arXiv subjects

Wenjing Zhang

Publications and source records attributed to Wenjing Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Fractal Characterization of Low-Correlation Signals in AI-Generated Image Detection

AI-generated imagery has reached near-photorealistic fidelity, yet this technology poses significant threats to information security and societal trust. Existing deepfake detection methods often exhibit limited robustness in open-world scenarios. To address this limitation, this paper investigates intrinsic discrepancies between synthetic and authentic images from a signal-level perspective. Our analysis reveals that low-correlation signals serve as distinctive markers for differentiating AI-generated imagery from real photographs. Building on this insight, we introduce a novel method for quantifying these signals based on fractal theory. By analyzing the fractal characteristics of low-correlation signals, our method effectively captures the subtle statistical anomalies inherent to the synthesis process. Extensive experimental results demonstrate the method's robustness and superior detection performance. This work emphasizes the need to shift research focus to a new signal-level direction for deepfake detection. Theoretically, this proposed approach is not limited to face image identification but can be applied to all AI-generated image detection tasks. This study provides a new research direction for deepfake detection.

cs.CV↗

arXiv2026

A Systematic Security Evaluation of OpenClaw and Its Variants

Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic security assessment of six representative OpenClaw-series agent frameworks, namely OpenClaw, AutoClaw, QClaw, KimiClaw, MaxClaw, and ArkClaw, under multiple backbone models. To support this study, we construct a benchmark of 205 test cases covering representative attack behaviors across the full agent execution lifecycle, enabling unified evaluation of risk exposure at both the framework and model levels. Our results show that all evaluated agents exhibit substantial security vulnerabilities, and that agentized systems are significantly riskier than their underlying models used in isolation. In particular, reconnaissance and discovery behaviors emerge as the most common weaknesses, while different frameworks expose distinct high-risk profiles, including credential leakage, lateral movement, privilege escalation, and resource development. These findings indicate that the security of modern agent systems is shaped not only by the safety properties of the backbone model, but also by the coupling among model capability, tool use, multi-step planning, and runtime orchestration. We further show that once an agent is granted execution capability and persistent runtime context, weaknesses arising in early stages can be amplified into concrete system-level failures. Overall, our study highlights the need to move beyond prompt-level safeguards toward lifecycle-wide security governance for intelligent agent frameworks.

cs.CR↗

arXiv2026

Paired 2-disjoint path covers of Bcube under the partitioned edge fault model

BCube, as a popular server-centric data center network (DCN), offers significant advantages in low latency, load balancing, and high bandwidth. The many-to-many paired $m$-disjoint path cover ($m$-DPC), a generalization of Hamiltonian paths, enhances message transmission efficiency by constructing disjoint paths that connect $m$ source-destination pairs while covering all the nodes. However, with the continuous expansion of DCNs, link and service failures have grown increasingly common, necessitating robust fault-tolerant algorithms to guarantee reliable communication.This paper mainly investigates the fault-tolerant paired 2-DPC embedding in BCube. We prove that under the partitioned edge fault (PEF) model, BCube retains a paired 2-DPC even when exponentially many edge failures occur.

math.CO↗

arXiv2026

Semantic Search At LinkedIn

Semantic search with large language models (LLMs) enables retrieval by meaning rather than keyword overlap, but scaling it requires major inference efficiency advances. We present LinkedIn's LLM-based semantic search framework for AI Job Search and AI People Search, combining an LLM relevance judge, embedding-based retrieval, and a compact Small Language Model trained via multi-teacher distillation to jointly optimize relevance and engagement. A prefill-oriented inference architecture co-designed with model pruning, context compression, and text-embedding hybrid interactions boosts ranking throughput by over 75x under a fixed latency constraint while preserving near-teacher-level NDCG, enabling one of the first production LLM-based ranking systems with efficiency comparable to traditional approaches and delivering significant gains in quality and user engagement.

