arXiv subjects

Junliang Liu

Publications and source records attributed to Junliang Liu.

At least 19 recordsLinked to original sources

arXiv2026

Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents

LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design exposes two sequential control points to untrusted publishers: a static skill may steer an otherwise correct task onto an unnecessarily costly trajectory. Prior work studies selection manipulation, malicious skill instructions, and tool-chain resource amplification largely separately, leaving their end-to-end composition unclear. We introduce Convergent Detour Hijacking (CDH), a text-only, runtime-independent attack that couples these stages. Under shared semantic cover, a description establishes relevance during selection, while an aligned body reuses that rationale to fabricate plausible dependencies during planning. CDH attracts an attacker-controlled coordinator alongside legitimate skills, recruits unnecessary benign skills into a bounded detour, and then re-enters the original route to preserve task completion. We evaluate it across multiple LLM backends and 491 held-out tasks under single-task and multi-turn conditions. On DeepSeek-V4-Pro, the matched coordinator is selected in 80.02% of tasks; among coordinator-hit runs that complete tasks, token consumption and end-to-end execution time increase by 66.91% and 92.45%, respectively, while aggregate task completion remains comparable. Thus, correct outcomes do not guarantee trajectory integrity or cost safety.

cs.CR↗

arXiv2026

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding

Rendering source code as images offers a promising way to reduce the input costs of Multimodal Large Language Models (MLLMs). Adjusting image resolution can trade visual token cost against content fidelity. However, resolution scaling alone overlooks two sources of inefficiency: blank regions created by line breaks and indentation, and code regions irrelevant to the current instruction. Moreover, the best compression setting varies across inputs, tasks, and models, limiting fixed-ratio strategies. We propose CodeShrink, an adaptive visual compression framework with three components. Blank-Free Rendering replaces whitespace-dependent layouts with compact layouts and explicit structural markers, removing layout-induced tokens. Adaptive Compression Configuration uses a lightweight agent trained with reinforcement learning to predict a per-input setting that balances token efficiency and readability. Dominant Token Selection jointly analyzes the instruction and code image to prune task-irrelevant visual tokens during inference. We evaluate CodeShrink on code question answering, clone detection, and code completion. CodeShrink reduces visual token use by up to 71.2\% while matching or exceeding uncompressed text-only inputs, and consistently outperforms text-based and visual compression baselines across all three tasks. These results show that combining layout compaction, adaptive configuration, and instruction-aware pruning can make multimodal code understanding more efficient. Our code is available at https://github.com/vinsontang1/CodeShrink.

cs.CV↗

arXiv2026

Doppler-shifted X-ray Spectroscopy of Nonradiative Electron Capture in Relativistic Collisions of Xe54+ Ions with Kr and Xe Atoms

We present an angular-resolved Doppler spectroscopy study of nonradiative electron capture in relativistic collisions of bare Xe54+ ions with Kr and Xe gas targets at the HIRFL-CSR storage ring. The energy spectra and angular distributions of X-rays emitted from fast-moving down-charged projectiles were measured at five observation angles of 35{\deg}, 60{\deg}, 90{\deg}, 120{\deg}, and 145{\deg} and three collision energies of 95, 146, and 197 MeV/u by employing the effect of Doppler shift. The transition intensities of Xe53+ ions with small energy differences were precisely determined. In symmetric Xe54+ \to Xe collisions, the transition intensities of Xe53+ and Xe52+ ions were identified when X-rays emitted by projectiles overlapped with K X-rays arising from target ionization. The anisotropy parameters of the K{\alpha_1}(+M2) transition were derived from the angular emission patterns of the corresponding spectral lines. The relative populations of the L, M, and N-shell excited levels of Xe53+ and Xe52+ were further deduced from the intensity ratios of I(Ly-{\beta})/I(Ly-{\alpha}), I(Ly-{\gamma})/I(Ly-{\alpha}), and I(K{\alpha})/I(Ly-{\alpha}). The energy dependence of the population of excited projectile levels was obtained for both targets. Furthermore, the experimental results were compared with theoretical calculations of nonradiative single- and double-electron capture based on the relativistic eikonal approximation and the independent-electron approximation. These findings provide valuable insights into the magnetic-sublevel population and n-resolved state-selective population of excited states produced in relativistic collisions of highly charged heavy ions with multi-electron atoms.

