arXiv subjects

Kun Wang

Publications and source records attributed to Kun Wang.

At least 235 records · Page 13Linked to original sources

arXiv2025

FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering

Large Language Models (LLMs) are often challenged by generating erroneous or hallucinated responses, especially in complex reasoning tasks. Leveraging Knowledge Graphs (KGs) as external knowledge sources has emerged as a viable solution. However, existing KG-enhanced methods, either retrieval-based or agent-based, encounter difficulties in accurately retrieving knowledge and efficiently traversing KGs at scale. In this paper, we propose a unified framework, FiDeLiS, designed to improve the factuality of LLM responses by anchoring answers to verifiable reasoning steps retrieved from KGs. To achieve this, we leverage step-wise beam search with a deductive scoring function, allowing the LLM to validate reasoning process step by step, and halt the search once the question is deducible. In addition, we propose a Path-RAG module to pre-select a smaller candidate set for each beam search step, reducing computational costs by narrowing the search space. Extensive experiments show that our method, as a training-free framework, not only improve the performance but also enhance the factuality and interpretability across different benchmarks. Code is released at https://github.com/Y-Sui/FiDeLiS.

cs.AI↗

arXiv2025

Semiotic Reconstruction of Destination Expectation Constructs An LLM-Driven Computational Paradigm for Social Media Tourism Analytics

Social media's rise establishes user-generated content (UGC) as pivotal for travel decisions, yet analytical methods lack scalability. This study introduces a dual-method LLM framework: unsupervised expectation extraction from UGC paired with survey-informed supervised fine-tuning. Findings reveal leisure/social expectations drive engagement more than foundational natural/emotional factors. By establishing LLMs as precision tools for expectation quantification, we advance tourism analytics methodology and propose targeted strategies for experience personalization and social travel promotion. The framework's adaptability extends to consumer behavior research, demonstrating computational social science's transformative potential in marketing optimization.

cs.CL↗

arXiv2025

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges

Mathematical reasoning, a core aspect of human cognition, is vital across many domains, from educational problem-solving to scientific advancements. As artificial general intelligence (AGI) progresses, integrating large language models (LLMs) with mathematical reasoning tasks is becoming increasingly significant. This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models (MLLMs). We review over 200 studies published since 2021, and examine the state-of-the-art developments in Math-LLMs, with a focus on multimodal settings. We categorize the field into three dimensions: benchmarks, methodologies, and challenges. In particular, we explore multimodal mathematical reasoning pipeline, as well as the role of (M)LLMs and the associated methodologies. Finally, we identify five major challenges hindering the realization of AGI in this domain, offering insights into the future direction for enhancing multimodal reasoning capabilities. This survey serves as a critical resource for the research community in advancing the capabilities of LLMs to tackle complex multimodal reasoning tasks.

cs.CL↗

arXiv2025

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberatively reason before making moderation decisions via online RL. First, we construct GuardReasoner-VLTrain, a reasoning corpus with 123K samples and 631K reasoning steps, spanning text, image, and text-image inputs. Then, based on it, we cold-start our model's reasoning ability via SFT. In addition, we further enhance reasoning regarding moderation through online RL. Concretely, to enhance diversity and difficulty of samples, we conduct rejection sampling followed by data augmentation via the proposed safety-aware data concatenation. Besides, we use a dynamic clipping parameter to encourage exploration in early stages and exploitation in later stages. To balance performance and token efficiency, we design a length-aware safety reward that integrates accuracy, format, and token cost. Extensive experiments demonstrate the superiority of our model. Remarkably, it surpasses the runner-up by 19.27% F1 score on average. We release data, code, and models (3B/7B) of GuardReasoner-VL at https://github.com/yueliu1999/GuardReasoner-VL/

cs.AI↗

arXiv2025

CellVerse: Do Large Language Models Really Understand Cell Biology?

