arXiv subjects

Wenbo Xu

Publications and source records attributed to Wenbo Xu.

At least 19 recordsLinked to original sources

arXiv2026

Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service

Embedding-as-a-Service (EaaS) has become an important semantic infrastructure for natural language and multimedia applications, but it is highly vulnerable to model stealing and copyright infringement. Existing EaaS watermarking methods face a fundamental robustness--utility--verifiability tension: trigger-based methods are fragile to paraphrasing, transformation-based methods are sensitive to dimensional perturbation, and region-based methods may incur false positives due to coincidental geometric affinity. To address this problem, we propose GeoMark, a geometry-aware localized watermarking framework for EaaS copyright protection. GeoMark uses a natural in-manifold embedding as a shared watermark target, constructs geometry-separated anchors with explicit target--anchor margins, and activates watermark injection only within adaptive local neighborhoods. This design decouples where watermarking is triggered from what ownership is attributed to, achieving localized triggering and centralized attribution. Experiments on four benchmark datasets show that GeoMark preserves downstream utility and geometric fidelity while maintaining robust copyright verification under paraphrasing, dimensional perturbation, and CSE (Clustering, Selection, Elimination) attacks, with improved verification stability and low false-positive risk.

cs.CR↗

arXiv2026

HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales

Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, presenting unprecedented challenges to digital content forensics. Existing benchmarks primarily focus on face-swapping or global text-to-video synthesis, overlooking the crucial dimensions of multimodal alignment and complex human-object or human-human interactions. To address these limitations, we introduce HumanForge, a unified, large-scale, and multi-paradigm human-centric video forgery benchmark containing over 18,000 synthesized videos across four distinct scenarios: audio-driven, pose-driven, semantic-driven, and interaction. To construct and annotate this dataset without labor-intensive manual labeling or blind monolithic prompting, we propose Gen2Anno (Generation-to-Annotation), a cooperative multi-agent pipeline. Gen2Anno orchestrates six specialized agents-ranging from driving asset profiling to MoE-based reference analysis and closed-loop verification-to dynamically execute video synthesis and produce structured annotations containing binary authenticity labels, generative model attribution, and natural-language contrastive forgery rationales. By systematically contrasting expected states derived from generation provenance with actual visual observations, the framework generates logically grounded forensic reasoning chains. Extensive benchmarks using state-of-the-art traditional detectors and Vision-Language Models demonstrate the significant challenges of cross-generator generalization, perturbation robustness, and explainable reasoning on HumanForge. The code and dataset will be publicly released.

cs.CV↗

arXiv2026

Sufficient Conditions for Unique Optimizer of Two-Dimensional Atomic Norm Minimization Under Multiple Frequencies

Atomic norm minimization (ANM) has been extensively applied for gridless angle estimation. However, with the increase of the number of antennas and the communication frequencies in massive MIMO systems, the accompanying beam squint effect significantly degrades angle estimation accuracy. Existing solutions either address this issue only in the one-dimensional (1D) SIMO case, or decouple the two-dimensional (2D) angle estimation into two separate 1D problems, which fails to achieve the optimal solution. In this paper, we employ the multi-frequency model to characterize the beam squint effect in MIMO channels and propose a multi-frequency version of the ANM objective for corresponding 2D angle estimation. To efficiently retrieve the angle parameters, we prove the existence of the equivalent semi-definite program formulation of the ANM objective and develop an algorithm based on the alternating direction method of multipliers for its solutions. Moreover, we derive the certification conditions of this objective to guarantee the existence of a unique optimal solution.

eess.SP↗

arXiv2026

A Knowledge-Informed Pretrained Model for Causal Discovery

Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes: either depending on costly interventional signals or partial ground truth as strong priors, or adopting purely data driven paradigms with limited guidance, which hinders practical deployment. Motivated by real-world scenarios where only coarse domain knowledge is available, we propose a knowledge-informed pretrained model for causal discovery that integrates weak prior knowledge as a principled middle ground. Our model adopts a dual source encoder-decoder architecture to process observational data in a knowledge-informed way. We design a diverse pretraining dataset and a curriculum learning strategy that smoothly adapts the model to varying prior strengths across mechanisms, graph densities, and variable scales. Extensive experiments on in-distribution, out-of distribution, and real-world datasets demonstrate consistent improvements over existing baselines, with strong robustness and practical applicability.

