Searcharxiv⌕ Search

arXiv subjects

Yan Xu

Publications and source records attributed to Yan Xu.

At least 91 records · Page 5Linked to original sources
arXiv2025

QFFT, Question-Free Fine-Tuning for Adaptive Reasoning

Recent advancements in Long Chain-of-Thought (CoT) reasoning models have improved performance on complex tasks, but they suffer from overthinking, which generates redundant reasoning steps, especially for simple questions. This paper revisits the reasoning patterns of Long and Short CoT models, observing that the Short CoT patterns offer concise reasoning efficiently, while the Long CoT patterns excel in challenging scenarios where the Short CoT patterns struggle. To enable models to leverage both patterns, we propose Question-Free Fine-Tuning (QFFT), a fine-tuning approach that removes the input question during training and learns exclusively from Long CoT responses. This approach enables the model to adaptively employ both reasoning patterns: it prioritizes the Short CoT patterns and activates the Long CoT patterns only when necessary. Experiments on various mathematical datasets demonstrate that QFFT reduces average response length by more than 50\%, while achieving performance comparable to Supervised Fine-Tuning (SFT). Additionally, QFFT exhibits superior performance compared to SFT in noisy, out-of-domain, and low-resource scenarios.

cs.CL↗
arXiv2025

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as process reward models (PRMs) or self-consistency operate as opaque boxes and do not provide checkable evidence for their judgments, possibly limiting their effectiveness. To address this issue, we draw inspiration from the idea that "the gold standard for supporting a mathematical claim is to provide a proof". We propose a retrospective, step-aware formal verification framework $Safe$. Rather than assigning arbitrary scores, we strive to articulate mathematical claims in formal mathematical language Lean 4 at each reasoning step and provide formal proofs to identify hallucinations. We evaluate our framework $Safe$ across multiple language models and various mathematical datasets, demonstrating a significant performance improvement while offering interpretable and verifiable evidence. We also propose $FormalStep$ as a benchmark for step correctness theorem proving with $30,809$ formal statements. To the best of our knowledge, our work represents the first endeavor to utilize formal mathematical language Lean 4 for verifying natural language content generated by LLMs, aligning with the reason why formal mathematical languages were created in the first place: to provide a robust foundation for hallucination-prone human-written proofs.

cs.CL↗
arXiv2025

FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation

Synthesizing high-quality dynamic medical videos remains a significant challenge due to the need for modeling both spatial consistency and temporal dynamics. Existing Transformer-based approaches face critical limitations, including insufficient channel interactions, high computational complexity from self-attention, and coarse denoising guidance from timestep embeddings when handling varying noise levels. In this work, we propose FEAT, a full-dimensional efficient attention Transformer, which addresses these issues through three key innovations: (1) a unified paradigm with sequential spatial-temporal-channel attention mechanisms to capture global dependencies across all dimensions, (2) a linear-complexity design for attention mechanisms in each dimension, utilizing weighted key-value attention and global channel attention, and (3) a residual value guidance module that provides fine-grained pixel-level guidance to adapt to different noise levels. We evaluate FEAT on standard benchmarks and downstream tasks, demonstrating that FEAT-S, with only 23\% of the parameters of the state-of-the-art model Endora, achieves comparable or even superior performance. Furthermore, FEAT-L surpasses all comparison methods across multiple datasets, showcasing both superior effectiveness and scalability. Code is available at https://github.com/Yaziwel/FEAT.

cs.CV↗
arXiv2025

Framing metaverse identity: A multidimensional framework for governing digital selves

