arXiv subjects

Jie Wang

Publications and source records attributed to Jie Wang.

At least 181 records · Page 10Linked to original sources

arXiv2025

Robust Radar HRRP Recognition under Non-uniform Jamming Based on Complex-valued Frequency Attention Network

Complex electromagnetic environments, often containing multiple jammers with different jamming patterns, produce non-uniform jamming power across the frequency spectrum. This spectral non-uniformity directly induces severe distortion in the target's HRRP, consequently compromising the performance and reliability of conventional HRRP-based target recognition methods. This paper proposes a novel, end-to-end trained network for robust radar target recognition. The core of our model is a CFA module that operates directly on the complex spectrum of the received echo. The CFA module learns to generate an adaptive frequency-domain filter, assigning lower weights to bands corrupted by strong jamming while preserving critical target information in cleaner bands. The filtered spectrum is then fed into a classifier backbone for recognition. Experimental results on simulated HRRP data with various jamming combinations demonstrate our method's superiority. Notably, under severe jamming conditions, our model achieves a recognition accuracy nearly 9% higher than traditional model-based approaches, all while introducing negligible computational overhead. This highlights its exceptional performance and robustness in challenging jamming environments.

eess.SP↗

arXiv2025

Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework

Federated clustering addresses the critical challenge of extracting patterns from decentralized, unlabeled data. However, it is hampered by the flaw that current approaches are forced to accept a compromise between performance and privacy: \textit{transmitting embedding representations risks sensitive data leakage, while sharing only abstract cluster prototypes leads to diminished model accuracy}. To resolve this dilemma, we propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing, thus moving beyond the limitations of conventional techniques. Our framework operates on a clear client-server logic; on the client-side, each participant constructs a private structural graph that captures intrinsic data relationships, which the server then securely aggregates and aligns to form a comprehensive global graph from which a unified clustering structure is derived. The framework offers two distinct modes to suit different needs. SPP-FGC is designed as an efficient one-shot method that completes its task in a single communication round, ideal for rapid analysis. For more complex, unstructured data like images, SPP-FGC+ employs an iterative process where clients and the server collaboratively refine feature representations to achieve superior downstream performance. Extensive experiments demonstrate that our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10\% (NMI) over federated baselines while maintaining provable privacy guarantees.

cs.LG↗

arXiv2025

ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting

Recognizing symbols in architectural CAD drawings is critical for various advanced engineering applications. In this paper, we propose a novel CAD data annotation engine that leverages intrinsic attributes from systematically archived CAD drawings to automatically generate high-quality annotations, thus significantly reducing manual labeling efforts. Utilizing this engine, we construct ArchCAD-400K, a large-scale CAD dataset consisting of 413,062 chunks from 5538 highly standardized drawings, making it over 26 times larger than the largest existing CAD dataset. ArchCAD-400K boasts an extended drawing diversity and broader categories, offering line-grained annotations. Furthermore, we present a new baseline model for panoptic symbol spotting, termed Dual-Pathway Symbol Spotter (DPSS). It incorporates an adaptive fusion module to enhance primitive features with complementary image features, achieving state-of-the-art performance and enhanced robustness. Extensive experiments validate the effectiveness of DPSS, demonstrating the value of ArchCAD-400K and its potential to drive innovation in architectural design and construction.

cs.CV↗

arXiv2025

Mitigating Hallucinations in Large Language Models via Causal Reasoning

Large language models (LLMs) exhibit logically inconsistent hallucinations that appear coherent yet violate reasoning principles, with recent research suggesting an inverse relationship between causal reasoning capabilities and such hallucinations. However, existing reasoning approaches in LLMs, such as Chain-of-Thought (CoT) and its graph-based variants, operate at the linguistic token level rather than modeling the underlying causal relationships between variables, lacking the ability to represent conditional independencies or satisfy causal identification assumptions. To bridge this gap, we introduce causal-DAG construction and reasoning (CDCR-SFT), a supervised fine-tuning framework that trains LLMs to explicitly construct variable-level directed acyclic graph (DAG) and then perform reasoning over it. Moreover, we present a dataset comprising 25,368 samples (CausalDR), where each sample includes an input question, explicit causal DAG, graph-based reasoning trace, and validated answer. Experiments on four LLMs across eight tasks show that CDCR-SFT improves the causal reasoning capability with the state-of-the-art 95.33% accuracy on CLADDER (surpassing human performance of 94.8% for the first time) and reduces the hallucination on HaluEval with 10% improvements. It demonstrates that explicit causal structure modeling in LLMs can effectively mitigate logical inconsistencies in LLM outputs. Code is available at https://github.com/MrLYG/CDCR-SFT.

