arXiv subjects

Junjie Wang

Publications and source records attributed to Junjie Wang.

At least 109 records · Page 6Linked to original sources

arXiv2026

Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detection

Detecting text generated by large language models (LLMs) is crucial but challenging. Existing detectors depend on impractical assumptions, such as white-box settings, or solely rely on text-level features, leading to imprecise detection ability. In this paper, we propose a simple but effective and practical LLM-generated text detection method, VaryBalance. The core of VaryBalance is that, compared to LLM-generated texts, there is a greater difference between human texts and their rewritten version via LLMs. Leveraging this observation, VaryBalance quantifies this through mean standard deviation and distinguishes human texts and LLM-generated texts. Comprehensive experiments demonstrated that VaryBalance outperforms the state-of-the-art detectors, i.e., Binoculars, by up to 34.3\% in terms of AUROC, and maintains robustness against multiple generating models and languages.

cs.AI↗

arXiv2026

GPUTB-2:An efficient E(3) network method for learning high-precision orthogonal Hamiltonian

Although equivariant neural networks have become a cornerstone for learning electronic Hamiltonians, the intrinsic non-orthogonality of linear combinations of atomic orbitals (LCAO) basis sets poses a fundamental challenge. The computational cost of Hamiltonian orthogonalization scales as O(N^3), which severely hinders electronic structure calculations for large-scale systems containing hundreds of thousands to millions of atoms. To address this issue, we develop GPUTB-2, a framework that learns implicitly orthogonality-preserving Hamiltonians by training directly on electronic band structures. Benefiting from an E(3)-equivariant network accelerated by Gaunt tensor product and SO(2) tensor product layers, GPUTB-2 achieves significantly higher accuracy than GPUTB across multiple benchmark systems. Moreover, GPUTB-2 accurately predicts large-scale electronic structures, including transport properties of temperature-perturbed SnSe and the band structures of magic-angle twisted bilayer graphene. By further integrating this framework with the linear-scaling quantum transport (LSQT) method, we investigate the electronic properties of million-atom amorphous graphene and uncover pressure-induced electronic structure transitions in more complex amorphous silicon. Together, these results establish GPUTB-2 as a high-accuracy and scalable approach for predicting orthogonal Hamiltonians.

cond-mat.mtrl-sci↗

arXiv2026

Unveiling pressurized bulk superconductivity in a trilayer nickelate Pr4Ni3O10 single crystal

The recent discovery of superconductivity in pressurized Ruddlesden-Popper (RP) nickelates has provided new perspectives on the mechanism of high-temperature superconductivity. Up to now, most experiments concentrated on the lanthanum-related RP phase, so the discovery of new superconducting RP nickelates is highly desirable to reveal their generality. Here we report that high-quality Pr4Ni3O10 single crystal is grown with an optical floating zone furnace under high oxygen pressure. High-pressure transport measurements show that the superconducting state arises above 10 GPa, and the maximum Tc reaches 39 K without saturation, significantly exceeding the value of 25-30 K of La4Ni3O10. Ultrasensitive d.c. magnetic susceptibility measurements under high pressure indicate bulk superconductivity with appreciable superconducting volume fractions. By performing in situ high-pressure synchrotron X-ray diffraction measurements at 16 K, a structural transition is found from monoclinic to tetragonal. Unlike La4Ni3O10, the electronic structure of the high-pressure phase of Pr4Ni3O10 from density functional theory exhibits a dramatic metallization of the sigma-bonding band consisting of three dz2 orbitals and van Hove singularity of coupled bands of dx2-y2 orbitals near the Fermi level, similar to the bilayer nickelate La3Ni2O7. These findings reveal some generic features of both crystal and electronic structures for high-temperature superconductivity in nickelates and multi-layer cuprates.