Recent studies have demonstrated the feasibility of modeling single-cell data as natural languages and the potential of leveraging powerful large language models (LLMs) for understanding cell biology. However, a comprehensive evaluation of LLMs' performance on language-driven single-cell analysis tasks still remains unexplored. Motivated by this challenge, we introduce CellVerse, a unified language-centric question-answering benchmark that integrates four types of single-cell multi-omics data and encompasses three hierarchical levels of single-cell analysis tasks: cell type annotation (cell-level), drug response prediction (drug-level), and perturbation analysis (gene-level). Going beyond this, we systematically evaluate the performance across 14 open-source and closed-source LLMs ranging from 160M to 671B on CellVerse. Remarkably, the experimental results reveal: (1) Existing specialist models (C2S-Pythia) fail to make reasonable decisions across all sub-tasks within CellVerse, while generalist models such as Qwen, Llama, GPT, and DeepSeek family models exhibit preliminary understanding capabilities within the realm of cell biology. (2) The performance of current LLMs falls short of expectations and has substantial room for improvement. Notably, in the widely studied drug response prediction task, none of the evaluated LLMs demonstrate significant performance improvement over random guessing. CellVerse offers the first large-scale empirical demonstration that significant challenges still remain in applying LLMs to cell biology. By introducing CellVerse, we lay the foundation for advancing cell biology through natural languages and hope this paradigm could facilitate next-generation single-cell analysis.

q-bio.QM↗

arXiv2025

The LHC sensitivity to weak gauginos in light of the latest muon $g-2$ and dark matter results

Among the electroweakinos, the weak gauginos have the largest production rate at the LHC and should therefore be the primary focus of searches. In this work, we examine the LHC sensitivity to weak gauginos in light of the latest constraints from the muon $g-2$ anomaly and dark matter (DM) observations. To simultaneously account for the observed $5σ$ deviation in muon $g-2$ and the correct DM relic abundance, the DM candidate in the MSSM must be bino-like: wino- or higgsino-like neutralinos require TeV-scale masses to avoid underabundance, rendering the electroweakino spectrum too heavy to yield a sizable $g-2$ contribution. Moreover, tight direct detection limits disfavor light higgsinos, which can induce sizable DM-nucleon scattering via bino-higgsino mixing. We thus focus on scenarios with a bino-like LSP and relatively heavy higgsinos. Two classes of wino spectra are considered: a light-wino scenario (LWo) with $m_{\tilde{W}} \lesssim 1$~TeV, and a heavy-wino scenario (HWo) with $m_{\tilde{W}} \gtrsim 1$~TeV. For each, we delineate the viable parameter space under current constraints and assess the discovery potential at future LHC stages. We find that while the high-luminosity LHC (HL-LHC) can probe a portion of the parameter space, the high-energy 27~TeV LHC (HE-LHC) is capable of covering most of it.

hep-ph↗

arXiv2025

MPd5 kagome superconductors studied by density functional calculations

Kagome materials, which are composed of hexagons tiled with a shared triangle, have inspired enormous interest due to their unique structures and rich physical properties; exploring superconducting material systems with new kagome structures is still an important research direction. Here, we predict a type of kagome superconductor, MPd5 (M is a group-IIA metal element), and identify that it exhibits coexistence of superconductivity and nontrivial topological properties. We uncover its phonon-mediated superconductivity by the density functional theory for superconductors, predicting the superconducting transition temperatures (Tc) of 2.64, 2.03, and 1.50 K for CaPd5, SrPd5, and BaPd5, respectively. These Tc can be effectively tuned through the application of external pressure and electron doping. The present results also demonstrate that MPd5 have topological properties; e.g., CaPd5 shows topological nontrivial intersection near the Fermi level (EF). Our results indicate that MPd5 materials can be an emerging material platform with rich exotic physics in their kagome structures, and render themselves excellent candidates for superconducting and advanced functional materials that could be utilized in topological quantum computing and information technology.

