arXiv subjects

Jie Wang

Publications and source records attributed to Jie Wang.

At least 217 records · Page 12Linked to original sources

arXiv2025

Covalently Integrated CNT@rGO for Superior Conductivity and Cycling Stability in Lithium-Ion Batterie

The limitations of conventional conductive agents in lithium-ion batteries, such as carbon black and graphite flakes, have driven the search for high-performance alternatives. Carbon nanotubes (CNTs) and graphene offer exceptional conductivity and lower dosage requirements, but face challenges related to high costs and complex fabrication processes. Here, we report a simple and cost-effective one-step chemical vapor deposition (CVD) method for the ultra-high yield growth (7692.31%) of CNTs on a reduced graphene oxide (rGO) substrate, forming a three-dimensional CNT@rGO composite with covalent integration. When employed as a conductive agent for lithium iron phosphate (LiFePO4) cathodes, the CNT@rGO composites significantly enhance rate performance across 1-6C rates, and demonstrate exceptional cycling stability, achieving 96.32% capacity retention after 300 cycles at 1C. The synergistic structure facilitates multiple conductive pathways, minimizes catalyst residue (0.52%), and ensures uniform dispersion, providing an effective and cost-efficient solution for next-generation battery technology. This study lays the foundation for the large-scale application of high-performance carbon conductive agents in battery technology.

physics.chem-ph↗

arXiv2025

Endo-4DGX: Robust Endoscopic Scene Reconstruction and Illumination Correction with Gaussian Splatting

Accurate reconstruction of soft tissue is crucial for advancing automation in image-guided robotic surgery. The recent 3D Gaussian Splatting (3DGS) techniques and their variants, 4DGS, achieve high-quality renderings of dynamic surgical scenes in real-time. However, 3D-GS-based methods still struggle in scenarios with varying illumination, such as low light and over-exposure. Training 3D-GS in such extreme light conditions leads to severe optimization problems and devastating rendering quality. To address these challenges, we present Endo-4DGX, a novel reconstruction method with illumination-adaptive Gaussian Splatting designed specifically for endoscopic scenes with uneven lighting. By incorporating illumination embeddings, our method effectively models view-dependent brightness variations. We introduce a region-aware enhancement module to model the sub-area lightness at the Gaussian level and a spatial-aware adjustment module to learn the view-consistent brightness adjustment. With the illumination adaptive design, Endo-4DGX achieves superior rendering performance under both low-light and over-exposure conditions while maintaining geometric accuracy. Additionally, we employ an exposure control loss to restore the appearance from adverse exposure to the normal level for illumination-adaptive optimization. Experimental results demonstrate that Endo-4DGX significantly outperforms combinations of state-of-the-art reconstruction and restoration methods in challenging lighting environments, underscoring its potential to advance robot-assisted surgical applications. Our code is available at https://github.com/lastbasket/Endo-4DGX.

cs.CV↗

arXiv2025

Sparse Polynomial Matrix Optimization

A polynomial matrix inequality is a formula asserting that a polynomial matrix is positive semidefinite. Polynomial matrix optimization concerns minimizing the smallest eigenvalue of a symmetric polynomial matrix subject to a tuple of polynomial matrix inequalities. This work explores the use of sparsity methods in reducing the complexity of sum-of-squares based methods in verifying polynomial matrix inequalities or solving polynomial matrix optimization. In the unconstrained setting, Newton polytopes can be employed to sparsify the monomial basis, resulting in smaller semidefinite programs. In the general setting, we show how to exploit different types of sparsity (term sparsity, correlative sparsity, matrix sparsity) encoded in polynomial matrices to derive sparse semidefinite programming relaxations for polynomial matrix optimization. For term sparsity, we show that the block structures of the term sparsity iterations with maximal chordal extensions converge to the one determined by PMI sign symmetries. For correlative sparsity, unlike the scalar case, we provide a counterexample showing that asymptotic convergence does not hold under the Archimedean condition and the running intersection property. By employing the theory of matrix-valued measures, we establish several results on detecting global optimality and retrieving optimal solutions under correlative sparsity. The effectiveness of sparsity methods on reducing computational complexity is demonstrated on various examples of polynomial matrix optimization.

math.OC↗

arXiv2025

Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias

Node representation learning on attributed graphs -- whose nodes are associated with rich attributes (e.g., texts and protein sequences) -- plays a crucial role in many important downstream tasks. To encode the attributes and graph structures simultaneously, recent studies integrate pre-trained models with graph neural networks (GNNs), where pre-trained models serve as node encoders (NEs) to encode the attributes. As jointly training large NEs and GNNs on large-scale graphs suffers from severe scalability issues, many methods propose to train NEs and GNNs separately. Consequently, they do not take feature convolutions in GNNs into consideration in the training phase of NEs, leading to a significant learning bias relative to the joint training. To address this challenge, we propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias. More importantly, we show that LD converges to the optimal objective function values by the joint training under mild assumptions. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.

