Searcharxiv⌕ Search

arXiv subjects

Ruoyu Wang

Publications and source records attributed to Ruoyu Wang.

At least 55 records · Page 3Linked to original sources
arXiv2026

Error Estimates of the Gain Approximation by Hermite-Galerkin Method in Feedback Particle Filter

The feedback particle filter (FPF) is a promising nonlinear filtering (NLF) method, but its practical implementation is hindered by the intractability of the gain function, which satisfies a boundary value problem (BVP). This paper proposes a novel two-step Hermite-Galerkin spectral method to address this challenge. First, the unknown density in the BVP is approximated by a kernel density estimator, whose error bounds are well-established in the literature. Second, rather than directly approximating the gain function, we approximate an auxiliary variable via the Galerkin spectral method using generalized Hermite functions. This auxiliary variable inherits the rapid decay property of the density at infinity, which aligns perfectly with the exponential decay characteristic of generalized Hermite functions, thereby obviating the need for artificial boundary conditions or domain truncation. Furthermore, we rigorously establish two fundamental error estimates: the kernel approximation error decays at the rate $O(N_p^{-\frac{s}{2s+1}})$, while the spectral approximation error converges at $O(M^{-s+1}\log M)$, providing complete theoretical guarantees for the method's accuracy. Comprehensive numerical experiments validate the theoretical results and demonstrate that the proposed method outperforms existing gain approximation schemes in both accuracy and computational efficiency.

math.NA↗
arXiv2026

State estimations and noise identifications with intermittent corrupted observations via Bayesian variational inference

This paper focuses on the state estimation problem in distributed sensor networks, where intermittent packet dropouts, corrupted observations, and unknown noise covariances coexist. To tackle this challenge, we formulate the joint estimation of system states, noise parameters, and network reliability as a Bayesian variational inference problem, and propose a novel variational Bayesian adaptive Kalman filter (VB-AKF) to approximate the joint posterior probability densities of the latent parameters. Unlike existing AKF that separately handle missing data and measurement outliers, the proposed VB-AKF adopts a dual-mask generative model with two independent Bernoulli random variables, explicitly characterizing both observable communication losses and latent data authenticity. Additionally, the VB-AKF integrates multiple concurrent multiple observations into the adaptive filtering framework, which significantly enhances statistical identifiability. Comprehensive numerical experiments verify the effectiveness and asymptotic optimality of the proposed method, showing that both parameter identification and state estimation asymptotically converge to the theoretical optimal lower bound with the increase in the number of sensors.

stat.ML↗
arXiv2026

Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance

Diffusion models generate synthetic images through an iterative refinement process. However, the misalignment between the simulation-free objective and the iterative process often causes accumulated gradient error along the sampling trajectory, which leads to unsatisfactory results and a failure to generalize. Guidance techniques like Classifier Free Guidance (CFG) and AutoGuidance (AG) alleviate this by extrapolating between the main and inferior signal for stronger generalization. Despite empirical success, the effective operational regimes of prevalent guidance methods are still under-explored, leading to ambiguity when selecting the appropriate guidance method given a precondition. In this work, we first conduct synthetic comparisons to isolate and demonstrate the effective regime of guidance methods represented by CFG and AG from the perspective of weak-to-strong principle. Based on this, we propose a hybrid instantiation called SGG under the principle, taking the benefits of both. Furthermore, we demonstrate that the W2S principle along with SGG can be migrated into the training objective, improving the generalization ability of unguided diffusion models. We validate our approach with comprehensive experiments. At inference time, evaluations on SD3 and SD3.5 confirm that SGG outperforms existing training-free guidance variants. Training-time experiments on transformer architectures demonstrate the effective migration and performance gains in both conditional and unconditional settings. Code is available at https://github.com/851695e35/SGG.