cond-mat.supr-con↗

arXiv2025

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

Large language models (LLMs) often exhibit hallucinations due to incorrect or outdated knowledge. Hence, model editing methods have emerged to enable targeted knowledge updates. To achieve this, a prevailing paradigm is the locating-then-editing approach, which first locates influential parameters and then edits them by introducing a perturbation. While effective, current studies have demonstrated that this perturbation inevitably disrupt the originally preserved knowledge within LLMs, especially in sequential editing scenarios. To address this, we introduce AlphaEdit, a novel solution that projects perturbation onto the null space of the preserved knowledge before applying it to the parameters. We theoretically prove that this projection ensures the output of post-edited LLMs remains unchanged when queried about the preserved knowledge, thereby mitigating the issue of disruption. Extensive experiments on various LLMs, including LLaMA3, GPT2-XL, and GPT-J, show that AlphaEdit boosts the performance of most locating-then-editing methods by an average of 36.7% with a single line of additional code for projection solely. Our code is available at: https://github.com/jianghoucheng/AlphaEdit.

cs.CL↗

arXiv2025

Period-luminosity and period-luminosity-metallicity relation for $δ$ Scuti Stars

$δ$ Scuti ($δ$ Sct) stars are potential distance tracers for studying the Milky Way structure. We conduct a comprehensive analysis of the period-luminosity (PL) and period-luminosity-metallicity (PLZ) relation for $δ$ Sct stars, integrating data from the Zwicky Transient Facility (ZTF), the Transiting Exoplanet Survey Satellite (TESS), Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), Apache Point Observatory Galactic Evolution Experiment (APOGEE), and Gaia. To mitigate the impact of the Gaia parallax zero point offset, we applied a correction method, determining the optimal zero point value to be $zp_\varpi = 35 \pm 2 \, μ\text{as}$. Using the three best bands, by varying the parallax error threshold, we found that the total error of the PLR zero point was minimized to 0.9\% at a parallax error threshold of 6\%. With this threshold, we derived the PL and PLZ relation for nine bands (from optical to mid-infrared) and five Wesenheit bands. Through our analysis, we conclude that the influence of metallicity on the PLR of $δ$ Sct stars is not significant, and the differences across various bands are minimal.

astro-ph.SR↗

arXiv2025

REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models

The rapid advancement of generative AI highlights the importance of text-to-image (T2I) security, particularly with the threat of backdoor poisoning. Timely disclosure and mitigation of security vulnerabilities in T2I models are crucial for ensuring the safe deployment of generative models. We explore a novel training-free backdoor poisoning paradigm through model editing, which is recently employed for knowledge updating in large language models. Nevertheless, we reveal the potential security risks posed by model editing techniques to image generation models. In this work, we establish the principles for backdoor attacks based on model editing, and propose a relationship-driven precise backdoor poisoning method, REDEditing. Drawing on the principles of equivalent-attribute alignment and stealthy poisoning, we develop an equivalent relationship retrieval and joint-attribute transfer approach that ensures consistent backdoor image generation through concept rebinding. A knowledge isolation constraint is proposed to preserve benign generation integrity. Our method achieves an 11\% higher attack success rate compared to state-of-the-art approaches. Remarkably, adding just one line of code enhances output naturalness while improving backdoor stealthiness by 24\%. This work aims to heighten awareness regarding this security vulnerability in editable image generation models.

