Searcharxiv⌕ Search

arXiv subjects

Li Zhu

Publications and source records attributed to Li Zhu.

At least 37 records · Page 2Linked to original sources
arXiv2026

SoK: Security of Autonomous LLM Agents in Agentic Commerce

Autonomous large language model (LLM) agents such as OpenClaw are pushing agentic commerce from human-supervised assistance toward machine actors that can negotiate, purchase services, manage digital assets, and execute transactions across on-chain and off-chain environments. Protocols such as the Trustless Agents standard (ERC-8004), Agent Payments Protocol (AP2), OKX Agent Payments Protocol (APP), the HTTP 402-based payment protocol (x402), Agent Commerce Protocol (ACP), the Agentic Commerce standard (ERC-8183), and Machine Payments Protocol (MPP) enable this transition, but they also create an attack surface that existing security frameworks do not capture well. This Systematization of Knowledge (SoK) develops a unified security framework for autonomous LLM agents in commerce and finance. We organize threats along five dimensions: agent integrity, transaction authorization, inter-agent trust, market manipulation, and regulatory compliance. From a systematically curated public corpus of academic papers, protocol documents, industry reports, and incident evidence, we derive 12 cross-layer attack vectors and show how failures propagate from reasoning and tooling layers into custody, settlement, market harm, and compliance exposure. We then propose a layered defense architecture addressing authorization gaps left by current agent-payment protocols. Overall, our analysis shows that securing agentic commerce is inherently a cross-layer problem that requires coordinated controls across LLM safety, protocol design, identity, market structure, and regulation. We conclude with a research roadmap and a benchmark agenda for secure autonomous commerce.

cs.CR↗
arXiv2026

Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning

Biosignals acquired from different locations on the body often provide temporally ordered views of the same underlying physiological process. However, most existing self supervised learning methods treat these signals as interchangeable views, overlooking the directional temporal dynamics that link them. A canonical example is the relationship between electrocardiography (ECG), which captures the electrical activation initiating each heartbeat, and photoplethysmography (PPG), which records the resulting peripheral pulse delayed by vascular dynamics. To capture this structured relationship, we introduce xMAE, a biosignal pretraining framework that leverages masked cross modal reconstruction across temporally ordered biosignals as a training time constraint to encourage physiologically meaningful timing structure in the learned representations. We show that pretraining with xMAE yields representations that outperform both unimodal and multimodal baselines on 15 of 19 downstream tasks, including cardiovascular outcome prediction, abnormal laboratory test detection, sleep staging, and demographic inference, while generalizing across devices, body locations, and acquisition settings. Further analysis suggests that the ECG PPG timing structure is reflected in the learned PPG representations. More broadly, xMAE demonstrates the effectiveness of incorporating temporal structure into multimodal pretraining when signals observe different stages of a shared underlying process. Code is available at https://github.com/hzhou3/xMAE.

cs.LG↗
arXiv2026

AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models

Large language models have demonstrated strong reasoning capabilities in general knowledge question answering. However, their ability to handle temporal information remains limited. To address this limitation, existing approaches often involve external tools or manual verification and are tailored to specific scenarios, leading to poor generalizability. Moreover, these methods apply a fixed pipeline to all questions, overlooking the fact that different types of temporal questions require distinct reasoning strategies, which leads to unnecessary processing for simple cases and inadequate reasoning for complex ones. To this end, we propose AdapTime, an adaptive temporal reasoning method that dynamically executes reasoning steps based on the input context. Specifically, it involves three temporal reasoning actions: reformulate, rewrite and review, with an LLM planner guiding the reasoning process. AdapTime integrates seamlessly with state-of-the-art LLMs and significantly enhances their temporal reasoning capabilities without relying on external support. Extensive experiments demonstrate the effectiveness of our approach.

cs.CL↗
arXiv2026

MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning

Diagnostic prediction and clinical reasoning are critical tasks in healthcare applications. While Large Language Models (LLMs) have shown strong capabilities in commonsense reasoning, they still struggle with diagnostic reasoning due to limited domain knowledge. Existing approaches often rely on internal model knowledge or static knowledge bases, resulting in knowledge insufficiency and limited adaptability, which hinder their capacity to perform diagnostic reasoning. Moreover, these methods focus solely on the accuracy of final predictions, overlooking alignment with standard clinical reasoning trajectories. To this end, we propose MultiDx, a two-stage diagnostic reasoning framework that performs differential diagnosis by analyzing evidence collected from multiple knowledge sources. Specifically, it first generates suspected diagnoses and reasoning paths by leveraging knowledge from web search, SOAP-formatted case, and clinical case database. Then it integrates multi-perspective evidence through matching, voting, and differential diagnosis to generate the final prediction.~Extensive experiments on two public benchmarks demonstrate the effectiveness of our approach.