cs.LG↗

arXiv2025

StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion

Voice Conversion (VC) modifies speech to match a target speaker while preserving linguistic content. Traditional methods usually extract speaker information directly from speech while neglecting the explicit utilization of linguistic content. Since VC fundamentally involves disentangling speaker identity from linguistic content, leveraging structured semantic features could enhance conversion performance. However, previous attempts to incorporate semantic features into VC have shown limited effectiveness, motivating the integration of explicit text modeling. We propose StarVC, a unified autoregressive VC framework that first predicts text tokens before synthesizing acoustic features. The experiments demonstrate that StarVC outperforms conventional VC methods in preserving both linguistic content (i.e., WER and CER) and speaker characteristics (i.e., SECS and MOS). Audio demo can be found at: https://thuhcsi.github.io/StarVC/.

cs.MM↗

arXiv2025

Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm

In speaker diarization, traditional clustering-based methods remain widely used in real-world applications. However, these methods struggle with the complex distribution of speaker embeddings and overlapping speech segments. To address these limitations, we propose an Overlapping Community Detection method based on Graph Attention networks and the Label Propagation Algorithm (OCDGALP). The proposed framework comprises two key components: (1) a graph attention network that refines speaker embeddings and node connections by aggregating information from neighboring nodes, and (2) a label propagation algorithm that assigns multiple community labels to each node, enabling simultaneous clustering and overlapping community detection. Experimental results show that the proposed method significantly reduces the Diarization Error Rate (DER), achieving a state-of-the-art 15.94% DER on the DIHARD-III dataset without oracle Voice Activity Detection (VAD), and an impressive 11.07% with oracle VAD.

cs.SD↗

arXiv2025

HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking

Recent advancements have significantly enhanced the performance of large language models (LLMs) in tackling complex reasoning tasks, achieving notable success in domains like mathematical and logical reasoning. However, these methods encounter challenges with complex planning tasks, primarily due to extended reasoning steps, diverse constraints, and the challenge of handling multiple distinct sub-tasks. To address these challenges, we propose HyperTree Planning (HTP), a novel reasoning paradigm that constructs hypertree-structured planning outlines for effective planning. The hypertree structure enables LLMs to engage in hierarchical thinking by flexibly employing the divide-and-conquer strategy, effectively breaking down intricate reasoning steps, accommodating diverse constraints, and managing multiple distinct sub-tasks in a well-organized manner. We further introduce an autonomous planning framework that completes the planning process by iteratively refining and expanding the hypertree-structured planning outlines. Experiments demonstrate the effectiveness of HTP, achieving state-of-the-art accuracy on the TravelPlanner benchmark with Gemini-1.5-Pro, resulting in a 3.6 times performance improvement over o1-preview.

cs.AI↗

arXiv2025

Strong Molecule-Light Entanglement with Molecular Cavity Optomechanics

We propose a molecular optomechanical platform to generate robust entanglement among bosonic modes-photons, phonons, and plasmons-under ambient conditions. The system integrates an ultrahigh-Q whispering-gallery-mode (WGM) optical resonator with a plasmonic nanocavity formed by a metallic nanoparticle and a single molecule. This hybrid architecture offers two critical advantages over standalone plasmonic systems: (i) Efficient redirection of Stokes photons from the lossy plasmonic mode into the long-lived WGM resonator, and (ii) Suppression of molecular absorption and approaching vibrational ground states via plasmon-WGM interactions. These features enable entanglement to transfer from the fragile plasmon-phonon subsystem to a photon-phonon bipartition in the blue-detuned regime, yielding robust stationary entanglement resilient to environmental noise. Remarkably, the achieved entanglement surpasses the theoretical bound for conventional two-mode squeezing in certain parameter regimes. Our scheme establishes a universal approach to safeguard entanglement in open quantum systems and opens avenues for noise-resilient quantum information technologies.

quant-ph↗

arXiv2025

Accelerating Large Language Model Reasoning via Speculative Search

Tree-search-based reasoning methods have significantly enhanced the reasoning capability of large language models (LLMs) by facilitating the exploration of multiple intermediate reasoning steps, i.e., thoughts. However, these methods suffer from substantial inference latency, as they have to generate numerous reasoning thoughts, severely limiting LLM applicability. To address this challenge, we propose a novel Speculative Search (SpecSearch) framework that significantly accelerates LLM reasoning by optimizing thought generation. Specifically, SpecSearch utilizes a small model to strategically collaborate with a large model at both thought and token levels, efficiently generating high-quality reasoning thoughts. The major pillar of SpecSearch is a novel quality-preserving rejection mechanism, which effectively filters out thoughts whose quality falls below that of the large model's outputs. Moreover, we show that SpecSearch preserves comparable reasoning quality to the large model. Experiments on both the Qwen and Llama models demonstrate that SpecSearch significantly outperforms state-of-the-art approaches, achieving up to 2.12$\times$ speedup with comparable reasoning quality.