This paper proposes a multidimensional framework for Metaverse Identity, addressing its definition, guiding principles, and critical challenges. Metaverse Identity is conceptualized as a users digital self, encompassing personal attributes, data footprints, social roles, and economic elements. To elucidate its core characteristics and implications, this framework introduces two guiding principles: Equivalence and Alignment, and Fusion and Expansiveness. The first principle advocates for consistency between metaverse and real-world identities in behavioral norms and social standards, ensuring rights protection and establishing conduct guidelines. The second emphasizes the deep integration and transformative evolution of metaverse identities, enabling them to transcend real-world constraints, meet diverse needs, and foster inclusivity. Together, these principles serve as complementary pillars, balancing ethical integration with dynamic co-evolution. Building on this foundation, the study identifies five critical challenges: interoperability, legal boundaries, privacy and identity management, risks from deepfakes and synthetic identities, and identity fragmentation impacting psychological well-being. To address these challenges, strategic recommendations are offered to guide stakeholders. By constructing this framework, the study fills a key theoretical gap, advances systematic research, and provides a foundation for policies and governance strategies to address the complexities of metaverse identities in a rapidly evolving digital domain.

cs.CY↗
arXiv2025

Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction

The improvement of LLMs' instruction-following capabilities depends critically on the availability of high-quality instruction-response pairs. While existing automatic data synthetic methods alleviate the burden of manual curation, they often rely heavily on either the quality of seed data or strong assumptions about the structure and content of web documents. To tackle these challenges, we propose Web Reconstruction (WebR), a fully automated framework for synthesizing high-quality instruction-tuning (IT) data directly from raw web documents with minimal assumptions. Leveraging the inherent diversity of raw web content, we conceptualize web reconstruction as an instruction-tuning data synthesis task via a novel dual-perspective paradigm--Web as Instruction and Web as Response--where each web document is designated as either an instruction or a response to trigger the reconstruction process. Comprehensive experiments show that datasets generated by WebR outperform state-of-the-art baselines by up to 16.65% across four instruction-following benchmarks. Notably, WebR demonstrates superior compatibility, data efficiency, and scalability, enabling enhanced domain adaptation with minimal effort. The data and code are publicly available at https://github.com/YJiangcm/WebR.

cs.CL↗
arXiv2025

Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Sparse large language models (LLMs) with Mixture of Experts (MoE) and close to a trillion parameters are dominating the realm of most capable language models. However, the massive model scale poses significant challenges for the underlying software and hardware systems. In this paper, we aim to uncover a recipe to harness such scale on Ascend NPUs. The key goals are better usage of the computing resources under the dynamic sparse model structures and materializing the expected performance gain on the actual hardware. To select model configurations suitable for Ascend NPUs without repeatedly running the expensive experiments, we leverage simulation to compare the trade-off of various model hyperparameters. This study led to Pangu Ultra MoE, a sparse LLM with 718 billion parameters, and we conducted experiments on the model to verify the simulation results. On the system side, we dig into Expert Parallelism to optimize the communication between NPU devices to reduce the synchronization overhead. We also optimize the memory efficiency within the devices to further reduce the parameter and activation management overhead. In the end, we achieve an MFU of 30.0% when training Pangu Ultra MoE, with performance comparable to that of DeepSeek R1, on 6K Ascend NPUs, and demonstrate that the Ascend system is capable of harnessing all the training stages of the state-of-the-art language models. Extensive experiments indicate that our recipe can lead to efficient training of large-scale sparse language models with MoE. We also study the behaviors of such models for future reference.

cs.CL↗
arXiv2025

The 2D Materials Roadmap

Over the past two decades, 2D materials have rapidly evolved into a diverse and expanding family of material platforms. Many members of this materials class have demonstrated their potential to deliver transformative impact on fundamental research and technological applications across different fields. In this roadmap, we provide an overview of the key aspects of 2D material research and development, spanning synthesis, properties and commercial applications. We specifically present roadmaps for high impact 2D materials, including graphene and its derivatives, transition metal dichalcogenides, MXenes as well as their heterostructures and moiré systems. The discussions are organized into thematic sections covering emerging research areas (e.g., twisted electronics, moiré nano-optoelectronics, polaritronics, quantum photonics, and neuromorphic computing), breakthrough applications in key technologies (e.g., 2D transistors, energy storage, electrocatalysis, filtration and separation, thermal management, flexible electronics, sensing, electromagnetic interference shielding, and composites) and other important topics (computational discovery of novel materials, commercialization and standardization). This roadmap focuses on the current research landscape, future challenges and scientific and technological advances required to address, with the intent to provide useful references for promoting the development of 2D materials.

