arXiv subjects

Jie Wang

Publications and source records attributed to Jie Wang.

At least 163 records · Page 9Linked to original sources

arXiv2026

EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

Translating legacy C codebases to Rust is increasingly demanded for building safety-critical systems. While various approaches have emerged for this task, they face inherent trade-offs: rule-based methods often struggle to satisfy code safety and idiomaticity requirements, while LLM-based methods frequently fail to generate semantically equivalent Rust code, due to the heavy dependencies of modules across the entire codebase. Recent studies have revealed that both solutions are limited to small-scale programs. In this paper, we propose EvoC2Rust, an automated framework for converting complete C projects to equivalent Rust ones. EvoC2Rust employs a skeleton-guided translation strategy for project-level translation. The pipeline consists of three stages: 1) it first decomposes the C project into functional modules, employs a feature-mapping-enhanced LLM to transform definitions and macros, and generates type-checked function stubs, which form a compilable Rust skeleton; 2) it then incrementally translates functions, replacing the corresponding stub placeholders; 3) finally, it repairs compilation errors by integrating LLM and static analysis. Through evolutionary augmentation, EvoC2Rust combines the advantages of both rule-based and LLM-based solutions. Our evaluation on open-source benchmarks and six industrial projects demonstrates the superior performance of EvoC2Rust in project-level C-to-Rust translation. The results show that our approach outperforms the strongest LLM-based baseline by 17.24% in syntax accuracy and 14.32% in semantic accuracy, while also achieving a 43.59% higher code safety rate than the best rule-based tool.

cs.SE↗

arXiv2026

Evaluating Accounting Reasoning Capabilities of Large Language Models

Large language models are transforming learning, cognition, and research across many fields. Effectively integrating them into professional domains, such as accounting, is a key challenge for enterprise digital transformation. To address this, we define vertical domain accounting reasoning and propose evaluation criteria derived from an analysis of the training data characteristics of representative GLM models. These criteria support systematic study of accounting reasoning and provide benchmarks for performance improvement. Using this framework, we evaluate GLM-6B, GLM-130B, GLM-4, and OpenAI GPT-4 on accounting reasoning tasks. Results show that prompt design significantly affects performance, with GPT-4 demonstrating the strongest capability. Despite these gains, current models remain insufficient for real-world enterprise accounting, indicating the need for further optimization to unlock their full practical value.

cs.CL↗

arXiv2026

Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that rely on distillation, Youtu-LLM (1.96B) is pre-trained from scratch to systematically cultivate reasoning and planning capabilities. The key technical advancements are as follows: (1) Compact Architecture with Long-Context Support: Built on a dense Multi-Latent Attention (MLA) architecture with a novel STEM-oriented vocabulary, Youtu-LLM supports a 128k context window. This design enables robust long-context reasoning and state tracking within a minimal memory footprint, making it ideal for long-horizon agent and reasoning tasks. (2) Principled "Commonsense-STEM-Agent" Curriculum: We curated a massive corpus of approximately 11T tokens and implemented a multi-stage training strategy. By progressively shifting the pre-training data distribution from general commonsense to complex STEM and agentic tasks, we ensure the model acquires deep cognitive abilities rather than superficial alignment. (3) Scalable Agentic Mid-training: Specifically for the agentic mid-training, we employ diverse data construction schemes to synthesize rich and varied trajectories across math, coding, and tool-use domains. This high-quality data enables the model to internalize planning and reflection behaviors effectively. Extensive evaluations show that Youtu-LLM sets a new state-of-the-art for sub-2B LLMs. On general benchmarks, it achieves competitive performance against larger models, while on agent-specific tasks, it significantly surpasses existing SOTA baselines, demonstrating that lightweight models can possess strong intrinsic agentic capabilities.

