arXiv subjects

Shuxin Li

Publications and source records attributed to Shuxin Li.

At least 19 recordsLinked to original sources

arXiv2026

PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs

Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. However, most existing variants fail to distinguish advantages among successful trajectories even when these trajectories differ substantially in their interaction efficiency. For instance, circuitous successes are often assigned the identical outcome reward, causing advantage collapse and severe performance bottlenecks. To this end, we propose Group Planning-aware Policy Optimization (PlanPO), a simple yet effective RL method for learning generalizable planning abilities beyond task-specific high-quality behavior patterns. Specifically, PlanPO introduces coarse-to-fine advantage signals, which capture the relative differences in trajectory-level lengths and turn-level response lengths conditioned on successful trajectories sampled for the same task. Within the group-relative optimization structure, this enables agents to actively learn generalizable and deliberate behaviors spanning interaction planning and textual generation from high-quality rollouts, without degenerating into vanilla length minimization. Experimentally, PlanPO improves over GRPO by 27.2\% on average across the challenging multi-turn benchmarks ALFWorld, WebShop, and SciWorld, outperforming recent powerful baselines while incurring negligible additional training cost.

cs.AI↗

arXiv2026

CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models

Palmprint recognition is deployed in security-critical applications, including access control and palm-based payment, due to its contactless acquisition and highly discriminative ridge-and-crease textures. However, the robustness of deep palmprint recognition systems against physically realizable attacks remains insufficiently understood. Existing studies are largely confined to the digital setting and do not adequately account for the texture-dominant nature of palmprint recognition or the distortions introduced during physical acquisition. To address this gap, we propose CAAP, a capture-aware adversarial patch framework for palmprint recognition. CAAP learns a universal patch that can be reused across inputs while remaining effective under realistic acquisition variation. To match the structural characteristics of palmprints, the framework adopts a cross-shaped patch topology, which enlarges spatial coverage under a fixed pixel budget and more effectively disrupts long-range texture continuity. CAAP further integrates three modules: ASIT for input-conditioned patch rendering, RaS for stochastic capture-aware simulation, and MS-DIFE for feature-level identity-disruptive guidance. We evaluate CAAP on the Tongji, IITD, and AISEC datasets against generic CNN backbones and palmprint-specific recognition models. Experiments show that CAAP achieves strong untargeted and targeted attack performance with favorable cross-model and cross-dataset transferability. The results further show that, although adversarial training can partially reduce the attack success rate, substantial residual vulnerability remains. These findings indicate that deep palmprint recognition systems remain vulnerable to physically realizable, capture-aware adversarial patch attacks, underscoring the need for more effective defenses in practice. Code available at https://github.com/ryliu68/CAAP.

cs.CV↗

arXiv2026

DEpiABS: Differentiable Epidemic Agent-Based Simulator

The COVID-19 pandemic highlighted the limitations of existing epidemic simulation tools. These tools provide information that guides non-pharmaceutical interventions (NPIs), yet many struggle to capture complex dynamics while remaining computationally practical and interpretable. We introduce DEpiABS, a scalable, differentiable agent-based model (DABM) that balances mechanistic detail, computational efficiency and interpretability. DEpiABS captures individual-level heterogeneity in health status, behaviour, and resource constraints, while also modelling epidemic processes like viral mutation and reinfection dynamics. The model is fully differentiable, enabling fast simulation and gradient-based parameter calibration. Building on this foundation, we introduce a z-score-based scaling method that maps small-scale simulations to any real-world population sizes with negligible loss in output granularity, reducing the computational burden when modelling large populations. We validate DEpiABS through sensitivity analysis and calibration to COVID-19 and flu data from ten regions of varying scales. Compared to the baseline, DEpiABS is more detailed, fully interpretable, and has reduced the average normal deviation in forecasting from 0.97 to 0.92 on COVID-19 mortality data and from 0.41 to 0.32 on influenza-like-illness data. Critically, these improvements are achieved without relying on auxiliary data, making DEpiABS a reliable, generalisable, and data-efficient framework for future epidemic response modelling.