cs.CL↗

arXiv2025

Particle loads for cosmological simulations with equal-mass dark matter and baryonic particles

Traditional cosmological hydrodynamical simulations usually assume equal-numbered but unequal-mass dark matter and baryonic particles, which can lead to spurious collisional heating due to energy equipartition. To avoid such a numerical heating effect, a simulation setup with equal-mass dark matter and baryonic particles, which corresponds to a particle number ratio of $N_{\rm DM}:N_{\rm gas} = Ω_{\rm cdm} / Ω_{\rm b}$, is preferred. However, previous studies have typically used grid-based particle loads to prepare such initial conditions, which can only reach specific values for $N_{\rm DM}:N_{\rm gas}$ due to symmetry requirements. In this study, we propose a method based on the glass approach that can generate two-component particle loads with more general $N_{\rm DM}:N_{\rm gas}$ ratios. The method simultaneously relaxes two Poisson particle distributions by introducing an additional repulsive force between particles of the same component. We show that the final particle load closely follows the expected minimal power spectrum, $P(k) \propto k^{4}$, exhibits good homogeneity and isotropy properties, and remains sufficiently stable under gravitational interactions. Both the dark matter and gas components individually also exhibit uniform and isotropic distributions. We apply our method to two-component cosmological simulations and demonstrate that an equal-mass particle setup effectively mitigates the spurious collisional heating that arises in unequal-mass simulations. Our method can be extended to generate multi-component uniform and isotropic distributions. Our code based on Gadget-2 is available at https://github.com/liaoshong/gadget-2glass .

astro-ph.CO↗

arXiv2025

RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains

Mixed-Integer Linear Programming (MILP) is a fundamental and powerful framework for modeling complex optimization problems across diverse domains. Recently, learning-based methods have shown great promise in accelerating MILP solvers by predicting high-quality solutions. However, most existing approaches are developed and evaluated in single-domain settings, limiting their ability to generalize to unseen problem distributions. This limitation poses a major obstacle to building scalable and general-purpose learning-based solvers. To address this challenge, we introduce RoME, a domain-Robust Mixture-of-Experts framework for predicting MILP solutions across domains. RoME dynamically routes problem instances to specialized experts based on learned task embeddings. The model is trained using a two-level distributionally robust optimization strategy: inter-domain to mitigate global shifts across domains, and intra-domain to enhance local robustness by introducing perturbations on task embeddings. We reveal that cross-domain training not only enhances the model's generalization capability to unseen domains but also improves performance within each individual domain by encouraging the model to capture more general intrinsic combinatorial patterns. Specifically, a single RoME model trained on three domains achieves an average improvement of 67.7% then evaluated on five diverse domains. We further test the pretrained model on MIPLIB in a zero-shot setting, demonstrating its ability to deliver measurable performance gains on challenging real-world instances where existing learning-based approaches often struggle to generalize.

cs.LG↗

arXiv2025

Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training

Pre-training has proven effective in addressing data scarcity and performance limitations in solving PDE problems with neural operators. However, challenges remain due to the heterogeneity of PDE datasets in equation types, which leads to high errors in mixed training. Additionally, dense pre-training models that scale parameters by increasing network width or depth incur significant inference costs. To tackle these challenges, we propose a novel Mixture-of-Experts Pre-training Operator Transformer (MoE-POT), a sparse-activated architecture that scales parameters efficiently while controlling inference costs. Specifically, our model adopts a layer-wise router-gating network to dynamically select 4 routed experts from 16 expert networks during inference, enabling the model to focus on equation-specific features. Meanwhile, we also integrate 2 shared experts, aiming to capture common properties of PDE and reduce redundancy among routed experts. The final output is computed as the weighted average of the results from all activated experts. We pre-train models with parameters from 30M to 0.5B on 6 public PDE datasets. Our model with 90M activated parameters achieves up to a 40% reduction in zero-shot error compared with existing models with 120M activated parameters. Additionally, we conduct interpretability analysis, showing that dataset types can be inferred from router-gating network decisions, which validates the rationality and effectiveness of the MoE architecture.