cs.CL↗

arXiv2025

SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning

Matrix preconditioning is a critical technique to accelerate the solution of linear systems, where performance heavily depends on the selection of preconditioning parameters. Traditional parameter selection approaches often define fixed constants for specific scenarios. However, they rely on domain expertise and fail to consider the instance-wise features for individual problems, limiting their performance. In contrast, machine learning (ML) approaches, though promising, are hindered by high inference costs and limited interpretability. To combine the strengths of both approaches, we propose a symbolic discovery framework-namely, Symbolic Matrix Preconditioning (SymMaP)-to learn efficient symbolic expressions for preconditioning parameters. Specifically, we employ a neural network to search the high-dimensional discrete space for expressions that can accurately predict the optimal parameters. The learned expression allows for high inference efficiency and excellent interpretability (expressed in concise symbolic formulas), making it simple and reliable for deployment. Experimental results show that SymMaP consistently outperforms traditional strategies across various benchmarks.

math.NA↗

arXiv2025

GRExplainer: A Universal Explanation Method for Temporal Graph Neural Networks

Dynamic graphs are widely used to represent evolving real-world networks. Temporal Graph Neural Networks (TGNNs) have emerged as a powerful tool for processing such graphs, but the lack of transparency and explainability limits their practical adoption. Research on TGNN explainability is still in its early stages and faces several key issues: (i) Current methods are tailored to specific TGNN types, restricting generality. (ii) They suffer from high computational costs, making them unsuitable for large-scale networks. (iii) They often overlook the structural connectivity of explanations and require prior knowledge, reducing user-friendliness. To address these issues, we propose GRExplainer, the first universal, efficient, and user-friendly explanation method for TGNNs. GRExplainer extracts node sequences as a unified feature representation, making it independent of specific input formats and thus applicable to both snapshot-based and event-based TGNNs (the major types of TGNNs). By utilizing breadth-first search and temporal information to construct input node sequences, GRExplainer reduces redundant computation and improves efficiency. To enhance user-friendliness, we design a generative model based on Recurrent Neural Networks (RNNs), enabling automated and continuous explanation generation. Experiments on six real-world datasets with three target TGNNs show that GRExplainer outperforms existing baseline methods in generality, efficiency, and user-friendliness.

cs.LG↗

arXiv2025

Dark matter in ALFALFA galaxies: Investigating galaxy-halo connection

This paper aims to investigate the galaxy-halo connection using a large sample of individual galaxies with $\mathrm{H\,I}$ integrated spectra. We determine their dark matter content by applying a dynamical method based on $\mathrm{H\,I}$ line widths measured with the curve-of-growth technique, together with inclination corrections inferred from optical images. We build a sample of 2453 gas-rich predominantly late-type galaxies spanning a stellar mass range of $10^{8.7}M_\odot$ to $10^{11.4}M_\odot$ by matching them one-to-one with their counterparts from the ALFALFA survey and the TNG100 simulation, ensuring a direct match of stellar mass and $\mathrm{H\,I}$ radius. We generate mock images and mock $\mathrm{H\,I}$ integrated spectra for TNG100 galaxies, and apply the same dynamical method to both ALFALFA and TNG100 mock galaxies to infer their dark matter masses. Across all stellar mass bins, ALFALFA galaxies exhibit lower median dark matter masses than the mock TNG100 simulation results. In each bin, this offset is driven by a tail of galaxies with comparatively low dark matter content, which becomes more prominent toward higher stellar masses. In the highest mass bin ($M_* > 10^{11} M_\odot$), late-type ALFALFA galaxies show a median dark matter mass that is 23% lower than that of their counterparts in the TNG100 dark-matter-only simulation, with 32% of ALFALFA galaxies having $M_\mathrm{DM}(<R_\mathrm{HI})<10^{11.5} M_\odot$, compared to 17% in the mock TNG100 sample. These results suggest that a larger fraction of massive late-type galaxies reside in relatively less massive dark matter haloes than predicted by the TNG100 simulation.

astro-ph.GA↗

arXiv2025

Few-shot Class-incremental Fault Diagnosis by Preserving Class-Agnostic Knowledge with Dual-Granularity Representations

