Searcharxiv⌕ Search

arXiv subjects

Li Wang

Publications and source records attributed to Li Wang.

At least 91 records · Page 5Linked to original sources
arXiv2026

Inference of interacting kernel in the mean-field regime

We study the problem of reconstructing interaction kernels in systems of interacting agents from macroscopic measurements when posed as an optimization problem. The reconstruction procedure depends on the formulation of the forward model, which may be given either by a finite-dimensional coupled ODE system tracking individual agent trajectories or by a mean-field PDE describing the evolution of the agent density. We investigate the similarities and differences between these two formulations in the mean-field regime. While the first variation derived from the particle system does not provide an unbiased estimator of the first variation associated with the limiting PDE, we prove that, under mild assumptions, the two are close in a weak sense with a convergence rate $\mathcal{O}(N^{-1/2})$. This rate is further confirmed by numerical evidences.

math.NA↗
arXiv2026

JKO for Landau: a variational particle method for homogeneous Landau equation

Inspired by the gradient flow viewpoint of the Landau equation and the corresponding dynamic formulation of the Landau metric in [arXiv:2007.08591], we develop a novel implicit particle method for the Landau equation in the framework of the JKO scheme. We first reformulate the Landau metric in a computationally friendly form, and then translate it into the Lagrangian viewpoint using the flow map. A key observation is that, while the flow map evolves according to a rather complicated integral equation, the unknown component is simply a score function of the corresponding density plus an additional term in the null space of the collision kernel. This insight guides us in designing and training the neural network for the flow map. Additionally, the objective function is in a double summation form, making it highly suitable for stochastic methods. Consequently, we design a tailored version of stochastic gradient descent that maintains particle interactions and significantly reduces the computational complexity. Compared to other deterministic particle methods, the proposed method enjoys exact entropy dissipation and unconditional stability, therefore making it suitable for large-scale plasma simulations over extended time periods.

math.NA↗
arXiv2026

Deep Kinetic JKO schemes for Vlasov-Fokker-Planck Equations

We introduce a deep neural network-based numerical method for solving kinetic Fokker Planck equations, including both linear and nonlinear cases. Building upon the conservative dissipative structure of Vlasov-type equations, we formulate a class of generalized minimizing movement schemes as iterative constrained minimization problems: the conservative part determines the constraint set, while the dissipative part defines the objective functional. This leads to an analog of the classical Jordan-Kinderlehrer-Otto (JKO) scheme for Wasserstein gradient flows, and we refer to it as the kinetic JKO scheme. To compute each step of the kinetic JKO iteration, we introduce a particle-based approximation in which the velocity field is parameterized by deep neural networks. The resulting algorithm can be interpreted as a kinetic-oriented neural differential equation that enables the representation of high-dimensional kinetic dynamics while preserving the essential variational and structural properties of the underlying PDE. We validate the method with extensive numerical experiments and demonstrate that the proposed kinetic JKO-neural ODE framework is effective for high-dimensional numerical simulations.

math.NA↗
arXiv2026

Sensitivity of the RECODE Reactor CEvNS Experiment to the Dark Axion Portal

Reactor CEvNS experiments provide a powerful probe of the physics beyond the Standard Model (BSM) with the intense flux of neutrinos, photons, and other particles produced in nuclear reactors. In this work, we investigate the sensitivity of reactor CEvNS experiments to the dark axion portal, which connects the axion or axion-like particle to the dark photon. We focus in particular on the RECODE experiment, while also considering other reactor-based experiments such as CONUS and MINER. We find that reactor CEvNS experiments offer enhanced sensitivity in the sub-MeV region compared with the existing constraints from B factories, and can probe the portal coupling down to $\mathcal{O}(10^{-3})$ for $G_{aγγ'}$.

hep-ph↗
arXiv2026

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

Large Language Models(LLMs) are widely deployed, yet are vulnerable to jailbreak prompts that elicit policy-violating outputs. Although prior studies have uncovered these risks, they typically treat all tokens as equally important during prompt mutation, overlooking the varying contributions of individual tokens to triggering model refusals. Consequently, these attacks introduce substantial redundant searching under query-constrained scenarios, reducing attack efficiency and hindering comprehensive vulnerability assessment. In this work, we conduct a token-level analysis of refusal behavior and observe that token contributions are highly skewed rather than uniform. Moreover, we find strong cross-model consistency in refusal tendencies, enabling the use of a surrogate model to estimate token-level contributions to the target model's refusals. Motivated by these findings, we propose TriageFuzz, a token-aware jailbreak fuzzing framework that adapts the fuzz testing approach with a series of customized designs. TriageFuzz leverages a surrogate model to estimate the contribution of individual tokens to refusal behaviors, enabling the identification of sensitive regions within the prompt. Furthermore, it incorporates a refusal-guided evolutionary strategy that adaptively weights candidate prompts with a lightweight scorer to steer the evolution toward bypassing safety constraints. Extensive experiments on six open-source LLMs and three commercial APIs demonstrate that TriageFuzz achieves comparable attack success rates (ASR) with significantly reduced query costs. Notably, it attains a 90% ASR with over 70% fewer queries compared to baselines. Even under an extremely restrictive budget of 25 queries, TriageFuzz outperforms existing methods, improving ASR by 20-40%.