cs.IR↗

arXiv2026

High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learning

Effective personalization on large-scale job platforms requires modeling members based on heterogeneous textual sources, including profiles, professional data, and search activity logs. As recommender systems increasingly adopt Large Language Models (LLMs), creating unified, interpretable, and concise representations from heterogeneous sources becomes critical, especially for latency-sensitive online environments. In this work, we propose a novel Reinforcement Learning (RL) framework to synthesize a unified textual representation for each member. Our approach leverages implicit user engagement signals (e.g., clicks, applies) as the primary reward to distill salient information. Additionally, the framework is complemented by rule-based rewards that enforce formatting and length constraints. Extensive offline experiments across multiple LinkedIn products, one of the world's largest job platforms, demonstrate significant improvements in key downstream business metrics. This work provides a practical, labeling-free, and scalable solution for constructing interpretable user representations that are directly compatible with LLM-based systems.

cs.IR↗

arXiv2026

MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction

Large language models (LLMs) excel at capturing semantic nuances and therefore show impressive relevance ranking performance in modern recommendation and search systems. However, they suffer from high computational overhead under industrial latency and throughput requirements. In particular, cross-encoder ranking systems often create long context prefill-heavy workloads, as the model has to be presented with the user, query and item information. To this end, we propose MixLM, a novel LLM-based ranking framework, which significantly improves the system throughput via reducing the input context length, while preserving the semantic strength of cross-encoder rankers. In contrast to a standard ranking system where the context is presented to the model as pure text, we propose to use mix-interaction, a mixture of text and embedding tokens to represent the input. Specifically, MixLM encodes all items in the catalog into a few embedding tokens and stores in a nearline cache. The encoded item descriptions are used during online inference, effectively reducing the item length from a few thousand text tokens to a few embedding tokens. We share insights from deploying our MixLM framework to a real-world search application at LinkedIn, including a detailed discussion of our training pipelines, as well as a thorough analysis of our online serving infrastructure optimization. With the same latency budget and on-par relevance metrics, MixLM increased throughput by 10.0x comparing with strong baselines, 75.9x over full-text LLM rerankers. The efficiency gains delivered by MixLM enabled full-traffic deployment of LLM-powered search, which resulted in a significant 0.47\% increase in Daily Active Users (DAU) in online A/B tests.

cs.IR↗

arXiv2026

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models

Recent advancements in slow thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking (generating redundant reasoning steps for simple problems), leading to excessive computational resource usage. While current mitigation strategies uniformly reduce reasoning tokens, they risk degrading performance on challenging tasks that require extended reasoning. This paper introduces Difficulty-Adaptive Slow Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought (CoT) based on problem difficulty. We first propose a Token Length Budget (TLB) metric to quantify difficulty, then leverage budget-aware reward shaping and budget preference optimization to implement DAST. DAST penalizes overlong responses for simple tasks while incentivizing sufficient reasoning for complex problems. Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking (reducing token usage by over 30\% on average) while preserving reasoning accuracy on complex problems. Our codes and models are available at https://github.com/AnonymousUser0520/AnonymousRepo01.

cs.LG↗

arXiv2026

REFA: Real-time Egocentric Facial Animations for Virtual Reality

We present a novel system for real-time tracking of facial expressions using egocentric views captured from a set of infrared cameras embedded in a virtual reality (VR) headset. Our technology facilitates any user to accurately drive the facial expressions of virtual characters in a non-intrusive manner and without the need of a lengthy calibration step. At the core of our system is a distillation based approach to train a machine learning model on heterogeneous data and labels coming form multiple sources, \eg synthetic and real images. As part of our dataset, we collected 18k diverse subjects using a lightweight capture setup consisting of a mobile phone and a custom VR headset with extra cameras. To process this data, we developed a robust differentiable rendering pipeline enabling us to automatically extract facial expression labels. Our system opens up new avenues for communication and expression in virtual environments, with applications in video conferencing, gaming, entertainment, and remote collaboration.

cs.CV↗

arXiv2026

Crowded Video Individual Counting Informed by Social Grouping and Spatial-Temporal Displacement Priors