cs.CL↗

arXiv2025

Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models

The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle diverse modalities such as vision, audio, and video, enabling robust reasoning across multimodal inputs remains challenging. This paper provides a systematic review of recent advances in RL-based reasoning for MLLMs, covering key algorithmic designs, reward mechanism innovations, and practical applications. We highlight two main RL paradigms, value-model-free and value-model-based methods, and analyze how RL enhances reasoning abilities by optimizing reasoning trajectories and aligning multimodal information. Additionally, we provide an extensive overview of benchmark datasets, evaluation protocols, and current limitations, and propose future research directions to address challenges such as sparse rewards, inefficient cross-modal reasoning, and real-world deployment constraints. Our goal is to provide a comprehensive and structured guide to RL-based multimodal reasoning.

cs.AI↗

arXiv2025

Ambient-pressure superconductivity onset at 10 K and robust Tc under high pressure in TiNbTaN3 medium-entropy nitride

Superconductivity has been one of the focal points in medium and high-entropy alloys (MEAs-HEAs) since the first discovery of the HEA superconductor in 2014. Until now, most HEAs' superconducting transition temperature (Tc) has not exceeded 10 K. Here we report the first observation of superconductivity in a bulk medium-entropy nitride (MEN), TiNbTaN3, which shows a Tc of 10 K at ambient pressure. Notably, the electronic specific heat coefficient γ(H) exhibits nonlinear H-dependence behavior, which is similar to other well-studied multigap superconductors. Furthermore, TiNbTaN3 exhibits extraordinary pressure resilience, maintaining robust superconductivity under high-pressure conditions. Density functional theory (DFT) calculations indicate that pressure exerts a negligible impact on the electronic structures of TiNbTaN3, thereby corroborating the experimental observations. These findings not only advance our understanding of emergent phenomena in entropy-stabilized nitrides but also establish a new material platform for finding more high-Tc superconductors with combinations of 4d/5d transition metal elements and light elements, motivating further investigations into high-entropy functional ceramics for extreme environment applications.

cond-mat.supr-con↗

arXiv2025

MAGI-1: Autoregressive Video Generation at Scale

We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates controllable generation via chunk-wise prompting and supports real-time, memory-efficient deployment by maintaining constant peak inference cost, regardless of video length. The largest variant of MAGI-1 comprises 24 billion parameters and supports context lengths of up to 4 million tokens, demonstrating the scalability and robustness of our approach. The code and models are available at https://github.com/SandAI-org/MAGI-1 and https://github.com/SandAI-org/MagiAttention. The product can be accessed at https://sand.ai.

cs.CV↗

arXiv2025

Efficient Bilinear Attention-based Fusion for Medical Visual Question Answering

Medical Visual Question Answering (MedVQA) has attracted growing interest at the intersection of medical image understanding and natural language processing for clinical applications. By interpreting medical images and providing precise answers to relevant clinical inquiries, MedVQA has the potential to support diagnostic decision-making and reduce workload across various fields like radiology. While recent approaches rely heavily on unified large pre-trained Visual-Language Models, research on more efficient fusion mechanisms remains relatively limited in this domain. In this paper, we introduce a fusion model, OMniBAN, that integrates Orthogonality loss, Multi-head attention, and a Bilinear Attention Network to achieve high computational efficiency as well as solid performance. We conduct comprehensive experiments and demonstrate how bilinear attention fusion can approximate the performance of larger fusion models like cross-modal Transformer. Our results show that OMniBAN requires fewer parameters (approximately 2/3 of Transformer-based Co-Attention) and substantially lower FLOPs (approximately 1/4), while achieving comparable overall performance and even slight improvements on closed-ended questions on two key MedVQA benchmarks. This balance between efficiency and accuracy suggests that OMniBAN could be a viable option for real-world medical image question answering, where computational resources are often constrained.