cond-mat.supr-con↗

arXiv2026

Weakly anisotropic superconductivity of Pr4Ni3O10 single crystals

Since the discovery of high-temperature superconductivity, studying the upper critical field and its anisotropy has been crucial for understanding superconducting mechanism and guiding applications. Here we perform in situ high-pressure angular-dependent electrical transport measurements on Pr4Ni3O10 single crystals using a custom diamond anvil cell (DAC) rotator and confirming its anisotropic superconductivity. The anisotropy parameter is approximately 1.6, decreasing with increasing temperature and approaches 1 near Tc. Comparing effective mass anisotropy and inter-block distance in cuprates and iron-based superconductors (FeSCs) reveals that Pr4Ni3O10 single crystals superconductors are consistent with a two-band model, where intralayer quantum confinement within the unit cell induces interlayer coherence, thereby leading to three-dimensional (3D) superconductivity. This study not only establishes the existence of anisotropic superconductivity in bulk Ruddlesden-Popper nickelates, but also provide critical insight into the role of dimensionality in high-temperature superconductivity.

cond-mat.supr-con↗

arXiv2026

From SERPs to Sound: How Search Engine Result Pages and AI-generated Podcasts Interact to Influence User Attitudes on Controversial Topics

Compared to search engine result pages (SERPs), AI-generated podcasts represent a relatively new and relatively more passive modality of information consumption, delivering narratives in a naturally engaging format. As these two media increasingly converge in everyday information-seeking behavior, it is essential to explore how their interaction influences user attitudes, particularly in contexts involving controversial, value-laden, and often debated topics. Addressing this need, we aim to understand how information mediums of present-day SERPs and AI-generated podcasts interact to shape the opinions of users. To this end, through a controlled user study (N=483), we investigated user attitudinal effects of consuming information via SERPs and AI-generated podcasts, focusing on how the sequence and modality of exposure shape user opinions. A majority of users in our study corresponded to attitude change outcomes, and we found an effect of sequence on attitude change. Our results further revealed a role of viewpoint bias and the degree of topic controversiality in shaping attitude change, although we found no effect of individual moderators.

cs.IR↗

arXiv2026

SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature

Evaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic "Needle-In-A-Haystack" tests often reward answer matching without requiring a causal, evidence-linked reasoning trace in the document. We propose the "Fish-in-the-Ocean" (FITO) paradigm, which requires models to construct explicit cross-modal evidence chains within native scientific documents. To operationalize FITO, we build SIN-Data, a scientific interleaved corpus that preserves the native interleaving of text and figures. On top of it, we construct SIN-Bench with four progressive tasks covering evidence discovery (SIN-Find), hypothesis verification (SIN-Verify), grounded QA (SIN-QA), and evidence-anchored synthesis (SIN-Summary). We further introduce "No Evidence, No Score", scoring predictions when grounded to verifiable anchors and diagnosing evidence quality via matching, relevance, and logic. Experiments on eight MLLMs show that grounding is the primary bottleneck: Gemini-3-pro achieves the best average overall score (0.573), while GPT-5 attains the highest SIN-QA answer accuracy (0.767) but underperforms on evidence-aligned overall scores, exposing a gap between correctness and traceable support.

cs.CL↗

arXiv2026

PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems

With the increasing deployment of large language models (LLMs) in affective agents and AI systems, maintaining a consistent and authentic LLM personality becomes critical for user trust and engagement. However, existing work overlooks a fundamental psychological consensus that personality traits are dynamic and context-dependent. To bridge this gap, we introduce PTCBENCH, a systematic benchmark designed to quantify the consistency of LLM personalities under controlled situational contexts. PTCBENCH subjects models to 12 distinct external conditions spanning diverse location contexts and life events, and rigorously assesses the personality using the NEO Five-Factor Inventory. Our study on 39,240 personality trait records reveals that certain external scenarios (e.g., "Unemployment") can trigger significant personality changes of LLMs, and even alter their reasoning capabilities. Overall, PTCBENCH establishes an extensible framework for evaluating personality consistency in realistic, evolving environments, offering actionable insights for developing robust and psychologically aligned AI systems.

cs.CL↗

arXiv2026

Towards Understanding and Characterizing Vulnerabilities in Intelligent Connected Vehicles through Real-World Exploits

