arXiv subjects

Bin Wang

Publications and source records attributed to Bin Wang.

At least 307 records · Page 17Linked to original sources

arXiv2025

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations

Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems. Despite recent progress, current document parsing methods have not been fairly and comprehensively evaluated due to the narrow coverage of document types and the simplified, unrealistic evaluation procedures in existing benchmarks. To address these gaps, we introduce OmniDocBench, a novel benchmark featuring high-quality annotations across nine document sources, including academic papers, textbooks, and more challenging cases such as handwritten notes and densely typeset newspapers. OmniDocBench supports flexible, multi-level evaluations--ranging from an end-to-end assessment to the task-specific and attribute--based analysis using 19 layout categories and 15 attribute labels. We conduct a thorough evaluation of both pipeline-based methods and end-to-end vision-language models, revealing their strengths and weaknesses across different document types. OmniDocBench sets a new standard for the fair, diverse, and fine-grained evaluation in document parsing. Dataset and code are available at https://github.com/opendatalab/OmniDocBench.

cs.CV↗

arXiv2025

Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching

Formula recognition presents significant challenges due to the complicated structure and varied notation of mathematical expressions. Despite continuous advancements in formula recognition models, the evaluation metrics employed by these models, such as BLEU and Edit Distance, still exhibit notable limitations. They overlook the fact that the same formula has diverse representations and is highly sensitive to the distribution of training data, thereby causing unfairness in formula recognition evaluation. To this end, we propose a Character Detection Matching (CDM) metric, ensuring the evaluation objectivity by designing an image-level rather than a LaTeX-level metric score. Specifically, CDM renders both the model-predicted LaTeX and the ground-truth LaTeX formulas into image-formatted formulas, then employs visual feature extraction and localization techniques for precise character-level matching, incorporating spatial position information. Such a spatially-aware and character-matching method offers a more accurate and equitable evaluation compared with previous BLEU and Edit Distance metrics that rely solely on text-based character matching. Experimentally, we evaluated various formula recognition models using CDM, BLEU, and ExpRate metrics. Their results demonstrate that the CDM aligns more closely with human evaluation standards and provides a fairer comparison across different models by eliminating discrepancies caused by diverse formula representations. Code is available at https://github.com/opendatalab/UniMERNet/tree/main/cdm.

cs.CV↗

arXiv2025

Fourth-order uniformly accurate integrators with long time near conservations for the nonlinear Dirac equation in the nonrelativistic regime

In this paper, we propose two novel fourth-order integrators that exhibit uniformly high accuracy and long-term near conservations for solving the nonlinear Dirac equation (NLDE) in the nonrelativistic regime. In this regime, the solution of the NLDE exhibits highly oscillatory behavior in time, characterized by a wavelength of O($\varepsilon^{2}$) with a small parameter $\varepsilon>0$. To ensure uniform temporal accuracy, we employ a two-scale approach in conjunction with exponential integrators, utilizing operator decomposition techniques for the NLDE. The proposed methods are rigorously proved to achieve fourth-order uniform accuracy in time for all $\varepsilon\in (0,1]$. Furthermore, we successfully incorporate symmetry into the integrator, and the long-term near conservation properties are analyzed through the modulated Fourier expansion. The proposed schemes are readily extendable to linear Dirac equations incorporating magnetic potentials, the dynamics of traveling wave solutions and the two/three-dimensional Dirac equations. The validity of all theoretical ndings and extensions is numerically substantiated through a series of numerical experiments.

