DoRA) improves upon LoRA by separating the magnitude and direction components of the weight matrix, leading to superior performance. However, DoRA's improvements are limited to the vertical dimension, resulting in an asymmetrical pattern between horizontal and vertical dimensions. This paper introduces BoRA, an innovative extension of LoRA and DoRA, characterized by symmetrical properties across horizontal and vertical dimensions. Our approach optimizes the weight matrix symmetrically by adjusting both column-wise and row-wise magnitudes. Extensive experiments demonstrate that BoRA surpasses state-of-the-art PEFT methods, including LoRA and DoRA, achieving superior results across various benchmarks.

In this review (written in Chinese), we introduce the computation of the minimal surface area in the scattering amplitude/Wilson loop duality, where the minimal surface ends on a light-like polygonal Wilson loop at the boundary of anti-de Sitter space (AdS). Due to its nonlinearity and the complexity of the boundary conditions, directly solving the equations of motion to compute the area is highly challenging. This paper reviews an alternative approach that bypasses the direct solution of the equations of motion and instead uses integrable systems to compute the area. We will provide boundary conditions for the Hitchin system, which is equivalent to the equations of motion, to describe the light-like polygonal boundary of the minimal surface. Starting from the solution of the Hitchin system, we will further derive the Y-system and the Thermodynamic Bethe Ansatz (TBA) equations, whose free energy provides the nontrivial part of the minimal surface area. Finally, we will discuss recent developments in this field and provide an outlook for future research., Comment: 16 pages, Written in Chinese

In this article, we address the challenge of identifying skilled mutual funds among a large pool of candidates, utilizing the linear factor pricing model. Assuming observable factors with a weak correlation structure for the idiosyncratic error, we propose a spatial-sign based multiple testing procedure (SS-BH). When latent factors are present, we first extract them using the elliptical principle component method (He et al. 2022) and then propose a factor-adjusted spatial-sign based multiple testing procedure (FSS-BH). Simulation studies demonstrate that our proposed FSS-BH procedure performs exceptionally well across various applications and exhibits robustness to variations in the covariance structure and the distribution of the error term. Additionally, real data application further highlights the superiority of the FSS-BH procedure.

Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies. We categorize biases as intrinsic and extrinsic, analyzing their manifestations in various NLP tasks. The review critically assesses a range of bias evaluation methods, including data-level, model-level, and output-level approaches, providing researchers with a robust toolkit for bias detection. We further explore mitigation strategies, categorizing them into pre-model, intra-model, and post-model techniques, highlighting their effectiveness and limitations. Ethical and legal implications of biased LLMs are discussed, emphasizing potential harms in real-world applications such as healthcare and criminal justice. By synthesizing current knowledge on bias in LLMs, this review contributes to the ongoing effort to develop fair and responsible AI systems. Our work serves as a comprehensive resource for researchers and practitioners working towards understanding, evaluating, and mitigating bias in LLMs, fostering the development of more equitable AI technologies.

This paper proposes a Chinese spelling correction method based on plugin extension modules, aimed at addressing the limitations of existing models in handling domain-specific texts. Traditional Chinese spelling correction models are typically trained on general-domain datasets, resulting in poor performance when encountering specialized terminology in domain-specific texts. To address this issue, we design an extension module that learns the features of domain-specific terminology, thereby enhancing the model's correction capabilities within specific domains. This extension module can provide domain knowledge to the model without compromising its general spelling correction performance, thus improving its accuracy in specialized fields. Experimental results demonstrate that after integrating extension modules for medical, legal, and official document domains, the model's correction performance is significantly improved compared to the baseline model without any extension modules.

In this paper, we propose Argus, a wearable add-on system based on stripped-down (i.e., compact, lightweight, low-power, limited-capability) mmWave radars. It is the first to achieve egocentric human mesh reconstruction in a multi-view manner. Compared with conventional frontal-view mmWave sensing solutions, it addresses several pain points, such as restricted sensing range, occlusion, and the multipath effect caused by surroundings. To overcome the limited capabilities of the stripped-down mmWave radars (with only one transmit antenna and three receive antennas), we tackle three main challenges and propose a holistic solution, including tailored hardware design, sophisticated signal processing, and a deep neural network optimized for high-dimensional complex point clouds. Extensive evaluation shows that Argus achieves performance comparable to traditional solutions based on high-capability mmWave radars, with an average vertex error of 6.5 cm, solely using stripped-down radars deployed in a multi-view configuration. It presents robustness and practicality across conditions, such as with unseen users and different host devices., Comment: 15 pages, 25 figures