cs.MA↗

arXiv2025

Tree-Based Stochastic Optimization for Solving Large-Scale Urban Network Security Games

Urban Network Security Games (UNSGs), which model the strategic allocation of limited security resources on city road networks, are critical for urban safety. However, finding a Nash Equilibrium (NE) in large-scale UNSGs is challenging due to their massive and combinatorial action spaces. One common approach to addressing these games is the Policy-Space Response Oracle (PSRO) framework, which requires computing best responses (BR) at each iteration. However, precisely computing exact BRs is impractical in large-scale games, and employing reinforcement learning to approximate BRs inevitably introduces errors, which limits the overall effectiveness of the PSRO methods. Recent advancements in leveraging non-convex stochastic optimization to approximate an NE offer a promising alternative to the burdensome BR computation. However, utilizing existing stochastic optimization techniques with an unbiased loss function for UNSGs remains challenging because the action spaces are too vast to be effectively represented by neural networks. To address these issues, we introduce Tree-based Stochastic Optimization (TSO), a framework that bridges the gap between the stochastic optimization paradigm for NE-finding and the demands of UNSGs. Specifically, we employ the tree-based action representation that maps the whole action space onto a tree structure, addressing the challenge faced by neural networks in representing actions when the action space cannot be enumerated. We then incorporate this representation into the loss function and theoretically demonstrate its equivalence to the unbiased loss function. To further enhance the quality of the converged solution, we introduce a sample-and-prune mechanism that reduces the risk of being trapped in suboptimal local optima. Extensive experimental results indicate the superiority of TSO over other baseline algorithms in addressing the UNSGs.

cs.LG↗

arXiv2025

VLM-3D:End-to-End Vision-Language Models for Open-World 3D Perception

Open-set perception in complex traffic environments poses a critical challenge for autonomous driving systems, particularly in identifying previously unseen object categories, which is vital for ensuring safety. Visual Language Models (VLMs), with their rich world knowledge and strong semantic reasoning capabilities, offer new possibilities for addressing this task. However, existing approaches typically leverage VLMs to extract visual features and couple them with traditional object detectors, resulting in multi-stage error propagation that hinders perception accuracy. To overcome this limitation, we propose VLM-3D, the first end-to-end framework that enables VLMs to perform 3D geometric perception in autonomous driving scenarios. VLM-3D incorporates Low-Rank Adaptation (LoRA) to efficiently adapt VLMs to driving tasks with minimal computational overhead, and introduces a joint semantic-geometric loss design: token-level semantic loss is applied during early training to ensure stable convergence, while 3D IoU loss is introduced in later stages to refine the accuracy of 3D bounding box predictions. Evaluations on the nuScenes dataset demonstrate that the proposed joint semantic-geometric loss in VLM-3D leads to a 12.8% improvement in perception accuracy, fully validating the effectiveness and advancement of our method.

cs.CV↗

arXiv2025

Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection

Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning (FL), where a small number of malicious clients can upload poisoned updates to compromise the federated global model. Existing backdoor detection techniques fall into two categories, passive and proactive, depending on whether the server proactively intervenes in the training process. However, both of them have practical limitations: passive detection methods are disrupted by common non-i.i.d. data distributions and random participation of FL clients, whereas current proactive detection methods are misled by an inevitable out-of-distribution (OOD) bias because they rely on backdoor coexistence effects. To address these issues, we introduce a novel proactive detection method dubbed Coward, inspired by our discovery of multi-backdoor collision effects, in which consecutively planted, distinct backdoors significantly suppress earlier ones. Correspondingly, we modify the federated global model by injecting a carefully designed backdoor-collided watermark, implemented via regulated dual-mapping learning on OOD data. This design not only enables an inverted detection paradigm compared to existing proactive methods, thereby naturally counteracting the adverse impact of OOD prediction bias, but also introduces a low-disruptive training intervention that inherently limits the strength of OOD bias, leading to significantly fewer misjudgments. Extensive experiments on benchmark datasets show that Coward achieves state-of-the-art performance and effectively alleviates OOD bias.