Few-Shot Class-Incremental Fault Diagnosis (FSC-FD), which aims to continuously learn from new fault classes with only a few samples without forgetting old ones, is critical for real-world industrial systems. However, this challenging task severely amplifies the issues of catastrophic forgetting of old knowledge and overfitting on scarce new data. To address these challenges, this paper proposes a novel framework built upon Dual-Granularity Representations, termed the Dual-Granularity Guidance Network (DGGN). Our DGGN explicitly decouples feature learning into two parallel streams: 1) a fine-grained representation stream, which utilizes a novel Multi-Order Interaction Aggregation module to capture discriminative, class-specific features from the limited new samples. 2) a coarse-grained representation stream, designed to model and preserve general, class-agnostic knowledge shared across all fault types. These two representations are dynamically fused by a multi-semantic cross-attention mechanism, where the stable coarse-grained knowledge guides the learning of fine-grained features, preventing overfitting and alleviating feature conflicts. To further mitigate catastrophic forgetting, we design a Boundary-Aware Exemplar Prioritization strategy. Moreover, a decoupled Balanced Random Forest classifier is employed to counter the decision boundary bias caused by data imbalance. Extensive experiments on the TEP benchmark and a real-world MFF dataset demonstrate that our proposed DGGN achieves superior diagnostic performance and stability compared to state-of-the-art FSC-FD approaches. Our code is publicly available at https://github.com/MentaY/DGGN

cs.LG↗

arXiv2025

Iterative Sampling Methods for Sinkhorn Distributionally Robust Optimization

Distributionally robust optimization (DRO) has emerged as a powerful paradigm for reliable decision-making under uncertainty. This paper focuses on DRO with ambiguity sets defined via the Sinkhorn discrepancy: an entropy-regularized Wasserstein distance, referred to as Sinkhorn DRO. Existing work primarily addresses Sinkhorn DRO from a dual perspective, leveraging its formulation as a conditional stochastic optimization problem, for which many stochastic gradient methods are applicable. However, the theoretical analyses of such methods often rely on the boundedness of the loss function, and it is indirect to obtain the worst-case distribution associated with Sinkhorn DRO. In contrast, we study Sinkhorn DRO from the primal perspective, by reformulating it as a bilevel program with several infinite-dimensional lower-level subproblems over probability space. This formulation enables us to simultaneously obtain the optimal robust decision and the worst-case distribution, which is valuable in practical settings, such as generating stress-test scenarios or designing robust learning algorithms. We propose both double-loop and single-loop sampling-based algorithms with theoretical guarantees to solve this bilevel program. Finally, we demonstrate the effectiveness of our approach through a numerical study on adversarial classification.

stat.ML↗

arXiv2025

A lower bound theorem for $d$-polytopes with $2d+2$ vertices

We establish a lower bound theorem for the number of $k$-faces ($1\le k\le d-2$) in a $d$-dimensional polytope $P$ (abbreviated as a $d$-polytope) with $2d+2$ vertices, extending the previously known case for $k=1$. We identify all minimisers for $d\le 5$. Two distinct lower bounds emerge, depending on the number of facets of $P$. When $P$ has precisely $d+2$ facets, the lower bound is tight when $d$ is odd. If $P$ has at least $d+3$ facets, the lower bound is always tight, and equality holds for some $1\le k\le d-2$ only when $P$ has precisely $d+3$ facets. Moreover, for $1\le k\le \ceil{d/3}-2$, the minimisers among $d$-polytopes with $2d+2$ vertices have precisely $d+3$ facets, while for $\floor{0.4d}\le k\le d-1$, the lower bound arises from $d$-polytopes with $d+2$ facets.

math.CO↗

arXiv2025

A lower bound theorem for $d$-polytopes with at most $3d-1$ vertices

We prove a lower bound theorem for the number of $k$-faces ($1\le k\le d-2$) in a $d$-dimensional polytope $P$ (or $d$-polytope) with up to $3d-1$ vertices. Previous lower bound theorems for $d$-polytopes with few vertices concern those with at most $2d$ vertices, $2d+1$ vertices, and $2d+2$ vertices. If $P$ has exactly $d+2$ facets and $2d+\ell$ vertices ($\ell\ge 1$), the lower bound is tight for certain combinations of $d$ and $\ell$. When $P$ has at least $d+3$ facets and $2d+\ell$ vertices ($\ell\ge 1$), the lower bound remains tight up to $\ell=d-1$, and equality for some $1\le k\le d-2$ is attained only when $P$ has precisely $d+3$ facets. We exhibit at least one minimiser for each number of vertices between $2d+1$ and $3d-1$, including two distinct minimisers with $2d+2$ vertices and three with $3d-2$ vertices.