The automatic differentiation (AD) in the vanilla physics-informed neural networks (PINNs) is the computational bottleneck for the high-efficiency analysis. The concept of derivative discretization in smoothed particle hydrodynamics (SPH) can provide an accelerated training method for PINNs. In this paper, smoothing kernel physics-informed neural networks (SK-PINNs) are established, which solve differential equations using smoothing kernel discretization. It is a robust framework capable of solving problems in the computational mechanics of complex domains. When the number of collocation points gradually increases, the training speed of SK-PINNs significantly surpasses that of vanilla PINNs. In cases involving large collocation point sets or higher-order problems, SK-PINN training can be up to tens of times faster than vanilla PINN. Additionally, analysis using neural tangent kernel (NTK) theory shows that the convergence rates of SK-PINNs are consistent with those of vanilla PINNs. The superior performance of SK-PINNs is demonstrated through various examples, including regular and complex domains, as well as forward and inverse problems in fluid dynamics and solid mechanics.

We study the zero-dimensional prototype of the path integrals in quantum mechanics and quantum field theory, with the action $S(\phi)=\frac{\sigma }{2}\phi^{2}+\frac{\lambda}{4}\phi^{4}$. Using the Lefschetz thimble decomposition and the saddle point expansion, we derive multiple asymptotic formal series of the correlation function associated with the perturbative and non-perturbative saddle points. Furthermore, we reconstruct the exact correlation function employing the Borel resummation. We then consider how to truncate the Dyson-Schwinger (DS) equations beginning with the perturbation expansion of the correlation functions, analogous to the one obtained from the Feynmann diagram in higher dimensions. For the case $\sigma<0$, we find that although the asymptotic series around the perturbative saddle point is Borel summable, it does not capture the full information. Consequently, contributions from non-perturbative saddle points must be included to ensure a complete truncation procedure., Comment: 1+16 pages, 6 figures, references added, typos corrected

Recent advances in motion diffusion models have enabled spatially controllable text-to-motion generation. However, despite achieving acceptable control precision, these models suffer from generation speed and fidelity limitations. To address these challenges, we propose ControlMM, a novel approach incorporating spatial control signals into the generative masked motion model. ControlMM achieves real-time, high-fidelity, and high-precision controllable motion generation simultaneously. Our approach introduces two key innovations. First, we propose masked consistency modeling, which ensures high-fidelity motion generation via random masking and reconstruction, while minimizing the inconsistency between the input control signals and the extracted control signals from the generated motion. To further enhance control precision, we introduce inference-time logit editing, which manipulates the predicted conditional motion distribution so that the generated motion, sampled from the adjusted distribution, closely adheres to the input control signals. During inference, ControlMM enables parallel and iterative decoding of multiple motion tokens, allowing for high-speed motion generation. Extensive experiments show that, compared to the state of the art, ControlMM delivers superior results in motion quality, with better FID scores (0.061 vs 0.271), and higher control precision (average error 0.0091 vs 0.0108). ControlMM generates motions 20 times faster than diffusion-based methods. Additionally, ControlMM unlocks diverse applications such as any joint any frame control, body part timeline control, and obstacle avoidance. Video visualization can be found at https://exitudio.github.io/ControlMM-page, Comment: project page https://exitudio.github.io/ControlMM-page

In multi-label emotion classification, particularly for low-resource languages like Arabic, the challenges of class imbalance and label correlation hinder model performance, especially in accurately predicting minority emotions. To address these issues, this study proposes a novel approach that combines stacked embeddings, meta-learning, and a hybrid loss function to enhance multi-label emotion classification for the Arabic language. The study extracts contextual embeddings from three fine-tuned language models-ArabicBERT, MarBERT, and AraBERT-which are then stacked to form enriched embeddings. A meta-learner is trained on these stacked embeddings, and the resulting concatenated representations are provided as input to a Bi-LSTM model, followed by a fully connected neural network for multi-label classification. To further improve performance, a hybrid loss function is introduced, incorporating class weighting, label correlation matrix, and contrastive learning, effectively addressing class imbalances and improving the handling of label correlations. Extensive experiments validate the proposed model's performance across key metrics such as Precision, Recall, F1-Score, Jaccard Accuracy, and Hamming Loss. The class-wise performance analysis demonstrates the hybrid loss function's ability to significantly reduce disparities between majority and minority classes, resulting in a more balanced emotion classification. An ablation study highlights the contribution of each component, showing the superiority of the model compared to baseline approaches and other loss functions. This study not only advances multi-label emotion classification for Arabic but also presents a generalizable framework that can be adapted to other languages and domains, providing a significant step forward in addressing the challenges of low-resource emotion classification tasks., Comment: The paper is submitted in Scientific Reports and is currently under review