cs.CR↗

arXiv2025

Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs

Reasoning is the fundamental capability of large language models (LLMs). Due to the rapid progress of LLMs, there are two main issues of current benchmarks: i) these benchmarks can be crushed in a short time (less than 1 year), and ii) these benchmarks may be easily hacked. To handle these issues, we propose the ever-scalingness for building the benchmarks which are scaling over complexity against crushing, instance against hacking and exploitation, oversight for easy verification, and coverage for real-world relevance. This paper presents Nondeterministic Polynomial-time Problem Challenge (NPPC), an ever-scaling reasoning benchmark for LLMs. Specifically, the NPPC has three main modules: i) npgym, which provides a unified interface of 25 well-known NP-complete problems and can generate any number of instances with any levels of complexities, ii) npsolver, which provides a unified interface to evaluate the problem instances with both online and offline models via APIs and local deployments, respectively, and iii) npeval, which provides the comprehensive and ready-to-use tools to analyze the performances of LLMs over different problems, the number of tokens, the reasoning errors and the solution errors. Extensive experiments over widely-used LLMs demonstrate: i) NPPC can successfully decrease the performances of advanced LLMs to below 10%, demonstrating that NPPC is not crushed by current models, ii) DeepSeek-R1, Claude-3.7-Sonnet, and o1/o3-mini are the most powerful LLMs, and iii) the numbers of tokens in the advanced LLMs, e.g., Claude-3.7-Sonnet and DeepSeek-R1, are observed first to increase and then decrease when the problem instances become more and more difficult. Through continuously scaling analysis, NPPC can provide critical insights into the limits of LLMs' reasoning capabilities, exposing fundamental limitations and suggesting future directions for further improvements.

cs.AI↗

arXiv2025

CNSv2: Probabilistic Correspondence Encoded Neural Image Servo

Visual servo based on traditional image matching methods often requires accurate keypoint correspondence for high precision control. However, keypoint detection or matching tends to fail in challenging scenarios with inconsistent illuminations or textureless objects, resulting significant performance degradation. Previous approaches, including our proposed Correspondence encoded Neural image Servo policy (CNS), attempted to alleviate these issues by integrating neural control strategies. While CNS shows certain improvement against error correspondence over conventional image-based controllers, it could not fully resolve the limitations arising from poor keypoint detection and matching. In this paper, we continue to address this problem and propose a new solution: Probabilistic Correspondence Encoded Neural Image Servo (CNSv2). CNSv2 leverages probabilistic feature matching to improve robustness in challenging scenarios. By redesigning the architecture to condition on multimodal feature matching, CNSv2 achieves high precision, improved robustness across diverse scenes and runs in real-time. We validate CNSv2 with simulations and real-world experiments, demonstrating its effectiveness in overcoming the limitations of detector-based methods in visual servo tasks.

cs.CV↗

arXiv2025

GraphChase: A Platform and Benchmark for Urban Network Security Games

After the achievement of solving two-player zero-sum games, more AI researchers focus on solving multiplayer games. Urban Network Security Games (\textbf{UNSGs}) represent a class of such games, modeling real-world scenarios where law enforcement must strategically allocate limited resources to intercept criminals escaping within urban networks, and have gained considerable research attention. However, progress in this field has been limited by the absence of a standardized experimental platform and realistic benchmarks with heterogeneous travel costs. To address this limitation, we introduce \textbf{GraphChase}, an open-source platform designed to support the development and evaluation of algorithms for UNSGs. GraphChase offers a unified environment for modeling diverse UNSG variants on unweighted and weighted road networks across urban topologies. It also incorporates learning-based algorithms as baseline references for researchers. Furthermore, our experiments with GraphChase reveal that existing approaches to UNSGs still face challenges in terms of robustness and scalability, and suffer performance degradation when deployed under weighted edge costs, highlighting a sim-to-real generalization gap. GraphChase thus provides a realistic testbed for developing and validating UNSGs solvers under realistic travel-time heterogeneity.

