arXiv subjects

Yan Huang

Publications and source records attributed to Yan Huang.

At least 127 records · Page 7Linked to original sources

arXiv2025

A score-based particle method for homogeneous Landau equation

We propose a novel score-based particle method for solving the Landau equation in plasmas, that seamlessly integrates learning with structure-preserving particle methods [arXiv:1910.03080]. Building upon the Lagrangian viewpoint of the Landau equation, a central challenge stems from the nonlinear dependence of the velocity field on the density. Our primary innovation lies in recognizing that this nonlinearity is in the form of the score function, which can be approximated dynamically via techniques from score-matching. The resulting method inherits the conservation properties of the deterministic particle method while sidestepping the necessity for kernel density estimation in [arXiv:1910.03080]. This streamlines computation and enhances scalability with dimensionality. Furthermore, we provide a theoretical estimate by demonstrating that the KL divergence between our approximation and the true solution can be effectively controlled by the score-matching loss. Additionally, by adopting the flow map viewpoint, we derive an update formula for exact density computation. Extensive examples have been provided to show the efficiency of the method, including a physically relevant case of Coulomb interaction.

math.NA↗

arXiv2025

Distributed Stochastic Bilevel Optimization: Improved Complexity and Heterogeneity Analysis

This paper consider solving a class of nonconvex-strongly-convex distributed stochastic bilevel optimization (DSBO) problems with personalized inner-level objectives. Most existing algorithms require computational loops for hypergradient estimation, leading to computational inefficiency. Moreover, the impact of data heterogeneity on convergence in bilevel problems is not explicitly characterized yet. To address these issues, we propose LoPA, a loopless personalized distributed algorithm that leverages a tracking mechanism for iterative approximation of inner-level solutions and Hessian-inverse matrices without relying on extra computation loops. Our theoretical analysis explicitly characterizes the heterogeneity across nodes (denoted by $b$), and establishes a sublinear rate of $\mathcal{O}( {\frac{1}{{{{\left( {1 - ρ} \right)}}K}} \!+ \!\frac{{(\frac{b}{\sqrt{m}})^{\frac{2}{3}} }}{{\left( {1 - ρ} \right)^{\frac{2}{3}} K^{\frac{2}{3}} }} \!+ \!\frac{1}{\sqrt{ K }}( {σ_{\operatorname{p} }} + \frac{1}{\sqrt{m}}{σ_{\operatorname{c} }} ) } )$ without the boundedness of local hypergradients, where ${σ_{\operatorname{p} }}$ and ${σ_{\operatorname{c} }}$ represent the gradient sampling variances associated with the inner- and outer-level variables, respectively. We also integrate LoPA with a gradient tracking scheme to eliminate the impact of data heterogeneity, yielding an improved rate of ${\mathcal{O}}(\frac{1}{ (1-ρ)^2K } \!+\! \frac{1}{\sqrt{K}}( σ_{\rm{p}} \!+\! \frac{1}{\sqrt{m}}σ_{\rm{c}} ) )$. The computational complexity of LoPA is of ${\mathcal{O}}({ε^{-2}})$ to an $ε$-stationary point, matching the communication complexity due to the loopless structure, which outperforms existing counterparts for DSBO. Numerical experiments validate the effectiveness of the proposed algorithm.

math.OC↗

arXiv2025

The Short-spacing Interferometer Array for Global 21-cm Signal Detection (SIGMA): Design of the Antennas and Layout

Numerous experiments have been designed to investigate the Cosmic Dawn (CD) and Epoch of Reionization (EoR) by examining redshifted 21-cm emissions from neutral hydrogen. Detecting the global spectrum of redshifted 21-cm signals is typically achieved through single-antenna experiments. However, this global 21-cm signal is deeply embedded in foreground emissions, which are about four orders of magnitude stronger. Extracting this faint signal is a significant challenge, requiring highly precise instrumental calibration. Additionally, accurately modelling receiver noise in single-antenna experiments is inherently complex. An alternative approach using a short-spacing interferometer is expected to alleviate these difficulties because the noise in different receivers is uncorrelated and averages to zero upon cross-correlation. The Short-spacing Interferometer array for Global 21-cm Signal detection (SIGMA) is an upcoming experiment aimed at detecting the global CD/EoR signal using this approach. We describe the SIGMA system with a focus on optimal antenna design and layout, and propose a framework to address cross-talk between antennas in future calibrations. The SIGMA system is intended to serve as a prototype to gain a better understanding of the system's instrumental effects and to optimize its performance further.