Video Individual Counting (VIC) is a recently introduced task aiming to estimate pedestrian flux from a video. It extends Video Crowd Counting (VCC) beyond the per-frame pedestrian count. In contrast to VCC that learns to count pedestrians across frames, VIC must identify co-existent pedestrians between frames, which turns out to be a correspondence problem. Existing VIC approaches, however, can underperform in congested scenes such as metro commuting. To address this, we build WuhanMetroCrowd, one of the first VIC datasets that characterize crowded, dynamic pedestrian flows. It features sparse-to-dense density levels, short-to-long video clips, slow-to-fast flow variations, front-to-back appearance changes, and light-to-heavy occlusions. To better adapt VIC approaches to crowds, we rethink the nature of VIC and recognize two informative priors: i) the social grouping prior that indicates pedestrians tend to gather in groups and ii) the spatial-temporal displacement prior that informs an individual cannot teleport physically. The former inspires us to relax the standard one-to-one (O2O) matching used by VIC to one-to-many (O2M) matching, implemented by an implicit context generator and a O2M matcher; the latter facilitates the design of a displacement prior injector, which strengthens not only O2M matching but also feature extraction and model training. These designs jointly form a novel and strong VIC baseline OMAN++. Extensive experiments show that OMAN++ not only outperforms state-of-the-art VIC baselines on the standard SenseCrowd, CroHD, and MovingDroneCrowd benchmarks, but also indicates a clear advantage in crowded scenes, with a 38.12% error reduction on our WuhanMetroCrowd dataset. Code, data, and pretrained models are available at https://github.com/tiny-smart/OMAN.

cs.CV↗

arXiv2025

Interfacial Polarons Driven by Charge Transfer In WSe2/Cuprate Superconductor Systems

Understanding the electronic properties of doped copper-oxygen planes remains a significant challenge in condensed matter physics and is crucial to unraveling the mechanisms behind high-temperature superconductivity in cuprates. Recently, the observation of charge transfer and interfacial polarons in superconducting interface has aroused extensive research interest. However, experimental data to investigate charge transfer on the CuO2 plane and the presence of polarons are still missing. Here we conduct extensive research on the optical and electronic properties of two-dimensional material supported on copper-based superconductors. Unlike monolayer-WSe2 on other substrates, monolayer-WSe2 on La1.85Sr0.15CuO4 (WSe2/LSCO) produces a special band structure. Using high-resolution spectroscopic ellipsometry and density functional theory calculation methods, the special electronic structure can be attributed to the formation of the interfacial small polaron at the WSe2/LSCO interface which is driven by charge transfer between the CuO2 plane of the cuprate superconductor and WSe2. In addition, the structural phase transition of the LSCO substrate was observed to reduce the electron-hole (e-h) interaction of WSe2. These findings may spur future investigations on the effect of the interfacial polaron on the superconductivity of cuprates, and highlight the significant influence of interface effects on the electronic structure of WSe2 films. It provides an effective method to further explore the intrinsic relationship between interfacial polarons and superconductivity.

cond-mat.supr-con↗

arXiv2025

Stochastic integral representations for the Ray-Knight theorem of the Levy forest

We present a simple stochastic integral representation for the local times of the height process of a spectrally positive Levy process stopped at a hitting time. From the representation we derive a strong stochastic equation for the local time process of the type of Bertoin and Le Gall (Illinois J. Math., 2006) and Dawson and Li (Ann. Probab., 2012). This leads to a representation of the Ray-Knight theorem of Le Gall and Le Jan (Ann. Probab., 1998) and Duquesne and Le Gall (Asterisque, 2002), which codes the genealogical forest of a continuous-state branching process. The results extend those in the recent work of Aidekon et al. (Sci. China Math., 2024) for a Brownian motion with a local time drift.

