arXiv subjects

Na Li

Publications and source records attributed to Na Li.

At least 91 records · Page 5Linked to original sources

arXiv2025

Bayesian compartmental modelling of MRSA transmission within hospitals in Edmonton, Canada

Methicillin-resistant Staphylococcus aureus (MRSA) is a bacterium that leads to severe infections in hospitalized patients. Previous epidemiological research has focused on MRSA transmission, but few studies have examined the influence of both hospital-acquired MRSA (HA-MRSA) and community-acquired MRSA (CA-MRSA) on MRSA spread in hospitals. In this study, we present a unique compartmental model for studying MRSA transmission patterns in hospitals in Edmonton, Alberta. The model consists of susceptible individuals, patients who have been colonized or infected with HA-MRSA or CA-MRSA, and isolated patients. We first use Bayesian inference with Markov chain Monte Carlo (MCMC) algorithms to estimate the posterior mean of parameters in the full model using data from hospitals in Edmonton. Then we develop multiple sub-models with varying assumptions about the origin of new MRSA colonization. We also estimate transmission rates in hospitals.

stat.AP↗

arXiv2025

Vox-Evaluator: Enhancing Stability and Fidelity for Zero-shot TTS with A Multi-Level Evaluator

Recent advances in zero-shot text-to-speech (TTS), driven by language models, diffusion models and masked generation, have achieved impressive naturalness in speech synthesis. Nevertheless, stability and fidelity remain key challenges, manifesting as mispronunciations, audible noise, and quality degradation. To address these issues, we introduce Vox-Evaluator, a multi-level evaluator designed to guide the correction of erroneous speech segments and preference alignment for TTS systems. It is capable of identifying the temporal boundaries of erroneous segments and providing a holistic quality assessment of the generated speech. Specifically, to refine erroneous segments and enhance the robustness of the zero-shot TTS model, we propose to automatically identify acoustic errors with the evaluator, mask the erroneous segments, and finally regenerate speech conditioning on the correct portions. In addition, the fine-gained information obtained from Vox-Evaluator can guide the preference alignment for TTS model, thereby reducing the bad cases in speech synthesis. Due to the lack of suitable training datasets for the Vox-Evaluator, we also constructed a synthesized text-speech dataset annotated with fine-grained pronunciation errors or audio quality issues. The experimental results demonstrate the effectiveness of the proposed Vox-Evaluator in enhancing the stability and fidelity of TTS systems through the speech correction mechanism and preference optimization. The demos are shown.

cs.SD↗

arXiv2025

RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models

Diffusion models have achieved state-of-the-art performance in generative modeling, yet their sampling procedures remain vulnerable to hallucinations-often stemming from inaccuracies in score approximation. In this work, we reinterpret diffusion sampling through the lens of optimization and introduce RODS (Robust Optimization-inspired Diffusion Sampler), a novel method that detects and corrects high-risk sampling steps using geometric cues from the loss landscape. RODS enforces smoother sampling trajectories and adaptively adjusts perturbations, reducing hallucinations without retraining and at minimal additional inference cost. Experiments on AFHQv2, FFHQ, and 11k-hands demonstrate that RODS maintains comparable image quality and preserves generation diversity. More importantly, it improves both sampling fidelity and robustness, detecting over 70% of hallucinated samples and correcting more than 25%, all while avoiding the introduction of new artifacts. We release our code at https://github.com/Yiqi-Verna-Tian/RODS.

cs.CV↗

arXiv2025

Long-range bipartite entanglement in XXZ spin chains with the exponential and power-law long-range interactions

Long-range bipartite entanglement (LBE) and its distribution properties are studied in XXZ spin chains with the exponential and power-law long-range interactions (ELRIs and PLRIs). LBE quantified by two-qubit concurrence decays exponentially along with two-site distance in the infinite chain with ELRIs in the thermodynamic limit, and the long-range behavior of two-spin entanglement can detect the quantum phase transition and identify different quantum phases away from the critical point. Moreover, a fine-grained LBE distribution relation is obtained for the infinite XXZ spin chain. On the other hand, in the finite XXZ spin chain with the conventional PLRIs, the long-range concurrence decays algebraically and the total one is no longer monotonic along with the chain length. The total LBE distribution property can exhibit a piecewise function, which has a close relationship with the decaying mode and strength of PLRIs. These LBE relations can be regarded as the generalization of Koashi-Bužek-Imoto bound for the prototypical long-range XXZ model, having potential applications in quantum information processing.