cs.LG↗

arXiv2025

STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem

Operator eigenvalue problems play a critical role in various scientific fields and engineering applications, yet numerical methods are hindered by the curse of dimensionality. Recent deep learning methods provide an efficient approach to address this challenge by iteratively updating neural networks. These methods' performance relies heavily on the spectral distribution of the given operator: larger gaps between the operator's eigenvalues will improve precision, thus tailored spectral transformations that leverage the spectral distribution can enhance their performance. Based on this observation, we propose the Spectral Transformation Network (STNet). During each iteration, STNet uses approximate eigenvalues and eigenfunctions to perform spectral transformations on the original operator, turning it into an equivalent but easier problem. Specifically, we employ deflation projection to exclude the subspace corresponding to already solved eigenfunctions, thereby reducing the search space and avoiding converging to existing eigenfunctions. Additionally, our filter transform magnifies eigenvalues in the desired region and suppresses those outside, further improving performance. Extensive experiments demonstrate that STNet consistently outperforms existing learning-based methods, achieving state-of-the-art performance in accuracy.

cs.LG↗

arXiv2025

Deep Forward-Backward Dynamic Programming Schemes for High-Dimensional Semilinear Nonlocal PDEs and FBSDE with Jumps

We propose a new deep learning algorithm for solving high-dimensional parabolic integro-differential equations (PIDEs) and forward-backward stochastic differential equations with jumps (FBSDEJs). This novel algorithm can be viewed as an extension and generalization of the DBDP2 scheme and a dynamic programming version of the forward-backward algorithm proposed recently for high-dimensional semilinear PDEs and semilinear PIDEs, respectively. Different from the DBDP2 scheme for semilinear PDEs, our algorithm approximate simultaneously the solution and the integral kernel by deep neural networks, while the gradient of the solution is approximated by numerical differential techniques. The related error estimates for the integral kernel approximation play key roles in deriving error estimates for the novel algorithm. Numerical experiments confirm our theoretical results and verify the effectiveness of the proposed methods.

math.NA↗

arXiv2025

Accelerating IC Thermal Simulation Data Generation via Block Krylov and Operator Action

Recent advances in data-driven approaches, such as neural operators (NOs), have shown substantial efficacy in reducing the solution time for integrated circuit (IC) thermal simulations. However, a limitation of these approaches is requiring a large amount of high-fidelity training data, such as chip parameters and temperature distributions, thereby incurring significant computational costs. To address this challenge, we propose a novel algorithm for the generation of IC thermal simulation data, named block Krylov and operator action (BlocKOA), which simultaneously accelerates the data generation process and enhances the precision of generated data. BlocKOA is specifically designed for IC applications. Initially, we use the block Krylov algorithm based on the structure of the heat equation to quickly obtain a few basic solutions. Then we combine them to get numerous temperature distributions that satisfy the physical constraints. Finally, we apply heat operators on these functions to determine the heat source distributions, efficiently generating precise data points. Theoretical analysis shows that the time complexity of BlocKOA is one order lower than the existing method. Experimental results further validate its efficiency, showing that BlocKOA achieves a 420-fold speedup in generating thermal simulation data for 5000 chips with varying physical parameters and IC structures. Even with just 4% of the generation time, data-driven approaches trained on the data generated by BlocKOA exhibits comparable performance to that using the existing method.

cs.AI↗

arXiv2025

AttentionPredictor: Temporal Patterns Matter for KV Cache Compression

With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation. To compress the KV cache, recent methods identify critical KV tokens through static modeling of attention scores. However, these methods often struggle to accurately determine critical tokens as they neglect the temporal patterns in attention scores, resulting in a noticeable degradation in LLM performance. To address this challenge, we propose AttentionPredictor, which is the first learning-based method to directly predict attention patterns for KV cache compression and critical token identification. Specifically, AttentionPredictor learns a lightweight, unified convolution model to dynamically capture spatiotemporal patterns and predict the next-token attention scores. An appealing feature of AttentionPredictor is that it accurately predicts the attention score and shares the unified prediction model, which consumes negligible memory, among all transformer layers. Moreover, we propose a cross-token critical cache prefetching framework that hides the token estimation time overhead to accelerate the decoding stage. By retaining most of the attention information, AttentionPredictor achieves 13$\times$ KV cache compression and 5.6$\times$ speedup in a cache offloading scenario with comparable LLM performance, significantly outperforming the state-of-the-arts. The code is available at https://github.com/MIRALab-USTC/LLM-AttentionPredictor.