Intelligent Connected Vehicles (ICVs) are a core component of modern transportation systems, and their security is crucial as it directly relates to user safety. Despite prior research, most existing studies focus only on specific sub-components of ICVs due to their inherent complexity. As a result, there is a lack of systematic understanding of ICV vulnerabilities. Moreover, much of the current literature relies on human subjective analysis, such as surveys and interviews, which tends to be high-level and unvalidated, leaving a significant gap between theoretical findings and real-world attacks. To address this issue, we conducted the first large-scale empirical study on ICV vulnerabilities. We began by analyzing existing ICV security literature and summarizing the prevailing taxonomies in terms of vulnerability locations and types. To evaluate their real-world relevance, we collected a total of 649 exploitable vulnerabilities, including 592 from eight ICV vulnerability discovery competitions, Anonymous Cup, between January 2023 and April 2024, covering 48 different vehicles. The remaining 57 vulnerabilities were submitted daily by researchers. Based on this dataset, we assessed the coverage of existing taxonomies and identified several gaps, discovering one new vulnerability location and 13 new vulnerability types. We further categorized these vulnerabilities into 6 threat types (e.g., privacy data breach) and 4 risk levels (ranging from low to critical) and analyzed participants' skills and the types of ICVs involved in the competitions. This study provides a comprehensive and data-driven analysis of ICV vulnerabilities, offering actionable insights for researchers, industry practitioners, and policymakers. To support future research, we have made our vulnerability dataset publicly available.

cs.CR↗

arXiv2025

PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level Design

Penetration testing is essential for assessing and strengthening system security against real-world threats, yet traditional workflows remain highly manual, expertise-intensive, and difficult to scale. Although recent advances in Large Language Models (LLMs) offer promising opportunities for automation, existing applications rely on simplistic prompting without task decomposition or domain adaptation, resulting in unreliable black-box behavior and limited insight into model capabilities across penetration testing stages. To address this gap, we introduce PentestEval, the first comprehensive benchmark for evaluating LLMs across six decomposed penetration testing stages: Information Collection, Weakness Gathering and Filtering, Attack Decision-Making, Exploit Generation and Revision. PentestEval integrates expert-annotated ground truth with a fully automated evaluation pipeline across 346 tasks covering all stages in 12 realistic vulnerable scenarios. Our stage-level evaluation of 9 widely used LLMs reveals generally weak performance and distinct limitations across the stages of penetration-testing workflow. End-to-end pipelines reach only 31% success rate, and existing LLM-powered systems such as PentestGPT, PentestAgent, and VulnBot exhibit similar limitations, with autonomous agents failing almost entirely. These findings highlight that autonomous penetration testing demands stronger structured reasoning, where modularization enhances each individual stage and improves overall performance. PentestEval provides the foundational benchmark needed for future research on fine-grained, stage-level evaluation, paving the way toward more reliable LLM-based automation.

cs.SE↗

arXiv2025

DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling

Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended exposure and potential misuse. Red teaming, which aims to proactively identify diverse prompts that can elicit unsafe outputs from the T2I system, is increasingly recognized as an essential method for assessing and improving safety before real-world deployment. However, existing automated red teaming approaches often treat prompt discovery as an isolated, prompt-level optimization task, which limits their scalability, diversity, and overall effectiveness. To bridge this gap, in this paper, we propose DREAM, a scalable red teaming framework to automatically uncover diverse problematic prompts from a given T2I system. Unlike prior work that optimizes prompts individually, DREAM directly models the probabilistic distribution of the target system's problematic prompts, which enables explicit optimization over both effectiveness and diversity, and allows efficient large-scale sampling after training. To achieve this without direct access to representative training samples, we draw inspiration from energy-based models and reformulate the objective into a simple and tractable form. We further introduce GC-SPSA, an efficient optimization algorithm that provides stable gradient estimates through the long and potentially non-differentiable T2I pipeline. During inference, we also propose a diversity-aware sampling strategy to enhance prompt variety. The effectiveness of DREAM is validated through extensive experiments, demonstrating state-of-the-art performance across a wide range of T2I models and safety filters in terms of both prompt success rate and diversity. Our code is available at https://github.com/AntigoneRandy/DREAM

cs.CR↗

arXiv2025

Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long videos. While existing keyframe sampling methods can improve temporal modeling efficiency, additional computational cost is introduced before feature encoding, and the binary frame selection paradigm is found suboptimal. Therefore, in this work, we propose Dynamic Token compression via LLM-guided Keyframe prior (DyToK), a training-free paradigm that enables dynamic token compression by harnessing VLLMs' inherent attention mechanisms. Our analysis reveals that VLLM attention layers naturally encoding query-conditioned keyframe priors, by which DyToK dynamically adjusts per-frame token retention ratios, prioritizing semantically rich frames while suppressing redundancies. Extensive experiments demonstrate that DyToK achieves state-of-the-art efficiency-accuracy tradeoffs. DyToK shows plug-and-play compatibility with existing compression methods, such as VisionZip and FastV, attaining 4.3x faster inference while preserving accuracy across multiple VLLMs, such as LLaVA-OneVision and Qwen2.5-VL. Code is available at https://github.com/yu-lin-li/DyToK .