cs.AI↗

arXiv2024

Factorization method for inverse elastic cavity scattering

This paper is concerned with the inverse elastic scattering problem to determine the shape and location of an elastic cavity. By establishing a one-to-one correspondence between the Herglotz wave function and its kernel, we introduce the far-field operator which is crucial in the factorization method. We present a theoretical factorization of the far-field operator and rigorously prove the properties of its associated operators involved in the factorization. Unlike the Dirichlet problem where the boundary integral operator of the single-layer potential involved in the factorization of the far-field operator is weakly singular, the boundary integral operator of the conormal derivative of the double-layer potential involved in the factorization of the far-field operator with Neumann boundary conditions is hypersingular, which forces us to prove that this operator is isomorphic using Fredholm's theorem. Meanwhile, we present theoretical analyses of the factorization method for various illumination and measurement cases, including compression-wave illumination and compression-wave measurement, shear-wave illumination and shear-wave measurement, and full-wave illumination and full-wave measurement. In addition, we also consider the limited aperture problem and provide a rigorous theoretical analysis of the factorization method in this case. Numerous numerical experiments are carried out to demonstrate the effectiveness of the proposed method, and to analyze the influence of various factors, such as polarization direction, frequency, wavenumber, and multi-scale scatterers on the reconstructed results.

math.NA↗

arXiv2024

A Survey for Large Language Models in Biomedicine

Recent breakthroughs in large language models (LLMs) offer unprecedented natural language understanding and generation capabilities. However, existing surveys on LLMs in biomedicine often focus on specific applications or model architectures, lacking a comprehensive analysis that integrates the latest advancements across various biomedical domains. This review, based on an analysis of 484 publications sourced from databases including PubMed, Web of Science, and arXiv, provides an in-depth examination of the current landscape, applications, challenges, and prospects of LLMs in biomedicine, distinguishing itself by focusing on the practical implications of these models in real-world biomedical contexts. Firstly, we explore the capabilities of LLMs in zero-shot learning across a broad spectrum of biomedical tasks, including diagnostic assistance, drug discovery, and personalized medicine, among others, with insights drawn from 137 key studies. Then, we discuss adaptation strategies of LLMs, including fine-tuning methods for both uni-modal and multi-modal LLMs to enhance their performance in specialized biomedical contexts where zero-shot fails to achieve, such as medical question answering and efficient processing of biomedical literature. Finally, we discuss the challenges that LLMs face in the biomedicine domain including data privacy concerns, limited model interpretability, issues with dataset quality, and ethics due to the sensitive nature of biomedical data, the need for highly reliable model outputs, and the ethical implications of deploying AI in healthcare. To address these challenges, we also identify future research directions of LLM in biomedicine including federated learning methods to preserve data privacy and integrating explainable AI methodologies to enhance the transparency of LLMs.

cs.CL↗

arXiv2024

In-Context Exploiter for Extensive-Form Games

Nash equilibrium (NE) is a widely adopted solution concept in game theory due to its stability property. However, we observe that the NE strategy might not always yield the best results, especially against opponents who do not adhere to NE strategies. Based on this observation, we pose a new game-solving question: Can we learn a model that can exploit any, even NE, opponent to maximize their own utility? In this work, we make the first attempt to investigate this problem through in-context learning. Specifically, we introduce a novel method, In-Context Exploiter (ICE), to train a single model that can act as any player in the game and adaptively exploit opponents entirely by in-context learning. Our ICE algorithm involves generating diverse opponent strategies, collecting interactive history training data by a reinforcement learning algorithm, and training a transformer-based agent within a well-designed curriculum learning framework. Finally, comprehensive experimental results validate the effectiveness of our ICE algorithm, showcasing its in-context learning ability to exploit any unknown opponent, thereby positively answering our initial game-solving question.