cond-mat.mtrl-sci↗
arXiv2025

Classification of sextic curves in the Fano 3-fold $\mathcal{V}_5$ with rational Galois covers in ${\mathbb P}^3$

In this paper, we classify sextic curves in the Fano $3$-fold $\bf \mathcal{V}_5$ (the smooth quintic del Pezzo $3$-fold) that admit rational Galois covers in the complex ${\mathbb P}^3$. We show that the moduli space of such sextic curves is of complex dimension $2$ through the invariants of the engaged Galois groups for the explicit constructions. This raises the intriguing question of understanding the moduli space of sextic curves in ${\mathcal V}_5$ through their Galois covers in ${\mathbb P}^3$.

math.AG↗
arXiv2025

The Gevrey Gelfand-Shilov regularizing effect of the Landau equation with soft potential

This paper studies the Cauchy problem for the spatially inhomogeneous Landau equation with soft potential in the perturbative framework around the Maxwellian distribution. Under a smallness assumption on the initial datum with exponential decay in the velocity variable, we establish the optimal Gevrey Gelfand-Shilov regularizing effect for the solution to the Cauchy problem.

math.AP↗
arXiv2025

An LLM-Driven Multi-Agent Debate System for Mendelian Diseases

Accurate diagnosis of Mendelian diseases is crucial for precision therapy and assistance in preimplantation genetic diagnosis. However, existing methods often fall short of clinical standards or depend on extensive datasets to build pretrained machine learning models. To address this, we introduce an innovative LLM-Driven multi-agent debate system (MD2GPS) with natural language explanations of the diagnostic results. It utilizes a language model to transform results from data-driven and knowledge-driven agents into natural language, then fostering a debate between these two specialized agents. This system has been tested on 1,185 samples across four independent datasets, enhancing the TOP1 accuracy from 42.9% to 66% on average. Additionally, in a challenging cohort of 72 cases, MD2GPS identified potential pathogenic genes in 12 patients, reducing the diagnostic time by 90%. The methods within each module of this multi-agent debate system are also replaceable, facilitating its adaptation for diagnosing and researching other complex diseases.

q-bio.GN↗
arXiv2025

CMEdataset Advancing China Map Detection and Standardization with Digital Image Resources

Digital images of Chinas maps play a crucial role in map detection, particularly in ensuring national sovereignty, territorial integrity, and map compliance. However, there is currently no publicly available dataset specifically dedicated to problematic maps the CME dataset. Existing datasets primarily focus on general map data and are insufficient for effectively identifying complex issues such as national boundary misrepresentations, missing elements, and blurred boundaries. Therefore, this study creates a Problematic Map dataset that covers five key problem areas, aiming to provide diverse samples for problematic map detection technologies, support high-precision map compliance detection, and enhance map data quality and timeliness. This dataset not only provides essential resources for map compliance, national security monitoring, and map updates, but also fosters innovation and application of related technologies.

cs.CV↗
arXiv2025

Sino-US S and T Frictions and Transnational Knowledge Flows: Evidence from machine learning and cross-national patent data

This paper identifies the impact of China-U.S. science and technology (S&T) friction on knowledge flows in different fields, using data on invention patent applications from China, the U.S., Europe, and the World Patent Office (WPO) along with machine-learning-based econometric methods. The empirical results find that the negative impacts of China-U.S. S&T frictions on cross-border knowledge flows are confined to a limited number of technology areas during the period of our observation. This paper further explores the characteristics of the negatively impacted technology areas, and the empirical results show that technology areas that rely more on basic scientific research, where the distribution of U.S. scientific and technological strength is more concentrated, and where the gap between U.S. and Chinese science and technology is narrower, are more likely to be the victims of the Sino-U.S. S&T friction.