math.CO↗

arXiv2025

Robust HRRP Recognition under Interrupted Sampling Repeater Jamming using a Prior Jamming Information-Guided Network

Radar automatic target recognition (RATR) based on high-resolution range profile (HRRP) has attracted increasing attention due to its ability to capture fine-grained structural features. However, recognizing targets under electronic countermeasures (ECM), especially the mainstream interrupted-sampling repeater jamming (ISRJ), remains a significant challenge, as HRRPs often suffer from serious feature distortion. To address this, we propose a robust HRRP recognition method guided by prior jamming information. Specifically, we introduce a point spread function (PSF) as prior information to model the HRRP distortion induced by ISRJ. Based on this, we design a recognition network that leverages this prior through a prior-guided feature interaction module and a hybrid loss function to enhance the model's discriminative capability. With the aid of prior information, the model can learn invariant features within distorted HRRP under different jamming parameters. Both the simulated and measured-data experiments demonstrate that our method consistently outperforms state-of-the-art approaches and exhibits stronger generalization capabilities when facing unseen jamming parameters.

eess.SP↗

arXiv2025

Strengthening and toughening mechanisms in heterostructured laminates revealed by a phase field-enhanced crystal plasticity simulation

Heterostructured (HS) materials exhibit excellent mechanical properties, combining high strength and significant ductility. Hetero-deformation-induced (HDI) hardening and strain de-localization are key to their strength-ductility synergy. However, existing models often fall short in addressing these aspects. In this work, a coupled framework integrating strain gradient crystal plasticity and phase field damage models is developed. The interface dominated HDI hardening in HS laminates is handled by introducing a heterogeneity coefficient into the back stress. The phase field model accounts for defect energy-driven damage and accurately represents the materials ductile damage behavior by accounting for effects of microstructure on crack initiation and propagation. Simulation results on HS laminates align well with experimental results and reflect the distribution of geometrically necessary dislocations and back stresses at interfaces between regions with dissimilar microstructure. Crack initiation and propagation are accurately described, providing valuable insights into fracture behavior. The model can predict how strength and ductility change upon variations of the HS laminate microstructure, thus providing an essential tool for microstructure optimization. This work enhances the understanding of deformation mechanisms in HS laminates and provides valuable insights for design and optimization of this class of materials.

cond-mat.mtrl-sci↗

arXiv2025

Real-World Reinforcement Learning of Active Perception Behaviors

A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today's standard robot learning techniques struggle to produce such active perception behaviors. We propose a simple real-world robot learning recipe to efficiently train active perception policies. Our approach, asymmetric advantage weighted regression (AAWR), exploits access to "privileged" extra sensors at training time. The privileged sensors enable training high-quality privileged value functions that aid in estimating the advantage of the target policy. Bootstrapping from a small number of potentially suboptimal demonstrations and an easy-to-obtain coarse policy initialization, AAWR quickly acquires active perception behaviors and boosts task performance. In evaluations on 8 manipulation tasks on 3 robots spanning varying degrees of partial observability, AAWR synthesizes reliable active perception behaviors that outperform all prior approaches. When initialized with a "generalist" robot policy that struggles with active perception tasks, AAWR efficiently generates information-gathering behaviors that allow it to operate under severe partial observability for manipulation tasks. Website: https://penn-pal-lab.github.io/aawr/

cs.RO↗

arXiv2025

RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies

Comprehensive, unbiased, and comparable evaluation of modern generalist policies is uniquely challenging: existing approaches for robot benchmarking typically rely on heavy standardization, either by specifying fixed evaluation tasks and environments, or by hosting centralized ''robot challenges'', and do not readily scale to evaluating generalist policies across a broad range of tasks and environments. In this work, we propose RoboArena, a new approach for scalable evaluation of generalist robot policies in the real world. Instead of standardizing evaluations around fixed tasks, environments, or locations, we propose to crowd-source evaluations across a distributed network of evaluators. Importantly, evaluators can freely choose the tasks and environments they evaluate on, enabling easy scaling of diversity, but they are required to perform double-blind evaluations over pairs of policies. Then, by aggregating preference feedback from pairwise comparisons across diverse tasks and environments, we can derive a ranking of policies. We instantiate our approach across a network of evaluators at seven academic institutions using the DROID robot platform. Through more than 600 pairwise real-robot evaluation episodes across seven generalist policies, we demonstrate that our crowd-sourced approach can more accurately rank the performance of existing generalist policies than conventional, centralized evaluation approaches, while being more scalable, resilient, and trustworthy. We open our evaluation network to the community and hope that it can enable more accessible comparisons of generalist robot policies.