cs.CR↗

arXiv2025

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models

The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutionized diverse applications. However, their safety implications remain underexplored. While prior work has exposed critical vulnerabilities in unimodal reasoning models, MLRMs introduce distinct risks from cross-modal reasoning pathways. This work presents the first systematic safety analysis of MLRMs through large-scale empirical studies comparing MLRMs with their base MLLMs. Our experiments reveal three critical findings: (1) The Reasoning Tax: Acquiring reasoning capabilities catastrophically degrades inherited safety alignment. MLRMs exhibit 37.44% higher jailbreaking success rates than base MLLMs under adversarial attacks. (2) Safety Blind Spots: While safety degradation is pervasive, certain scenarios (e.g., Illegal Activity) suffer 25 times higher attack rates -- far exceeding the average 3.4 times increase, revealing scenario-specific vulnerabilities with alarming cross-model and datasets consistency. (3) Emergent Self-Correction: Despite tight reasoning-answer safety coupling, MLRMs demonstrate nascent self-correction -- 16.9% of jailbroken reasoning steps are overridden by safe answers, hinting at intrinsic safeguards. These findings underscore the urgency of scenario-aware safety auditing and mechanisms to amplify MLRMs' self-correction potential. To catalyze research, we open-source OpenSafeMLRM, the first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods. Our work calls for immediate efforts to harden reasoning-augmented AI, ensuring its transformative potential aligns with ethical safeguards.

cs.LG↗

arXiv2025

A 0.3\% calibration of the W UMa-type contact binary luminosity based on Gaia DR3

W Ursa Majoris (W UMa)-type contact binary systems (CBs) with period--luminosity (PL) relations are valuable distance indicators. The PL relations of CBs are affected by metallicity. Here, we establish PL relations and period--luminosity--metallicity (PLZ) relations in nine bands from optical to mid-infrared ($BP$, $G$, $RP$, $J$, $H$, $K_S$, $W1$, $W2$, $W3$) and in five Wesenheit bands based on Gaia DR3 parallaxes. The dispersion of PLZ relations gradually decreases from the optical to mid-infrared bands, with the minimum dispersion of 0.138 mag. We fit the best PL relations for three bands ($W1$, $W_{G,BP,RP}$, $W_{W1,BP,RP}$) under different parallax uncertainty criteria and determine a parallax (after correction) zero point of $zp_\varpi=24\pm4$ $μ$as. After fixing the parallax zero point, we find that the total zero errors of the PL and PLZ relation are smallest when the parallax uncertainty is less than 2\%, resulting in a calibrated CB luminosity with an accuracy of 0.33\%, which is more accurate than the classical Cepheids. Furthermore, by examining the absolute magnitude residuals in different metallicity intervals, we find that the use of a linear metallicity effect is appropriate for CBs with different metallicities. These results indicate that CBs are excellent standard candles.

astro-ph.SR↗

arXiv2025

Backdoor Graph Condensation

Graph condensation has recently emerged as a prevalent technique to improve the training efficiency for graph neural networks (GNNs). It condenses a large graph into a small one such that a GNN trained on this small synthetic graph can achieve comparable performance to a GNN trained on the large graph. However, while existing graph condensation studies mainly focus on the best trade-off between graph size and the GNNs' performance (model utility), they overlook the security issues of graph condensation. To bridge this gap, we first explore backdoor attack against the GNNs trained on the condensed graphs. We introduce an effective backdoor attack against graph condensation, termed BGC. This attack aims to (1) preserve the condensed graph quality despite trigger injection, and (2) ensure trigger efficacy through the condensation process, achieving a high attack success rate. Specifically, BGC consistently updates triggers during condensation and targets representative nodes for poisoning. Extensive experiments demonstrate the effectiveness of our attack. BGC achieves a high attack success rate (close to 1.0) and good model utility in all cases. Furthermore, the results against multiple defense methods demonstrate BGC's resilience under their defenses. Finally, we analyze the key hyperparameters that influence the attack performance. Our code is available at: https://github.com/JiahaoWuGit/BGC.