physics.atom-ph↗

arXiv2026

Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions

The source distribution in conditional flow matching is a design parameter that can be calibrated to data, not a default isotropic prior. We exploit this in Multi-Fidelity Flow Matching (MFFM), a cascade refinement framework for parametric PDE solutions: the source is calibrated to the empirical low-to-high-fidelity residual scale with local Gaussian-blur correlation, and the velocity network is conditioned on the low-fidelity solution. Conditioning makes the residual refinement problem substantially easier than unconditional field generation, while residual-calibrated source noise improves the flow-matching training geometry. A multi-resolution cascade applies the same construction independently between adjacent fidelities. After level-wise flow-matching pretraining, we fine-tune the composed cascade end-to-end with a deterministic one-step rollout, which makes one velocity evaluation per cascade level the optimized operating point at inference. The result is a learned analog of multigrid refinement that reaches the finest grid in $L$ deterministic network evaluations per query. We validate MFFM on eight benchmarks: two super-resolution problems and six spatiotemporal forecasting tasks from PDEBench, The Well, and the FNO Navier--Stokes dataset.

cs.LG↗

arXiv2026

VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

Automated vulnerability detection is a fundamental task in software security, yet existing learning-based methods still struggle to capture the structural dependencies, domain-specific vulnerability knowledge, and complex program semantics required for accurate detection. Recent Large Language Models (LLMs) have shown strong code understanding ability, but directly prompting them with raw source code often leads to missed vulnerabilities or false alarms, especially when vulnerable and benign functions differ only in subtle semantic details. To address this, we propose VulTriage, a triple-path context augmentation framework for LLM-based vulnerability detection. VulTriage enhances the LLM input through three complementary paths: a Control Path that extracts and verbalizes AST, CFG, and DFG information to expose control and data dependencies; a Knowledge Path that retrieves relevant CWE-derived vulnerability patterns and examples through hybrid dense--sparse retrieval; and a Semantic Path that summarizes the functional behavior of the code before the final judgment. These contexts are integrated into a unified instruction to guide the LLM toward more reliable vulnerability reasoning. Experiments on the PrimeVul pair test set show that VulTriage achieves state-of-the-art performance, outperforming existing deep learning and LLM-based baselines on key pair-wise and classification metrics. Further ablation studies verify the effectiveness of each path, and additional experiments on the Kotlin dataset demonstrate the generalization ability of VulTriage under low-resource and class-imbalanced settings. Our code is available at https://github.com/vinsontang1/VulTriage

cs.AI↗

arXiv2026

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

Software vulnerability detection plays a critical role in ensuring system security, where real-world auditing requires not only determining whether a function is vulnerable but also pinpointing the specific lines responsible. However, existing approaches either rely on a single information source -- sequential, structural, or semantic -- failing to jointly exploit the complementary strengths across modalities, or treat statement-level localization merely as a byproduct of function-level detection without explicit line-level supervision. To address these limitations, we propose DCVD (Dual-Channel Cross-Modal Vulnerability Detection), a unified framework that performs joint function-level detection and statement-level localization. DCVD extracts control-dependency and semantic features through two parallel branches and integrates them via contrastive alignment coupled with bidirectional cross-attention, effectively bridging the cross-modal representation gap. It further introduces explicit supervision signals at both the function and statement levels, enabling collaborative optimization across the two granularities. Extensive experiments on a large-scale real-world vulnerability benchmark demonstrate that DCVD consistently outperforms state-of-the-art methods on both function-level detection and statement-level localization. Our code is available at https://github.com/vinsontang1/DCVD.

