arXiv subjects

Fang Liu

Publications and source records attributed to Fang Liu.

At least 109 records · Page 6Linked to original sources

arXiv2025

EfficientEdit: Accelerating Code Editing via Edit-Oriented Speculative Decoding

Large Language Models (LLMs) have demonstrated remarkable capabilities in code editing, substantially enhancing software development productivity. However, the inherent complexity of code editing tasks forces existing approaches to rely on LLMs' autoregressive end-to-end generation, where decoding speed plays a critical role in efficiency. While inference acceleration techniques like speculative decoding are applied to improve the decoding efficiency, these methods fail to account for the unique characteristics of code editing tasks where changes are typically localized and existing code segments are reused. To address this limitation, we propose EfficientEdit, a novel method that improves LLM-based code editing efficiency through two key mechanisms based on speculative decoding: (1) effective reuse of original code segments while identifying potential edit locations, and (2) efficient generate edit content via high-quality drafts from edit-oriented draft models and a dynamic verification mechanism that balances quality and acceleration. Experimental results show that EfficientEdit can achieve up to 10.38$\times$ and 13.09$\times$ speedup compared to standard autoregressive decoding in CanItEdit and CodeIF-Bench, respectively, outperforming state-of-the-art inference acceleration approaches by up to 90.6%. The code and data are available at https://github.com/zhu-zhu-ding/EfficientEdit.

cs.SE↗

arXiv2025

Explainable Fault Localization for Programming Assignments via LLM-Guided Annotation

Providing timely and personalized guidance for students' programming assignments, offers significant practical value for helping students complete assignments and enhance their learning. In recent years, various automated Fault Localization (FL) techniques have demonstrated promising results in identifying errors in programs. However, existing FL techniques face challenges when applied to educational contexts. Most approaches operate at the method level without explanatory feedback, resulting in granularity too coarse for students who need actionable insights to identify and fix their errors. While some approaches attempt line-level fault localization, they often depend on predicting line numbers directly in numerical form, which is ill-suited to LLMs. To address these challenges, we propose FLAME, a fine-grained, explainable Fault Localization method tailored for programming assignments via LLM-guided Annotation and Model Ensemble. FLAME leverages rich contextual information specific to programming assignments to guide LLMs in identifying faulty code lines. Instead of directly predicting line numbers, we prompt the LLM to annotate faulty code lines with detailed explanations, enhancing both localization accuracy and educational value. To further improve reliability, we introduce a weighted multi-model voting strategy that aggregates results from multiple LLMs to determine the suspiciousness of each code line. Extensive experimental results demonstrate that FLAME outperforms state-of-the-art fault localization baselines on programming assignments, successfully localizing 207 more faults at top-1 over the best-performing baseline. Beyond educational contexts, FLAME also generalizes effectively to general-purpose software codebases, outperforming all baselines on the Defects4J benchmark.

cs.SE↗

arXiv2025

Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy

Recent advances in deep generative modeling have unlocked unprecedented opportunities for video synthesis. In real-world applications, however, users often seek tools to faithfully realize their creative editing intentions with precise and consistent control. Despite the progress achieved by existing methods, ensuring fine-grained alignment with user intentions remains an open and challenging problem. In this work, we present Shape-for-Motion, a novel framework that incorporates a 3D proxy for precise and consistent video editing. Shape-for-Motion achieves this by converting the target object in the input video to a time-consistent mesh, i.e., a 3D proxy, allowing edits to be performed directly on the proxy and then inferred back to the video frames. To simplify the editing process, we design a novel Dual-Propagation Strategy that allows users to perform edits on the 3D mesh of a single frame, and the edits are then automatically propagated to the 3D meshes of the other frames. The 3D meshes for different frames are further projected onto the 2D space to produce the edited geometry and texture renderings, which serve as inputs to a decoupled video diffusion model for generating edited results. Our framework supports various precise and physically-consistent manipulations across the video frames, including pose editing, rotation, scaling, translation, texture modification, and object composition. Our approach marks a key step toward high-quality, controllable video editing workflows. Extensive experiments demonstrate the superiority and effectiveness of our approach. Project page: https://shapeformotion.github.io/

cs.CV↗

arXiv2025

Multimodal Learning for Fake News Detection in Short Videos Using Linguistically Verified Data and Heterogeneous Modality Fusion