math.NA↗

arXiv2025

LEGION: Learning to Ground and Explain for Synthetic Image Detection

The rapid advancements in generative technology have emerged as a double-edged sword. While offering powerful tools that enhance convenience, they also pose significant social concerns. As defenders, current synthetic image detection methods often lack artifact-level textual interpretability and are overly focused on image manipulation detection, and current datasets usually suffer from outdated generators and a lack of fine-grained annotations. In this paper, we introduce SynthScars, a high-quality and diverse dataset consisting of 12,236 fully synthetic images with human-expert annotations. It features 4 distinct image content types, 3 categories of artifacts, and fine-grained annotations covering pixel-level segmentation, detailed textual explanations, and artifact category labels. Furthermore, we propose LEGION (LEarning to Ground and explain for Synthetic Image detectiON), a multimodal large language model (MLLM)-based image forgery analysis framework that integrates artifact detection, segmentation, and explanation. Building upon this capability, we further explore LEGION as a controller, integrating it into image refinement pipelines to guide the generation of higher-quality and more realistic images. Extensive experiments show that LEGION outperforms existing methods across multiple benchmarks, particularly surpassing the second-best traditional expert on SynthScars by 3.31% in mIoU and 7.75% in F1 score. Moreover, the refined images generated under its guidance exhibit stronger alignment with human preferences. The code, model, and dataset will be released.

cs.CV↗

arXiv2025

Testing for the Minimum Mean-Variance Spanning Set

This paper explores the estimation and inference of the minimum spanning set (MSS), the smallest subset of risky assets that spans the mean-variance efficient frontier of the full asset set. We establish identification conditions for the MSS and develop a novel procedure for its estimation and inference. Our theoretical analysis shows that the proposed MSS estimator covers the true MSS with probability approaching 1 and converges asymptotically to the true MSS at any desired confidence level, such as 0.95 or 0.99. Monte Carlo simulations confirm the strong finite-sample performance of the MSS estimator. We apply our method to evaluate the relative importance of individual stock momentum and factor momentum strategies, along with a set of well-established stock return factors. The empirical results highlight factor momentum, along with several stock momentum and return factors, as key drivers of mean-variance efficiency. Furthermore, our analysis uncovers the sources of contribution from these factors and provides a ranking of their relative importance, offering new insights into their roles in mean-variance analysis.

q-fin.PM↗

arXiv2025

Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia

Southeast Asia (SEA) is a region of extraordinary linguistic and cultural diversity, yet it remains significantly underrepresented in vision-language (VL) research. This often results in artificial intelligence (AI) models that fail to capture SEA cultural nuances. To fill this gap, we present SEA-VL, an open-source initiative dedicated to developing high-quality, culturally relevant data for SEA languages. By involving contributors from SEA countries, SEA-VL aims to ensure better cultural relevance and diversity, fostering greater inclusivity of underrepresented languages in VL research. Beyond crowdsourcing, our initiative goes one step further in the exploration of the automatic collection of culturally relevant images through crawling and image generation. First, we find that image crawling achieves approximately ~85% cultural relevance while being more cost- and time-efficient than crowdsourcing. Second, despite the substantial progress in generative vision models, synthetic images remain unreliable in accurately reflecting SEA cultures. The generated images often fail to reflect the nuanced traditions and cultural contexts of the region. Collectively, we gather 1.28M SEA culturally-relevant images, more than 50 times larger than other existing datasets. Through SEA-VL, we aim to bridge the representation gap in SEA, fostering the development of more inclusive AI systems that authentically represent diverse cultures across SEA.

cs.CV↗

arXiv2025

SeisRDT: Latent Diffusion Model Based On Representation Learning For Seismic Data Interpolation And Reconstruction

Due to limitations such as geographic, physical, or economic factors, collected seismic data often have missing traces. Traditional seismic data reconstruction methods face the challenge of selecting numerous empirical parameters and struggle to handle large-scale continuous missing traces. With the advancement of deep learning, various diffusion models have demonstrated strong reconstruction capabilities. However, these UNet-based diffusion models require significant computational resources and struggle to learn the correlation between different traces in seismic data. To address the complex and irregular missing situations in seismic data, we propose a latent diffusion transformer utilizing representation learning for seismic data reconstruction. By employing a mask modeling scheme based on representation learning, the representation module uses the token sequence of known data to infer the token sequence of unknown data, enabling the reconstructed data from the diffusion model to have a more consistent data distribution and better correlation and accuracy with the known data. We propose the Representation Diffusion Transformer architecture, and a relative positional bias is added when calculating attention, enabling the diffusion model to achieve global modeling capability for seismic data. Using a pre-trained data compression model compresses the training and inference processes of the diffusion model into a latent space, which, compared to other diffusion model-based reconstruction methods, reduces computational and inference costs. Reconstruction experiments on field and synthetic datasets indicate that our method achieves higher reconstruction accuracy than existing methods and can handle various complex missing scenarios.

