arXiv subjects

Dong Wang

Publications and source records attributed to Dong Wang.

At least 217 records · Page 12Linked to original sources

arXiv2025

LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation

Diffusion models excel at generating high-quality outputs but face challenges in data-scarce domains, where exhaustive retraining or costly paired data are often required. To address these limitations, we propose Latent Aligned Diffusion Bridges (LADB), a semi-supervised framework for sample-to-sample translation that effectively bridges domain gaps using partially paired data. By aligning source and target distributions within a shared latent space, LADB seamlessly integrates pretrained source-domain diffusion models with a target-domain Latent Aligned Diffusion Model (LADM), trained on partially paired latent representations. This approach enables deterministic domain mapping without the need for full supervision. Compared to unpaired methods, which often lack controllability, and fully paired approaches that require large, domain-specific datasets, LADB strikes a balance between fidelity and diversity by leveraging a mixture of paired and unpaired latent-target couplings. Our experimental results demonstrate superior performance in depth-to-image translation under partial supervision. Furthermore, we extend LADB to handle multi-source translation (from depth maps and segmentation masks) and multi-target translation in a class-conditioned style transfer task, showcasing its versatility in handling diverse and heterogeneous use cases. Ultimately, we present LADB as a scalable and versatile solution for real-world domain translation, particularly in scenarios where data annotation is costly or incomplete.

cs.CV↗

arXiv2025

Designing Effective AI Explanations for Misinformation Detection: A Comparative Study of Content, Social, and Combined Explanations

In this paper, we study the problem of AI explanation of misinformation, where the goal is to identify explanation designs that help improve users' misinformation detection abilities and their overall user experiences. Our work is motivated by the limitations of current Explainable AI (XAI) approaches, which predominantly focus on content explanations that elucidate the linguistic features and sentence structures of the misinformation. To address this limitation, we explore various explanations beyond content explanation, such as "social explanation" that considers the broader social context surrounding misinformation, as well as a "combined explanation" where both the content and social explanations are presented in scenarios that are either aligned or misaligned with each other. To evaluate the comparative effectiveness of these AI explanations, we conduct two online crowdsourcing experiments in the COVID-19 (Study 1 on Prolific) and Politics domains (Study 2 on MTurk). Our results show that AI explanations are generally effective in aiding users to detect misinformation, with effectiveness significantly influenced by the alignment between content and social explanations. We also find that the order in which explanation types are presented - specifically, whether a content or social explanation comes first - can influence detection accuracy, with differences found between the COVID-19 and Political domains. This work contributes towards more effective design of AI explanations, fostering a deeper understanding of how different explanation types and their combinations influence misinformation detection.

cs.HC↗

arXiv2025

AWorld: Orchestrating the Training Recipe for Agentic AI

The learning from practice paradigm is crucial for developing capable Agentic AI systems, yet it is severely hampered by inefficient experience generation, a bottleneck especially pronounced in complex benchmarks like GAIA. To address this, we introduce AWorld, an open-source system engineered for large-scale agent-environment interaction. By distributing tasks across a cluster, AWorld accelerates experience collection by 14.6x compared to standard single-node, sequential execution. This critical speedup makes extensive reinforcement learning practical and scalable. Leveraging this capability, we trained a Qwen3-32B-based agent that achieves pass@1 accuracy of 32.23% on the GAIA test set, which surpasses GPT-4o (27.91%) and rivals DeepSeek-V3 (31.89%). Our open-source system and the resulting agent provide a practical blueprint for a complete agentic AI training pipeline, from efficient interaction to demonstrable model improvement.

cs.AI↗

arXiv2025

Statistical Invisibility of a Physical Attack on QRNGs After Randomness Extraction