cs.CV↗
arXiv2026

Few-Step Diffusion Sampling Through Instance-Aware Discretizations

Diffusion and flow matching models generate high-fidelity data by simulating paths defined by Ordinary or Stochastic Differential Equations (ODEs/SDEs), starting from a tractable prior distribution. The probability flow ODE formulation enables the use of advanced numerical solvers to accelerate sampling. Orthogonal yet vital to solver design is the discretization strategy. While early approaches employed handcrafted heuristics and recent methods adopt optimization-based techniques, most existing strategies enforce a globally shared timestep schedule across all samples. This uniform treatment fails to account for instance-specific complexity in the generative process, potentially limiting performance. Motivated by controlled experiments on synthetic data, which reveals the suboptimality of global schedules under instance-specific dynamics, we propose an instance-aware discretization framework. Our method learns to adapt timestep allocations based on input-dependent priors, extending gradient-based discretization search to the conditional generative setting. Empirical results across diverse settings, including synthetic data, pixel-space diffusion, latent-space images and video flow matching models, demonstrate that our method consistently improves generation quality with marginal tuning cost compared to training and negligible inference overhead.

cs.CV↗
arXiv2026

Pushan: Trace-Free Deobfuscation of Virtualization-Obfuscated Binaries

In the ever-evolving battle against malware, binary obfuscation techniques are a formidable barrier to effective analysis by both human security analysts and automated systems. In particular, virtualization or VM-based obfuscation is one of the strongest protection mechanisms that evade automated analysis. Despite widespread use of virtualization, existing automated deobfuscation techniques suffer from three major drawbacks. First, they only work on execution traces, which prevents them from recovering all logic in an obfuscated binary. Second, they depend on dynamic symbolic execution, which is expensive and does not scale in practice. Third, they cannot generate "well-formed" code, which prevents existing binary decompilers from generating human-friendly output. This paper introduces PUSHAN, a novel and generic technique for deobfuscating virtualization-obfuscated binaries while overcoming the limitations of existing techniques. PUSHAN is trace-free and avoids path-constraint accumulation by using VPC-sensitive, constraint-free symbolic emulation to recover a complete CFG of the virtualized function. It is the first approach that also decompiles the protected code into high-quality C pseudocode to enable effective analysis. Crucially, PUSHAN circumvents reliance on path satisfiability, a known NP-hard problem that hampers scalability. We evaluate PUSHAN on more than 1,000 binaries, including targets protected by academic state of the art (Tigress) and commercial-strength obfuscators VMProtect and Themida. PUSHAN successfully deobfuscates these binaries, retrieves their complete CFGs, and decompiles them to C pseudocode. We further demonstrate applicability by analyzing a previously unanalyzed VMProtect-obfuscated malware sample from VirusTotal, where our decompiled output enables LLM-assisted code simplification, reuse, and program understanding.

cs.CR↗
arXiv2026

Parallel Diffusion Solver via Residual Dirichlet Policy Optimization

Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature. Existing solver-based acceleration methods often face significant image quality degradation under a low-latency budget, primarily due to accumulated truncation errors arising from the inability to capture high-curvature trajectory segments. In this paper, we propose the Ensemble Parallel Direction solver (dubbed as EPD-Solver), a novel ODE solver that mitigates these errors by incorporating multiple parallel gradient evaluations in each step. Motivated by the geometric insight that sampling trajectories are largely confined to a low-dimensional manifold, EPD-Solver leverages the Mean Value Theorem for vector-valued functions to approximate the integral solution more accurately. Importantly, since the additional gradient computations are independent, they can be fully parallelized, preserving low-latency sampling nature. We introduce a two-stage optimization framework. Initially, EPD-Solver optimizes a small set of learnable parameters via a distillation-based approach. We further propose a parameter-efficient Reinforcement Learning (RL) fine-tuning scheme that reformulates the solver as a stochastic Dirichlet policy. Unlike traditional methods that fine-tune the massive backbone, our RL approach operates strictly within the low-dimensional solver space, effectively mitigating reward hacking while enhancing performance in complex text-to-image (T2I) generation tasks. In addition, our method is flexible and can serve as a plugin (EPD-Plugin) to improve existing ODE samplers.

cs.CV↗
arXiv2026

Harnessing Synthetic Data from Generative AI for Statistical Inference

The emergence of generative AI models has dramatically expanded the availability and use of synthetic data across scientific, industrial, and policy domains. While these developments open new possibilities for data analysis, they also raise fundamental statistical questions about when synthetic data can be used in a valid, reliable, and principled manner. This paper reviews the current landscape of synthetic data generation and use from a statistical perspective, with the goal of clarifying the assumptions under which synthetic data can meaningfully support downstream discovery, inference, and prediction. We survey major classes of modern generative models, their intended use cases, and the benefits they offer, while also highlighting their limitations and characteristic failure modes. We additionally examine common pitfalls that arise when synthetic data are treated as surrogates for real observations, including biases from model misspecification, attenuated uncertainty, and difficulties in generalization. Building on these insights, we discuss emerging frameworks for the principled use of synthetic data. We conclude with practical recommendations, open problems, and cautions intended to guide both method developers and applied researchers.