cs.CV↗

arXiv2025

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

Text-to-image (T2I) diffusion models have achieved impressive image generation quality and are increasingly fine-tuned for personalized applications. However, these models often inherit unsafe behaviors from toxic pretraining data, raising growing safety concerns. While recent safety-driven unlearning methods have made promising progress in suppressing model toxicity, they are found to be fragile to downstream fine-tuning, as we reveal that state-of-the-art methods largely fail to retain their effectiveness even when fine-tuned on entirely benign datasets. To mitigate this problem, in this paper, we propose ResAlign, a safety-driven unlearning framework with enhanced resilience against downstream fine-tuning. By modeling downstream fine-tuning as an implicit optimization problem with a Moreau envelope-based reformulation, ResAlign enables efficient gradient estimation to minimize the recovery of harmful behaviors. Additionally, a meta-learning strategy is proposed to simulate a diverse distribution of fine-tuning scenarios to improve generalization. Extensive experiments across a wide range of datasets, fine-tuning methods, and configurations demonstrate that ResAlign consistently outperforms prior unlearning approaches in retaining safety, while effectively preserving benign generation capability. Our code and pretrained models are publicly available at https://github.com/AntigoneRandy/ResAlign.

cs.LG↗

arXiv2025

Super-hard and superconducting boron clathrates in the prediction of U-B compounds

The binary metal borides provide a promising platform for searching unique materials with superconductivity and super-hardness under high pressure, owing to the distinctive bonding characters of boron. In this work, combined the first-principles calculations and crystal structure predictions, we predicted 4 exotic stoichiometries and 8 unique U-B compounds under high pressure. The predicted compounds have layered or caged structure units and 4 of them host high hardness under ambient pressure. By removal of the U atoms, we predicted three meta-stable boron clathrates at ambient pressure. Remarkably, the Vickers hardness of the predicted C2/m-B6 is estimated to be 49-53 GPa, and the C2/m-B12 is superconducting with the Tc value of 16.12 K. Our calculations enrich the phase diagram of binary metal borides and boron allotropes, providing insights for the future theoretical and experimental studies on unique materials.

cond-mat.supr-con↗

arXiv2025

Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation

Object-goal navigation in open-vocabulary settings requires agents to locate novel objects in unseen environments, yet existing approaches suffer from opaque decision-making processes and low success rate on locating unseen objects. To address these challenges, we propose Nav-$R^2$, a framework that explicitly models two critical types of relationships, target-environment modeling and environment-action planning, through structured Chain-of-Thought (CoT) reasoning coupled with a Similarity-Aware Memory. We construct a Nav$R^2$-CoT dataset that teaches the model to perceive the environment, focus on target-related objects in the surrounding context and finally make future action plans. Our SA-Mem preserves the most target-relevant and current observation-relevant features from both temporal and semantic perspectives by compressing video frames and fusing historical observations, while introducing no additional parameters. Compared to previous methods, Nav-R^2 achieves state-of-the-art performance in localizing unseen objects through a streamlined and efficient pipeline, avoiding overfitting to seen object categories while maintaining real-time inference at 2Hz. Resources will be made publicly available at \href{https://github.com/AMAP-EAI/Nav-R2}{github link}.

cs.CV↗

arXiv2025

Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation

Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g., impracticality due to the requirement of white-box information or high control authority, and a lack of stealthiness or effectiveness as they often target all agents or specific fixed agents. To address these issues, we propose AdapAM, a novel framework for adversarial attacks on black-box MAS. AdapAM incorporates two key components: (1) Adaptive Selection Policy simultaneously selects the victim and determines the anticipated malicious action (the action would lead to the worst impact on MAS), balancing effectiveness and stealthiness. (2) Proxy-based Perturbation to Induce Malicious Action utilizes generative adversarial imitation learning to approximate the target MAS, allowing AdapAM to generate perturbed observations using white-box information and thus induce victims to execute malicious action in black-box settings. We evaluate AdapAM across eight multi-agent environments and compare it with four state-of-the-art and commonly-used baselines. Results demonstrate that AdapAM achieves the best attack performance in different perturbation rates. Besides, AdapAM-generated perturbations are the least noisy and hardest to detect, emphasizing the stealthiness.