cs.CL↗

arXiv2025

OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling

Optimization modeling is one of the most crucial but technical parts of operations research (OR). To automate the modeling process, existing works have leveraged large language models (LLMs), prompting them to break down tasks into steps for generating variables, constraints, and objectives. However, due to the highly complex mathematical structures inherent in OR problems, standard fixed-step decomposition often fails to achieve high performance. To address this challenge, we introduce OptiTree, a novel tree search approach designed to enhance modeling capabilities for complex problems through adaptive problem decomposition into simpler subproblems. Specifically, we develop a modeling tree that organizes a wide range of OR problems based on their hierarchical problem taxonomy and complexity, with each node representing a problem category and containing relevant high-level modeling thoughts. Given a problem to model, we recurrently search the tree to identify a series of simpler subproblems and synthesize the global modeling thoughts by adaptively integrating the hierarchical thoughts. Experiments show that OptiTree significantly improves the modeling accuracy compared to the state-of-the-art, achieving over 10\% improvements on the challenging benchmarks. The code is released at https://github.com/MIRALab-USTC/OptiTree/tree/main.

cs.AI↗

arXiv2025

DVAGen: Dynamic Vocabulary Augmented Generation

Language models trained with a fixed vocabulary struggle to generalize to novel or out-of-vocabulary words, limiting their flexibility in handling diverse token combinations. Existing dynamic vocabulary approaches attempt to address this limitation but face challenges such as fragmented codebases, lack of support for modern LLMs, and limited inference scalability. To overcome these issues, we introduce DVAGen, a fully open-source, unified framework designed for training, evaluation, and visualization of dynamic vocabulary-augmented language models. Our framework modularizes the pipeline for ease of customization, integrates seamlessly with open-source LLMs, and is the first to provide both CLI and WebUI tools for real-time result inspection. We validate the effectiveness of dynamic vocabulary methods on modern LLMs and demonstrate support for batch inference, significantly improving inference throughput.

cs.CL↗

arXiv2025

Probabilistic Constellation Shaping for OFDM ISAC Signals Under Temporal-Frequency Filtering

Integrated sensing and communications (ISAC) is considered an innovative technology in sixth-generation (6G) wireless networks, where utilizing orthogonal frequency division multiplexing (OFDM) communication signals for sensing provides a cost-effective solution for implementing ISAC. However, the sensing performance of matched and mismatched filtering schemes can be significantly deteriorated due to the signaling randomness induced by finite-alphabet modulations with nonconstant modulus, such as quadrature amplitude modulation (QAM) constellations. Therefore, improving sensing performance without significantly compromising communication capability (i.e., maintaining randomness), remains a challenging task. To that end, we propose a unified probabilistic constellation shaping (PCS) framework that is compatible with both matched and mismatched filtering schemes, by maximizing the communication rate while imposing constraints on mean square error (MSE) of sensing channel state information (CSI), power, and probability distribution. Specifically, the MSE of sensing CSI is leveraged to optimize sensing capability, which is illustrated to be a more comprehensive metric compared to the output SNR after filtering (SNRout) and integrated sidelobes ratio (ISLR). Additionally, the internal relationships among these three sensing metrics are explicitly analyzed. Finally, both simulations and field measurements validate the efficiency of proposed PCS approach in achieving a flexible S&C trade-off, as well as its credibility in enhancing 6G wireless transmission in real-world scenarios.

eess.SP↗

arXiv2025

Logo-VGR: Visual Grounded Reasoning for Open-world Logo Recognition

Recent advances in multimodal large language models (MLLMs) have been primarily evaluated on general-purpose benchmarks, while their applications in domain-specific scenarios, such as intelligent product moderation, remain underexplored. To address this gap, we introduce an open-world logo recognition benchmark, a core challenge in product moderation. Unlike traditional logo recognition methods that rely on memorizing representations of tens of thousands of brands-an impractical approach in real-world settings-our proposed method, Logo-VGR, enables generalization to large-scale brand recognition with supervision from only a small subset of brands. Specifically, we reformulate logo recognition as a comparison-based task, requiring the model to match product images with candidate logos rather than directly generating brand labels. We further observe that existing models tend to overfit by memorizing brand distributions instead of learning robust multimodal reasoning, which results in poor performance on unseen brands. To overcome this limitation, Logo-VGR introduces a new paradigm of domain-specific multimodal reasoning: Logo Perception Grounding injects domain knowledge, and Logo-Guided Visual Grounded Reasoning enhances the model's reasoning capability. Experimental results show that Logo-VGR outperforms strong baselines by nearly 10 points in OOD settings, demonstrating superior generalization.