cs.LG↗

arXiv2026

MARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Models

Deepfake detection is a widely researched topic that is crucial for combating the spread of malicious content, with existing methods mainly modeling the problem as classification or spatial localization. The rapid advancements in generative models impose new demands on Deepfake detection. In this paper, we propose multimodal alignment and reinforcement for explainable Deepfake detection via vision-language models, termed MARE, which aims to enhance the accuracy and reliability of Vision-Language Models (VLMs) in Deepfake detection and reasoning. Specifically, MARE designs comprehensive reward functions, incorporating reinforcement learning from human feedback (RLHF), to incentivize the generation of text-spatially aligned reasoning content that adheres to human preferences. Besides, MARE introduces a forgery disentanglement module to capture intrinsic forgery traces from high-level facial semantics, thereby improving its authenticity detection capability. We conduct thorough evaluations on the reasoning content generated by MARE. Both quantitative and qualitative experimental results demonstrate that MARE achieves state-of-the-art performance in terms of accuracy and reliability.

cs.CV↗

arXiv2025

Rethinking Pan-sharpening: A New Training Process for Full-Resolution Generalization

The field of pan-sharpening has recently seen a trend towards increasingly large and complex models, often trained on single, specific satellite datasets. This one-dataset, one-model approach leads to high computational overhead and impractical deployment. More critically, it overlooks a core challenge: poor generalization from reduced-resolution (RR) training to real-world full-resolution (FR) data. In response to this issue, we challenge this paradigm. We introduce a multiple-in-one training strategy, where a single, compact model is trained simultaneously on three distinct satellite datasets (WV2, WV3, and GF2). Our experiments show the primary benefit of this unified strategy is a significant and universal boost in FR generalization (QNR) across all tested models, directly addressing this overlooked problem. This paradigm also inherently solves the one-model-per-dataset challenge, and we support it with a highly reproducible, dependency-free codebase for true usability. Finally, we propose PanTiny, a lightweight framework designed specifically for this new, robust paradigm. We demonstrate it achieves a superior performance-to-efficiency balance, proving that principled, simple and robust design is more effective than brute-force scaling in this practical setting. Our work advocates for a community-wide shift towards creating efficient, deployable, and truly generalizable models for pan-sharpening. The code is open-sourced at https://github.com/Zirconium233/PanTiny.

cs.CV↗

arXiv2025

Hierarchically Block-Sparse Recovery With Prior Support Information

We provide new recovery bounds for hierarchical compressed sensing (HCS) based on prior support information (PSI). A detailed PSI-enabled reconstruction model is formulated using various forms of PSI. The hierarchical block orthogonal matching pursuit with PSI (HiBOMP-P) algorithm is designed in a recursive form to reliably recover hierarchically block-sparse signals. We derive exact recovery conditions (ERCs) measured by the mutual incoherence property (MIP), wherein hierarchical MIP concepts are proposed, and further develop reconstructible sparsity levels to reveal sufficient conditions for ERCs. Leveraging these MIP analyses, we present several extended insights, including reliable recovery conditions in noisy scenarios and the optimal hierarchical structure for cases where sparsity is not equal to zero. Our results further confirm that HCS offers improved recovery performance even when the prior information does not overlap with the true support set, whereas existing methods heavily rely on this overlap, thereby compromising performance if it is absent.