cs.CL↗
arXiv2026

Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline

Existing facial forgery detection methods typically focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation. To address this, we introduce Forgery Attribution Report Generation, a new multimodal task that jointly localizes forged regions ("Where") and generates natural language explanations grounded in the editing process ("Why"). This dual-focus approach goes beyond traditional forensics, providing a comprehensive understanding of the manipulation. To enable research in this domain, we present Multi-Modal Tamper Tracing (MMTT), a large-scale dataset of 152,217 samples, each with a process-derived ground-truth mask and a human-authored textual description, ensuring high annotation precision and linguistic richness. We further propose ForgeryTalker, a unified end-to-end framework that integrates vision and language via a shared encoder (image encoder + Q-former) and dual decoders for mask and text generation, enabling coherent cross-modal reasoning. Experiments show that ForgeryTalker achieves competitive performance on both report generation and forgery localization subtasks, i.e., 59.3 CIDEr and 73.67 IoU, respectively, establishing a baseline for explainable multimedia forensics. Dataset and code will be released to foster future research.

cs.CV↗
arXiv2026

Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval

In this work, we focus on text-based person retrieval, which identifies individuals based on textual descriptions. Despite advancements enabled by synthetic data for pretraining, a significant domain gap, due to variations in lighting, color, and viewpoint, limits the effectiveness of the pretrain-finetune paradigm. To overcome this issue, we propose a unified pipeline incorporating domain adaptation at both image and region levels. Our method features two key components: Domain-aware Diffusion (DaD) for image-level adaptation, which aligns image distributions between synthetic and real-world domains, e.g., CUHK-PEDES, and Multi-granularity Relation Alignment (MRA) for region-level adaptation, which aligns visual regions with descriptive sentences, thereby addressing disparities at a finer granularity. This dual-level strategy effectively bridges the domain gap, achieving state-of-the-art performance on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets. The dataset, model, and code are available at https://github.com/Shuyu-XJTU/MRA.

cs.CV↗
arXiv2026

Look, Compare and Draw: Differential Query Transformer for Automatic Oil Painting

This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge lies in mitigating the duplicate and common-place strokes, which often lead to less aesthetic outcomes. Inspired by the human painting process, \ie, observing, comparing, and drawing, we incorporate differential image analysis into a neural oil painting model, allowing the model to effectively concentrate on the incremental impact of successive brushstrokes. To operationalize this concept, we propose the Differential Query Transformer (DQ-Transformer), a new architecture that leverages differentially derived image representations enriched with positional encoding to guide the stroke prediction process. This integration enables the model to maintain heightened sensitivity to local details, resulting in more refined and nuanced stroke generation. Furthermore, we incorporate adversarial training into our framework, enhancing the accuracy of stroke prediction and thereby improving the overall realism and fidelity of the synthesized paintings. Extensive qualitative evaluations, complemented by a controlled user study, validate that our DQ-Transformer surpasses existing methods in both visual realism and artistic authenticity, typically achieving these results with fewer strokes. The stroke-by-stroke painting animations are available on our project website.

cs.CV↗
arXiv2026

The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts

The detection and grounding of multimedia manipulation has emerged as a critical challenge in combating AI-generated disinformation. While existing methods have made progress in recent years, we identify two fundamental limitations in current approaches: (1) Underestimation of MLLM-driven deception risk: prevailing techniques primarily address rule-based text manipulations, yet fail to account for sophisticated misinformation synthesized by multimodal large language models (MLLMs) that can dynamically generate semantically coherent, contextually plausible yet deceptive narratives conditioned on manipulated images; (2) Unrealistic misalignment artifacts: currently focused scenarios rely on artificially misaligned content that lacks semantic coherence, rendering them easily detectable. To address these gaps holistically, we propose a new adversarial pipeline that leverages MLLMs to generate high-risk disinformation. Our approach begins with constructing the MLLM-Driven Synthetic Multimodal (MDSM) dataset, where images are first altered using state-of-the-art editing techniques and then paired with MLLM-generated deceptive texts that maintain semantic consistency with the visual manipulations. Building upon this foundation, we present the Artifact-aware Manipulation Diagnosis via MLLM (AMD) framework featuring two key innovations: Artifact Pre-perception Encoding strategy and Manipulation-Oriented Reasoning, to tame MLLMs for the MDSM problem. Comprehensive experiments validate our framework's superior generalization capabilities as a unified architecture for detecting MLLM-powered multimodal deceptions. In cross-domain testing on the MDSM dataset, AMD achieves the best average performance, with 88.18 ACC, 60.25 mAP, and 61.02 mIoU scores.