stat.ML↗
arXiv2026

The USTC-NERCSLIP Systems for the CHiME-9 MCoRec Challenge

This report details our submission to the CHiME-9 MCoRec Challenge on recognizing and clustering multiple concurrent natural conversations within indoor social settings. Unlike conventional meetings centered on a single shared topic, this scenario contains multiple parallel dialogues--up to eight speakers across up to four simultaneous conversations--with a speech overlap rate exceeding 90%. To tackle this, we propose a multimodal cascaded system that leverages per-speaker visual streams extracted from synchronized 360 degree video together with single-channel audio. Our system improves three components of the pipeline by leveraging enhanced audio-visual pretrained models: Active Speaker Detection (ASD), Audio-Visual Target Speech Extraction (AVTSE), and Audio-Visual Speech Recognition (AVSR). The AVSR module further incorporates Whisper and LLM techniques to boost transcription accuracy. Our best single cascaded system achieves a Speaker Word Error Rate (WER) of 32.44% on the development set. By further applying ROVER to fuse outputs from diverse front-end and back-end variants, we reduce Speaker WER to 31.40%. Notably, our LLM-based zero-shot conversational clustering achieves a speaker clustering F1 score of 1.0, yielding a final Joint ASR-Clustering Error Rate (JACER) of 15.70%.

eess.AS↗
arXiv2026

Twin Co-Adaptive Dialogue for Progressive Image Generation

Modern text-to-image generation systems have enabled the creation of remarkably realistic and high-quality visuals, yet they often falter when handling the inherent ambiguities in user prompts. In this work, we present Twin-Co, a framework that leverages synchronized, co-adaptive dialogue to progressively refine image generation. Instead of a static generation process, Twin-Co employs a dynamic, iterative workflow where an intelligent dialogue agent continuously interacts with the user. Initially, a base image is generated from the user's prompt. Then, through a series of synchronized dialogue exchanges, the system adapts and optimizes the image according to evolving user feedback. The co-adaptive process allows the system to progressively narrow down ambiguities and better align with user intent. Experiments demonstrate that Twin-Co not only enhances user experience by reducing trial-and-error iterations but also improves the quality of the generated images, streamlining creative process across various applications.

cs.CV↗
arXiv2026

Learning to Retrieve Navigable Candidates for Efficient Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions and navigate through previously unseen environments. Recent approaches increasingly employ large language models (LLMs) as high-level navigators due to their flexibility and reasoning capability. However, prompt-based LLM navigation often suffers from inefficient decision-making, as the model must repeatedly interpret instructions from scratch and reason over noisy and verbose navigable candidates at each step. In this paper, we propose a retrieval-augmented framework to improve the efficiency and stability of LLM-based VLN without modifying or fine-tuning the underlying language model. Our approach introduces retrieval at two complementary levels. At the episode level, an instruction-level embedding retriever selects semantically similar successful navigation trajectories as in-context exemplars, providing task-specific priors for instruction grounding. At the step level, an imitation-learned candidate retriever prunes irrelevant navigable directions before LLM inference, reducing action ambiguity and prompt complexity. Both retrieval modules are lightweight, modular, and trained independently of the LLM. We evaluate our method on the Room-to-Room (R2R) benchmark. Experimental results demonstrate consistent improvements in Success Rate, Oracle Success Rate, and SPL on both seen and unseen environments. Ablation studies further show that instruction-level exemplar retrieval and candidate pruning contribute complementary benefits to global guidance and step-wise decision efficiency. These results indicate that retrieval-augmented decision support is an effective and scalable strategy for enhancing LLM-based vision-and-language navigation.

cs.CV↗
arXiv2026

How to Ask for Belief Statistics without Distortion?