quant-ph↗

arXiv2025

One-Step Flow Policy Mirror Descent

Diffusion policies have achieved great success in online reinforcement learning (RL) due to their strong expressive capacity. However, the inference of diffusion policy models relies on a slow iterative sampling process, which limits their responsiveness. To overcome this limitation, we propose Flow Policy Mirror Descent (FPMD), an online RL algorithm that enables 1-step sampling during flow policy inference. Our approach exploits a theoretical connection between the distribution variance and the discretization error of single-step sampling in straight interpolation flow matching models, and requires no extra distillation or consistency training. We present two algorithm variants based on rectified flow policy and MeanFlow policy, respectively. Extensive empirical evaluations on MuJoCo and visual DeepMind Control Suite benchmarks demonstrate that our algorithms show strong performance comparable to diffusion policy baselines while requiring orders of magnitude less computational cost during inference.

cs.LG↗

arXiv2025

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

While integrating tools like Code Interpreter and Search has significantly enhanced Large Language Model (LLM) reasoning in models like ChatGPT Agent and Gemini-Pro, practical guidance on optimal tool use is lacking. The core challenge is effectively combining textual reasoning, coding, and search for diverse questions. In this paper, we propose Tool-Use Mixture (TUMIX), an ensemble framework that runs multiple agents in parallel, each employing distinct tool-use strategies and answer paths. Agents in TUMIX iteratively share and refine responses based on the question and previous answers. In experiments, TUMIX achieves significant gains over state-of-the-art tool-augmented and test-time scaling methods, delivering an average accuracy improvement of up to 3.55% over the best baseline on Gemini-2.5-Pro and Gemini-2.5-Flash across key reasoning benchmarks, with near-equal inference costs. We find that agent diversity and quality are crucial and can be enhanced by using LLMs to auto-optimize agent designs. Furthermore, TUMIX can halt refinement upon reaching sufficient confidence, preserving performance at only 49% of the inference cost. Further scaling can achieve higher performance, albeit at a greater cost.

cs.CL↗

arXiv2025

PIRF: Physics-Informed Reward Fine-Tuning for Diffusion Models

Diffusion models have demonstrated strong generative capabilities across scientific domains, but often produce outputs that violate physical laws. We propose a new perspective by framing physics-informed generation as a sparse reward optimization problem, where adherence to physical constraints is treated as a reward signal. This formulation unifies prior approaches under a reward-based paradigm and reveals a shared bottleneck: reliance on diffusion posterior sampling (DPS)-style value function approximations, which introduce non-negligible errors and lead to training instability and inference inefficiency. To overcome this, we introduce Physics-Informed Reward Fine-tuning (PIRF), a method that bypasses value approximation by computing trajectory-level rewards and backpropagating their gradients directly. However, a naive implementation suffers from low sample efficiency and compromised data fidelity. PIRF mitigates these issues through two key strategies: (1) a layer-wise truncated backpropagation method that leverages the spatiotemporally localized nature of physics-based rewards, and (2) a weight-based regularization scheme that improves efficiency over traditional distillation-based methods. Across five PDE benchmarks, PIRF consistently achieves superior physical enforcement under efficient sampling regimes, highlighting the potential of reward fine-tuning for advancing scientific generative modeling.

cs.LG↗

arXiv2025

Error-In-Variables Methods for Efficient System Identification with Finite-Sample Guarantees

This paper addresses the problem of learning linear dynamical systems from noisy observations. In this setting, existing algorithms either yield biased parameter estimates or have large sample complexities. We resolve these issues by adapting the instrumental variable method and the bias compensation method, originally proposed for error-in-variables models, to our setting. We provide refined non-asymptotic analysis for both methods. Under mild conditions, our algorithms achieve superior sample complexities that match the best-known sample complexity for learning a fully observable system without observation noise.

eess.SY↗

arXiv2025

Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding

This paper proposes an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear stochastic systems. This method reveals an infinite-dimensional feature representation induced by the system's nonlinear stochastic dynamics, enabling a linear representation of the state-action value function. For practical implementation, this representation is approximated using finite-dimensional truncations, specifically via two prominent kernel approximation methods: random feature truncation and Nystrom approximation. To characterize the effectiveness of these approximations, we provide an in-depth theoretical analysis to characterize the approximation error arising from the finite-dimension truncation and statistical error due to finite-sample approximation in both policy evaluation and policy optimization. Empirically, our algorithm performs favorably against existing stochastic control algorithms on several benchmark problems.

cs.LG↗

arXiv2025

Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations

Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducing a pre-training stage that learns dynamics representations, derived from factorizations of the transition dynamics. We first theoretically justify that the optimal decision variable of offline IL lies in the representation space, significantly reducing the parameters to learn in the downstream IL. Moreover, the dynamics representations can be learned from arbitrary data collected with the same dynamics, allowing the reuse of massive non-expert data and mitigating the limited data issues. We present a tractable loss function inspired by noise contrastive estimation to learn the dynamics representations at the pre-training stage. Experiments on MuJoCo demonstrate that our proposed algorithm can mimic expert policies with as few as a single trajectory. Experiments on real quadrupeds show that we can leverage pre-trained dynamics representations from simulator data to learn to walk from a few real-world demonstrations.