astro-ph.IM↗

arXiv2025

FlowDistill: Scalable Traffic Flow Prediction via Distillation from LLMs

Accurate traffic flow prediction is vital for optimizing urban mobility, yet it remains difficult in many cities due to complex spatio-temporal dependencies and limited high-quality data. While deep graph-based models demonstrate strong predictive power, their performance often comes at the cost of high computational overhead and substantial training data requirements, making them impractical for deployment in resource-constrained or data-scarce environments. We propose the FlowDistill, a lightweight and scalable traffic prediction framework based on knowledge distillation from large language models (LLMs). In this teacher-student setup, a fine-tuned LLM guides a compact multi-layer perceptron (MLP) student model using a novel combination of the information bottleneck principle and teacher-bounded regression loss, ensuring the distilled model retains only essential and transferable knowledge. Spatial and temporal correlations are explicitly encoded to enhance the model's generalization across diverse urban settings. Despite its simplicity, FlowDistill consistently outperforms state-of-the-art models in prediction accuracy while requiring significantly less training data, and achieving lower memory usage and inference latency, highlighting its efficiency and suitability for real-world, scalable deployment.

cs.LG↗

arXiv2025

Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models

Hallucinations in generative AI, particularly in Large Language Models (LLMs), pose a significant challenge to the reliability of multilingual applications. Existing benchmarks for hallucination detection focus primarily on English and a few widely spoken languages, lacking the breadth to assess inconsistencies in model performance across diverse linguistic contexts. To address this gap, we introduce Poly-FEVER, a large-scale multilingual fact verification benchmark specifically designed for evaluating hallucination detection in LLMs. Poly-FEVER comprises 77,973 labeled factual claims spanning 11 languages, sourced from FEVER, Climate-FEVER, and SciFact. It provides the first large-scale dataset tailored for analyzing hallucination patterns across languages, enabling systematic evaluation of LLMs such as ChatGPT and the LLaMA series. Our analysis reveals how topic distribution and web resource availability influence hallucination frequency, uncovering language-specific biases that impact model accuracy. By offering a multilingual benchmark for fact verification, Poly-FEVER facilitates cross-linguistic comparisons of hallucination detection and contributes to the development of more reliable, language-inclusive AI systems. The dataset is publicly available to advance research in responsible AI, fact-checking methodologies, and multilingual NLP, promoting greater transparency and robustness in LLM performance. The proposed Poly-FEVER is available at: https://huggingface.co/datasets/HanzhiZhang/Poly-FEVER.

cs.CL↗

arXiv2025

Hierarchical Contextual Manifold Alignment for Structuring Latent Representations in Large Language Models

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter modifications that introduce additional computational overhead. A hierarchical alignment method was introduced to restructure token embeddings without altering core model weights, ensuring that representational distributions maintained coherence across different linguistic contexts. Experimental evaluations demonstrated improvements in rare token retrieval, adversarial robustness, and long-range dependency tracking, highlighting the advantages of hierarchical structuring in mitigating inconsistencies in latent space organization. The comparative analysis against conventional fine-tuning and embedding perturbation methods revealed that hierarchical restructuring maintained computational efficiency while achieving measurable gains in representation quality. Structural refinements introduced through the alignment process resulted in improved contextual stability across varied linguistic tasks, reducing inconsistencies in token proximity relationships and enhancing interpretability in language generation. A detailed computational assessment confirmed that the realignment process introduced minimal inference overhead, ensuring that representational improvements did not compromise model efficiency. The findings reinforced the broader significance of structured representation learning, illustrating that hierarchical embedding modifications could serve as an effective strategy for refining latent space distributions while preserving pre-learned semantic associations.

cs.CL↗

arXiv2025

Aligning Multimodal LLM with Human Preference: A Survey

Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in tackling complex tasks involving visual, auditory, and textual data. However, critical issues related to truthfulness, safety, o1-like reasoning, and alignment with human preference remain insufficiently addressed. This gap has spurred the emergence of various alignment algorithms, each targeting different application scenarios and optimization goals. Recent studies have shown that alignment algorithms are a powerful approach to resolving the aforementioned challenges. In this paper, we aim to provide a comprehensive and systematic review of alignment algorithms for MLLMs. Specifically, we explore four key aspects: (1) the application scenarios covered by alignment algorithms, including general image understanding, multi-image, video, and audio, and extended multimodal applications; (2) the core factors in constructing alignment datasets, including data sources, model responses, and preference annotations; (3) the benchmarks used to evaluate alignment algorithms; and (4) a discussion of potential future directions for the development of alignment algorithms. This work seeks to help researchers organize current advancements in the field and inspire better alignment methods. The project page of this paper is available at https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Alignment.