cs.CR↗

arXiv2026

Angular distribution of K{\alpha} x rays following nonradiative double electron capture in relativistic collisions of Xe54+ ions with Kr and Xe atoms

We present experimental study of nonradiative double electron capture processes in collisions of 95 and 146 MeV/u bare xenon ions with krypton and xenon gaseous atoms at the HIRFL-CSR storage ring. Angular distributions of the characteristic K{\alpha} radiation of the down-charged projectile ions Xe52+* are measured, which are closely related to the magnetic sublevel population of the excited 1s2l_j states of Xe52+*. It was found that the K{\alpha}1 radiation shows pronounced anisotropic and is sensitive to the collision energies and the target atoms, whereas the K{\alpha}2 radiation gives rise to isotropic. Moreover, obviously difference in the anisotropy parameters of Lyman-{\alpha}1 of Xe53+* ions and K{\alpha} transitions of Xe52+* ions separately following nonradiative single and double electron capture into the L-shell levels of projectiles is obtained and discussed.

physics.atom-ph↗

arXiv2026

EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection

Automated academic poster generation aims to distill lengthy research papers into concise, visually coherent presentations. Existing Multimodal Large Language Models (MLLMs) based approaches, however, suffer from three critical limitations: low information density in full-paper inputs, excessive token consumption, and unreliable layout verification. We present EfficientPosterGen, an end-to-end framework that addresses these challenges through semantic-aware retrieval and token-efficient multimodal generation. EfficientPosterGen introduces three core innovations: (1) Semantic-aware Key Information Retrieval (SKIR), which constructs a semantic contribution graph to model inter-segment relationships and selectively preserves important content; (2) Visual-based Context Compression (VCC), which renders selected text segments into images to shift textual information into the visual modality, significantly reducing token usage while generating poster-ready bullet points; and (3) Agentless Layout Violation Detection (ALVD), a deterministic color-gradient-based algorithm that reliably detects content overflow and spatial sparsity without auxiliary MLLMs. Extensive experiments demonstrate that EfficientPosterGen achieves substantial improvements in token efficiency and layout reliability while maintaining high poster quality, offering a scalable solution for automated academic poster generation. Our code is available at https://github.com/vinsontang1/EfficientPosterGen-Code.

cs.CV↗

arXiv2026

Charge redistribution at metal-ZrO2 interfaces: A combined DFT and continuum electrostatic study

Nanoscale metallic inclusions (NMIs) are commonly observed within oxide scales formed during high-temperature oxidation, revealing the existence of chemical and electronic heterogeneity beyond conventional corrosion theories that assume homogeneous, fully oxidized films. Using tetragonal zirconia (tZrO2) facing a series of face-centered cubic (fcc) metals as the model system, this work investigates the short-range and long-range charge redistributions across metal-oxide interfaces by coupling density functional theory (DFT) calculations with continuum modeling. We show that metal-oxide contact induces a short-range charge redistribution confined to a few atomic layers and a long-range redistribution of space charge that can extend over macroscopic distances within weakly doped oxides. DFT calculations show that the short-range redistribution is dominated by metal induced gap states (MIGS) in tZrO2 facing noble metals like Au and Ag, and by chemical bonding in tZrO2 facing active metals like Al. DFT-informed continuum theoretical analysis shows that the range of space-charge redistribution is governed by the doping level of tZrO2, and that the Schottky barrier height (SBH) exhibits a stronger dependence on the metal work function than the doping level. Both the short-range and long-range charge redistributions can alter the transport of charge carriers via their associated electric fields, extending several nm to hundreds of nm from the interface, depending on the doping concentrations, suggesting possible heterogeneous oxide growth caused by NMIs.

cond-mat.mtrl-sci↗

arXiv2026

Mapping optical, chemical, structural features in ZrO2 via cross-sectional SEM-Cathodoluminescence correlation microscopy