math.PR↗

arXiv2025

In-Context Learning for Deep Joint Source-Channel Coding Over MIMO Channels

Large language models have demonstrated the ability to perform \textit{in-context learning} (ICL), whereby the model performs predictions by directly mapping the query and a few examples from the given task to the output variable. In this paper, we study ICL for deep joint source-channel coding (DeepJSCC) in image transmission over multiple-input multiple-output (MIMO) systems, where an ICL denoiser is employed for MIMO symbol estimation. We first study the transceiver without any hardware impairments and explore the integration of transformer-based ICL with DeepJSCC in both open-loop and closed-loop MIMO systems, depending on the availability of channel state information (CSI) at the transceiver. For both open-loop and closed-loop scenarios, we propose two MIMO transceiver architectures that leverage context information, i.e., pilot sequences and their outputs, as additional inputs, enabling the DeepJSCC encoder, DeepJSCC decoder, and the ICL denoiser to jointly learn encoding, decoding, and estimation strategies tailored to each channel realization. Next, we extend our study to a more challenging scenario where the transceiver suffers from in-phase and quadrature (IQ) imbalance, resulting in nonlinear MIMO estimation. In this case, the context information is also exploited, facilitating joint learning across the DeepJSCC encoder, decoder, and the ICL denoiser under hardware impairments and varying channel conditions. Numerical results demonstrate that the ICL denoiser for MIMO estimation significantly outperforms the conventional least-squares method, with even greater advantages under IQ imbalance. Moreover, the proposed transformer-based ICL framework, integrated with contextual information, achieves significant improvements in end-to-end image reconstruction quality under transceiver IQ imbalance.

eess.SP↗

arXiv2025

Zero-Dimensional Stacking Domains Enable Strong-Ductile Synergy in Additive Manufactured Titanium

Alloying by addition of oxygen interstitials during additive manufacturing provides new routes to strengthen and toughen metals and alloys. The underlying mechanisms by which such interstitial atoms lead to enhanced properties remain, however, unclear, not least due a lack of quantitative atomic-scale models linking microstructure to properties. Here using quasi-3D imaging based on multi-slice electron ptychography, we reveal the importance of a new type of interstitial-character lattice defect, namely zero-dimensional stacking domains (ZDSDs), present in high density in AM-processed oxygen-modulated pure titanium. These ZDSDs promote slip diversity, and support intense work hardening, enabling a three-fold enhancement in both strength and ductility in Ti-0.45O compared to conventional pure Ti. The work demonstrates the potential for using interstitial solutes to enhance mechanical properties in a range of critical engineering alloys.

cond-mat.mtrl-sci↗

arXiv2025

LANTERN: Scalable Distillation of Large Language Models for Job-Person Fit and Explanation

Large language models (LLMs) have achieved strong performance across a wide range of natural language processing tasks. However, deploying LLMs at scale for domain specific applications, such as job-person fit and explanation in job seeking platforms, introduces distinct challenges. At LinkedIn, the job person fit task requires analyzing a candidate's public profile against job requirements to produce both a fit assessment and a detailed explanation. Directly applying open source or finetuned LLMs to this task often fails to yield high quality, actionable feedback due to the complexity of the domain and the need for structured outputs. Moreover, the large size of these models leads to high inference latency and limits scalability, making them unsuitable for online use. To address these challenges, we introduce LANTERN, a novel LLM knowledge distillation framework tailored specifically for job person fit tasks. LANTERN involves modeling over multiple objectives, an encoder model for classification purpose, and a decoder model for explanation purpose. To better distill the knowledge from a strong black box teacher model to multiple downstream models, LANTERN incorporates multi level knowledge distillation that integrates both data and logit level insights. In addition to introducing the knowledge distillation framework, we share our insights on post training techniques and prompt engineering, both of which are crucial for successfully adapting LLMs to domain specific downstream tasks. Extensive experimental results demonstrate that LANTERN significantly improves task specific metrics for both job person fit and explanation. Online evaluations further confirm its effectiveness, showing measurable gains in job seeker engagement, including a 0.24\% increase in apply rate and a 0.28\% increase in qualified applications.