This paper has been accepted in the NeurIPS 2024 D & B Track. Harmful memes have proliferated on the Chinese Internet, while research on detecting Chinese harmful memes significantly lags behind due to the absence of reliable datasets and effective detectors. To this end, we focus on the comprehensive detection of Chinese harmful memes. We construct ToxiCN MM, the first Chinese harmful meme dataset, which consists of 12,000 samples with fine-grained annotations for various meme types. Additionally, we propose a baseline detector, Multimodal Knowledge Enhancement (MKE), incorporating contextual information of meme content generated by the LLM to enhance the understanding of Chinese memes. During the evaluation phase, we conduct extensive quantitative experiments and qualitative analyses on multiple baselines, including LLMs and our MKE. The experimental results indicate that detecting Chinese harmful memes is challenging for existing models while demonstrating the effectiveness of MKE. The resources for this paper are available at https://github.com/DUT-lujunyu/ToxiCN_MM.

We present a counting formula that relates the number of physical Bethe states of integrable models with a twisted boundary condition to the number of states in the untwisted or partially twisted limit., Comment: 29+3 pages

Disclaimer: Samples in this paper may be harmful and cause discomfort! Patronizing and condescending language (PCL) is a form of speech directed at vulnerable groups. As an essential branch of toxic language, this type of language exacerbates conflicts and confrontations among Internet communities and detrimentally impacts disadvantaged groups. Traditional pre-trained language models (PLMs) perform poorly in detecting PCL due to its implicit toxicity traits like hypocrisy and false sympathy. With the rise of large language models (LLMs), we can harness their rich emotional semantics to establish a paradigm for exploring implicit toxicity. In this paper, we introduce PclGPT, a comprehensive LLM benchmark designed specifically for PCL. We collect, annotate, and integrate the Pcl-PT/SFT dataset, and then develop a bilingual PclGPT-EN/CN model group through a comprehensive pre-training and supervised fine-tuning staircase process to facilitate implicit toxic detection. Group detection results and fine-grained detection from PclGPT and other models reveal significant variations in the degree of bias in PCL towards different vulnerable groups, necessitating increased societal attention to protect them., Comment: Accepted for EMNLP2024 (Findings)

Integrating audio encoders with LLMs through connectors has enabled these models to process and comprehend audio modalities, significantly enhancing speech-to-text tasks, including automatic speech recognition (ASR) and automatic speech translation (AST). However, these methods often overlook the critical aspect of language adaptation in multilingual settings, relying instead on multilingual data without adequately addressing language differences. To address this gap, we propose the Ideal-LLM model, which employs dual multilingual encoders to enrich language feature information and utilizes a language-adapted connector to target the adaptation of each language specifically. By leveraging the complementary strengths of Whisper and MMS encoders, our approach ensures richer multilingual representations. Additionally, the language-adapted connector enhances modal transformation via a language weight selector tailored for each language. Experimental results demonstrate that Ideal-LLM significantly improves ASR performance, achieving a 32.6% relative reduction in average word error rates compared to the standard speech encoder integrated with LLMs and yields an average BLEU score of 36.78 for AST task., Comment: 5 pages, 3 figures, submitted to ICASSP 2025

In this paper, a gradient flow model is proposed for conducting ground state calculations in Wigner formalism of many-body system in the framework of density functional theory. More specifically, an energy functional for the ground state in Wigner formalism is proposed to provide a new perspective for ground state calculations of the Wigner function. Employing density functional theory, a gradient flow model is designed based on the energy functional to obtain the ground state Wigner function representing the whole many-body system. Subsequently, an efficient algorithm is developed using the operator splitting method and the Fourier spectral collocation method, whose numerical complexity of single iteration is $O(n_{\rm DoF}\log n_{\rm DoF})$. Numerical experiments demonstrate the anticipated accuracy, encompassing the one-dimensional system with up to $2^{21}$ particles and the three-dimensional system with defect, showcasing the potential of our approach to large-scale simulations and computations of systems with defect., Comment: 20 pages, 6 figures