eess.SP↗

arXiv2025

TCSR-SQL: Towards Table Content-aware Text-to-SQL with Self-retrieval

Large Language Model-based (LLM-based) Text-to-SQL methods have achieved important progress in generating SQL queries for real-world applications. When confronted with table content-aware questions in real-world scenarios, ambiguous data content keywords and nonexistent database schema column names within the question lead to the poor performance of existing methods. To solve this problem, we propose a novel approach towards Table Content-aware Text-to-SQL with Self-Retrieval (TCSR-SQL). It leverages LLM's in-context learning capability to extract data content keywords within the question and infer possible related database schema, which is used to generate Seed SQL to fuzz search databases. The search results are further used to confirm the encoding knowledge with the designed encoding knowledge table, including column names and exact stored content values used in the SQL. The encoding knowledge is sent to obtain the final Precise SQL following multi-rounds of generation-execution-revision process. To validate our approach, we introduce a table-content-aware, question-related benchmark dataset, containing 2115 question-SQL pairs. Comprehensive experiments conducted on this benchmark demonstrate the remarkable performance of TCSR-SQL, achieving an improvement of at least 27.8% in execution accuracy compared to other state-of-the-art methods.

cs.DB↗

arXiv2025

Image Recognition with Online Lightweight Vision Transformer: A Survey

The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networks, vision transformers inherently capture long-range dependencies and enable parallel processing, yet lack inductive biases and efficiency benefits, facing significant computational and memory challenges that limit its real-world applicability. This paper surveys various online strategies for generating lightweight vision transformers for image recognition, focusing on three key areas: Efficient Component Design, Dynamic Network, and Knowledge Distillation. We evaluate the relevant exploration for each topic on the ImageNet-1K benchmark, analyzing trade-offs among precision, parameters, throughput, and more to highlight their respective advantages, disadvantages, and flexibility. Finally, we propose future research directions and potential challenges in the lightweighting of vision transformers with the aim of inspiring further exploration and providing practical guidance for the community. Project Page: https://github.com/ajxklo/Lightweight-VIT

cs.CV↗

arXiv2025

Weakly Supervised Multimodal Temporal Forgery Localization via Multitask Learning

The spread of Deepfake videos has caused a trust crisis and impaired social stability. Although numerous approaches have been proposed to address the challenges of Deepfake detection and localization, there is still a lack of systematic research on the weakly supervised multimodal fine-grained temporal forgery localization (WS-MTFL). In this paper, we propose a novel weakly supervised multimodal temporal forgery localization via multitask learning (WMMT), which addresses the WS-MTFL under the multitask learning paradigm. WMMT achieves multimodal fine-grained Deepfake detection and temporal partial forgery localization using merely video-level annotations. Specifically, visual and audio modality detection are formulated as two binary classification tasks. The multitask learning paradigm is introduced to integrate these tasks into a multimodal task. Furthermore, WMMT utilizes a Mixture-of-Experts structure to adaptively select appropriate features and localization head, achieving excellent flexibility and localization precision in WS-MTFL. A feature enhancement module with temporal property preserving attention mechanism is proposed to identify the intra- and inter-modality feature deviation and construct comprehensive video features. To further explore the temporal information for weakly supervised learning, an extensible deviation perceiving loss has been proposed, which aims to enlarge the deviation of adjacent segments of the forged samples and reduce the deviation of genuine samples. Extensive experiments demonstrate the effectiveness of multitask learning for WS-MTFL, and the WMMT achieves comparable results to fully supervised approaches in several evaluation metrics.

cs.CV↗

arXiv2025

A Multimodal Deviation Perceiving Framework for Weakly-Supervised Temporal Forgery Localization

Current researches on Deepfake forensics often treat detection as a classification task or temporal forgery localization problem, which are usually restrictive, time-consuming, and challenging to scale for large datasets. To resolve these issues, we present a multimodal deviation perceiving framework for weakly-supervised temporal forgery localization (MDP), which aims to identify temporal partial forged segments using only video-level annotations. The MDP proposes a novel multimodal interaction mechanism (MI) and an extensible deviation perceiving loss to perceive multimodal deviation, which achieves the refined start and end timestamps localization of forged segments. Specifically, MI introduces a temporal property preserving cross-modal attention to measure the relevance between the visual and audio modalities in the probabilistic embedding space. It could identify the inter-modality deviation and construct comprehensive video features for temporal forgery localization. To explore further temporal deviation for weakly-supervised learning, an extensible deviation perceiving loss has been proposed, aiming at enlarging the deviation of adjacent segments of the forged samples and reducing that of genuine samples. Extensive experiments demonstrate the effectiveness of the proposed framework and achieve comparable results to fully-supervised approaches in several evaluation metrics.