Belief elicitation is ubiquitous in experiments but can distort behavior in the main tasks. We study when, and how, an experimenter can ask for a series of action-dependent belief statistics after a subject chooses an action, while incentivize truthful reports without distorting the subject's optimal action in the main experimental tasks. We first propose a novel mechanism called the Counterfactual Scoring Rule (CSR), which achieves such nondistortionary elicitation of any single belief statistic by decomposing it into supplemental action-independent statistics. In contrast, when eliciting a fixed set of belief statistics without such decomposition, we show that robust nondistortionary elicitation is achievable if and only if the questions satisfy a joint alignment condition with the task payoff. The necessity of joint alignment is established through a graph theoretical approach, while its sufficiency follows from invoking an adaptation of the Becker-DeGroot-Marschak mechanism. Our characterization applies to experiments with general task-payoff structures and belief elicitation questions.

econ.TH↗
arXiv2026

Semiparametric Efficient Fusion of Individual Data and Summary Statistics

Suppose we have individual data from an internal study and various summary statistics from relevant external studies. External summary statistics have the potential to improve statistical inference for the internal population; however, it may lead to efficiency loss or bias if not used properly. We study the fusion of individual data and summary statistics in a semiparametric framework to investigate the efficient use of external summary statistics. Under a weak transportability assumption, we establish the semiparametric efficiency bound for estimating a general functional of the internal data distribution, which is no larger than that using only internal data and underpins the potential efficiency gain of integrating individual data and summary statistics. We propose a data-fused efficient estimator that achieves this efficiency bound. In addition, an adaptive fusion estimator is proposed to eliminate the bias of the original data-fused estimator when the transportability assumption fails. We establish the asymptotic oracle property of the adaptive fusion estimator. Simulations and application to a Helicobacter pylori infection dataset demonstrate the promising numerical performance of the proposed method.

stat.ME↗
arXiv2026

WFR-MFM: One-Step Inference for Dynamic Unbalanced Optimal Transport

Reconstructing dynamical evolution from limited observations is a fundamental challenge in single-cell biology, where dynamic unbalanced optimal transport provides a principled framework for modeling coupled transport and mass variation. However, existing approaches rely on trajectory simulation at inference time, making inference a key bottleneck for scalable applications. In this work, we propose a mean-flow framework for unbalanced flow matching that summarizes both transport and mass-growth dynamics over arbitrary time intervals using mean velocity and mass-growth fields, enabling fast one-step generation without trajectory simulation. To solve dynamic unbalanced optimal transport under the Wasserstein-Fisher-Rao geometry, we further build on this framework to develop Wasserstein-Fisher-Rao Mean Flow Matching (WFR-MFM). Across synthetic and real single-cell RNA sequencing datasets, WFR-MFM achieves orders-of-magnitude faster inference than a range of existing baselines while maintaining high predictive accuracy, and enables efficient perturbation response prediction on large synthetic datasets with thousands of conditions.

cs.LG↗
arXiv2026

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent

Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive rich visual-text alignment, instruction-tuning is often text-driven with weaker visual supervision, leading to the degradation of pre-trained visual understanding and causing visual forgetting. Existing approaches, such as direct fine-tuning and continual learning methods, fail to explicitly address this issue, often compressing visual representations and prioritizing task alignment over visual retention, which further worsens visual forgetting. To overcome this limitation, we introduce a novel perspective leveraging effective rank to quantify the degradation of visual representation richness, interpreting this degradation through the information bottleneck principle as excessive compression that leads to the degradation of crucial pre-trained visual knowledge. Building on this view, we propose a modality-decoupled gradient descent (MDGD) method that regulates gradient updates to maintain the effective rank of visual representations while mitigating the over-compression effects described by the information bottleneck. By explicitly disentangling the optimization of visual understanding from task-specific alignment, MDGD preserves pre-trained visual knowledge while enabling efficient task adaptation. To enable lightweight instruction-tuning, we further develop a memory-efficient fine-tuning approach using gradient masking, which selectively updates a subset of model parameters to enable parameter-efficient fine-tuning (PEFT), reducing computational overhead while preserving rich visual representations. Extensive experiments across various downstream tasks and backbone MLLMs demonstrate that MDGD effectively mitigates visual forgetting from pre-trained tasks while enabling strong adaptation to new tasks.