Understanding how nanoscale heterogeneities influence charge transport and mass transfer in oxides is critical for developing advanced materials for energy and electronic uses. In high-temperature applications, the formation of thermal oxides with complex chemical and structural features plays a central role in material lifetime. While thermally grown zirconia (ZrO2) on zirconium alloys exhibits strong chemical and microstructural gradients across the oxide thickness, linking these heterogeneities to electronic-defect landscapes remains challenging. We demonstrate cross-sectional scanning electron microscope-cathodoluminescence (SEM-CL) as a mesoscale probe of spatial variations in luminescence in zirconia and establish correlations with co-registered electron backscatter diffraction (EBSD) and electron probe micro-analysis (EPMA) on the same region. The SEM-CL signal is dominated by the ~2.7 eV defect band, but its intensity varies strongly across the oxide cross section. Correlative EBSD-CL analysis reveals that CL intensity increases with grain area and decreases at the grain boundaries, consistent with enhanced non-radiative recombination associated with microstructural disorder. EPMA mapping shows that a substantial fraction of CL-dark features co-localize with secondary phase precipitates enriched in iron. These results show that SEM-CL contrast in corrosion-grown ZrO2 is controlled by both chemical heterogeneity and microstructural disorder, underscoring the need for correlative registration to interpret CL images. This multi-modal approach provides an efficient route to connect electronic properties and luminescence signatures across complex oxide cross sections to underlying chemistry and microstructure, thereby providing a pathway to relate local defect landscapes to regions likely to bias electronic/ionic transport during oxidation.

cond-mat.mtrl-sci↗

arXiv2025

Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety

Multimodal large language models (MLLMs) are increasingly deployed as the core reasoning engine for web-facing systems, powering GUI agents and front-end automation that must interpret page structure, select actionable widgets, and execute multi-step interactions reliably. However, existing benchmarks largely emphasize visual perception or UI code generation, showing insufficient evaluation on the reasoning, robustness and safety capability required for end-to-end web applications. To bridge the gap, we introduce a comprehensive web understanding benchmark, named WebRRSBench, that jointly evaluates Reasoning, Robustness, and Safety across eight tasks, such as position relationship reasoning, color robustness, and safety critical detection, etc. The benchmark is constructed from 729 websites and contains 3799 QA pairs that probe multi-step inference over page structure, text, widgets, and safety-critical interactions. To ensure reliable measurement, we adopt standardized prompts, a protocolized and deterministic evaluation pipeline, and multi-stage quality control combining automatic checks with targeted human verification. We evaluate 11 MLLMs on WebRRSBench. The results reveal significant gaps: models still struggle with compositional and cross-element reasoning over realistic layouts, show limited robustness when facing perturbations in user interfaces and content such as layout rearrangements or visual style shifts, and are rather conservative in recognizing and avoiding safety critical or irreversible actions. Our code and appendix are available at https: //github.com/annoy-worker/WebRSSBench.

cs.AI↗

arXiv2025

SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design

Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural nuances of slide designs. To address this, we formalize the Reference Image to Slide Generation task and propose Slide2Code, the first benchmark with difficulty-tiered samples based on a novel Slide Complexity Metric. We introduce SlideCoder, a layout-aware, retrieval-augmented framework for generating editable slides from reference images. SlideCoder integrates a Color Gradient-based Segmentation algorithm and a Hierarchical Retrieval-Augmented Generation method to decompose complex tasks and enhance code generation. We also release SlideMaster, a 7B open-source model fine-tuned with improved reverse-engineered data. Experiments show that SlideCoder outperforms state-of-the-art baselines by up to 40.5 points, demonstrating strong performance across layout fidelity, execution accuracy, and visual consistency. Our code is available at https://github.com/vinsontang1/SlideCoder.