cs.CV↗
arXiv2026

BCH and LCD cyclic codes of length $n=λ(q^m+1)$ over finite fields

BCH and LCD cyclic codes of length $n=λ(q^m+1)$ with $λ\mid q-1$ are studied. A complete characterization of $q$-cyclotomic cosets modulo $n$ is given: Theorem \ref{th4} provides a necessary and sufficient condition for any $0\le γ<n$ to be a coset leader, and for odd $m$, the two largest coset leaders are explicitly determined (Theorem \ref{th9} and Theorem \ref{th14}). Based on these results, the dimensions of several families of BCH codes are determined, and the lower bound on the minimal distance of $\mathcal{C}_{(q,n,2δ+1,n-δ+1)}$ is raised to $2(δ+1)$ (Theorem \ref{th15}--\ref{th5}). Notably, several of these codes are optimal. When $m$ is odd, the necessary and sufficient condition for the BCH code $\mathcal{C}_{(q,n,δ,0)}$ to be dually-BCH is proved (Theorem \ref{th11}). Finally, an exact enumeration of all LCD cyclic codes of this length is derived (Theorem \ref{th3}). All of the above results extend previous results that were limited to $λ=1$.

cs.IT↗
arXiv2026

Decoupled Complementary Spectral-Spatial Learning for Background Representation Enhancement in Hyperspectral Anomaly Detection

A recent class of hyperspectral anomaly detection methods can be trained once on background datasets and then deployed universally without per-scene retraining or parameter tuning, showing strong efficiency and robustness. Building upon this paradigm, we propose a decoupled complementary spectral--spatial learning framework for background representation enhancement. The framework follows a two-stage training strategy: (1) we first train a spectral enhancement network via reverse distillation to obtain robust background spectral representations; and (2) we then freeze the spectral branch as a teacher and train a spatial branch as a complementary student (the "rebellious student") to capture spatial patterns overlooked by the teacher. Complementary learning is achieved through decorrelation objectives that reduce representational redundancy between the two branches, together with reconstruction regularization to prevent the student from learning irrelevant noise. After training, the framework jointly enhances background representations from both spectral and spatial perspectives, and the resulting enhanced features can be plugged into parameter-free, training-free detectors (e.g., the Reed--Xiaoli (RX) detector) for test-time deployment without per-scene retraining or parameter tuning. Experiments on the HAD100 benchmark demonstrate substantial improvements over representative baselines with modest computational overhead, validating the effectiveness of the proposed complementary learning paradigm. Our code is publicly available at https://github.com/xjpp2016/FERS.

cs.CV↗
arXiv2026

Semantic-Deviation-Anchored Multi-Branch Fusion for Unsupervised Anomaly Detection and Localization in Unstructured Conveyor-Belt Coal Scenes

Reliable foreign-object anomaly detection and pixel-level localization in conveyor-belt coal scenes are essential for safe and intelligent mining operations. This task is particularly challenging due to the highly unstructured environment: coal and gangue are randomly piled, backgrounds are complex and variable, and foreign objects often exhibit low contrast, deformation, occlusion, resulting in coupling with their surroundings. These characteristics weaken the stability and regularity assumptions that many anomaly detection methods rely on in structured industrial settings, leading to notable performance degradation. To support evaluation and comparison in this setting, we construct \textbf{CoalAD}, a benchmark for unsupervised foreign-object anomaly detection with pixel-level localization in coal-stream scenes. We further propose a complementary-cue collaborative perception framework that extracts and fuses complementary anomaly evidence from three perspectives: object-level semantic composition modeling, semantic-attribution-based global deviation analysis, and fine-grained texture matching. The fused outputs provide robust image-level anomaly scoring and accurate pixel-level localization. Experiments on CoalAD demonstrate that our method outperforms widely used baselines across the evaluated image-level and pixel-level metrics, and ablation studies validate the contribution of each component. The code is available at https://github.com/xjpp2016/USAD.