The rapid proliferation of short video platforms has necessitated advanced methods for detecting fake news. This need arises from the widespread influence and ease of sharing misinformation, which can lead to significant societal harm. Current methods often struggle with the dynamic and multimodal nature of short video content. This paper presents HFN, Heterogeneous Fusion Net, a novel multimodal framework that integrates video, audio, and text data to evaluate the authenticity of short video content. HFN introduces a Decision Network that dynamically adjusts modality weights during inference and a Weighted Multi-Modal Feature Fusion module to ensure robust performance even with incomplete data. Additionally, we contribute a comprehensive dataset VESV (VEracity on Short Videos) specifically designed for short video fake news detection. Experiments conducted on the FakeTT and newly collected VESV datasets demonstrate improvements of 2.71% and 4.14% in Marco F1 over state-of-the-art methods. This work establishes a robust solution capable of effectively identifying fake news in the complex landscape of short video platforms, paving the way for more reliable and comprehensive approaches in combating misinformation.

cs.CV↗

arXiv2025

An Empirical Study on Failures in Automated Issue Solving

Automated issue solving seeks to autonomously identify and repair defective code snippets across an entire codebase. SWE-Bench has emerged as the most widely adopted benchmark for evaluating progress in this area. While LLM-based agentic tools show great promise, they still fail on a substantial portion of tasks. Moreover, current evaluations primarily report aggregate issue-solving rates, which obscure the underlying causes of success and failure, making it challenging to diagnose model weaknesses or guide targeted improvements. To bridge this gap, we first analyze the performance and efficiency of three SOTA tools, spanning both pipeline-based and agentic architectures, in automated issue solving tasks of SWE-Bench-Verified under varying task characteristics. Furthermore, to move from high-level performance metrics to underlying cause analysis, we conducted a systematic manual analysis of 150 failed instances. From this analysis, we developed a comprehensive taxonomy of failure modes comprising 3 primary phases, 9 main categories, and 25 fine-grained subcategories. Then we systematically analyze the distribution of the identified failure modes, the results reveal distinct failure fingerprints between the two architectural paradigms, with the majority of agentic failures stemming from flawed reasoning and cognitive deadlocks. Motivated by these insights, we propose a collaborative Expert-Executor framework. It introduces a supervisory Expert agent tasked with providing strategic oversight and course-correction for a primary Executor agent. This architecture is designed to correct flawed reasoning and break the cognitive deadlocks that frequently lead to failure. Experiments show that our framework solves 22.2% of previously intractable issues for a leading single agent. These findings pave the way for building more robust agents through diagnostic evaluation and collaborative design.

cs.SE↗

arXiv2025

Enhanced second-harmonic generation from WS$_2$/ReSe$_2$ heterostructure

Van der Waals stacking presents new opportunities for nonlinear optics with its remarkable tunability and scalability. However, the fundamental role of interlayer interactions in modifying the overall nonlinear optical susceptibilities remains elusive. In this letter, we report an anisotropic enhancement of second-harmonic generation (SHG) from a WS$_2$/ReSe$_2$ heterobilayer, where the individual composite layers possess distinctive crystal phases. We investigate polarization-resolved response and twist-angle dependence in SHG and reveal that band alignment alone is insufficient to explain the observed anisotropy in the modified SHG response. Spectral shifts in excitonic features highlight band renormalization, supporting the role of hybridization between the two layers. Furthermore, SHG enhancement is highly anisotropic and can even be suppressed in some orientations, suggesting possible intensity-borrowing mechanisms within the heterostructure. Our work demonstrates the ability to tune both the intensity and polarization dependence of nonlinear optical responses with van der Waals stacking of distinctive crystal phases.

cond-mat.mtrl-sci↗

arXiv2025

Asymmetric stress engineering of dense dislocations in brittle superconductors for strong vortex pinning

Large lossless currents in high-temperature superconductors (HTS) critically rely on dense defects with suitable size and dimensionality to pin vortices, with dislocations being particularly effective due to their one-dimensional geometry to interact extensively with vortex lines. However, in non-metallic compounds such as HTS with rigid lattices, conventional deformation methods typically lead to catastrophic fracture rather than dislocation-mediated plasticity, making it a persistent challenge to introduce dislocations at high density. Here, we propose an asymmetric stress field strategy using extrusion to directly nucleate a high-density of dislocations in HTS by activating shear-driven lattice slip and twisting under superimposed hydrostatic compression. As demonstrated in iron-based superconductors (IBS), atomic displacements of nearly one angstrom trigger the formation of tilted dislocation lines with a density approaching that of metals. With further structural refinement, these dislocations serve as strong pinning centers that lead to a fivefold enhancement in the current-carrying capacity of IBS at 33 T, along with low anisotropy and a large irreversibility field. This work not only establishes a scalable route to engineer pinning landscapes in HTS, but also offers a generalizable framework for manipulating dislocation structures in rigid crystalline systems.