cs.LG↗
arXiv2026

SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving

We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent methods that rely on complex training paradigms (e.g., mid-training, SFT, reinforcement learning, and their combinations), we explore how to push the limits of a lightweight SFT-only approach for SWE tasks. SWE-Lego comprises three core building blocks, with key findings summarized as follows: 1) the SWE-Lego dataset, a collection of 32k highquality task instances and 18k validated trajectories, combining real and synthetic data to complement each other in both quality and quantity; 2) a refined SFT procedure with error masking and a difficulty-based curriculum, which demonstrably improves action quality and overall performance. Empirical results show that with these two building bricks alone,the SFT can push SWE-Lego models to state-of-the-art performance among open-source models of comparable size on SWE-bench Verified: SWE-Lego-Qwen3-8B reaches 42.2%, and SWE-Lego-Qwen3-32B attains 52.6%. 3) We further evaluate and improve test-time scaling (TTS) built upon the SFT foundation. Based on a well-trained verifier, SWE-Lego models can be significantly boosted--for example, 42.2% to 49.6% and 52.6% to 58.8% under TTS@16 for the 8B and 32B models, respectively.

cs.SE↗
arXiv2025

Pre-training, fine-tuning, and distillation (PFD): Automatically generating machine learning force fields from universal models

Universal force fields generalizable across the periodic table represent a new trend in computational materials science. However, the applications of universal force fields in material simulations are limited by their slow inference speed and the lack of first-principles accuracy. Instead of building a single model simultaneously satisfying these characteristics, a strategy that quickly generates material-specific models from the universal model may be more feasible. Here, we propose a new workflow pattern, PFD (Pre-training, Fine-tuning, and Distillation), which automatically generates machine-learning force fields for specific materials from a pre-trained universal model through fine-tuning and distillation. By fine-tuning the pre-trained model, our PFD workflow generates force fields with first-principles accuracy while requiring one to two orders of magnitude less training data compared to traditional methods. The inference speed of the generated force field is further improved through distillation, meeting the requirements of large-scale molecular simulations. Comprehensive testing across diverse materials including complex systems, such as amorphous carbon, interface, etc., reveals marked enhancements in training efficiency, which suggests the PFD workflow a practical and reliable approach for force field generation in computational material sciences.

cond-mat.mtrl-sci↗
arXiv2025

CLIO: A Tour Guide Robot with Co-speech Actions for Visual Attention Guidance and Enhanced User Engagement

While audio guides can offer rich information about an exhibit, it is challenging for visitors to focus on specific exhibit details based only on the verbal description. We present \textit{CLIO}, a tour guide robot with co-speech actions to direct visitors' visual attention and thus enhance the overall user engagement in a guided tour. \textit{CLIO} is equipped with designed actions to engage visitors. It builds eye contact with the visitor through tracking a visitor's face and blinking its eyes, or orient their attention by its head movement and laser pointer. We further use a Large Language Model (LLM) to coordinate the designed actions with a given narrative script for exhibition. We conducted a user study to evaluate the \textit{CLIO} system in a mock-up exhibition of historical photographs. We collected feedback from questionnaires and quantitative data from a mobile eye tracker. Experimental results validated that the engaging actions are well designed and demonstrated its efficacy in guiding visual attention of the visitors. It was evidenced that \textit{CLIO} achieved an enhanced engagement compared to the baseline system with only audio guidance.

cs.HC↗
arXiv2025

A maximin optimal approach for sampling designs in two-phase studies

Data collection costs can vary widely across variables in data science tasks. Two-phase designs can be employed to save data collection costs. This paper considers the two-phase studies where inexpensive variables are collected for all subjects in the first phase, and expensive variables are measured for a subsample of subjects in the second phase based on a predetermined sampling rule. The estimation efficiency under two-phase designs relies heavily on the sampling rule. Existing literature primarily focuses on designing sampling rules for estimating a scalar parameter in some parametric models or specific estimating problems. However, real-world scenarios are usually model-unknown and involve two-phase designs for model-free estimation of a scalar or multi-dimensional parameter. This paper proposes a maximin criterion to design an optimal sampling rule based on semiparametric efficiency bounds. The proposed method is model-free and applicable to general estimating problems. The resulting sampling rule can minimize the semiparametric efficiency bound when the parameter is scalar and improve the bound for every component when the parameter is multi-dimensional. Simulation studies demonstrate that the proposed designs reduce the variance of the resulting estimator in various settings. The implementation of the proposed design is illustrated in a real data analysis.

stat.ME↗