In this paper, we derive two bound-preserving and mass-conserving schemes based on the fractional-step method and high-order compact (HOC) finite difference method for nonlinear convection-dominated diffusion equations. We split the one-dimensional equation into three stages, and employ appropriate temporal and spatial discrete schemes respectively. We show that our scheme is weakly monotonic and that the bound-preserving property can be achieved using the bound-preserving limiter under some mild step constraints. By employing the alternating direction implicit (ADI) method, we extend the scheme to two-dimensional problems, further reducing computational cost. We also provide various numerical experiments to verify our theoretical results., Comment: 36 pages, 5 tables, 69 figures

The StutteringSpeech Challenge focuses on advancing speech technologies for people who stutter, specifically targeting Stuttering Event Detection (SED) and Automatic Speech Recognition (ASR) in Mandarin. The challenge comprises three tracks: (1) SED, which aims to develop systems for detection of stuttering events; (2) ASR, which focuses on creating robust systems for recognizing stuttered speech; and (3) Research track for innovative approaches utilizing the provided dataset. We utilizes an open-source Mandarin stuttering dataset AS-70, which has been split into new training and test sets for the challenge. This paper presents the dataset, details the challenge tracks, and analyzes the performance of the top systems, highlighting improvements in detection accuracy and reductions in recognition error rates. Our findings underscore the potential of specialized models and augmentation strategies in developing stuttered speech technologies., Comment: 8 pages, 2 figures, accepted by SLT 2024

Patronizing and Condescending Language (PCL) is a form of discriminatory toxic speech targeting vulnerable groups, threatening both online and offline safety. While toxic speech research has mainly focused on overt toxicity, such as hate speech, microaggressions in the form of PCL remain underexplored. Additionally, dominant groups' discriminatory facial expressions and attitudes toward vulnerable communities can be more impactful than verbal cues, yet these frame features are often overlooked. In this paper, we introduce the PCLMM dataset, the first Chinese multimodal dataset for PCL, consisting of 715 annotated videos from Bilibili, with high-quality PCL facial frame spans. We also propose the MultiPCL detector, featuring a facial expression detection module for PCL recognition, demonstrating the effectiveness of modality complementarity in this challenging task. Our work makes an important contribution to advancing microaggression detection within the domain of toxic speech., Comment: Under review in ICASSP 2025

A novel method was developed to detect double-$\Lambda$ hypernuclear events in nuclear emulsions using machine learning techniques. The object detection model, the Mask R-CNN, was trained using images generated by Monte Carlo simulations, image processing, and image-style transformation based on generative adversarial networks. Despite being exclusively trained on $\prescript{6\ }{\Lambda\Lambda}{\rm{He}}$ events, the model achieved a detection efficiency of 93.8$\%$ for $\prescript{6\ }{\Lambda\Lambda}{\rm{He}}$ and 82.0$\%$ for $\prescript{5\ }{\Lambda\Lambda}{\rm{H}}$ events in the produced images. In addition, the model demonstrated its ability to detect the $\prescript{6\ }{\Lambda\Lambda}{\rm{He}}$ event named the Nagara event, which is the only uniquely identified double-$\Lambda$ hypernuclear event reported to date. It also exhibited a proper segmentation of the event topology. Furthermore, after analyzing 0.2$\%$ of the entire emulsion data from the J-PARC E07 experiment utilizing the developed approach, six new candidates for double-$\Lambda$ hypernuclear events were detected, suggesting that more than 2000 double-strangeness hypernuclear events were recorded in the entire dataset. This method is sufficiently effective for mining more latent double-$\Lambda$ hypernuclear events recorded in nuclear emulsion sheets by reducing the time required for manual visual inspection by a factor of five hundred.