cs.CV↗

arXiv2025

OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding

In this paper, we propose spatio-temporal omni-object video grounding, dubbed OmniSTVG, a new STVG task that aims at localizing spatially and temporally all targets mentioned in the textual query from videos. Compared to classic STVG locating only a single target, OmniSTVG enables localization of not only an arbitrary number of text-referred targets but also their interacting counterparts in the query from the video, making it more flexible and practical in real scenarios for comprehensive understanding. In order to facilitate exploration of OmniSTVG, we introduce BOSTVG, a large-scale benchmark dedicated to OmniSTVG. Specifically, our BOSTVG consists of 10,018 videos with 10.2M frames and covers a wide selection of 287 classes from diverse scenarios. Each sequence in BOSTVG, paired with a free-form textual query, encompasses a varying number of targets ranging from 1 to 10. To ensure high quality, each video is manually annotated with meticulous inspection and refinement. To our best knowledge, BOSTVG is to date the first and the largest benchmark for OmniSTVG. To encourage future research, we introduce a simple yet effective approach, named OmniTube, which, drawing inspiration from Transformer-based STVG methods, is specially designed for OmniSTVG and demonstrates promising results. By releasing BOSTVG, we hope to go beyond classic STVG by locating every object appearing in the query for more comprehensive understanding, opening up a new direction for STVG. Our benchmark, model, and results will be released at https://github.com/JellyYao3000/OmniSTVG.

cs.CV↗

arXiv2025

A Universal Scheme for Dynamic Partitioned Shortest Path Index: Survey, Improvement, and Experiments

Shortest Path (SP) computation is a fundamental operation in many real-life applications such as navigation on road networks, link analysis on social networks, etc. These networks tend to be massive, and graph partitioning is commonly leveraged to scale up the SP algorithms. However, the Partitioned Shortest Path (PSP) index has never been systematically investigated. Moreover, few studies have explored its index maintenance in dynamic networks. In this paper, we survey the dynamic PSP index and propose a universal scheme for its design and analysis. Specifically, we first review the SP algorithms and put forward a novel structure-based partition method classification to facilitate the selection of partition methods. Furthermore, we summarize the existing Pre-boundary PSP strategy and propose two novel strategies (No-boundary and Post-boundary) to improve its index performance. Lastly, we propose a universal scheme with three dimensions (SP algorithm, partition method, and PSP strategy) to facilitate the analysis and design of the PSP index. Based on this scheme, we put forward five new PSP indexes with a prominent query or update efficiency performance. Extensive experiments are conducted to evaluate the performance of the PSP index and the effectiveness of the proposed techniques, with valuable guidance on the PSP index design.

cs.DB↗

arXiv2025

PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection

Pedestrian detection in intelligent transportation systems has made significant progress but faces two critical challenges: (1) insufficient fusion of complementary information between visible and infrared spectra, particularly in complex scenarios, and (2) sensitivity to illumination changes, such as low-light or overexposed conditions, leading to degraded performance. To address these issues, we propose PedDet, an adaptive spectral optimization complementarity framework specifically enhanced and optimized for multispectral pedestrian detection. PedDet introduces the Multi-scale Spectral Feature Perception Module (MSFPM) to adaptively fuse visible and infrared features, enhancing robustness and flexibility in feature extraction. Additionally, the Illumination Robustness Feature Decoupling Module (IRFDM) improves detection stability under varying lighting by decoupling pedestrian and background features. We further design a contrastive alignment to enhance intermodal feature discrimination. Experiments on LLVIP and MSDS datasets demonstrate that PedDet achieves state-of-the-art performance, improving the mAP by 6.6% with superior detection accuracy even in low-light conditions, marking a significant step forward for road safety. Code will be available at https://github.com/AIGeeksGroup/PedDet.