cond-mat.supr-con↗

arXiv2025

OmniMRI: A Unified Vision--Language Foundation Model for Generalist MRI Interpretation

Magnetic Resonance Imaging (MRI) is indispensable in clinical practice but remains constrained by fragmented, multi-stage workflows encompassing acquisition, reconstruction, segmentation, detection, diagnosis, and reporting. While deep learning has achieved progress in individual tasks, existing approaches are often anatomy- or application-specific and lack generalizability across diverse clinical settings. Moreover, current pipelines rarely integrate imaging data with complementary language information that radiologists rely on in routine practice. Here, we introduce OmniMRI, a unified vision-language foundation model designed to generalize across the entire MRI workflow. OmniMRI is trained on a large-scale, heterogeneous corpus curated from 60 public datasets, over 220,000 MRI volumes and 19 million MRI slices, incorporating image-only data, paired vision-text data, and instruction-response data. Its multi-stage training paradigm, comprising self-supervised vision pretraining, vision-language alignment, multimodal pretraining, and multi-task instruction tuning, progressively equips the model with transferable visual representations, cross-modal reasoning, and robust instruction-following capabilities. Qualitative results demonstrate OmniMRI's ability to perform diverse tasks within a single architecture, including MRI reconstruction, anatomical and pathological segmentation, abnormality detection, diagnostic suggestion, and radiology report generation. These findings highlight OmniMRI's potential to consolidate fragmented pipelines into a scalable, generalist framework, paving the way toward foundation models that unify imaging and clinical language for comprehensive, end-to-end MRI interpretation.

cs.CV↗

arXiv2025

Domain-aware Category-level Geometry Learning Segmentation for 3D Point Clouds

Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global geometric patterns in point clouds while ignoring the category-level distribution and alignment. In this paper, a category-level geometry learning framework is proposed to explore the domain-invariant geometric features for domain generalized 3D semantic segmentation. Specifically, Category-level Geometry Embedding (CGE) is proposed to perceive the fine-grained geometric properties of point cloud features, which constructs the geometric properties of each class and couples geometric embedding to semantic learning. Secondly, Geometric Consistent Learning (GCL) is proposed to simulate the latent 3D distribution and align the category-level geometric embeddings, allowing the model to focus on the geometric invariant information to improve generalization. Experimental results verify the effectiveness of the proposed method, which has very competitive segmentation accuracy compared with the state-of-the-art domain generalized point cloud methods.

cs.CV↗

arXiv2025

AutoPLC: Generating Vendor-Aware Structured Text for Programmable Logic Controllers

Among the programming languages for Programmable Logic Controllers (PLCs), Structured Text (ST) is widely adopted for industrial automation due to its expressiveness and flexibility. However, major vendors implement ST with proprietary extensions and hardware-specific libraries - Siemens' SCL and CODESYS' ST each differ in syntax and functionality. This fragmentation forces engineers to relearn implementation details across platforms, creating substantial productivity barriers. To address this challenge, we developed AutoPLC, a framework capable of automatically generating vendor-aware ST code directly from natural language requirements. Our solution begins by building two essential knowledge sources tailored to each vendor's specifications: a structured API library containing platform-exclusive functions, and an annotated case database that captures real-world implementation experience. Building on these foundations, we created a four-stage generation process that combines step-wise planning (enhanced with a lightweight natural language state machine support for control logic), contextual case retrieval using LLM-based reranking, API recommendation guided by industrial data, and dynamic validation through direct interaction with vendor IDEs. Implemented for Siemens TIA Portal and the CODESYS platform, AutoPLC achieves 90%+ compilation success on our 914-task benchmark (covering general-purpose and process control functions), outperforming all selected baselines, at an average cost of only $0.13 per task. Experienced PLC engineers positively assessed the practical utility of the generated code, including cases that failed compilation. We open-source our framework at https://github.com/cangkui/AutoPLC.

cs.SE↗

arXiv2025

Accelerating multiparametric quantitative MRI using self-supervised scan-specific implicit neural representation with model reinforcement