In fine-tuning large language models (LLMs), conserving computational resources while maintaining effectiveness and improving outcomes within the same computational constraints is crucial. The Low-Rank Adaptation (LoRA) strategy balances efficiency and performance in fine-tuning large models by reducing the number of trainable parameters and computational costs. However, current advancements in LoRA might be focused on its fine-tuning methodologies, with not as much exploration as might be expected into further compression of LoRA. Since most of LoRA's parameters might still be superfluous, this may lead to unnecessary wastage of computational resources. In this paper, we propose \textbf{CoRA}: leveraging shared knowledge to optimize LoRA training by substituting its matrix $B$ with a common subspace from large models. Our two-fold method includes (1) Freezing the substitute matrix $B$ to halve parameters while training matrix $A$ for specific tasks and (2) Using the substitute matrix $B$ as an enhanced initial state for the original matrix $B$, achieving improved results with the same parameters. Our experiments show that the first approach achieves the same efficacy as the original LoRA fine-tuning while being more efficient than halving parameters. At the same time, the second approach has some improvements compared to LoRA's original fine-tuning performance. They generally attest to the effectiveness of our work.

As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their resource-intensive nature, inherent subjectivity, misalignment with real-world user preferences, and the risk of feedback loops that amplify model biases. To overcome these limitations, we introduce WildFeedback, a novel framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically. Given a corpus of multi-turn user-LLM conversation, WildFeedback identifies and classifies user feedback to LLM responses between conversation turns. The user feedback is then used to create examples of preferred and dispreferred responses according to users' preference. Our experiments demonstrate that LLMs fine-tuned on WildFeedback dataset exhibit significantly improved alignment with user preferences, as evidenced by both traditional benchmarks and our proposed checklist-guided evaluation. By incorporating in-situ feedback from actual users, WildFeedback addresses the scalability, subjectivity, and bias challenges that plague existing approaches, marking a significant step toward developing LLMs that are more responsive to the diverse and evolving needs of their users., Comment: 24 pages

In this study, we present MedS-Bench, a comprehensive benchmark designed to evaluate the performance of large language models (LLMs) in clinical contexts. Unlike existing benchmarks that focus on multiple-choice question answering, MedS-Bench spans 11 high-level clinical tasks, including clinical report summarization, treatment recommendations, diagnosis, named entity recognition, and medical concept explanation, among others. We evaluated six leading LLMs, e.g., MEDITRON, Mistral, InternLM 2, Llama 3, GPT-4, and Claude-3.5 using few-shot prompting, and found that even the most sophisticated models struggle with these complex tasks. To address these limitations, we developed MedS-Ins, a large-scale instruction tuning dataset for medicine. MedS-Ins comprises 58 medically oriented language corpora, totaling 13.5 million samples across 122 tasks. To demonstrate the dataset's utility, we conducted a proof-of-concept experiment by performing instruction tuning on a lightweight, open-source medical language model. The resulting model, MMedIns-Llama 3, significantly outperformed existing models across nearly all clinical tasks. To promote further advancements in the application of LLMs to clinical challenges, we have made the MedS-Ins dataset fully accessible and invite the research community to contribute to its expansion.Additionally, we have launched a dynamic leaderboard for MedS-Bench, which we plan to regularly update the test set to track progress and enhance the adaptation of general LLMs to the medical domain. Leaderboard: https://henrychur.github.io/MedS-Bench/. Github: https://github.com/MAGIC-AI4Med/MedS-Ins.

Textual personality detection aims to identify personality traits by analyzing user-generated content. To achieve this effectively, it is essential to thoroughly examine user-generated content from various perspectives. However, previous studies have struggled with automatically extracting and effectively integrating information from multiple perspectives, thereby limiting their performance on personality detection. To address these challenges, we propose the Multi-view Mixture-of-Experts Model for Textual Personality Detection (MvP). MvP introduces a Multi-view Mixture-of-Experts (MoE) network to automatically analyze user posts from various perspectives. Additionally, it employs User Consistency Regularization to mitigate conflicts among different perspectives and learn a multi-view generic user representation. The model's training is optimized via a multi-task joint learning strategy that balances supervised personality detection with self-supervised user consistency constraints. Experimental results on two widely-used personality detection datasets demonstrate the effectiveness of the MvP model and the benefits of automatically analyzing user posts from diverse perspectives for textual personality detection., Comment: Accepted by NLPCC 2024

News recommendation emerges as a primary means for users to access content of interest from the vast amount of news. The title clickbait extensively exists in news domain and increases the difficulty for news recommendation to offer satisfactory services for users. Fortunately, we find that news abstract, as a critical field of news, aligns cohesively with the news authenticity. To this end, we propose a Title Debiasing News Recommendation with Cross-field Contrastive learning (TDNR-C2) to overcome the title bias by incorporating news abstract. Specifically, a multi-field knowledge extraction module is devised to extract multi-view knowledge about news from various fields. Afterwards, we present a cross-field contrastive learning module to conduct bias removal via contrasting learned knowledge from title and abstract fileds. Experimental results on a real-world dataset demonstrate the superiority of the proposed TDNR-C2 over existing state-of-the-art methods. Further analysis also indicates the significance of news abstract for title debiasing.