cs.CR↗
arXiv2026

TAMTRL: Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning in Long-Context Compression

The rapid progress of large language models (LLMs) has led to remarkable performance gains across a wide range of tasks. However, when handling long documents that exceed the model's context window limit, the entire context cannot be processed in a single pass, making chunk-wise processing necessary. This requires multiple turns to read different chunks and update memory. However, supervision is typically provided only by the final outcome, which makes it difficult to evaluate the quality of memory updates at each turn in the multi-turn training setting. This introduces a temporal credit assignment challenge. Existing approaches, such as LLM-as-a-judge or process reward models, incur substantial computational overhead and suffer from estimation noise. To better address the credit assignment problem in multi-turn memory training, we propose Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning (TAMTRL). TAMTRL leverages relevant documents as teacher signals by aligning them with each turn of model input and assigns rewards through normalized probabilities in a self-supervised manner. This provides fine-grained learning signals for each memory update and improves long-context processing. Experiments with multiple models of varying scales across seven long-context benchmarks show that TAMTRL consistently outperforms strong baselines, demonstrating its effectiveness. Our code is available at https://anonymous.4open.science/r/TAMTRL-F1F8.

cs.CL↗
arXiv2026

On the Calibration of Bayesian Success Criteria and Operating Characteristics for Clinical Trials

Recently, the U.S. Food and Drug Administration (FDA) released draft guidance \citep{FDA2026} signaling a paradigm shift that facilitates the use of Bayesian methodology as the primary analysis and decision framework for drug approval. The cornerstone and fundamental challenge of this framework is the specification and calibration of Bayesian success criteria to control decision errors, ensuring reliable clinical and regulatory outcomes. In this work, we systematically investigate various Bayesian decision-error metrics, their theoretical interrelationships, and their alignment with conventional Frequentist counterparts. This investigation provides critical theoretical insights and practical guidance on calibrating Bayesian success criteria and operating characteristics to ensure robust decision-making and the integrity of public health decisions. We illustrate this framework using a clinical trial evaluating revascularization strategies for cardiogenic shock. A Shiny application will be available at www.trialdesign.org to assist sponsors and regulators in evaluating calibration strategies consistent with recent regulatory perspectives.

stat.ME↗
arXiv2026

Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models

Large Language Models (LLMs) have been widely deployed, especially through free Web-based applications that expose them to diverse user-generated inputs, including those from long-tail distributions such as low-resource languages and encrypted private data. This open-ended exposure increases the risk of jailbreak attacks that undermine model safety alignment. While recent studies have shown that leveraging long-tail distributions can facilitate such jailbreaks, existing approaches largely rely on handcrafted rules, limiting the systematic evaluation of these security and privacy vulnerabilities. In this work, we present EvoJail, an automated framework for discovering long-tail distribution attacks via multi-objective evolutionary search. EvoJail formulates long-tail attack prompt generation as a multi-objective optimization problem that jointly maximizes attack effectiveness and minimizes output perplexity, and introduces a semantic-algorithmic solution representation to capture both high-level semantic intent and low-level structural transformations of encryption-decryption logic. Building upon this representation, EvoJail integrates LLM-assisted operators into a multi-objective evolutionary framework, enabling adaptive and semantically informed mutation and crossover for efficiently exploring a highly structured and open-ended search space. Extensive experiments demonstrate that EvoJail consistently discovers diverse and effective long-tail jailbreak strategies, achieving competitive performance with existing methods in both individual and ensemble level.

cs.CR↗
arXiv2026

Unstable Slip in Fault Gouge Driven by Temperature and Water

Microscale granular sliding within fault gouge is fundamental to earthquake nucleation, yet the mechanism by which temperature affects friction through interfacial water remains poorly understood. Here, large-scale molecular dynamics simulations were conducted on a hydrophilic quartz-water-quartz interface over 300-500 K to quantify temperature-dependent changes in frictional strength, real contact area, and water-layer structure. Results show that both the friction coefficient and friction force decrease monotonically with increasing temperature, following near-linear relationships of $μ\propto T^{-1}$ and $F_t \propto A$, indicating that frictional weakening is primarily governed by temperature-driven contact restructuring. Structural analyses further show that heating progressively disrupts the hydrogen-bond network in the first adsorption layer, reduces adsorption-layer density, and weakens radial distribution peaks, demonstrating a transition of interfacial water from an ordered, strongly adsorbed state to a more diffuse, weakly bound configuration with delayering and quasi-phase-transition behavior. This interfacial reconstruction weakens intergranular bridging and structural cohesion, promoting a shift from structural locking to water-mediated lubrication. These results suggest that frictional stability under coupled temperature-water conditions is strongly controlled by the thermal evolution of interfacial water structure.