cs.CV↗
arXiv2026

Enhancing Conversational Agents via Task-Oriented Adversarial Memory Adaptation

Conversational agents struggle to handle long conversations due to context window limitations. Therefore, memory systems are developed to leverage essential historical information. Existing memory systems typically follow a pipeline of offline memory construction and update, and online retrieval. Despite the flexible online phase, the offline phase remains fixed and task-independent. In this phase, memory construction operates under a predefined workflow and fails to emphasize task relevant information. Meanwhile, memory updates are guided by generic metrics rather than task specific supervision. This leads to a misalignment between offline memory preparation and task requirements, which undermines downstream task performance. To this end, we propose an Adversarial Memory Adaptation mechanism (AMA) that aligns memory construction and update with task objectives by simulating task execution. Specifically, first, a challenger agent generates question answer pairs based on the original dialogues. The constructed memory is then used to answer these questions, simulating downstream inference. Subsequently, an evaluator agent assesses the responses and performs error analysis. Finally, an adapter agent analyzes the error cases and performs dual level updates on both the construction strategy and the content. Through this process, the memory system receives task aware supervision signals in advance during the offline phase, enhancing its adaptability to downstream tasks. AMA can be integrated into various existing memory systems, and extensive experiments on long dialogue benchmark LoCoMo demonstrate its effectiveness.

cs.CL↗
arXiv2026

Wavelet-Driven Masked Multiscale Reconstruction for PPG Foundation Models

Wearable foundation models have the potential to transform digital health by learning transferable representations from large-scale biosignals collected in everyday settings. While recent progress has been made in large-scale pretraining, most approaches overlook the spectral structure of photoplethysmography (PPG) signals, wherein physiological rhythms unfold across multiple frequency bands. Motivated by the insight that many downstream health-related tasks depend on multi-resolution features spanning fine-grained waveform morphology to global rhythmic dynamics, we introduce Masked Multiscale Reconstruction (MMR) for PPG representation learning - a self-supervised pretraining framework that explicitly learns from hierarchical time-frequency scales of PPG data. The pretraining task is designed to reconstruct randomly masked out coefficients obtained from a wavelet-based multiresolution decomposition of PPG signals, forcing the transformer encoder to integrate information across temporal and spectral scales. We pretrain our model with MMR using ~17 million unlabeled 10-second PPG segments from ~32,000 smartwatch users. On 17 of 19 diverse health-related tasks, MMR trained on large-scale wearable PPG data improves over or matches state-of-the-art open-source PPG foundation models, time-series foundation models, and other self-supervised baselines. Extensive analysis of our learned embeddings and systematic ablations underscores the value of wavelet-based representations, showing that they capture robust and physiologically-grounded features. Together, these results highlight the potential of MMR as a step toward generalizable PPG foundation models.

cs.LG↗
arXiv2026

MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA, missing end-to-end multimodal evidence use. We introduce MMDeepResearch-Bench (MMDR-Bench), a benchmark of 140 expert-crafted tasks across 21 domains, where each task provides an image-text bundle to evaluate multimodal understanding and citation-grounded report generation. Compared to prior setups, MMDR-Bench emphasizes report-style synthesis with explicit evidence use, where models must connect visual artifacts to sourced claims and maintain consistency across narrative, citations, and visual references. We further propose a unified, interpretable evaluation pipeline: Formula-LLM Adaptive Evaluation (FLAE) for report quality, Trustworthy Retrieval-Aligned Citation Evaluation (TRACE) for citation-grounded evidence alignment, and Multimodal Support-Aligned Integrity Check (MOSAIC) for text-visual integrity, each producing fine-grained signals that support error diagnosis beyond a single overall score. Experiments across 25 state-of-the-art models reveal systematic trade-offs between generation quality, citation discipline, and multimodal grounding, highlighting that strong prose alone does not guarantee faithful evidence use and that multimodal integrity remains a key bottleneck for deep research agents.