cs.LG↗

arXiv2025

Revisiting CMSSM with Non-Universal Gaugino Masses under Current Constraints

To address the longstanding tension between the Constrained Minimal Supersymmetric Standard Model (CMSSM) and recent experimental data, we investigate non-universal gaugino masses within an SU(5) Grand Unified Theory (GUT) framework, focusing on the $\tilde{g}$-SUGRA scenario where $\lvert M_{3} \rvert \gg \lvert M_{1} \rvert, \lvert M_{2} \rvert$. This hierarchy enables a heavier gluino, thereby evading current experimental bounds on supersymmetric particles. Our analysis reveals that precise Higgs measurements place stringent constraints on the model, requiring $\tanβ\gtrsim 5$ and $ M_{0} \gtrsim 20 \, \tanβ\,\text{GeV}$. Although the $\tilde{g}$-SUGRA scenario can help reconcile the persistent $(g-2)_μ$ anomaly, the Higgs constraints significantly restrict its parameter space, making a large contribution to $(g-2)_μ$ challenging. We also assess the discovery prospects in upcoming dark matter direct detection experiments, including PandaX-xT (200 t.y.), LZ (projected), and XENONnT (20 t.y.), which may not fully cover the viable parameter space. In contrast, future collider experiments$-$such as the High-Luminosity LHC at $3\,\mathrm{ab}^{-1}$ and $\mathrm{CLIC}_{1500}$ at $2.5\,\mathrm{ab}^{-1}$$-$can comprehensively probe the remaining regions. These findings highlight $\tilde{g}$-SUGRA as a promising solution to the CMSSM tension and offer clear, testable predictions for upcoming collider searches.

hep-ph↗

arXiv2025

Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization

Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and action categories, which is labor-intensive and time-consuming. Although some unsupervised methods have utilized the ``iteratively clustering and localization'' paradigm for TAL, they still suffer from two pivotal impediments: 1) unsatisfactory video clustering confidence, and 2) unreliable video pseudolabels for model training. To address these limitations, we present a novel self-paced iterative learning model to enhance clustering and localization training simultaneously, thereby facilitating more effective unsupervised TAL. Concretely, we improve the clustering confidence through exploring the contextual feature-robust visual information. Thereafter, we design two (constant- and variable- speed) incremental instance learning strategies for easy-to-hard model training, thus ensuring the reliability of these video pseudolabels and further improving overall localization performance. Extensive experiments on two public datasets have substantiated the superiority of our model over several state-of-the-art competitors.

cs.CV↗

arXiv2025

High-Order and Energy-Stable Implicit-Explicit Relaxation Runge-Kutta Schemes for Gradient Flows

In this paper, we propose a class of high-order and energy-stable implicit-explicit relaxation Runge-Kutta (IMEX RRK) schemes for solving the phase-field gradient flow models. By incorporating the scalar auxiliary variable (SAV) method, the original equations are reformulated into equivalent forms, and the modified energy is introduced. Then, based on the reformulated equations, we propose a kind of IMEX RRK methods, which are rigorously proved to preserve the energy dissipation law and achieve high-order accuracy for both Allen-Cahn and Cahn-Hilliard equations. Numerical experiments are conducted to validate the theoretical results, including the accuracy of the approximate solution and the efficiency of the proposed scheme. Furthermore, the schemes are extended to multi-component gradient flows, with the vector-valued Allen-Cahn equations serving as a representative example.

math.NA↗

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

Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model

Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment results in notable data imbalances. Furthermore, models that are excessively customized and devoid of causal connections further undermine the generalizability and interpretability. To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process. Going beyond this process, we utilize the back-door adjustment to specifically address the sub-regions identified as non-causal in the upstream phase. Specifically, we employ a novel image inpainting technique. By using a fine-tuned unconditional Diffusion Probabilistic Model (DDPM) as the generative prior, we in-fill the masks defined as environmental parts, offering the possibility of reliable extrapolation for potential data distributions. CaPaint overcomes the high complexity dilemma of optimal ST causal discovery models by reducing the data generation complexity from exponential to quasi-linear levels. Extensive experiments conducted on five real-world ST benchmarks demonstrate that integrating the CaPaint concept allows models to achieve improvements ranging from 4.3% to 77.3%. Moreover, compared to traditional mainstream ST augmenters, CaPaint underscores the potential of diffusion models in ST enhancement, offering a novel paradigm for this field. Our project is available at https://anonymous.4open.science/r/12345-DFCC.

cs.CV↗