cs.AI↗

arXiv2024

Configurable Mirror Descent: Towards a Unification of Decision Making

Decision-making problems, categorized as single-agent, e.g., Atari, cooperative multi-agent, e.g., Hanabi, competitive multi-agent, e.g., Hold'em poker, and mixed cooperative and competitive, e.g., football, are ubiquitous in the real world. Various methods are proposed to address the specific decision-making problems. Despite the successes in specific categories, these methods typically evolve independently and cannot generalize to other categories. Therefore, a fundamental question for decision-making is: \emph{Can we develop \textbf{a single algorithm} to tackle \textbf{ALL} categories of decision-making problems?} There are several main challenges to address this question: i) different decision-making categories involve different numbers of agents and different relationships between agents, ii) different categories have different solution concepts and evaluation measures, and iii) there lacks a comprehensive benchmark covering all the categories. This work presents a preliminary attempt to address the question with three main contributions. i) We propose the generalized mirror descent (GMD), a generalization of MD variants, which considers multiple historical policies and works with a broader class of Bregman divergences. ii) We propose the configurable mirror descent (CMD) where a meta-controller is introduced to dynamically adjust the hyper-parameters in GMD conditional on the evaluation measures. iii) We construct the \textsc{GameBench} with 15 academic-friendly games across different decision-making categories. Extensive experiments demonstrate that CMD achieves empirically competitive or better outcomes compared to baselines while providing the capability of exploring diverse dimensions of decision making.

cs.AI↗

arXiv2024

Reinforcement Nash Equilibrium Solver

Nash Equilibrium (NE) is the canonical solution concept of game theory, which provides an elegant tool to understand the rationalities. Though mixed strategy NE exists in any game with finite players and actions, computing NE in two- or multi-player general-sum games is PPAD-Complete. Various alternative solutions, e.g., Correlated Equilibrium (CE), and learning methods, e.g., fictitious play (FP), are proposed to approximate NE. For convenience, we call these methods as "inexact solvers", or "solvers" for short. However, the alternative solutions differ from NE and the learning methods generally fail to converge to NE. Therefore, in this work, we propose REinforcement Nash Equilibrium Solver (RENES), which trains a single policy to modify the games with different sizes and applies the solvers on the modified games where the obtained solution is evaluated on the original games. Specifically, our contributions are threefold. i) We represent the games as $α$-rank response graphs and leverage graph neural network (GNN) to handle the games with different sizes as inputs; ii) We use tensor decomposition, e.g., canonical polyadic (CP), to make the dimension of modifying actions fixed for games with different sizes; iii) We train the modifying strategy for games with the widely-used proximal policy optimization (PPO) and apply the solvers to solve the modified games, where the obtained solution is evaluated on original games. Extensive experiments on large-scale normal-form games show that our method can further improve the approximation of NE of different solvers, i.e., $α$-rank, CE, FP and PRD, and can be generalized to unseen games.

cs.GT↗

arXiv2024

Grasper: A Generalist Pursuer for Pursuit-Evasion Problems

Pursuit-evasion games (PEGs) model interactions between a team of pursuers and an evader in graph-based environments such as urban street networks. Recent advancements have demonstrated the effectiveness of the pre-training and fine-tuning paradigm in PSRO to improve scalability in solving large-scale PEGs. However, these methods primarily focus on specific PEGs with fixed initial conditions that may vary substantially in real-world scenarios, which significantly hinders the applicability of the traditional methods. To address this issue, we introduce Grasper, a GeneRAlist purSuer for Pursuit-Evasion pRoblems, capable of efficiently generating pursuer policies tailored to specific PEGs. Our contributions are threefold: First, we present a novel architecture that offers high-quality solutions for diverse PEGs, comprising critical components such as (i) a graph neural network (GNN) to encode PEGs into hidden vectors, and (ii) a hypernetwork to generate pursuer policies based on these hidden vectors. As a second contribution, we develop an efficient three-stage training method involving (i) a pre-pretraining stage for learning robust PEG representations through self-supervised graph learning techniques like GraphMAE, (ii) a pre-training stage utilizing heuristic-guided multi-task pre-training (HMP) where heuristic-derived reference policies (e.g., through Dijkstra's algorithm) regularize pursuer policies, and (iii) a fine-tuning stage that employs PSRO to generate pursuer policies on designated PEGs. Finally, we perform extensive experiments on synthetic and real-world maps, showcasing Grasper's significant superiority over baselines in terms of solution quality and generalizability. We demonstrate that Grasper provides a versatile approach for solving pursuit-evasion problems across a broad range of scenarios, enabling practical deployment in real-world situations.