cs.CV↗

arXiv2025

DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in automated front-end engineering, e.g., generating UI code from visual designs. However, existing front-end UI code generation benchmarks have the following limitations: (1) While framework-based development becomes predominant in modern front-end programming, current benchmarks fail to incorporate mainstream development frameworks. (2) Existing evaluations focus solely on the UI code generation task, whereas practical UI development involves several iterations, including refining editing, and repairing issues. (3) Current benchmarks employ unidimensional evaluation, lacking investigation into influencing factors like task difficulty, input context variations, and in-depth code-level analysis. To bridge these gaps, we introduce DesignBench, a multi-framework, multi-task evaluation benchmark for assessing MLLMs' capabilities in automated front-end engineering. DesignBench encompasses three widely-used UI frameworks (React, Vue, and Angular) alongside vanilla HTML/CSS, and evaluates on three essential front-end tasks (generation, edit, and repair) in real-world development workflows. DesignBench contains 900 webpage samples spanning over 11 topics, 9 edit types, and 6 issue categories, enabling detailed analysis of MLLM performance across multiple dimensions. Our systematic evaluation reveals critical insights into MLLMs' framework-specific limitations, task-related bottlenecks, and performance variations under different conditions, providing guidance for future research in automated front-end development. Our code and data are available at https://github.com/WebPAI/DesignBench.

cs.SE↗

arXiv2025

DGIQA: Depth-guided Feature Attention and Refinement for Generalizable Image Quality Assessment

A long-held challenge in no-reference image quality assessment (NR-IQA) learning from human subjective perception is the lack of objective generalization to unseen natural distortions. To address this, we integrate a novel Depth-Guided cross-attention and refinement (Depth-CAR) mechanism, which distills scene depth and spatial features into a structure-aware representation for improved NR-IQA. This brings in the knowledge of object saliency and relative contrast of the scene for more discriminative feature learning. Additionally, we introduce the idea of TCB (Transformer-CNN Bridge) to fuse high-level global contextual dependencies from a transformer backbone with local spatial features captured by a set of hierarchical CNN (convolutional neural network) layers. We implement TCB and Depth-CAR as multimodal attention-based projection functions to select the most informative features, which also improve training time and inference efficiency. Experimental results demonstrate that our proposed DGIQA model achieves state-of-the-art (SOTA) performance on both synthetic and authentic benchmark datasets. More importantly, DGIQA outperforms SOTA models on cross-dataset evaluations as well as in assessing natural image distortions such as low-light effects, hazy conditions, and lens flares.

cs.CV↗

arXiv2025

UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesis

The concept of waterbody style transfer remains largely unexplored in the underwater imaging and vision literature. Traditional image style transfer (STx) methods primarily focus on artistic and photorealistic blending, often failing to preserve object and scene geometry in images captured in high-scattering mediums such as underwater. The wavelength-dependent nonlinear attenuation and depth-dependent backscattering artifacts further complicate learning underwater image STx from unpaired data. This paper introduces UStyle, the first data-driven learning framework for transferring waterbody styles across underwater images without requiring prior reference images or scene information. We propose a novel depth-aware whitening and coloring transform (DA-WCT) mechanism that integrates physics-based waterbody synthesis to ensure perceptually consistent stylization while preserving scene structure. To enhance style transfer quality, we incorporate carefully designed loss functions that guide UStyle to maintain colorfulness, lightness, structural integrity, and frequency-domain characteristics, as well as high-level content in VGG and CLIP (contrastive language-image pretraining) feature spaces. By addressing domain-specific challenges, UStyle provides a robust framework for no-reference underwater image STx, surpassing state-of-the-art (SOTA) methods that rely solely on end-to-end reconstruction loss. Furthermore, we introduce the UF7D dataset, a curated collection of high-resolution underwater images spanning seven distinct waterbody styles, establishing a benchmark to support future research in underwater image STx. The UStyle inference pipeline and UF7D dataset are released at: https://github.com/uf-robopi/UStyle.

cs.CV↗

arXiv2022

Elastic Strain Associated with Irradiation-Induced Defects in Self-ion Irradiated Tungsten