In this paper, we present a class of high-order and efficient compact difference schemes for nonlinear convection diffusion equations, which can preserve both bounds and mass. For the one-dimensional problem, we first introduce a high-order compact Strang splitting scheme (denoted as HOC-Splitting), which is fourth-order accurate in space and second-order accurate in time. Then, by incorporating the Lagrange multiplier approach with the HOC-Splitting scheme, we construct two additional bound-preserving or/and mass-conservative HOC-Splitting schemes that do not require excessive computational cost and can automatically ensure the uniform bounds of the numerical solution. These schemes combined with an alternating direction implicit (ADI) method are generalized to the two-dimensional problem, which further enhance the computational efficiency for large-scale modeling and simulation. Besides, we present an optimal-order error estimate for the bound-preserving ADI scheme in the discrete $L_2$ norm. Finally, ample numerical examples are presented to verify the theoretical results and demonstrate the accuracy, efficiency, and effectiveness in preserving bounds or/and mass of the proposed schemes., Comment: 32 pages, 6 tables, 35 figures

In this paper, we investigate alpha testing for high-dimensional linear factor pricing models. We propose a spatial sign-based max-type test to handle sparse alternative cases. Additionally, we prove that this test is asymptotically independent of the spatial-sign-based sum-type test proposed by Liu et al. (2023). Based on this result, we introduce a Cauchy Combination test procedure that combines both the max-type and sum-type tests. Simulation studies and real data applications demonstrate that the new proposed test procedure is robust not only for heavy-tailed distributions but also for the sparsity of the alternative hypothesis.

This study explores text-to-SQL parsing by leveraging the powerful reasoning capabilities of large language models (LLMs). Despite recent advancements, existing LLM-based methods have not adequately addressed scalability, leading to inefficiencies when processing wide tables. Furthermore, current interaction-based approaches either lack a step-by-step, interpretable SQL generation process or fail to provide an efficient and universally applicable interaction design. To address these challenges, we introduce Interactive-T2S, a framework that generates SQL queries through direct interactions with databases. This framework includes four general tools that facilitate proactive and efficient information retrieval by the LLM. Additionally, we have developed detailed exemplars to demonstrate the step-wise reasoning processes within our framework. Our experiments on the BIRD-Dev dataset, employing a setting without oracle knowledge, reveal that our method achieves state-of-the-art results with only two exemplars, underscoring the effectiveness and robustness of our framework., Comment: 15 pages, 7 figures

Chalcogenide material-based integrated photonic devices have garnered widespread attention due to their unique wideband transparency. Despite their recognized CMOS compatibility, the fabrication of these devices relies predominantly on lithography techniques. However, chalcogenide thin films are highly susceptible to oxidation, necessitating customized process flows and complex protective measures during lithography. These requirements are hardly compatible with current commercial CMOS manufacturing platforms designed for silicon photonics, significantly limiting the practical applications of chalcogenide photonic devices. In this work, we ingeniously exploit the ease of oxidation of chalcogenide materials, presenting a novel laser-induced localized oxidation technique for spatial patterning on chalcogenide thin films, enabling concise lithography-free fabrication of chalcogenide integrated photonic devices. Using Sb2S3 as an example, we experimentally demonstrate localized multi-level oxidation with a sizable overall refractive index contrast of 0.7 at near-infrared, featuring a high spatial resolution of 0.6 um. Based on this technique, multiple integrated photonic devices are demonstrated, showing versatile functionalities, including color printing at visible and metasurface-based spatial light modulation at near-infrared regions. Leveraging the inherent phase-change property of Sb2S3, an active Fresnel zone plate, enabling switchable beam focusing, is further demonstrated, indicating the feasibility of concise fabrication of active photonic devices. Our work offers a brand-new modulation dimension for chalcogenide materials and provides a significantly simplified approach for realizing chalcogenide-integrated photonic devices.