cs.CV↗

arXiv2025

Rejection or Inclusion in the Emotion-Identity Dynamics of TikTok Refugees on RedNote

This study examines cross-cultural interactions between Chinese users and self-identified "TikTok Refugees"(foreign users who migrated to RedNote after TikTok's U.S. ban). Based on a dataset of 1,862 posts and 403,054 comments, we use large language model-based sentiment classification and BERT-based topic modelling to explore how both groups engage with the TikTok refugee phenomenon. We analyse what themes foreign users express, how Chinese users respond, how stances (Pro-China, Neutral, Pro-Foreign) shape emotional expression, and how affective responses differ across topics and identities. Results show strong affective asymmetry: Chinese users respond with varying emotional intensities across topics and stances: pride and praise dominate cultural threads, while political discussions elicit high levels of contempt and anger, especially from Pro-China commenters. Pro-Foreign users exhibit the strongest negative emotions across all topics, whereas neutral users express curiosity and joy but still reinforce mainstream discursive norms. Cross-topic comparisons reveal that appearance-related content produces the most emotionally balanced interactions, while politics generates the highest polarization. Our findings reveal distinct emotion-stance structures in Sino-foreign online interactions and offer empirical insights into identity negotiation in transnational digital publics.

cs.SI↗

arXiv2025

FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models Adaptation

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely heavily on task-specific hard labels, limiting their generalization to unseen categories. Recent popular distillation-based prompt learning methods improve generalization by exploiting larger teacher VLMs and unsupervised knowledge transfer, yet their repetitive teacher model online inference sacrifices the inherent training efficiency advantage of prompt learning. In this paper, we propose {\large {\textbf{F}}}aster {\large {\textbf{D}}}istillation-{\large {\textbf{B}}}ased {\large {\textbf{P}}}rompt {\large {\textbf{L}}}earning (\textbf{FDBPL}), which addresses these issues by sharing soft supervision contexts across multiple training stages and implementing accelerated I/O. Furthermore, FDBPL introduces a region-aware prompt learning paradigm with dual positive-negative prompt spaces to fully exploit randomly cropped regions that containing multi-level information. We propose a positive-negative space mutual learning mechanism based on similarity-difference learning, enabling student CLIP models to recognize correct semantics while learning to reject weakly related concepts, thereby improving zero-shot performance. Unlike existing distillation-based prompt learning methods that sacrifice parameter efficiency for generalization, FDBPL maintains dual advantages of parameter efficiency and strong downstream generalization. Comprehensive evaluations across 11 datasets demonstrate superior performance in base-to-new generalization, cross-dataset transfer, and robustness tests, achieving $2.2\times$ faster training speed.

cs.CV↗

arXiv2025

Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network

Audio temporal forgery localization (ATFL) aims to find the precise forgery regions of the partial spoof audio that is purposefully modified. Existing ATFL methods rely on training efficient networks using fine-grained annotations, which are obtained costly and challenging in real-world scenarios. To meet this challenge, in this paper, we propose a progressive audio-language co-learning network (LOCO) that adopts co-learning and self-supervision manners to prompt localization performance under weak supervision scenarios. Specifically, an audio-language co-learning module is first designed to capture forgery consensus features by aligning semantics from temporal and global perspectives. In this module, forgery-aware prompts are constructed by using utterance-level annotations together with learnable prompts, which can incorporate semantic priors into temporal content features dynamically. In addition, a forgery localization module is applied to produce forgery proposals based on fused forgery-class activation sequences. Finally, a progressive refinement strategy is introduced to generate pseudo frame-level labels and leverage supervised semantic contrastive learning to amplify the semantic distinction between real and fake content, thereby continuously optimizing forgery-aware features. Extensive experiments show that the proposed LOCO achieves SOTA performance on three public benchmarks.