Purpose: To develop a self-supervised scan-specific deep learning framework for reconstructing accelerated multiparametric quantitative MRI (qMRI). Methods: We propose REFINE-MORE (REference-Free Implicit NEural representation with MOdel REinforcement), combining an implicit neural representation (INR) architecture with a model reinforcement module that incorporates MR physics constraints. The INR component enables informative learning of spatiotemporal correlations to initialize multiparametric quantitative maps, which are then further refined through an unrolled optimization scheme enforcing data consistency. To improve computational efficiency, REFINE-MORE integrates a low-rank adaptation strategy that promotes rapid model convergence. We evaluated REFINE-MORE on accelerated multiparametric quantitative magnetization transfer imaging for simultaneous estimation of free water spin-lattice relaxation, tissue macromolecular proton fraction, and magnetization exchange rate, using both phantom and in vivo brain data. Results: Under 4x and 5x accelerations on in vivo data, REFINE-MORE achieved superior reconstruction quality, demonstrating the lowest normalized root-mean-square error and highest structural similarity index compared to baseline methods and other state-of-the-art model-based and deep learning approaches. Phantom experiments further showed strong agreement with reference values, underscoring the robustness and generalizability of the proposed framework. Additionally, the model adaptation strategy improved reconstruction efficiency by approximately fivefold. Conclusion: REFINE-MORE enables accurate and efficient scan-specific multiparametric qMRI reconstruction, providing a flexible solution for high-dimensional, accelerated qMRI applications.

physics.med-ph↗

arXiv2025

Extreme Thermal Insulation in Nano-Bubble Wrap Materials

Achieving ultra-low thermal conductivity under ambient conditions is a fundamental challenge constrained by classical heat transport limits and material design trade-offs. Here, we introduce a new class of nano-bubble wrap architectures that achieve exceptionally low thermal conductivity by integrating nanoscale gas confinement with atomically thin, weakly coupled van der Waals solids. Using scalable patterning of 2D monolayers into periodic nano-bubbles and nano-wrinkles, we construct materials with structural analogies to macroscopic bubble wrap but engineered at length scales much shorter than the mean free path of air and the mean free path of phonons in the atomically thin monolayers. Time-domain thermoreflectance measurements reveal out-of-plane thermal conductivities nearly an order of magnitude lower than that of air and commercial aerogels, reaching critical values below 0.001 W $\cdot$ M$^{-1}$K$^{-1}$ under room temperature and atmospheric pressure. This extreme thermal resistance arises from the combined suppression of gas-phase conduction, phonon transport, and interfacial coupling. Our findings establish nano-bubble wraps as a versatile platform for tuning heat flow in ultrathin materials and open new pathways for designing thermal metamaterials and energy-efficient technologies.

cond-mat.mtrl-sci↗

arXiv2025

GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting

We introduce GaussianOcc, a systematic method that investigates the two usages of Gaussian splatting for fully self-supervised and efficient 3D occupancy estimation in surround views. First, traditional methods for self-supervised 3D occupancy estimation still require ground truth 6D poses from sensors during training. To address this limitation, we propose Gaussian Splatting for Projection (GSP) module to provide accurate scale information for fully self-supervised training from adjacent view projection. Additionally, existing methods rely on volume rendering for final 3D voxel representation learning using 2D signals (depth maps, semantic maps), which is both time-consuming and less effective. We propose Gaussian Splatting from Voxel space (GSV) to leverage the fast rendering properties of Gaussian splatting. As a result, the proposed GaussianOcc method enables fully self-supervised (no ground truth pose) 3D occupancy estimation in competitive performance with low computational cost (2.7 times faster in training and 5 times faster in rendering). The relevant code is available in https://github.com/GANWANSHUI/GaussianOcc.git.

cs.CV↗

arXiv2025

AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning

Fine-tuning large language models (LLMs) for specific tasks requires diverse, high-quality training data. However, obtaining sufficient relevant data remains a significant challenge. Existing data synthesis methods either depend on extensive seed datasets or struggle to balance task relevance and data diversity. To address these challenges, we propose Attribute-guided multI-hop Data Expansion (AIDE), a novel data synthesis framework that uses a multi-hop process to expand very few seed data points while ensuring data diversity and task relevance. AIDE extracts the main topic and key knowledge attributes from the seeds to guide the synthesis steps. The process repeats for K hops, using the generated data as seeds. To prevent irrelevant data generation as the hop depth increases, AIDE incorporates a residual connection mechanism. Our empirical results show that AIDE enables fine-tuning of Mistral-7B, Llama-3.1-8B and Llama-3.2-3B from 10 seeds, surpassing the models fine-tuned on human curated data. Furthermore, AIDE outperforms state-of-the-art data synthesis methods, such as Evol-Instruct, by over 30% in task-specific fine-tuning. Code is available at https://github.com/Code4Graph/AIDE.