physics.geo-ph↗

arXiv2025

Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation

Recent studies on end-to-end speech translation(ST) have facilitated the exploration of multilingual end-to-end ST and end-to-end simultaneous ST. In this paper, we investigate end-to-end simultaneous speech translation in a one-to-many multilingual setting which is closer to applications in real scenarios. We explore a separate decoder architecture and a unified architecture for joint synchronous training in this scenario. To further explore knowledge transfer across languages, we propose an asynchronous training strategy on the proposed unified decoder architecture. A multi-way aligned multilingual end-to-end ST dataset was curated as a benchmark testbed to evaluate our methods. Experimental results demonstrate the effectiveness of our models on the collected dataset. Our codes and data are available at: https://github.com/XiaoMi/TED-MMST.

cs.CL↗

arXiv2025

SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages

Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA, compromising the quality of AI models for SEA languages. Evaluating models for SEA languages is challenging due to the scarcity of high-quality datasets, compounded by the dominance of English training data, raising concerns about potential cultural misrepresentation. To address these challenges, we introduce SEACrowd, a collaborative initiative that consolidates a comprehensive resource hub that fills the resource gap by providing standardized corpora in nearly 1,000 SEA languages across three modalities. Through our SEACrowd benchmarks, we assess the quality of AI models on 36 indigenous languages across 13 tasks, offering valuable insights into the current AI landscape in SEA. Furthermore, we propose strategies to facilitate greater AI advancements, maximizing potential utility and resource equity for the future of AI in SEA.

cs.CL↗

arXiv2025

SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

Survey paper plays a crucial role in scientific research, especially given the rapid growth of research publications. Recently, researchers have begun using LLMs to automate survey generation for better efficiency. However, the quality gap between LLM-generated surveys and those written by human remains significant, particularly in terms of outline quality and citation accuracy. To close these gaps, we introduce SurveyForge, which first generates the outline by analyzing the logical structure of human-written outlines and referring to the retrieved domain-related articles. Subsequently, leveraging high-quality papers retrieved from memory by our scholar navigation agent, SurveyForge can automatically generate and refine the content of the generated article. Moreover, to achieve a comprehensive evaluation, we construct SurveyBench, which includes 100 human-written survey papers for win-rate comparison and assesses AI-generated survey papers across three dimensions: reference, outline, and content quality. Experiments demonstrate that SurveyForge can outperform previous works such as AutoSurvey.

cs.CL↗

arXiv2025

Solving nonlinear Klein-Gordon equation with non-smooth solution by a geometric low-regularity integrator

In this paper, we formulate and analyse a geometric low-regularity integrator for solving the nonlinear Klein-Gordon equation in the $d$-dimensional space with $d=1,2,3$. The integrator is constructed based on the two-step trigonometric method and thus it has a simple form. Error estimates are rigorously presented to show that the integrator can achieve second-order time accuracy in the energy space under the regularity requirement in $H^{1+\frac{d}{4}}\times H^{\frac{d}{4}}$. Moreover, the time symmetry of the scheme ensures its good long-time energy, momentum and action conservations which are rigorously proved by the technique of modulated Fourier expansions. A numerical test is presented and the numerical results demonstrate the superiorities of the new integrator over some existing methods.

math.NA↗

arXiv2025

Lateral Contrast Enhancement in Tomographic Volumetric 3D-Printing via Binary Photoinhibition