cs.CV↗

arXiv2025

TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback

Learning large-scale pre-trained models on broad-ranging data and then transfer to a wide range of target tasks has become the de facto paradigm in many machine learning (ML) communities. Such big models are not only strong performers in practice but also offer a promising way to break out of the task-specific modeling restrictions, thereby enabling task-agnostic and unified ML systems. However, such a popular paradigm is mainly unexplored by the recommender systems (RS) community. A critical issue is that standard recommendation models are primarily built on categorical identity features. That is, the users and the interacted items are represented by their unique IDs, which are generally not shareable across different systems or platforms. To pursue the transferable recommendations, we propose studying pre-trained RS models in a novel scenario where a user's interaction feedback involves a mixture-of-modality (MoM) items, e.g., text and images. We then present TransRec, a very simple modification made on the popular ID-based RS framework. TransRec learns directly from the raw features of the MoM items in an end-to-end training manner and thus enables effective transfer learning under various scenarios without relying on overlapped users or items. We empirically study the transferring ability of TransRec across four different real-world recommendation settings. Besides, we look at its effects by scaling source and target data size. Our results suggest that learning neural recommendation models from MoM feedback provides a promising way to realize universal RS.

cs.IR↗

arXiv2025

Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts

Evaluating the ability of large language models (LLMs) to process lengthy contexts is critical, especially for retrieving query-relevant information embedded within them. We introduce Sequential-NIAH, a benchmark specifically designed to evaluate the capability of LLMs to extract sequential information items (known as \emph{needles}) from long contexts. The benchmark includes three needle generation pipelines: synthetic-temporal, real-temporal, and real-logical orders, with context lengths ranging from 8K to 128K, which comprises 14,000 samples (2,000 for testing). To facilitate the evaluation of this benchmark, we trained an evaluation model that assesses the correctness of LLM responses by comparing their completeness and sequential consistency against the ground truth, which provides a more reliable evaluation metric than GPT-4 or Claude. We conducted experiments on six well-known LLMs, revealing that even the best-performing model achieved a maximum accuracy of only 63.50% on test set of this benchmark. Further analysis highlights the growing challenges posed by increasing the context length or the number of needles, underscoring substantial room for improvement of LLMs. Additionally, noise analysis validates the reliability and challenge of the benchmark, making Sequential-NIAH an important reference for advancing research on long text information extraction capabilities of LLMs.

cs.CL↗

arXiv2025

Highly tunable Gilbert damping in two-dimensional van der Waals ferromagnet Fe3GaTe2: From bilayer to the twisted bilayer

Van der Waals ferromagnet Fe3GaTe2 possesses both a high Curie temperature and robust perpendicular magnetic anisotropy, holding promise for practical spintronic applications. In particular, understanding and engineering its Gilbert damping which determines magnetization dynamics are crucial for its applications. Here, we investigate the Gilbert damping of bilayer and the twisted bilayer Fe3GaTe2 through first-principles calculations. For the bilayer Fe3GaTe2, we obtain a quite low Gilbert damping when its magnetization is along the z axis at room temperature. In addition, the bilayer Fe3GaTe2 exhibits a large orientational anisotropy of Gilbert damping when its magnetization is rotated from the magnetic easy axis to the hard one. Such anisotropy is attributed to the distinct band structures caused by the anisotropic spin-orbit coupling. Surprisingly, we find that twisting the bilayer Fe3GaTe2 can effectively reduce the Gilbert damping for the perpendicular magnetization, and enhance the orientational anisotropy of Gilbert damping up to 635% when rotating the magnetization from the magnetic easy axis to the hard one. These findings open up an entirely new avenue for the manipulation of Gilbert damping and its anisotropy in two-dimensional van der Waals ferromagnets.

cond-mat.mtrl-sci↗