cs.CL↗

arXiv2025

MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance

General-domain large multimodal models (LMMs) have achieved significant advances in various image-text tasks. However, their performance in the Intelligent Traffic Surveillance (ITS) domain remains limited due to the absence of dedicated multimodal datasets. To address this gap, we introduce MITS (Multimodal Intelligent Traffic Surveillance), the first large-scale multimodal benchmark dataset specifically designed for ITS. MITS includes 170,400 independently collected real-world ITS images sourced from traffic surveillance cameras, annotated with eight main categories and 24 subcategories of ITS-specific objects and events under diverse environmental conditions. Additionally, through a systematic data generation pipeline, we generate high-quality image captions and 5 million instruction-following visual question-answer pairs, addressing five critical ITS tasks: object and event recognition, object counting, object localization, background analysis, and event reasoning. To demonstrate MITS's effectiveness, we fine-tune mainstream LMMs on this dataset, enabling the development of ITS-specific applications. Experimental results show that MITS significantly improves LMM performance in ITS applications, increasing LLaVA-1.5's performance from 0.494 to 0.905 (+83.2%), LLaVA-1.6's from 0.678 to 0.921 (+35.8%), Qwen2-VL's from 0.584 to 0.926 (+58.6%), and Qwen2.5-VL's from 0.732 to 0.930 (+27.0%). We release the dataset, code, and models as open-source, providing high-value resources to advance both ITS and LMM research.

cs.CV↗

arXiv2025

Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic preservation over pixel-level reconstruction and demand robust performance across diverse data distributions and downstream tasks. These challenges call for advanced semantic compression paradigms. Motivated by the zero-shot and representational capabilities of multimodal foundation models, we propose a novel semantic compression method based on the contrastive language-image pretraining (CLIP) model. Rather than compressing images for reconstruction, we propose compressing the CLIP feature embeddings into minimal bits while preserving semantic information across different tasks. Experiments show that our method maintains semantic integrity across benchmark datasets, achieving an average bit rate of approximately 2-3* 10(-3) bits per pixel. This is less than 5% of the bitrate required by mainstream image compression approaches for comparable performance. Remarkably, even under extreme compression, the proposed approach exhibits zero-shot robustness across diverse data distributions and downstream tasks.

cs.CV↗

arXiv2025

Powering Job Search at Scale: LLM-Enhanced Query Understanding in Job Matching Systems

Query understanding is essential in modern relevance systems, where user queries are often short, ambiguous, and highly context-dependent. Traditional approaches often rely on multiple task-specific Named Entity Recognition models to extract structured facets as seen in job search applications. However, this fragmented architecture is brittle, expensive to maintain, and slow to adapt to evolving taxonomies and language patterns. In this paper, we introduce a unified query understanding framework powered by a Large Language Model (LLM), designed to address these limitations. Our approach jointly models the user query and contextual signals such as profile attributes to generate structured interpretations that drive more accurate and personalized recommendations. The framework improves relevance quality in online A/B testing while significantly reducing system complexity and operational overhead. The results demonstrate that our solution provides a scalable and adaptable foundation for query understanding in dynamic web applications.

cs.IR↗

arXiv2025

Optimization of Private Semantic Communication Performance: An Uncooperative Covert Communication Method

In this paper, a novel covert semantic communication framework is investigated. Within this framework, a server extracts and transmits the semantic information, i.e., the meaning of image data, to a user over several time slots. An attacker seeks to detect and eavesdrop the semantic transmission to acquire details of the original image. To avoid data meaning being eavesdropped by an attacker, a friendly jammer is deployed to transmit jamming signals to interfere the attacker so as to hide the transmitted semantic information. Meanwhile, the server will strategically select time slots for semantic information transmission. Due to limited energy, the jammer will not communicate with the server and hence the server does not know the transmit power of the jammer. Therefore, the server must jointly optimize the semantic information transmitted at each time slot and the corresponding transmit power to maximize the privacy and the semantic information transmission quality of the user. To solve this problem, we propose a prioritised sampling assisted twin delayed deep deterministic policy gradient algorithm to jointly determine the transmitted semantic information and the transmit power per time slot without the communications between the server and the jammer. Compared to standard reinforcement learning methods, the propose method uses an additional Q network to estimate Q values such that the agent can select the action with a lower Q value from the two Q networks thus avoiding local optimal action selection and estimation bias of Q values. Simulation results show that the proposed algorithm can improve the privacy and the semantic information transmission quality by up to 77.8% and 14.3% compared to the traditional reinforcement learning methods.

cs.AI↗