Elastic interactions play an important role in controlling irradiation damage evolution, but remain largely unexplored experimentally. Using transmission electron microscopy (TEM) and high-resolution on-axis transmission Kikuchi diffraction (HR-TKD), we correlate the evolution of irradiation-induced damage structures and the associated lattice strains in self-ion irradiated pure tungsten. TEM reveals different dislocation loop structures as a function of sample thickness, suggesting that free surfaces limit the formation of extended defect structures found in thicker samples. HR-TKD strain analysis shows the formation of crystallographically-orientated long-range strain fluctuation above 0.01 dpa and a decrease of total elastic energy above 0.1 dpa.

cond-mat.mtrl-sci↗

arXiv2022

NSSIA: A New Self-Sovereign Identity Scheme with Accountability

Self-Sovereign Identity (SSI) is a new distributed method for identity management, commonly used to address the problem that users are lack of control over their identities. However, the excessive pursuit of self-sovereignty in the most existing SSI schemes hinders sanctions against attackers. To deal with the malicious behavior, a few SSI schemes introduce accountability mechanisms, but they sacrifice users' privacy. What's more, the digital identities (static strings or updatable chains) in the existing SSI schemes are as inputs to a third-party executable program (mobile app, smart contract, etc.) to achieve identity reading, storing and proving, users' self-sovereignty are weakened. To solve the above problems, we present a new self-sovereign identity scheme to strike a balance between privacy and accountability and get rid of the dependence on the third-party program. In our scheme, one and only individual-specific executable code is generated as a digital avatar-i for each human to interact with others in cyberspace without a third-party program, in which the embedding of biometrics enhances uniqueness and user control over their identity. In addition, a joint accountability mechanism, which is based on the shamir (t, n) threshold algorithm and a consortium blockchain, is designed to restrict the power of each regulatory authority and protect users' privacy. Finally, we analyze the security, SSI properties and conduct detailed experiments in term of the cost of computation, storage and blockchain gas. The analysis results indicate that our scheme resists the known attacks and fulfills all the six SSI properties. Compared with the state-of-the-art schemes, the extensive experiment results show that the cost is larger in server storage, blockchain storage and blockchain gas, but is still low enough for practical situations.

cs.CR↗

arXiv2020

Non-destructive study of collision cascade damage in self-ion irradiated tungsten using HR-EBSD and ECCI

Understanding defect production and evolution under irradiation is a long-standing multi-scale problem. Conventionally, experimental examination of irradiation-induced defects (IIDs) has mainly relied on transmission electron microscopy (TEM), which offers high spatial resolution but requires destructive sample preparation. Furthermore, limited field of view and low strain sensitivity make multi-scale characterisation and quantitative strain measurements difficult. Here we explore the potential of using advanced techniques in the scanning electron microscope (SEM) to non-destructively probe irradiation damage at the surface of bulk materials. Electron channelling contrast imaging (ECCI) is used to image nano-scale irradiation-induced defects in 20 MeV self-ion irradiated tungsten, the main candidate material for fusion reactor armour. The results show an evolution of the damage microstructure from uniformly and randomly distributed nano-scale defects at 0.01 dpa (displacement per atom) to string structures extending over hundreds of nanometres at 1 dpa. Cross-correlation based high-resolution EBSD (HR-EBSD) is used to probe the lattice strain fields associated with IIDs. While there is little strain fluctuation at 0.01 dpa, significant heterogeneity in the lattice strains is observed at 0.1 dpa, increasing with dose until saturation at 0.32 dpa. The characteristic length scale of strain fluctuations is ~500 nm. Together, ECCI and HR-EBSD reveal a transition from a structure where defects are disordered to a structure with long-range order driven by elastic interactions between pre-existing defects and new cascade damage. This study demonstrates that SEM provides an attractive tool for rapid throughput, non-destructive, multi-scale and multi-aspect characterisation of irradiation damage.

cond-mat.mtrl-sci↗