cs.AI↗

arXiv2024

Self-adaptive PSRO: Towards an Automatic Population-based Game Solver

Policy-Space Response Oracles (PSRO) as a general algorithmic framework has achieved state-of-the-art performance in learning equilibrium policies of two-player zero-sum games. However, the hand-crafted hyperparameter value selection in most of the existing works requires extensive domain knowledge, forming the main barrier to applying PSRO to different games. In this work, we make the first attempt to investigate the possibility of self-adaptively determining the optimal hyperparameter values in the PSRO framework. Our contributions are three-fold: (1) Using several hyperparameters, we propose a parametric PSRO that unifies the gradient descent ascent (GDA) and different PSRO variants. (2) We propose the self-adaptive PSRO (SPSRO) by casting the hyperparameter value selection of the parametric PSRO as a hyperparameter optimization (HPO) problem where our objective is to learn an HPO policy that can self-adaptively determine the optimal hyperparameter values during the running of the parametric PSRO. (3) To overcome the poor performance of online HPO methods, we propose a novel offline HPO approach to optimize the HPO policy based on the Transformer architecture. Experiments on various two-player zero-sum games demonstrate the superiority of SPSRO over different baselines.

cs.AI↗

arXiv2024

Finding XPath Bugs in XML Document Processors via Differential Testing

Extensible Markup Language (XML) is a widely used file format for data storage and transmission. Many XML processors support XPath, a query language that enables the extraction of elements from XML documents. These systems can be affected by logic bugs, which are bugs that cause the processor to return incorrect results. In order to tackle such bugs, we propose a new approach, which we realized as a system called XPress. As a test oracle, XPress relies on differential testing, which compares the results of multiple systems on the same test input, and identifies bugs through discrepancies in their outputs. As test inputs, XPress generates both XML documents and XPath queries. Aiming to generate meaningful queries that compute non-empty results, XPress selects a so-called targeted node to guide the XPath expression generation process. Using the targeted node, XPress generates XPath expressions that reference existing context related to the targeted node, such as its tag name and attributes, while also guaranteeing that a predicate evaluates to true before further expanding the query. We tested our approach on six mature XML processors, BaseX, eXist-DB, Saxon, PostgreSQL, libXML2, and a commercial database system. In total, we have found 20 unique bugs in these systems, of which 25 have been verified by the developers, and 12 of which have been fixed. XPress is efficient, as it finds 12 unique bugs in BaseX in 24 hours, which is 2x as fast as naive random generation. We expect that the effectiveness and simplicity of our approach will help to improve the robustness of many XML processors.

cs.SE↗

arXiv2023

Population-size-Aware Policy Optimization for Mean-Field Games

In this work, we attempt to bridge the two fields of finite-agent and infinite-agent games, by studying how the optimal policies of agents evolve with the number of agents (population size) in mean-field games, an agent-centric perspective in contrast to the existing works focusing typically on the convergence of the empirical distribution of the population. To this end, the premise is to obtain the optimal policies of a set of finite-agent games with different population sizes. However, either deriving the closed-form solution for each game is theoretically intractable, training a distinct policy for each game is computationally intensive, or directly applying the policy trained in a game to other games is sub-optimal. We address these challenges through the Population-size-Aware Policy Optimization (PAPO). Our contributions are three-fold. First, to efficiently generate efficient policies for games with different population sizes, we propose PAPO, which unifies two natural options (augmentation and hypernetwork) and achieves significantly better performance. PAPO consists of three components: i) the population-size encoding which transforms the original value of population size to an equivalent encoding to avoid training collapse, ii) a hypernetwork to generate a distinct policy for each game conditioned on the population size, and iii) the population size as an additional input to the generated policy. Next, we construct a multi-task-based training procedure to efficiently train the neural networks of PAPO by sampling data from multiple games with different population sizes. Finally, extensive experiments on multiple environments show the significant superiority of PAPO over baselines, and the analysis of the evolution of the generated policies further deepens our understanding of the two fields of finite-agent and infinite-agent games.

cs.LG↗