Current prevailing designs of quantum random number generators (QRNGs) designs typically employ post-processing techniques to distill raw random data, followed by statistical verification with suites like NIST SP 800-22. This paper demonstrates that this widely adopted practice harbors a critical flaw. We show that the powerful extraction process can create a false sense of security by perfectly concealing physical-layer attacks, rendering the subsequent statistical tests blind to a compromised entropy source. We substantiate this claim across two major QRNG architectures. Experimentally, we severely compromise an QRNG based on amplified spontaneous emission (ASE) with a power supply ripple attack. While the resulting raw data catastrophically fails NIST tests, a standard Toeplitz extraction transforms it into a final sequence that passes flawlessly. This outcome highlights a profound danger: since the validation process is insensitive to the quality of the raw data, it implies that even a fully predictable input could be processed to produce a certified, yet completely insecure, random sequence. Our theoretical analysis confirms this vulnerability extends to phase-noise-based QRNGs, suggesting a need for security validation to evolve beyond statistical analysis of the final output and consider the entire generation process.

quant-ph↗

arXiv2025

ASCMamba: Multimodal Time-Frequency Mamba for Acoustic Scene Classification

Acoustic Scene Classification (ASC) is a fundamental problem in computational audition, which seeks to classify environments based on the distinctive acoustic features. In the ASC task of the APSIPA ASC 2025 Grand Challenge, the organizers introduce a multimodal ASC task. Unlike traditional ASC systems that rely solely on audio inputs, this challenge provides additional textual information as inputs, including the location where the audio is recorded and the time of recording. In this paper, we present our proposed system for the ASC task in the APSIPA ASC 2025 Grand Challenge. Specifically, we propose a multimodal network, ASCMamba, which integrates audio and textual information for fine-grained acoustic scene understanding and effective multimodal ASC. The proposed ASCMamba employs a DenseEncoder to extract hierarchical spectral features from spectrograms, followed by a dual-path Mamba blocks that capture long-range temporal and frequency dependencies using Mamba-based state space models. In addition, we present a two-step pseudo-labeling mechanism to generate more reliable pseudo-labels. Results show that the proposed system outperforms all the participating teams and achieves a 6.2% improvement over the baseline. Code, model and pre-trained checkpoints are available at https://github.com/S-Orion/ASCMamba.git.

cs.SD↗

arXiv2025

Forget the Data and Fine-Tuning! Just Fold the Network to Compress

We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers, significantly reducing the model size without the need for fine-tuning or access to training data. Unlike existing methods, model folding preserves data statistics during compression by leveraging k-means clustering, and using novel data-free techniques to prevent variance collapse or explosion. Our theoretical framework and experiments across standard benchmarks, including ResNet18 and LLaMA-7B, demonstrate that model folding achieves comparable performance to data-driven compression techniques and outperforms recently proposed data-free methods, especially at high sparsity levels. This approach is particularly effective for compressing large-scale models, making it suitable for deployment in resource-constrained environments.

cs.LG↗

arXiv2025

Solar magnetic flux rope eruptions caused by inverse flux feeding processes

Large-scale solar eruptions are generally accepted to have coronal magnetic flux ropes as their core structures. Recent studies found that the solar eruptions could be initiated by a sequence of flux feeding processes, during with chromospheric fibrils rise and merge with the pre-existing coronal flux rope. Further theoretical analyses have demonstrated that the normal flux feeding, i.e. the axial magnetic flux within the fibril is in the same direction as that in the flux rope, results in the accumulation of the total axial flux within the flux rope, so as to initiate the eruption. If the directions of the axial flux in the fibril and the flux rope are opposite, it is termed inverse flux feeding, whose influence on coronal flux ropes, however, is still unclear. In this paper, we use a 2.5-dimensional magnetohydrodynamic model to simulate the evolution of coronal flux ropes associated with inverse flux feeding. It is found that inverse flux feeding is also efficient in causing solar eruptions: although the total signed axial magnetic flux of the rope decreases after inverse flux feeding, the total unsigned axial flux can accumulate; the eruption occurs if the unsigned axial flux of the rope reaches a critical value, which is almost the same as the threshold for normal flux feeding. The total axial currents within the rope are also similar during the onset of the eruptions caused by both normal and inverse flux feeding. Our simulation results suggest that it is the unsigned axial magnetic flux rather than the signed axial flux that regulates the onset of coronal flux rope eruptions.