cs.CL↗

arXiv2025

Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation

Large language models (LLMs) have demonstrated impressive performance in code generation, particularly when augmented with chain-of-thought (CoT) prompting techniques. They break down requirements into intermediate reasoning steps, which act as design rationales to guide LLMs in writing code like human programmers. Thus, the quality of these steps is crucial for ensuring the correctness and reliability of the generated code. However, little is known about the quality of CoT generated by LLMs. To what extent can we trust the thoughts generated by LLMs? How good are they? This paper empirically explores the external and internal factors of why LLMs generate unsatisfactory CoTs by analyzing 1,023 failed code samples on two widely used code generation benchmarks. We also evaluate their impact on code generation performance by analyzing 210 CoT-code pairs and refining the unsatisfied CoTs by prompting LLMs. Our study reveals three key findings: (1) External factors (53.60%), such as unclear requirements and lack of context, mainly affect CoT quality, while internal factors (40.10%) stem from LLMs' misunderstanding prompts. (2) Even when CoTs are correct, 18.5% of the generated code contains errors due to instruction-following issues; conversely, 11.90% of correct code is paired with flawed CoTs. (3) Refining low-quality CoTs is feasible, i.e., LLMs improve when given detailed problem descriptions. These findings highlight key challenges in CoT-based code generation and suggest directions for improving LLM reasoning and reliability.

cs.SE↗

arXiv2025

Riemannian Complex Hermit Positive Definite Convolution Network for Polarimetric SAR Image Classification

Deep learning has been extensively utilized for PolSAR image classification. However, most existing methods transform the polarimetric covariance matrix into a real- or complex-valued vector to comply with standard deep learning frameworks in Euclidean space. This approach overlooks the inherent structure of the covariance matrix, which is a complex Hermitian positive definite (HPD) matrix residing in the Riemannian manifold. Vectorization disrupts the matrix structure and misrepresents its geometric properties. To mitigate this drawback, we propose HPDNet, a novel framework that directly processes HPD matrices on the Riemannian manifold. The HPDnet fully considers the complex phase information by decomposing a complex HPD matrix into the real- and imaginarymatrices. The proposed HPDnet consists of several HPD mapping layers and rectifying layers, which can preserve the geometric structure of the data and transform them into a more separable manifold representation. Subsequently, a complex LogEig layer is developed to project the manifold data into a tangent space, ensuring that conventional Euclidean-based deep learning networks can be applied to further extract contextual features for classification. Furthermore, to optimize computational efficiency, we design a fast eigenvalue decomposition method for parallelized matrix processing. Experiments conducted on three real-world PolSAR datasets demonstrate that the proposed method outperforms state-of-the-art approaches, especially in heterogeneous regions.

cs.CV↗

arXiv2025

Determining the complex second-order optical susceptibility in macroscale van der Waals heterobilayers

We report on the experimental characterization of the second-order susceptibility in MoSe$_2$/WS$_2$ heterobilayers, including their hidden complex phases. To this end, we developed a heterodyne-detection scheme for second-harmonic generation and applied it to macroscale heterobilayer samples prepared using the gold-tape exfoliation method. The heterodyne scheme enabled us to distinguish the relative orientation of the crystal domains, and further, it allowed us to characterize the complex phases of the susceptibility relative to a reference quartz sample. By comparing the results from the monolayer regions and the heterobilayer region over several hundred microns of the sample area, we determined that the contribution of interlayer effects to second-harmonic generation is within the experimental uncertainty arising from the sample inhomogeneity. The results here provide fundamental quantitative information necessary for the precise design of nanophotonic systems based on stacking engineering.

cond-mat.mtrl-sci↗

arXiv2025

PRECISE: PRivacy-loss-Efficient and Consistent Inference based on poSterior quantilEs

Differential Privacy (DP) is a mathematical framework for releasing information with formal privacy guarantees. While numerous DP procedures have been developed for statistical analysis and machine learning, valid statistical inference methods offering high utility under DP constraints remain limited. We formalize this gap by introducing the notion of valid Privacy-Preserving Interval Estimation (PPIE) and propose a new PPIE approach -- PRECISE -- to constructing privacy-preserving posterior intervals with the goal of offering a better privacy-utility tradeoff than existing DP inferential methods. PRECISE is a general-purpose and model-agnostic method that generates intervals using quantile estimates obtained from a sanitized posterior histogram with DP guarantees. We explicitly characterize the global sensitivity of the histogram formed from posterior samples for the parameter of interest, enabling its sanitization with formal DP guarantees. We also analyze the sources of error in the mean squared error (MSE) of the histogram-based private quantile estimator and prove its consistency for the true posterior quantiles as the sample size or privacy loss increases with along with its rate of convergence. We conduct extensive experiments to compare the utilities of PRECISE with common existing privacy-preserving inferential approaches across a wide range of inferential tasks, data types and sizes, DP types, and privacy loss levels. The results demonstrated a significant advantage of PRECISE with its nominal coverage and substantially narrower intervals than the existing methods, which are prone to either under-coverage or impractically wide intervals.

stat.ME↗