cs.MA↗

arXiv2025

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on external knowledge makes RAG systems vulnerable to corpus poisoning attacks that manipulate generated outputs via poisoned document injection. Existing poisoning attack strategies typically treat the retrieval and generation stages as disjointed, limiting their effectiveness. We propose Joint-GCG, the first framework to unify gradient-based attacks across both retriever and generator models through three innovations: (1) Cross-Vocabulary Projection for aligning embedding spaces, (2) Gradient Tokenization Alignment for synchronizing token-level gradient signals, and (3) Adaptive Weighted Fusion for dynamically balancing attacking objectives. Evaluations demonstrate that Joint-GCG achieves at most 25% and an average of 5% higher attack success rate than previous methods across multiple retrievers and generators. While optimized under a white-box assumption, the generated poisons show unprecedented transferability to unseen models. Joint-GCG's innovative unification of gradient-based attacks across retrieval and generation stages fundamentally reshapes our understanding of vulnerabilities within RAG systems. Our code is available at https://github.com/NicerWang/Joint-GCG.

cs.CR↗

arXiv2025

On the Role of Interlayer Electrons on the Frictional Behavior of Two-Dimensional Electrides

Friction accounts for up to 30% of global energy consumption, underscoring the urgent need for superlubricity in advanced materials. Two-dimensional (2D) electrides are layered materials with cationic layers separated by 2D confined electrons that act as anions. This study reveals the unique frictional properties of these compounds and the underlying mechanisms. We establish that interlayer friction correlates with the cationic charges and sliding-induced charge redistribution. Remarkably, the 2D electride Ba2N stands out for its lower interlayer friction than graphene, despite its stronger interlayer adhesion, defying conventional tribological understanding. This anomalous behavior arises from electron redistribution as the dominant energy dissipation pathway. Combining ab initio calculations and deep potential molecular dynamics (DPMD) simulations, we show that incommensurate twisted interfaces (2° < θ < 58°) in Ba2N achieve structural superlubricity by suppressing out-of-plane buckling and energy corrugation. Notably, a critical normal load of 2.3 GPa enables barrier-free sliding in commensurate Ba2N (θ = 0°), with an ultralow shear-to-load ratio of 0.001, suggesting the potential for superlubricity. Moreover, electron doping effectively reduces interlayer friction by controllably modulating stacking energies in 2D electrides. These findings establish 2D electrides as a transformative platform for energy-efficient tribology, enabling scalable superlubricity through twist engineering, load adaptation, or electrostatic gating. Our work advances the fundamental understanding of electron-mediated friction, with Ba2N serving a model system for cost-effective, high-performance material design.

cond-mat.mtrl-sci↗

arXiv2025

AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning

Controllable captioning is essential for precise multimodal alignment and instruction following, yet existing models often lack fine-grained control and reliable evaluation protocols. To address this gap, we present the AnyCap Project, an integrated solution spanning model, dataset, and evaluation. We introduce AnyCapModel (ACM), a lightweight plug-and-play framework that enhances the controllability of existing foundation models for omni-modal captioning without retraining the base model. ACM reuses the original captions from base models while incorporating user instructions and modality features to generate improved captions. To remedy the data scarcity in controllable multimodal captioning, we build AnyCapDataset (ACD), covering three modalities, 28 user-instruction types, and 300\,k high-quality data entries. We further propose AnyCapEval, a new benchmark that provides more reliable evaluation metrics for controllable captioning by decoupling content accuracy and stylistic fidelity. ACM markedly improves caption quality across a diverse set of base models on AnyCapEval. Notably, ACM-8B raises GPT-4oś content scores by 45\% and style scores by 12\%, and it also achieves substantial gains on widely used benchmarks such as MIA-Bench and VidCapBench.

cs.CV↗