cs.RO↗

arXiv2025

Exploiting Term Sparsity in Symmetry-Adapted Basis for Polynomial Optimization

Polynomial optimization problems are infinite-dimensional, nonconvex, NP-hard, and are often handled in practice with the moment-sums of squares hierarchy of semidefinite programming bounds. We consider problems where the objective function and constraint polynomials are invariant under the action of a finite group. The present paper simultaneously exploits group symmetry and term sparsity in order to reduce the computational cost of the hierarchy. We first exploit symmetry by writing the semidefinite matrices in a symmetry-adapted basis according to an isotypic decomposition. The matrices in such a basis are block diagonal. Secondly, we exploit term sparsity on each block to further reduce the optimization matrix variables. This is a non-trivial extension of the term sparsity-based hierarchy related to sign symmetry that was introduced by two of the authors. Our method is compared with existing techniques via benchmarks on quartics with dihedral, cyclic and symmetric group symmetry.

math.OC↗

arXiv2025

Visionary Co-Driver: Enhancing Driver Perception of Potential Risks with LLM and HUD

Drivers' perception of risky situations has always been a challenge in driving. Existing risk-detection methods excel at identifying collisions but face challenges in assessing the behavior of road users in non-collision situations. This paper introduces Visionary Co-Driver, a system that leverages large language models to identify non-collision roadside risks and alert drivers based on their eye movements. Specifically, the system combines video processing algorithms and LLMs to identify potentially risky road users. These risks are dynamically indicated on an adaptive heads-up display interface to enhance drivers' attention. A user study with 41 drivers confirms that Visionary Co-Driver improves drivers' risk perception and supports their recognition of roadside risks.

cs.HC↗

arXiv2025

Simultaneous variances of Pauli strings, weighted independence numbers, and a new kind of perfection of graphs

A set of Pauli stings is well characterized by the graph that encodes its commutatitivity structure, i.e., by its frustration graph. This graph provides a natural interface between graph theory and quantum information, which we explore in this work. We investigate all aspects of this interface for a special class of graphs that bears tight connections between the groundstate structures of a spin systems and topological structure of a graph. We call this class $\hbar$-perfect, as it extends the class of perfect and $h$-perfect graphs. Having an $\hbar$-perfect graph opens up several applications: we find efficient schemes for entanglement detection, a connection to the complexity of shadow tomography, tight uncertainty relations and a construction for computing good lower on bounds ground state energies. Conversely this also induces quantum algorithms for computing the independence number. Albeit those algorithms do not immediately promise an advantage in runtime, we show that an approximate Hamilton encoding of the independence number can be achieved with an amount of qubits that typically scales logarithmically in the number of vertices. We also we also determine the behavior of $\hbar$-perfectness under basic graph operations and evaluate their prevalence among all graphs.

quant-ph↗

arXiv2025

Power Delivery for Cryogenic Scalable Quantum Applications: Challenges and Opportunities

Quantum technologies offer unprecedented capabilities in computation and secure information transfer. Their implementation requires qubits to operate at cryogenic temperatures (CT) while control and readout electronics typically still remains at room temperature (RT). As systems scale to millions of qubits, the electronics should also operate at CT to avoid a wiring bottleneck. However, wired power transfer from RT for such electronics introduces severe challenges, including thermal load between cooling stages, Joule heating, noise coupling, and wiring scalability. This paper addresses those challenges by evaluating several candidate architectures for scalable power transfer in the dilution frige: high-voltage (HV) wired power transfer, radiative wireless transfer, non-radiative wireless transfer, and a hybrid HV and non-radiative transfer. These architectures are analyzed in terms of thermal load, power loss, heating, coupling noise, power density, scalability, reliability, and complexity. Comparative analysis demonstrates the trade-offs among these architectures, while highlighting HV non-radiative transfer as a promising candidate for scalable quantum systems.

eess.SY↗