physics.geo-ph↗
arXiv2026

Tidal Synchronization of Binaries in Pleiades

Tidal interactions in close binaries play a key role in the long-term rotational and orbital evolution. The distributions of circularization across open clusters (OCs) place strong observational constraints on tidal dissipation in binaries. However, direct observational constraints on synchronization among binaries in OCs remain limited. For the 125 Myr OC Pleiades, this work combines cluster membership from Gaia Data Release 3, rotation periods from the K2 mission, and orbital solutions of the binary population from a long-term spectroscopic survey, to investigate the degree of tidal synchronization in each binary by comparing the pseudo-synchronization period to the rotation period of the primary stars. Among 42 binaries with reliable orbital periods Porb and rotation periods, we identify seven tidally synchronized systems with Porb < 8.6 days, including one early-type system and six late-type systems. For binaries with longer Porb, primaries generally are super-synchronized, and most systems are eccentric. We find a synchronization transition near Porb ~ 8.6-14 days, comparable to the known circularization period (Porb ~ 7.2 days) in the Pleiades, which suggests similar critical period scales for synchronization and circularization in this coeval population. Synchronization depends much more strongly on mass ratio than on primary mass. Most synchronized systems in Pleiades have high mass ratios and are likely to evolve into double white dwarf systems. Tides likely impose strong rotational braking on close early-type binaries, while their influence on late-type close binaries is weaker, and their spins largely follow the single-star sequence.

astro-ph.SR↗
arXiv2026

Searching for White Dwarf Candidates Formed Through Binary evolution in Star Clusters

White dwarfs (WDs), the evolutionary endpoints of most stars, can form through both single-star and binary channels. While single-star evolutionary models enable reliable WD age estimates, binary evolution introduces interactions that can accelerate WD formation and result in a variety of exotic WDs, which may exhibit strong magnetic fields, rapid rotation, or even serve as potential gravitational wave sources. Such systems offer valuable insights into magnetic field generation, angular momentum evolution, and compact object physics. Star clusters, with their approximately coeval populations, allow precise age determination of member WDs. If a WD's total age derived from single-star evolution exceeds that of its host cluster, it likely indicates a binary origin. In this study, we use \textit{Gaia} 5D astrometry to identify 439 WD candidates in 117 open clusters, with 244 likely formed via binary evolution. We discuss the possibility of dynamical ejection for WDs meeting only 2D (proper motion space) membership criteria. Spectroscopic observations further reveal a subset with strong magnetic fields and rapid rotation, supporting their binary evolutionary origin.

astro-ph.SR↗
arXiv2026

On the levels of rational regular orthogonal matrices for generalized cospectral graphs

For an $n$-vertex graph $G$ with adjacency matrix $A$, the walk matrix $W(G)$ of $G$ is the matrix $[e,Ae,\ldots,A^{n-1}e]$, where $e$ is the all-ones vector. Suppose that $W(G)$ is nonsingular and $p$ is an odd prime such that $W(G)$ has rank $n-1$ over the finite field $\mathbb{Z}/p\mathbb{Z}$. Let $H$ be a graph that is generalized cospectral with $G$, and $Q$ be the corresponding rational regular orthogonal matrix satisfying $Q^\mathsf{T} A(G) Q=A(H)$. We prove that \begin{equation*} v_p(\ell(Q))\le \frac{1}{2}v_p (\det W(G)) \end{equation*} where $\ell(Q)$ is the minimum positive integer $k$ such that $kQ$ is an integral matrix, and $v_p(m)$ is the maximum nonnegative integer $s$ such that $p^s$ divides $m$. This significantly improves upon a recent result of Qiu et al. [Discrete Math. 346 (2023) 113177] stating that $v_p(\ell(Q))\le v_p (\det W(G))-1.$

math.CO↗
arXiv2026

SAM4Dcap: Training-free Biomechanical Twin System from Monocular Video

Quantitative biomechanical analysis is essential for clinical diagnosis and injury prevention but is often restricted to laboratories due to the high cost of optical motion capture systems. While multi-view video approaches have lowered barriers, they remain impractical for home-based scenarios requiring monocular capture. This paper presents SAM4Dcap, an open-source, end-to-end framework for estimating biomechanical metrics from monocular video without additional training. SAM4Dcap integrates the temporally consistent 4D human mesh recovery of SAM-Body4D with the OpenSim biomechanical solver. The pipeline converts reconstructed meshes into trajectory files compatible with diverse musculoskeletal models. We introduce automated prompting strategies and a Linux-native build for processing. Preliminary evaluations on walking and drop-jump tasks indicate that SAM4Dcap has the potential to achieve knee kinematic predictions comparable to multi-view systems, although some discrepancies in hip flexion and residual jitter remain. By bridging advanced computer vision with established biomechanical simulation, SAM4Dcap provides a flexible, accessible foundation for non-laboratory motion analysis.