Empathetic response generation, aiming to understand the user's situation and feelings and respond empathically, is crucial in building human-like dialogue systems. Traditional approaches typically employ maximum likelihood estimation as the optimization objective during training, yet fail to align the empathy levels between generated and target responses. To this end, we propose an empathetic response generation framework using reinforcement learning (EmpRL). The framework develops an effective empathy reward function and generates empathetic responses by maximizing the expected reward through reinforcement learning. EmpRL utilizes the pre-trained T5 model as the generator and further fine-tunes it to initialize the policy. To align the empathy levels between generated and target responses within a given context, an empathy reward function containing three empathy communication mechanisms -- emotional reaction, interpretation, and exploration -- is constructed using pre-designed and pre-trained empathy identifiers. During reinforcement learning training, the proximal policy optimization algorithm is used to fine-tune the policy, enabling the generation of empathetic responses. Both automatic and human evaluations demonstrate that the proposed EmpRL framework significantly improves the quality of generated responses, enhances the similarity in empathy levels between generated and target responses, and produces empathetic responses covering both affective and cognitive aspects.

Large language models (LLMs) such as ChatGPT and GPT-4 have demonstrated impressive capabilities in various generative tasks. However, their performance is often hampered by limitations in accessing and leveraging long-term memory, leading to specific vulnerabilities and biases, especially during long interactions. This paper introduces ChatLogic, an innovative framework specifically targeted at LLM reasoning tasks that can enhance the performance of LLMs in multi-step deductive reasoning tasks by integrating logic programming. In ChatLogic, the language model plays a central role, acting as a controller and participating in every system operation stage. We propose a novel method of converting logic problems into symbolic integration with an inference engine. This approach leverages large language models' situational understanding and imitation skills and uses symbolic memory to enhance multi-step deductive reasoning capabilities. Our results show that the ChatLogic framework significantly improves the multi-step reasoning capabilities of LLMs. The source code and data are available at \url{https://github.com/Strong-AI-Lab/ChatLogic}, Comment: 8 pages, 3 figures. This paper has been accepted by WCCI IJCNN 2024

Existing research on learning with noisy labels predominantly focuses on synthetic label noise. Although synthetic noise possesses well-defined structural properties, it often fails to accurately replicate real-world noise patterns. In recent years, there has been a concerted effort to construct generalizable and controllable instance-dependent noise datasets for image classification, significantly advancing the development of noise-robust learning in this area. However, studies on noisy label learning for text classification remain scarce. To better understand label noise in real-world text classification settings, we constructed the benchmark dataset NoisyAG-News through manual annotation. Initially, we analyzed the annotated data to gather observations about real-world noise. We qualitatively and quantitatively demonstrated that real-world noisy labels adhere to instance-dependent patterns. Subsequently, we conducted comprehensive learning experiments on NoisyAG-News and its corresponding synthetic noise datasets using pre-trained language models and noise-handling techniques. Our findings reveal that while pre-trained models are resilient to synthetic noise, they struggle against instance-dependent noise, with samples of varying confusion levels showing inconsistent performance during training and testing. These real-world noise patterns pose new, significant challenges, prompting a reevaluation of noisy label handling methods. We hope that NoisyAG-News will facilitate the development and evaluation of future solutions for learning with noisy labels., Comment: 20 pages , 13 figure

Using the Kreuzer-Skarke database of 4-dimensional reflexive polytopes, we systematically constructed a new database of orientifold Calabi-Yau threefolds with $h^{1,1}(X) \leq 12$. Our approach involved non-trivial $\mathbb{Z}_2$ involutions, incorporating both divisor exchanges and multi-divisor reflections acting on the Calabi-Yau threefolds. Each proper involution results in an orientifold Calabi-Yau threefolds and we constructed 320,386,067 such examples. We developed a novel algorithm that significantly reduces the complexity of determining all the fixed loci under the involutions, and clarifies the types of O-planes. Our results show that under proper involutions, the majority of cases end up with O3/O7-plane systems, and most of these further admit a naive Type IIB string vacua. Additionally, a new type of free action was determined. We also computed the smoothness and the splitting of Hodge numbers in the $\mathbb{Z}_2$-orbifold limit for these orientifold Calabi-Yau threefolds., Comment: 55 pages, 2 figures

In our research, we have developed a novel mechanism that allows for a significant reduction in the smallest sampling unit of digital image sensors (DIS) to as small as 1/16th of a pixel, through measuring the intra-pixel quantum efficiency for the first time and recomputing the image. Employing our method, the physical sampling resolution of DIS can be enhanced by 16 times. The method has undergone rigorous testing in real-world imaging scenarios.