astro-ph.SR↗

arXiv2025

Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text

Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features. However, this approach incurs a significant memory overhead and struggles to effectively capture the intricate relationships between vertices belonging to the same instance. Consequently, irregular text layouts often lead to the prediction of outlined vertices, diminishing the quality of results. To address these challenges, we present an innovative approach rooted in Sparse R-CNN: a cascade decoding pipeline for polygon prediction. Our method ensures precision by iteratively refining polygon predictions, considering both the scale and location of preceding results. Leveraging this stabilized regression pipeline, even employing just a single feature vector to guide polygon instance regression yields promising detection results. Simultaneously, the leverage of instance-level feature proposal substantially enhances memory efficiency (>50% less vs. the state-of-the-art method DPText-DETR) and reduces inference speed (>40% less vs. DPText-DETR) with minor performance drop on benchmarks.

cs.CV↗

arXiv2025

Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation

Aerial Vision-and-Language Navigation (VLN) is a novel task enabling Unmanned Aerial Vehicles (UAVs) to navigate in outdoor environments through natural language instructions and visual cues. However, it remains challenging due to the complex spatial relationships in aerial scenes.In this paper, we propose a training-free, zero-shot framework for aerial VLN tasks, where the large language model (LLM) is leveraged as the agent for action prediction. Specifically, we develop a novel Semantic-Topo-Metric Representation (STMR) to enhance the spatial reasoning capabilities of LLMs. This is achieved by extracting and projecting instruction-related semantic masks onto a top-down map, which presents spatial and topological information about surrounding landmarks and grows during the navigation process. At each step, a local map centered at the UAV is extracted from the growing top-down map, and transformed into a ma trix representation with distance metrics, serving as the text prompt to LLM for action prediction in response to the given instruction. Experiments conducted in real and simulation environments have proved the effectiveness and robustness of our method, achieving absolute success rate improvements of 26.8% and 5.8% over current state-of-the-art methods on simple and complex navigation tasks, respectively. The dataset and code will be released soon.

cs.RO↗

arXiv2025

Unconditional energy dissipation of Strang splitting for the matrix-valued Allen-Cahn equation

The energy dissipation property of the Strang splitting method was first demonstrated for the matrix-valued Allen-Cahn (MAC) equation under restrictive time-step constraints [J. Comput. Phys. 454, 110985, 2022]. In this work, we eliminate this limitation through a refined stability analysis framework, rigorously proving that the Strang splitting method preserves the energy dissipation law unconditionally for arbitrary time steps. The refined proof hinges on a precise estimation of the double-well potential term in the modified energy functional. Leveraging this unconditional energy dissipation property, we rigorously establish that the Strang splitting method achieves global-in-time $H^1$-stability, preserves determinant boundedness, and maintains second-order temporal convergence for the matrix-valued Allen-Cahn equation. To validate these theoretical findings, we conduct numerical experiments confirming the method's energy stability and determinant bound preservation for the MAC equation.

math.NA↗

arXiv2025

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Prompting advanced LLMs with reasoning capabilities to use search engines during inference is often suboptimal, as the LLM might not fully possess the capability on how to interact optimally with the search engine. This paper introduces Search-R1, an extension of reinforcement learning (RL) for reasoning frameworks where the LLM learns to autonomously generate (multiple) search queries during step-by-step reasoning with real-time retrieval. Search-R1 optimizes LLM reasoning trajectories with multi-turn search interactions, leveraging retrieved token masking for stable RL training and a simple outcome-based reward function. Experiments on seven question-answering datasets show that Search-R1 improves performance by 41% (Qwen2.5-7B) and 20% (Qwen2.5-3B) over various RAG baselines under the same setting. This paper further provides empirical insights into RL optimization methods, LLM choices, and response length dynamics in retrieval-augmented reasoning. The code and model checkpoints are available at https://github.com/PeterGriffinJin/Search-R1.