cs.CV↗

arXiv2025

Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding

Transformer has attracted increasing interest in STVG, owing to its end-to-end pipeline and promising result. Existing Transformer-based STVG approaches often leverage a set of object queries, which are initialized simply using zeros and then gradually learn target position information via iterative interactions with multimodal features, for spatial and temporal localization. Despite simplicity, these zero object queries, due to lacking target-specific cues, are hard to learn discriminative target information from interactions with multimodal features in complicated scenarios (\e.g., with distractors or occlusion), resulting in degradation. Addressing this, we introduce a novel Target-Aware Transformer for STVG (TA-STVG), which seeks to adaptively generate object queries via exploring target-specific cues from the given video-text pair, for improving STVG. The key lies in two simple yet effective modules, comprising text-guided temporal sampling (TTS) and attribute-aware spatial activation (ASA), working in a cascade. The former focuses on selecting target-relevant temporal cues from a video utilizing holistic text information, while the latter aims at further exploiting the fine-grained visual attribute information of the object from previous target-aware temporal cues, which is applied for object query initialization. Compared to existing methods leveraging zero-initialized queries, object queries in our TA-STVG, directly generated from a given video-text pair, naturally carry target-specific cues, making them adaptive and better interact with multimodal features for learning more discriminative information to improve STVG. In our experiments on three benchmarks, TA-STVG achieves state-of-the-art performance and significantly outperforms the baseline, validating its efficacy.

cs.CV↗

arXiv2025

VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition

Existing weakly supervised group activity recognition methods rely on object detectors or attention mechanisms to capture key areas automatically. However, they overlook the semantic information associated with captured areas, which may adversely affect the recognition performance. In this paper, we propose a novel framework named Visual Conceptual Knowledge Guided Action Map (VicKAM) which effectively captures the locations of individual actions and integrates them with action semantics for weakly supervised group activity recognition.It generates individual action prototypes from training set as visual conceptual knowledge to bridge action semantics and visual representations. Guided by this knowledge, VicKAM produces action maps that indicate the likelihood of each action occurring at various locations, based on image correlation theorem. It further augments individual action maps using group activity related statistical information, representing individual action distribution under different group activities, to establish connections between action maps and specific group activities. The augmented action map is incorporated with action semantic representations for group activity recognition.Extensive experiments on two public benchmarks, the Volleyball and the NBA datasets, demonstrate the effectiveness of our proposed method, even in cases of limited training data. The code will be released later.

cs.CV↗

arXiv2025

IncepFormerNet: A multi-scale multi-head attention network for SSVEP classification

In recent years, deep learning (DL) models have shown outstanding performance in EEG classification tasks, particularly in Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer-Interfaces(BCI)systems. DL methods have been successfully applied to SSVEP-BCI. This study proposes a new model called IncepFormerNet, which is a hybrid of the Inception and Transformer architectures. IncepFormerNet adeptly extracts multi-scale temporal information from time series data using parallel convolution kernels of varying sizes, accurately capturing the subtle variations and critical features within SSVEP signals.Furthermore, the model integrates the multi-head attention mechanism from the Transformer architecture, which not only provides insights into global dependencies but also significantly enhances the understanding and representation of complex patterns.Additionally, it takes advantage of filter bank techniques to extract features based on the spectral characteristics of SSVEP data. To validate the effectiveness of the proposed model, we conducted experiments on two public datasets, . The experimental results show that IncepFormerNet achieves an accuracy of 87.41 on Dataset 1 and 71.97 on Dataset 2 using a 1.0-second time window. To further verify the superiority of the proposed model, we compared it with other deep learning models, and the results indicate that our method achieves significantly higher accuracy than the others.The source codes in this work are available at: https://github.com/CECNL/SSVEP-DAN.

eess.SP↗

arXiv2025

The coincidence of Rényi-Parry measures for $β$-transformation

We present a complete characterization of two different non-integers with the same Rényi-Parry measure. We prove that for two non-integers $β_1 ,β_2 >1$, the Rényi-Parry measures coincide if and only if $β_1$ is the root of equation $x^2-qx-p=0$, where $p,q\in\mathbb{N}$ with $p\leq q$, and $β_2 = β_1 + 1$, which confirms a conjecture of Bertrand-Mathis in \cite[Section III]{Bertrand-1998}.