cs.SD↗

arXiv2025

C*: Unifying Programming and Verification in C

Ensuring the correct functionality of systems software, given its safety-critical and low-level nature, is a primary focus in formal verification research and applications. Despite advances in verification tooling, conventional programmers are rarely involved in the verification of their own code, resulting in higher development and maintenance costs for verified software. A key barrier to programmer participation in verification practices is the disconnect of environments and paradigms between programming and verification practices, which limits accessibility and real-time verification. We introduce C*, a proof-integrated language design for C programming. C* extends C with verification capabilities, powered by a symbolic execution engine and an LCF-style proof kernel. It enables real-time verification by allowing programmers to embed proof-code blocks alongside implementation code, facilitating interactive updates to the current proof state. Its expressive and extensible proof support allows users to build reusable libraries of logical definitions, theorems, and programmable proof automation. Crucially, C* unifies implementation and proof code development by using C as the common language. We implemented a prototype of C* and evaluated it on a representative benchmark of small C programs and a challenging real-world case study: the attach function of pKVM's buddy allocator. Our results demonstrate that C* supports the verification of a broad subset of C programming idioms and effectively handles complex reasoning tasks in real-world scenarios.

cs.PL↗

arXiv2025

MERE: Hardware-Software Co-Design for Masking Cache Miss Latency in Embedded Processors

Runahead execution is a technique to mask memory latency caused by irregular memory accesses. By pre-executing the application code during occurrences of long-latency operations and prefetching anticipated cache-missed data into the cache hierarchy, runahead effectively masks memory latency for subsequent cache misses and achieves high prefetching accuracy; however, this technique has been limited to superscalar out-of-order and superscalar in-order cores. For implementation in scalar in-order cores, the challenges of area-/energy-constraint and severe cache contention remain. Here, we build the first full-stack system featuring runahead, MERE, from SoC and a dedicated ISA to the OS and programming model. Through this deployment, we show that enabling runahead in scalar in-order cores is possible, with minimal area and power overheads, while still achieving high performance. By re-constructing the sequential runahead employing a hardware/software co-design approach, the system can be implemented on a mature processor and SoC. Building on this, an adaptive runahead mechanism is proposed to mitigate the severe cache contention in scalar in-order cores. Combining this, we provide a comprehensive solution for embedded processors managing irregular workloads. Our evaluation demonstrates that the proposed MERE attains 93.5% of a 2-wide out-of-order core's performance while constraining area and power overheads below 5%, with the adaptive runahead mechanism delivering an additional 20.1% performance gain through mitigating the severe cache contention issues.

cs.AR↗

arXiv2024

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges.

cs.CV↗

arXiv2024

The Mitochondrial Genome of Cathaya argyrophylla Reaches 18.99 Mb: Analysis of Super-Large Mitochondrial Genomes in Pinaceae

Mitochondrial genomes in the Pinaceae family are notable for their large size and structural complexity. In this study, we sequenced and analyzed the mitochondrial genome of Cathaya argyrophylla, an endangered and endemic Pinaceae species, uncovering a genome size of 18.99 Mb, meaning the largest mitochondrial genome reported to date. To investigate the mechanisms behind this exceptional size, we conducted comparative analyses with other Pinaceae species possessing both large and small mitochondrial genomes, as well as with other gymnosperms. We focused on repeat sequences, transposable element activity, RNA editing events, chloroplast-derived sequence transfers (mtpts), and sequence homology with nuclear genomes. Our findings indicate that while Cathaya argyrophylla and other extremely large Pinaceae mitochondrial genomes contain substantial amounts of repeat sequences and show increased activity of LINEs and LTR retrotransposons, these factors alone do not fully account for the genome expansion. Notably, we observed a significant incorporation of chloroplast-derived sequences in Cathaya argyrophylla and other large mitochondrial genomes, suggesting that extensive plastid-to-mitochondrial DNA transfer may play a crucial role in genome enlargement. Additionally, large mitochondrial genomes exhibited distinct patterns of RNA editing and limited similarity with nuclear genomes compared to smaller genomes. These results suggest that the massive mitochondrial genomes in Pinaceae are likely the result of multiple contributing factors, including repeat sequences, transposon activity, and extensive plastid sequence incorporation. Our study enhances the understanding of mitochondrial genome evolution in plants and provides valuable genetic information for the conservation and study of Cathaya argyrophylla.

q-bio.GN↗