cs.CL↗

arXiv2025

Anti-Tamper Protection for Unauthorized Individual Image Generation

With the advancement of personalized image generation technologies, concerns about forgery attacks that infringe on portrait rights and privacy are growing. To address these concerns, protection perturbation algorithms have been developed to disrupt forgery generation. However, the protection algorithms would become ineffective when forgery attackers apply purification techniques to bypass the protection. To address this issue, we present a novel approach, Anti-Tamper Perturbation (ATP). ATP introduces a tamper-proof mechanism within the perturbation. It consists of protection and authorization perturbations, where the protection perturbation defends against forgery attacks, while the authorization perturbation detects purification-based tampering. Both protection and authorization perturbations are applied in the frequency domain under the guidance of a mask, ensuring that the protection perturbation does not disrupt the authorization perturbation. This design also enables the authorization perturbation to be distributed across all image pixels, preserving its sensitivity to purification-based tampering. ATP demonstrates its effectiveness in defending forgery attacks across various attack settings through extensive experiments, providing a robust solution for protecting individuals' portrait rights and privacy. Our code is available at: https://github.com/Seeyn/Anti-Tamper-Perturbation .

cs.CR↗

arXiv2025

Meta CLIP 2: A Worldwide Scaling Recipe

Contrastive Language-Image Pretraining (CLIP) is a popular foundation model, supporting from zero-shot classification, retrieval to encoders for multimodal large language models (MLLMs). Although CLIP is successfully trained on billion-scale image-text pairs from the English world, scaling CLIP's training further to learning from the worldwide web data is still challenging: (1) no curation method is available to handle data points from non-English world; (2) the English performance from existing multilingual CLIP is worse than its English-only counterpart, i.e., "curse of multilinguality" that is common in LLMs. Here, we present Meta CLIP 2, the first recipe training CLIP from scratch on worldwide web-scale image-text pairs. To generalize our findings, we conduct rigorous ablations with minimal changes that are necessary to address the above challenges and present a recipe enabling mutual benefits from English and non-English world data. In zero-shot ImageNet classification, Meta CLIP 2 ViT-H/14 surpasses its English-only counterpart by 0.8% and mSigLIP by 0.7%, and surprisingly sets new state-of-the-art without system-level confounding factors (e.g., translation, bespoke architecture changes) on multilingual benchmarks, such as CVQA with 57.4%, Babel-ImageNet with 50.2% and XM3600 with 64.3% on image-to-text retrieval.

cs.CV↗

arXiv2025

Efficient and stable diffusion generated methods for ground state computation in Bose--Einstein condensates

This paper investigates numerical methods for approximating the ground state of Bose--Einstein condensates (BECs) by introducing two relaxed formulations of the Gross--Pitaevskii energy functional. These formulations achieve first- and second-order accuracy with respect to the relaxation parameter $ τ$, and are shown to converge to the original energy functional as $ τ\to 0 $. A key feature of the relaxed functionals is their concavity, which ensures that local minima lie on the boundary of the concave hull. This property prevents energy increases during constraint normalization and enables the development of energy-dissipative algorithms. Numerical methods based on sequential linear programming are proposed, accompanied by rigorous analysis of their stability with respect to the relaxed energy. To enhance computational efficiency, an adaptive strategy is introduced, dynamically refining solutions obtained with larger relaxation parameters to achieve higher accuracy with smaller ones. Numerical experiments demonstrate the stability, convergence, and energy dissipation of the proposed methods, while showcasing the adaptive strategy's effectiveness in improving computational performance.