cs.CV↗
arXiv2026

Boundary estimates and Green function's expansion for elliptic systems with random coefficients

We investigate boundary estimates for elliptic operators with stationary random coefficients exhibiting integrable correlations, arising from stochastic homogenization theory. As practical applications, we establish decay estimates for Green functions in both quenched and annealed senses. Furthermore, we derive notable annealed estimates for boundary correctors, including central limit theorem (CLT)-scaling type estimates. By extending the lemma of Bella, Giunti, and Otto [10] to accommodate boundary conditions, we ultimately obtain error estimates for the two-scale expansion of Green functions at the level of mixed derivatives, thereby establishing connections to other related fields.

math.AP↗
arXiv2026

Normalized solutions of quasilinear Schrödinger-Poisson system with critical nonlinear term in bounded domain

This work examines a quasilinear Schrödinger-Poisson system involving a critical nonlinearity, expressed as \[ -Δu + ϕu + λu = |u|^{q-2} u + |u|^4 u, \quad x \in Ω_r, \] \[ -Δϕ- \varepsilon^4 Δ_4 ϕ= u^2, \qquad\qquad\qquad\quad\ x \in Ω_r, \] \[ \enspace u = ϕ= 0, \qquad\qquad\qquad\qquad\qquad\enspace\ \ \,x \in \partial Ω_r \] subject to the normalized condition \[ \int_{Ω_r} |u|^2\, \mathrm d x = b^2. \] Here $\varepsilon > 0$, $q \in (2, 8/3)$, $Ω_r \subset \mathbb R^3$ is a bounded domain. By means of a truncation method combined with genus theory, we establish the existence of multiple families of normalized solutions. Due to the presence of a critical exponent in the nonlinear term, the associated energy functional fails to satisfy the usual compactness properties. To address this issue, we invoke the concentration-compactness principle. Furthermore, we derive the asymptotic result that the aforementioned system reduces to the classical Schrödinger-Poisson system (with $\varepsilon = 0$). Our findings extend several recent results concerning problems of this type.

math.AP↗
arXiv2026

Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directions

Traditional Simultaneous Localization and Mapping (SLAM) systems often face limitations including coarse rendering quality, insufficient recovery of scene details, and poor robustness in dynamic environments. 3D Gaussian Splatting (3DGS), with its efficient explicit representation and high-quality rendering capabilities, offers a new reconstruction paradigm for SLAM. This survey comprehensively reviews key technical approaches for integrating 3DGS with SLAM. We analyze performance optimization of representative methods across four critical dimensions: rendering quality, tracking accuracy, reconstruction speed, and memory consumption, delving into their design principles and breakthroughs. Furthermore, we examine methods for enhancing the robustness of 3DGS-SLAM in complex environments such as motion blur and dynamic environments. Finally, we discuss future challenges and development trends in this area. This survey aims to provide a technical reference for researchers and foster the development of next-generation SLAM systems characterized by high fidelity, efficiency, and robustness.

cs.RO↗
arXiv2026

Baseline Method of the Foundation Model Challenge for Ultrasound Image Analysis

Ultrasound (US) imaging exhibits substantial heterogeneity across anatomical structures and acquisition protocols, posing significant challenges to the development of generalizable analysis models. Most existing methods are task-specific, limiting their suitability as clinically deployable foundation models. To address this limitation, the Foundation Model Challenge for Ultrasound Image Analysis (FM\_UIA~2026) introduces a large-scale multi-task benchmark comprising 27 subtasks across segmentation, classification, detection, and regression. In this paper, we present the official baseline for FM\_UIA~2026 based on a unified Multi-Head Multi-Task Learning (MH-MTL) framework that supports all tasks within a single shared network. The model employs an ImageNet-pretrained EfficientNet--B4 backbone for robust feature extraction, combined with a Feature Pyramid Network (FPN) to capture multi-scale contextual information. A task-specific routing strategy enables global tasks to leverage high-level semantic features, while dense prediction tasks exploit spatially detailed FPN representations. Training incorporates a composite loss with task-adaptive learning rate scaling and a cosine annealing schedule. Validation results demonstrate the feasibility and robustness of this unified design, establishing a strong and extensible baseline for ultrasound foundation model research. The code and dataset are publicly available at \href{https://github.com/lijiake2408/Foundation-Model-Challenge-for-Ultrasound-Image-Analysis}{GitHub}.

cs.CV↗