math.DS↗

arXiv2024

GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy

The robotics community has consistently aimed to achieve generalizable robot manipulation with flexible natural language instructions. One primary challenge is that obtaining robot trajectories fully annotated with both actions and texts is time-consuming and labor-intensive. However, partially-annotated data, such as human activity videos without action labels and robot trajectories without text labels, are much easier to collect. Can we leverage these data to enhance the generalization capabilities of robots? In this paper, we propose GR-MG, a novel method which supports conditioning on a text instruction and a goal image. During training, GR-MG samples goal images from trajectories and conditions on both the text and the goal image or solely on the image when text is not available. During inference, where only the text is provided, GR-MG generates the goal image via a diffusion-based image-editing model and conditions on both the text and the generated image. This approach enables GR-MG to leverage large amounts of partially-annotated data while still using languages to flexibly specify tasks. To generate accurate goal images, we propose a novel progress-guided goal image generation model which injects task progress information into the generation process. In simulation experiments, GR-MG improves the average number of tasks completed in a row of 5 from 3.35 to 4.04. In real-robot experiments, GR-MG is able to perform 58 different tasks and improves the success rate from 68.7\% to 78.1\% and 44.4\% to 60.6\% in simple and generalization settings, respectively. It also outperforms comparing baseline methods in few-shot learning of novel skills. Video demos, code, and checkpoints are available on the project page: https://gr-mg.github.io/.

cs.RO↗

arXiv2024

HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection

Millimeter-wave radar plays a vital role in 3D object detection for autonomous driving due to its all-weather and all-lighting-condition capabilities for perception. However, radar point clouds suffer from pronounced sparsity and unavoidable angle estimation errors. To address these limitations, incorporating a camera may partially help mitigate the shortcomings. Nevertheless, the direct fusion of radar and camera data can lead to negative or even opposite effects due to the lack of depth information in images and low-quality image features under adverse lighting conditions. Hence, in this paper, we present the radar-camera fusion network with Hybrid Generation and Synchronization (HGSFusion), designed to better fuse radar potentials and image features for 3D object detection. Specifically, we propose the Radar Hybrid Generation Module (RHGM), which fully considers the Direction-Of-Arrival (DOA) estimation errors in radar signal processing. This module generates denser radar points through different Probability Density Functions (PDFs) with the assistance of semantic information. Meanwhile, we introduce the Dual Sync Module (DSM), comprising spatial sync and modality sync, to enhance image features with radar positional information and facilitate the fusion of distinct characteristics in different modalities. Extensive experiments demonstrate the effectiveness of our approach, outperforming the state-of-the-art methods in the VoD and TJ4DRadSet datasets by $6.53\%$ and $2.03\%$ in RoI AP and BEV AP, respectively. The code is available at https://github.com/garfield-cpp/HGSFusion.

cs.CV↗

arXiv2024

Performance of the Segment Anything Model in Various RFI/Events Detection in Radio Astronomy

The emerging era of big data in radio astronomy demands more efficient and higher-quality processing of observational data. While deep learning methods have been applied to tasks such as automatic radio frequency interference (RFI) detection, these methods often face limitations, including dependence on training data and poor generalization, which are also common issues in other deep learning applications within astronomy. In this study, we investigate the use of the open-source image recognition and segmentation model, Segment Anything Model (SAM), and its optimized version, HQ-SAM, due to their impressive generalization capabilities. We evaluate these models across various tasks, including RFI detection and solar radio burst (SRB) identification. For RFI detection, HQ-SAM (SAM) shows performance that is comparable to or even superior to the SumThreshold method, especially with large-area broadband RFI data. In the search for SRBs, HQ-SAM demonstrates strong recognition abilities for Type II and Type III bursts. Overall, with its impressive generalization capability, SAM (HQ-SAM) can be a promising candidate for further optimization and application in RFI and event detection tasks in radio astronomy.

astro-ph.IM↗

arXiv2024

AED: An black-box NLP classifier model attacker

Deep Neural Networks (DNNs) have been successful in solving real-world tasks in domains such as connected and automated vehicles, disease, and job hiring. However, their implications are far-reaching in critical application areas. Hence, there is a growing concern regarding the potential bias and robustness of these DNN models. A transparency and robust model is always demanded in high-stakes domains where reliability and safety are enforced, such as healthcare and finance. While most studies have focused on adversarial image attack scenarios, fewer studies have investigated the robustness of DNN models in natural language processing (NLP) due to their adversarial samples are difficult to generate. To address this gap, we propose a word-level NLP classifier attack model called "AED," which stands for Attention mechanism enabled post-model Explanation with Density peaks clustering algorithm for synonyms search and substitution. AED aims to test the robustness of NLP DNN models by interpretability their weaknesses and exploring alternative ways to optimize them. By identifying vulnerabilities and providing explanations, AED can help improve the reliability and safety of DNN models in critical application areas such as healthcare and automated transportation. Our experiment results demonstrate that compared with other existing models, AED can effectively generate adversarial examples that can fool the victim model while maintaining the original meaning of the input.

cs.LG↗