cs.CV↗
arXiv2025

SoK: Web3 RegTech for Cryptocurrency VASP AML/CFT Compliance

The decentralized architecture of Web3 technologies creates fundamental challenges for Anti-Money Laundering and Counter-Financing of Terrorism compliance. Traditional regulatory technology solutions designed for centralized financial systems prove inadequate for blockchain's transparent yet pseudonymous networks. This systematization examines how blockchain-native RegTech solutions leverage distributed ledger properties to enable novel compliance capabilities. We develop three taxonomies organizing the Web3 RegTech domain: a regulatory paradigm evolution framework across ten dimensions, a compliance protocol taxonomy encompassing five verification layers, and a RegTech lifecycle framework spanning preventive, real-time, and investigative phases. Through analysis of 41 operational commercial platforms and 28 academic prototypes selected from systematic literature review (2015-2025), we demonstrate that Web3 RegTech enables transaction graph analysis, real-time risk assessment, cross-chain analytics, and privacy-preserving verification approaches that are difficult to achieve or less commonly deployed in traditional centralized systems. Our analysis reveals critical gaps between academic innovation and industry deployment, alongside persistent challenges in cross-chain tracking, DeFi interaction analysis, privacy protocol monitoring, and scalability. We synthesize architectural best practices and identify research directions addressing these gaps while respecting Web3's core principles of decentralization, transparency, and user sovereignty.

cs.CR↗
arXiv2025

HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series

Wearable sensors provide abundant physiological time series, yet the principles governing their predictive utility remain unclear. We hypothesize that temporal resolution is a fundamental axis of representation learning, with different clinical and behavioral outcomes relying on structure at distinct scales. To test this resolution hypothesis, we introduce HiMAE (Hierarchical Masked Autoencoder), a self supervised framework that combines masked autoencoding with a hierarchical convolutional encoder decoder. HiMAE produces multi resolution embeddings that enable systematic evaluation of which temporal scales carry predictive signal, transforming resolution from a hyperparameter into a probe for interpretability. Across classification, regression, and generative benchmarks, HiMAE consistently outperforms state of the art foundation models that collapse scale, while being orders of magnitude smaller. HiMAE is an efficient representation learner compact enough to run entirely on watch, achieving sub millisecond inference on smartwatch class CPUs for true edge inference. Together, these contributions position HiMAE as both an efficient self supervised learning method and a discovery tool for scale sensitive structure in wearable health.

cs.LG↗
arXiv2025

HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Application

Effective deep search agents must not only access open-domain and domain-specific knowledge but also apply complex rules-such as legal clauses, medical manuals and tariff rules. These rules often feature vague boundaries and implicit logic relationships, making precise application challenging for agents. However, this critical capability is largely overlooked by current agent benchmarks. To fill this gap, we introduce HSCodeComp, the first realistic, expert-level e-commerce benchmark designed to evaluate deep search agents in hierarchical rule application. In this task, the deep reasoning process of agents is guided by these rules to predict 10-digit Harmonized System Code (HSCode) of products with noisy but realistic descriptions. These codes, established by the World Customs Organization, are vital for global supply chain efficiency. Built from real-world data collected from large-scale e-commerce platforms, our proposed HSCodeComp comprises 632 product entries spanning diverse product categories, with these HSCodes annotated by several human experts. Extensive experimental results on several state-of-the-art LLMs, open-source, and closed-source agents reveal a huge performance gap: best agent achieves only 46.8% 10-digit accuracy, far below human experts at 95.0%. Besides, detailed analysis demonstrates the challenges of hierarchical rule application, and test-time scaling fails to improve performance further.

cs.AI↗
arXiv2025

The Minimal Binomial Multiples of Polynomials over Finite Fields

Let $f(X)$ be a nonconstant polynomial over $\mathbb{F}_{q}$, with a nonzero constant term. The order of $f(X)$ is a classical notion in the theory of polynomials over finite fields, and recently the definition of freeness of binomials of $f(X)$ was given in \cite{Martínez}. Generalizing these two notions, we introduce the definition of the minimal binomial multiple of $f(X)$ in this paper, which is the monic binomial with the lowest degree among the binomials over $\mathbb{F}_{q}$ divided by $f(X)$. Based on the equivalent characterization of binomials via the defining sets of their radicals, we prove that a series of properties of the classical order can be naturally generalized to this case. In particular, the minimal binomial multiple of $f(X)$ is presented explicitly in terms of the defining set of the radical of $f(X)$. And a criterion for $f(X)$ being free of binomials is given. As an application, for any positive integer $N$ and nonzero element $λ$ in $\mathbb{F}_{q}$, the $λ$-constacyclic codes of length $N$ with minimal distance $2$ are determined.

math.NT↗