Tomographic volumetric 3D-printing (TVP) utilizes a nonlinear photoresponse of polymer precursor to cure all points in a three-dimensional (3D) object in parallel. A key challenge in TVP is to build up dose contrast between in-part and out-of-part points in a lateral plane, which relies on coordinated illumination from various projecting angles. This challenge has mainly been tackled by projection optimization. Here we show that designing material responses to photo-excitation can be a more effective way of addressing this challenge. By introducing a secondary photo-inhibitory species that reacts to external ultraviolet (UV) stimulus, we create a binary photoinhibition (BPI) system that greatly enhances the achievable dose contrast in a lateral plane. We first show that, in theory, combining dose subtraction with sufficient projection angles can guarantee an exact mathematical reconstruction of any greyscale design. We then propose a theoretical framework for BPI, in which a single stationary state with swappable stability can be used to realize dose subtraction. We use oxygen-lophyl radical pair as an approximation to show improvements in print quality enabled by enhanced dose contrast. In situ shadowgraphy shows that BPI improves the lateral patterning with various geometric features, creating differentiable changes in refractive index within 54 um or less. We show qualitative improvements in surface features and internal hollowness in physical prints. The direct impacts of UV light on the formation of positive and negative features on vertical and lateral planes of 5 workpieces are analyzed quantitatively. We conclude that introducing BPI with UV irradiation grants us direct control over the formation of negative features on the lateral plane.

physics.optics↗

arXiv2025

Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study

Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. In this paper, we systematically explore the abilities of open LLMs with less than ten billion parameters to handle multilingual machine translation (MT) tasks. We conduct comprehensive evaluations on six popular LLMs and find that models like Gemma2-9B exhibit impressive multilingual translation capabilities. We then introduce the Parallel-First Monolingual-Second (PFMS) data mixing strategy in the continual pretraining stage to further enhance the MT performance and present GemmaX2-28, a 9B model achieving top-tier multilingual translation performance across 28 languages. Specifically, GemmaX2-28 consistently outperforms the state-of-the-art (SOTA) models such as TowerInstruct and XALMA and achieves competitive performance with Google Translate and GPT-4-turbo.

cs.CL↗

arXiv2025

Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length. A deep compression Variational Autoencoder, Video-VAE, is designed for video generation tasks, achieving 16x16 spatial and 8x temporal compression ratios, while maintaining exceptional video reconstruction quality. User prompts are encoded using two bilingual text encoders to handle both English and Chinese. A DiT with 3D full attention is trained using Flow Matching and is employed to denoise input noise into latent frames. A video-based DPO approach, Video-DPO, is applied to reduce artifacts and improve the visual quality of the generated videos. We also detail our training strategies and share key observations and insights. Step-Video-T2V's performance is evaluated on a novel video generation benchmark, Step-Video-T2V-Eval, demonstrating its state-of-the-art text-to-video quality when compared with both open-source and commercial engines. Additionally, we discuss the limitations of current diffusion-based model paradigm and outline future directions for video foundation models. We make both Step-Video-T2V and Step-Video-T2V-Eval available at https://github.com/stepfun-ai/Step-Video-T2V. The online version can be accessed from https://yuewen.cn/videos as well. Our goal is to accelerate the innovation of video foundation models and empower video content creators.

cs.CV↗

arXiv2025

Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction

Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in voice data collection, weakness in dynamic control, and limited intelligence. To address these challenges, this paper introduces Step-Audio, the first production-ready open-source solution. Key contributions include: 1) a 130B-parameter unified speech-text multi-modal model that achieves unified understanding and generation, with the Step-Audio-Chat version open-sourced; 2) a generative speech data engine that establishes an affordable voice cloning framework and produces the open-sourced lightweight Step-Audio-TTS-3B model through distillation; 3) an instruction-driven fine control system enabling dynamic adjustments across dialects, emotions, singing, and RAP; 4) an enhanced cognitive architecture augmented with tool calling and role-playing abilities to manage complex tasks effectively. Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following. On open-source benchmarks like LLaMA Question, shows 9.3% average performance improvement, demonstrating our commitment to advancing the development of open-source multi-modal language technologies. Our code and models are available at https://github.com/stepfun-ai/Step-Audio.