math.NA↗

arXiv2025

GFM-Planner: Perception-Aware Trajectory Planning with Geometric Feature Metric

Like humans who rely on landmarks for orientation, autonomous robots depend on feature-rich environments for accurate localization. In this paper, we propose the GFM-Planner, a perception-aware trajectory planning framework based on the geometric feature metric, which enhances LiDAR localization accuracy by guiding the robot to avoid degraded areas. First, we derive the Geometric Feature Metric (GFM) from the fundamental LiDAR localization problem. Next, we design a 2D grid-based Metric Encoding Map (MEM) to efficiently store GFM values across the environment. A constant-time decoding algorithm is further proposed to retrieve GFM values for arbitrary poses from the MEM. Finally, we develop a perception-aware trajectory planning algorithm that improves LiDAR localization capabilities by guiding the robot in selecting trajectories through feature-rich areas. Both simulation and real-world experiments demonstrate that our approach enables the robot to actively select trajectories that significantly enhance LiDAR localization accuracy.

cs.RO↗

arXiv2025

A robust and stable phase field method for structural topology optimization

This paper presents a novel phase-field-based methodology for solving minimum compliance problems in topology optimization under fixed external loads and body forces. The proposed framework characterizes the optimal structure through an order parameter function, analogous to phase-field models in materials science, where the design domain and its boundary are intrinsically represented by the order parameter function. The topology optimization problem is reformulated as a constrained minimization problem with respect to this order parameter, requiring simultaneous satisfaction of three critical properties: bound preservation, volume conservation, and monotonic objective functional decay throughout the optimization process. The principal mathematical challenge arises from handling domain-dependent body forces, which necessitates the development of a constrained optimization framework. To address this, we develop an operator-splitting algorithm incorporating Lagrange multipliers, enhanced by a novel limiter mechanism. This hybrid approach guarantees strict bound preservation, exact volume conservation, and correct objective functional decaying rate. Numerical implementation demonstrates the scheme's robustness through comprehensive 2D and 3D benchmarks.

math.OC↗

arXiv2025

A Survey of Reinforcement Learning for Software Engineering

Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015. Simultaneously, the rapid advancement of Large Language Models (LLMs) has further fueled interest in integrating RL with LLMs to enable more adaptive and intelligent systems. In the field of software engineering (SE), the increasing complexity of systems and the rising demand for automation have motivated researchers to apply RL to a broad range of tasks, from software design and development to quality assurance and maintenance. Despite growing research in RL-for-SE, there remains a lack of a comprehensive and systematic survey of this evolving field. To address this gap, we reviewed 115 peer-reviewed studies published across 22 premier SE venues since the introduction of DRL. We conducted a comprehensive analysis of publication trends, categorized SE topics and RL algorithms, and examined key factors such as dataset usage, model design and optimization, and evaluation practices. Furthermore, we identified open challenges and proposed future research directions to guide and inspire ongoing work in this evolving area. To summarize, this survey offers the first systematic mapping of RL applications in software engineering, aiming to support both researchers and practitioners in navigating the current landscape and advancing the field. Our artifacts are publicly available: https://github.com/KaiWei-Lin-lanina/RL4SE.

cs.SE↗

arXiv2025

Item-centric Exploration for Cold Start Problem

Recommender systems face a critical challenge in the item cold-start problem, which limits content diversity and exacerbates popularity bias by struggling to recommend new items. While existing solutions often rely on auxiliary data, but this paper illuminates a distinct, yet equally pressing, issue stemming from the inherent user-centricity of many recommender systems. We argue that in environments with large and rapidly expanding item inventories, the traditional focus on finding the "best item for a user" can inadvertently obscure the ideal audience for nascent content. To counter this, we introduce the concept of item-centric recommendations, shifting the paradigm to identify the optimal users for new items. Our initial realization of this vision involves an item-centric control integrated into an exploration system. This control employs a Bayesian model with Beta distributions to assess candidate items based on a predicted balance between user satisfaction and the item's inherent quality. Empirical online evaluations reveal that this straightforward control markedly improves cold-start targeting efficacy, enhances user satisfaction with newly explored content, and significantly increases overall exploration efficiency.

cs.IR↗