cs.RO↗

arXiv2025

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

Model compression is crucial for minimizing memory storage and accelerating inference in deep learning (DL) models, including recent foundation models like large language models (LLMs). Users can access different compressed model versions according to their resources and budget. However, while existing compression operations primarily focus on optimizing the trade-off between resource efficiency and model performance, the privacy risks introduced by compression remain overlooked and insufficiently understood. In this work, through the lens of membership inference attack (MIA), we propose CompLeak, the first privacy risk evaluation framework examining three widely used compression configurations that are pruning, quantization, and weight clustering supported by the commercial model compression framework of Google's TensorFlow-Lite (TF-Lite) and Facebook's PyTorch Mobile. CompLeak has three variants, given available access to the number of compressed models and original model. CompLeakNR starts by adopting existing MIA methods to attack a single compressed model, and identifies that different compressed models influence members and non-members differently. When the original model and one compressed model are available, CompLeakSR leverages the compressed model as a reference to the original model and uncovers more privacy by combining meta information (e.g., confidence vector) from both models. When multiple compressed models are available with/without accessing the original model, CompLeakMR innovatively exploits privacy leakage info from multiple compressed versions to substantially signify the overall privacy leakage. We conduct extensive experiments on seven diverse model architectures (from ResNet to foundation models of BERT and GPT-2), and six image and textual benchmark datasets.

cs.CR↗

arXiv2025

Efficient Online Reinforcement Learning for Diffusion Policy

Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target distribution, which is impossible in online RL since we cannot sample from the optimal policy. Backpropagating policy gradient through the diffusion process incurs huge computational costs and instability, thus being expensive and not scalable. To enable efficient training of diffusion policies in online RL, we generalize the conventional denoising score matching by reweighting the loss function. The resulting Reweighted Score Matching (RSM) preserves the optimal solution and low computational cost of denoising score matching, while eliminating the need to sample from the target distribution and allowing learning to optimize value functions. We introduce two tractable reweighted loss functions to solve two commonly used policy optimization problems, policy mirror descent and max-entropy policy, resulting in two practical algorithms named Diffusion Policy Mirror Descent (DPMD) and Soft Diffusion Actor-Critic (SDAC). We conducted comprehensive comparisons on MuJoCo benchmarks. The empirical results show that the proposed algorithms outperform recent diffusion-policy online RLs on most tasks, and the DPMD improves more than 120% over soft actor-critic on Humanoid and Ant.

cs.LG↗

arXiv2025

Deep Learning based Joint Geometry and Attribute Up-sampling for Large-Scale Colored Point Clouds

Colored point cloud, which includes geometry and attribute components, is a mainstream representation enabling realistic and immersive 3D applications. To generate large-scale and denser colored point clouds, we propose a deep learning-based Joint Geometry and Attribute Up-sampling (JGAU) method that learns to model both geometry and attribute patterns while leveraging spatial attribute correlations. First, we establish and release a large-scale dataset for colored point cloud up-sampling called SYSU-PCUD, containing 121 large-scale colored point clouds with diverse geometry and attribute complexities across six categories and four sampling rates. Second, to improve the quality of up-sampled point clouds, we propose a deep learning-based JGAU framework that jointly up-samples geometry and attributes. It consists of a geometry up-sampling network and an attribute up-sampling network, where the latter leverages the up-sampled auxiliary geometry to model neighborhood correlations of the attributes. Third, we propose two coarse attribute up-sampling methods, Geometric Distance Weighted Attribute Interpolation (GDWAI) and Deep Learning-based Attribute Interpolation (DLAI), to generate coarse up-sampled attributes for each point. Then, an attribute enhancement module is introduced to refine these up-sampled attributes and produce high-quality point clouds by further exploiting intrinsic attribute and geometry patterns. Extensive experiments show that the Peak Signal-to-Noise Ratio (PSNR) achieved by the proposed JGAU method is 33.90 decibels, 32.10 decibels, 31.10 decibels, and 30.39 decibels for up-sampling rates of 4 times, 8 times, 12 times, and 16 times, respectively. Compared to state-of-the-art methods, JGAU achieves average PSNR gains of 2.32 decibels, 2.47 decibels, 2.28 decibels, and 2.11 decibels at these four up-sampling rates, demonstrating significant improvement.

cs.CV↗

arXiv2025

USM-VC: Mitigating Timbre Leakage with Universal Semantic Mapping Residual Block for Voice Conversion