cs.CL↗

arXiv2025

Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecasting

Traffic prediction is critical for optimizing travel scheduling and enhancing public safety, yet the complex spatial and temporal dynamics within traffic data present significant challenges for accurate forecasting. In this paper, we introduce a novel model, the Spatiotemporal-aware Trend-Seasonality Decomposition Network (STDN). This model begins by constructing a dynamic graph structure to represent traffic flow and incorporates novel spatio-temporal embeddings to jointly capture global traffic dynamics. The representations learned are further refined by a specially designed trend-seasonality decomposition module, which disentangles the trend-cyclical component and seasonal component for each traffic node at different times within the graph. These components are subsequently processed through an encoder-decoder network to generate the final predictions. Extensive experiments conducted on real-world traffic datasets demonstrate that STDN achieves superior performance with remarkable computation cost. Furthermore, we have released a new traffic dataset named JiNan, which features unique inner-city dynamics, thereby enriching the scenario comprehensiveness in traffic prediction evaluation.

cs.LG↗

arXiv2025

Gravitational odd-parity perturbation of a Horndeski hairy black hole: quasinormal mode and parameter constraint

During the binary black hole coalescence, gravitational waves emitted at the ringdown stage can be well described by black hole perturbation theory, where the quasinormal modes (QNMs) become the important ingredient in modeling the pattern waveform. In general relativity (GR), the QNMs can be obtained from solving the Regge-Wheeler (RW) equation of a non-rotating black hole. While in Horndeski gravity, the isospectrality between the odd and even parity perturbations is broken due to the scalar field, but the odd perturbation equation can be simplified into a modified RW equation from the perturbed action. In this paper, we propose a new auxiliary field and tortoise coordinate to refine the modified RW equation in Horndeski gravity, and calculate the QNMs frequencies of the odd perturbation of a specific hairy black hole. It is found that this proposal not only cures the superluminal propagation addressed in the previous literature, but also hold the original QNM spectrum of the odd perturbation. Moreover, our results indicate that such a Horndeski hairy black hole is stable under the odd perturbation, which is also verified by the time evolution of the perturbation. In particular, in contrary to GR, the modes with $\ell=2$ can decay faster than modes with $\ell>2$ for a certain range of the Horndeski hair, and the link between the null geodesics and QNM for the odd perturbation in the current theory is violated. Then, we use the ringdown QNMs to preliminarily investigate the signal-to-noise-ratio (SNR) rescaled measurement error of the Horndeski hair. We obtain significant effects of the angular momentum and overtone on the error bound of the hair parameter. We hope that our findings could inspire more theoretical and phenomenological work on the test of the no-hair theorem of black hole using gravitational wave physics.

gr-qc↗

arXiv2025

GUI Agents with Foundation Models: A Comprehensive Survey

Recent advances in foundation models, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), have facilitated the development of intelligent agents capable of performing complex tasks. By leveraging the ability of (M)LLMs to process and interpret Graphical User Interfaces (GUIs), these agents can autonomously execute user instructions, simulating human-like interactions such as clicking and typing. This survey consolidates recent research on (M)LLM-based GUI agents, highlighting key innovations in data resources, frameworks, and applications. We begin by reviewing representative datasets and benchmarks, followed by an overview of a generalized, unified framework that encapsulates the essential components of prior studies, supported by a detailed taxonomy. Additionally, we explore relevant commercial applications. Drawing insights from existing work, we identify key challenges and propose future research directions. We hope this survey will inspire further advancements in the field of (M)LLM-based GUI agents.

cs.AI↗