econ.GN↗
arXiv2025

Kernel compensation method for Maxwell eigenproblem with mimetic finite difference discretization

We present a kernel compensation method for Maxwell eigenproblem for photonic crystals to avoid the infinite-dimensional kernels that cause many difficulties in the calculation of energy gaps. The quasi-periodic problem is first transformed into a periodic one on the cube by the Floquet-Bloch theory. Then the compensation operator is introduced in Maxwell's equation with the shifted curl operator. The discrete problem depends on the compatible discretization of the de Rham complex, which is implemented by the mimetic finite difference method in this paper. We prove that the compensation term exactly fills up the kernel of the original problem and avoids spurious eigenvalues. Also, we propose an efficient preconditioner and its FFT and multigrid solvers, which allow parallel computing. Numerical experiments for different three-dimensional lattices are performed to validate the accuracy and effectiveness of the method.

math.NA↗
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

Sparsity-Induced Global Matrix Autoregressive Model with Auxiliary Network Data

Jointly modeling and forecasting economic and financial variables across a large set of countries has long been a significant challenge. Two primary approaches have been utilized to address this issue: the vector autoregressive model with exogenous variables (VARX) and the matrix autoregression (MAR). The VARX model captures domestic dependencies, but treats variables exogenous to represent global factors driven by international trade. In contrast, the MAR model simultaneously considers variables from multiple countries but ignores the trade network. In this paper, we propose an extension of the MAR model that achieves these two aims at once, i.e., studying both international dependencies and the impact of the trade network on the global economy. Additionally, we introduce a sparse component to the model to differentiate between systematic and idiosyncratic cross-predictability. To estimate the model parameters, we propose both a likelihood estimation method and a bias-corrected alternating minimization version. We provide theoretical and empirical analyses of the model's properties, alongside presenting intriguing economic insights derived from our findings.

stat.ML↗
arXiv2025

Prediction of Halo Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and a Transformer Model

We present a transformer model, named DeepHalo, to predict the occurrence of halo coronal mass ejections (CMEs). Our model takes as input an active region (AR) and a profile, where the profile contains a time series of data samples in the AR that are collected 24 hours before the beginning of a day, and predicts whether the AR would produce a halo CME during that day. Each data sample contains physical parameters, or features, derived from photospheric vector magnetic field data taken by the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO). We survey and match CME events in the Space Weather Database Of Notification, Knowledge, Information (DONKI) and Large Angle and Spectrometric Coronagraph (LASCO) CME Catalog, and compile a list of CMEs including halo CMEs and non-halo CMEs associated with ARs in the period between November 2010 and August 2023. We use the information gathered above to build the labels (positive versus negative) of the data samples and profiles at hand, where the labels are needed for machine learning. Experimental results show that DeepHalo with a true skill statistics (TSS) score of 0.907 outperforms a closely related long short-term memory network with a TSS score of 0.821. To our knowledge, this is the first time that the transformer model has been used for halo CME prediction.

astro-ph.SR↗
arXiv2025

Improving the Temporal Resolution of SOHO/MDI Magnetograms of Solar Active Regions Using a Deep Generative Model

We present a novel deep generative model, named GenMDI, to improve the temporal resolution of line-of-sight (LOS) magnetograms of solar active regions (ARs) collected by the Michelson Doppler Imager (MDI) on board the Solar and Heliospheric Observatory (SOHO). Unlike previous studies that focus primarily on spatial super-resolution of MDI magnetograms, our approach can perform temporal super-resolution, which generates and inserts synthetic data between observed MDI magnetograms, thus providing finer temporal structure and enhanced details in the LOS data. The GenMDI model employs a conditional diffusion process, which synthesizes images by considering both preceding and subsequent magnetograms, ensuring that the generated images are not only of high-quality, but also temporally coherent with the surrounding data. Experimental results show that the GenMDI model performs better than the traditional linear interpolation method, especially in ARs with dynamic evolution in magnetic fields.

astro-ph.SR↗