eess.IV↗

arXiv2025

CXR-AD: Component X-ray Image Dataset for Industrial Anomaly Detection

Internal defect detection constitutes a critical process in ensuring component quality, for which anomaly detection serves as an effective solution. However, existing anomaly detection datasets predominantly focus on surface defects in visible-light images, lacking publicly available X-ray datasets targeting internal defects in components. To address this gap, we construct the first publicly accessible component X-ray anomaly detection (CXR-AD) dataset, comprising real-world X-ray images. The dataset covers five industrial component categories, including 653 normal samples and 561 defect samples with precise pixel-level mask annotations. We systematically analyze the dataset characteristics and identify three major technical challenges: (1) strong coupling between complex internal structures and defect regions, (2) inherent low contrast and high noise interference in X-ray imaging, and (3) significant variations in defect scales and morphologies. To evaluate dataset complexity, we benchmark three state-of-the-art anomaly detection frameworks (feature-based, reconstruction-based, and zero-shot learning methods). Experimental results demonstrate a 29.78% average performance degradation on CXR-AD compared to MVTec AD, highlighting the limitations of current algorithms in handling internal defect detection tasks. To the best of our knowledge, CXR-AD represents the first publicly available X-ray dataset for component anomaly detection, providing a real-world industrial benchmark to advance algorithm development and enhance precision in internal defect inspection technologies.

cs.CV↗

arXiv2025

Solving Low-Rank Semidefinite Programs via Manifold Optimization

We propose a manifold optimization approach to solve linear semidefinite programs (SDP) with low-rank solutions, with an emphasis on SDP relaxations for polynomial optimization problems. This approach incorporates the inexact augmented Lagrangian method (ALM) and the Burer-Monteiro factorization, and features the self-adaptive strategies for updating the factorization size and the penalty parameter. We establish global convergence of the inexact ALM, despite the non-convexity brought by the Burer-Monteiro factorization. We further provide a practical algorithm building on the inexact ALM, and along with the algorithm we release an open-source SDP solver ManiSDP. Comprehensive numerical experiments demonstrate that ManiSDP achieves state-of-the-art in terms of efficiency, accuracy, and scalability, and is faster than several advanced SDP solvers (MOSEK, SDPLR, SDPNAL+, STRIDE) by up to orders of magnitudes on a variety of linear SDPs. The largest SDP solved by ManiSDP (in about 8.5 hours with maximal KKT residue 3.5e-13) is the second-order moment relaxation of a binary quadratic program with 120 variables, which has matrix dimension 7261 and contains 17,869,161 affine constraints.

math.OC↗

arXiv2025

SONC Optimization and Exact Nonnegativity Certificates via Second-Order Cone Programming

The second-order cone (SOC) is a class of simple convex cones and optimizing over them can be done more efficiently than with semidefinite programming. It is interesting both in theory and in practice to investigate which convex cones admit a representation using SOCs, given that they have a strong expressive ability. In this paper, we prove constructively that the cone of sums of nonnegative circuits (SONC) admits a SOC representation. Based on this, we give a new algorithm for unconstrained polynomial optimization via SOC programming. We also provide a hybrid numeric-symbolic scheme which combines the numerical procedure with a rounding-projection algorithm to obtain exact nonnegativity certificates. Numerical experiments demonstrate the efficiency of our algorithm for polynomials with fairly large degree and number of variables.

math.OC↗

arXiv2025

Exploiting Sparsity in Complex Polynomial Optimization

In this paper, we study the sparsity-adapted complex moment-Hermitian sum of squares (moment-HSOS) hierarchy for complex polynomial optimization problems, where the sparsity includes correlative sparsity and term sparsity. We compare the strengths of the sparsity-adapted complex moment-HSOS hierarchy with the sparsity-adapted real moment-SOS hierarchy on either randomly generated complex polynomial optimization problems or the AC optimal power flow problem. The results of numerical experiments show that the sparsity-adapted complex moment-HSOS hierarchy provides a trade-off between the computational cost and the quality of obtained bounds for large-scale complex polynomial optimization problems.

math.OC↗

arXiv2025

Mechanistic Modeling of Lipid Nanoparticle Formation for the Delivery of Nucleic Acid Therapeutics

Nucleic acids such as mRNA have emerged as a promising therapeutic modality with the capability of addressing a wide range of diseases. Lipid nanoparticles (LNPs) as a delivery platform for nucleic acids were used in the COVID-19 vaccines and have received much attention. While modern manufacturing processes which involve rapidly mixing an organic stream containing the lipids with an aqueous stream containing the nucleic acids are conceptually straightforward, detailed understanding of LNP formation and structure is still limited and scale-up can be challenging. Mathematical and computational methods are a promising avenue for deepening scientific understanding of the LNP formation process and facilitating improved process development and control. This article describes strategies for the mechanistic modeling of LNP formation, starting with strategies to estimate and predict important physicochemical properties of the various species such as diffusivities and solubilities. Subsequently, a framework is outlined for constructing mechanistic models of reactor- and particle-scale processes. Insights gained from the various models are mapped back to product quality attributes and process insights. Lastly, the use of the models to guide development of advanced process control and optimization strategies is discussed.

cond-mat.soft↗