Voice conversion (VC) transforms source speech into a target voice by preserving the content. However, timbre information from the source speaker is inherently embedded in the content representations, causing significant timbre leakage and reducing similarity to the target speaker. To address this, we introduce a Universal Semantic Matching (USM) residual block to a content extractor. The residual block consists of two weighted branches: 1) universal semantic dictionary based Content Feature Re-expression (CFR) module, supplying timbre-free content representation. 2) skip connection to the original content layer, providing complementary fine-grained information. In the CFR module, each dictionary entry in the universal semantic dictionary represents a phoneme class, computed statistically using speech from multiple speakers, creating a stable, speaker-independent semantic set. We introduce a CFR method to obtain timbre-free content representations by expressing each content frame as a weighted linear combination of dictionary entries using corresponding phoneme posteriors as weights. Extensive experiments across various VC frameworks demonstrate that our approach effectively mitigates timbre leakage and significantly improves similarity to the target speaker.

eess.AS↗

arXiv2025

Linear and Numerical SDoF Bounds of Active RIS-Assisted MIMO Wiretap Interference Channel

The multiple-input multiple-output (MIMO) wiretap interference channel (IC) serves as a canonical model for information-theoretic security, where a multiple-antenna eavesdropper attempts to intercept communications in a two-user MIMO IC system. The secure degrees-of-freedom (SDoF) of an active reconfigurable intelligent surface (RIS)-assisted MIMO wiretap IC is with practical interests but remains unexplored. In this paper, we establish both sum-SDoF lower and upper bounds through linear beamforming conditions and numerical methods. Specifically, our proposed lower bound is derived from transmission scheme design and corresponding solutions to the sum-SDoF maximization problem, formulated by linear integer programming. The solutions to this optimization problem addresses RIS element allocation for leakage and interference cancellation. The proposed upper bound is obtained by solving a nuclear norm minimization problem, leveraging the fact that nuclear norm serves as a convex relaxation of the rank function. For symmetry antenna configurations, we derive a closed-form lower bound. Extensive numerical simulations show that our proposed lower and upper bounds coincide across many antenna configurations, and our proposed lower bound outperforms the existing benchmark.

cs.IT↗

arXiv2025

TS-RSR: A provably efficient approach for batch Bayesian Optimization

This paper presents a new approach for batch Bayesian Optimization (BO) called Thompson Sampling-Regret to Sigma Ratio directed sampling (TS-RSR), where we sample a new batch of actions by minimizing a Thompson Sampling approximation of a regret to uncertainty ratio. Our sampling objective is able to coordinate the actions chosen in each batch in a way that minimizes redundancy between points whilst focusing on points with high predictive means or high uncertainty. Theoretically, we provide rigorous convergence guarantees on our algorithm's regret, and numerically, we demonstrate that our method attains state-of-the-art performance on a range of challenging synthetic and realistic test functions, where it outperforms several competitive benchmark batch BO algorithms.

cs.LG↗

arXiv2025

On an extension of Shlyk's theorem

In this paper, we prove that the intersection of all non-nilpotent maximal subgroups of a non-solvable group containing the normalizer of some Sylow subgroup is nilpotent, which provides an extension of Shlyk's theorem.

math.GR↗

arXiv2025

Pulse duration dependence of material response in ultrafast laser-induced surface-penetrating nanovoids in fused silica

The focused ultrafast laser, with its ability to initiate nonlinear absorption in transparent materials, has emerged as one of the most effective approaches for micro-nano processing. In this study, we carried out research on the processing of high-aspect-ratio nanovoids on fused silica by using the single-pulse ultrafast Bessel beam. The thermodynamic response behaviors of the materials on surface and deep inside are found to exhibit pronounced disparities with the variation in laser pulse duration. As the pulse duration increases from 0.2 ps to 9.0 ps, the intensity of material ablation on silica surface exhibits a gradually decreasing trend, while for the void formation deep inside silica, the void diameter exhibits a trend of initial increase followed by decrease. In particular, no nanovoids are even induced deep inside when the pulse duration is 0.2 ps. The mechanism causing such differences is discussed and considered to be related to the peak intensity, group velocity dispersion, and plasma defocusing. By covering a polymer film on silica surface to influence the energy deposition, the thermomechanical response behaviors of the materials to laser pulse duration are modulated, and the material sputtering on nanovoid opening is suppressed. On this basis, surface-penetrating nanovoid arrays are fabricated on a 2-mm-thick silica sample using 2 ps Bessel beam. Given the nanovoid diameter of approximately 150 nm, the aspect ratio of the nanovoids on fused silica sample exceeds 13000:1. This outcome creates significant possibilities for the stealth dicing and processing of 3D photonic crystals, optical integrated devices, and nanofluidics.

physics.optics↗