BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Xi Zhang

Xi Zhang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceCryptography and SecurityApplicationsComputation and LanguageComputer Visioncond-mat.mtrl-sciMachine Learningmath.DGq-fin.RM

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
9topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

9 published item(s)

preprint2026arXiv

Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents

Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable action. Existing skills remain largely informal: Markdown skills and instruction packs encode procedures as long natural-language documents, while function calling, Model Context Protocol (MCP) servers, and framework tools structure individual actions but usually leave workflow state, policy enforcement, and completion discipline outside the skill itself. We introduce Formal Skill, a runtime-native abstraction that represents reusable capability with JSON metadata and action schemas, reliable Python executors, hook-governed control logic, Formal Skill routing, and skill-local runtime state. By moving reusable procedure from repeated prompt text into executable state machines and hook policies, Formal Skill gives agents a token-efficient and enforceable control surface. We implement the abstraction in FairyClaw, an open-source event-driven runtime for executable, observable, and composable Formal Skills. On Harness-Bench, FairyClaw obtains highly competitive average scores while using substantially fewer tokens, with especially strong results on tasks that expose the role of Formal Skill.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

From static to adaptive: immune memory-based jailbreak detection for large language models

Large Language Models (LLMs) serve as the backbone of modern AI systems, yet they remain susceptible to adversarial jailbreak attacks. Consequently, robust detection of such malicious inputs is paramount for ensuring model safety. Traditional detection methods typically rely on external models trained on fixed, large-scale datasets, which often incur significant computational overhead. While recent methods shift toward leveraging internal safety signals of models to enable more lightweight and efficient detection. However, these methods remain inherently static and struggle to adapt to the evolving nature of jailbreak attacks. Drawing inspiration from the biological immune mechanism, we introduce the Immune Memory Adaptive Guard (IMAG) framework. By distilling and encoding safety patterns into a persistent, evolvable memory bank, IMAG enables adaptive generalization to emerging threats. Specifically, the framework orchestrates three synergistic components: Immune Detection, which employs retrieval for high-efficiency interception of known jailbreak attacks; Active Immunity, which performs proactive behavioral simulation to resolve ambiguous unknown queries; Memory Updating, which integrates validated attack patterns back into the memory bank. This closed-loop architecture transitions LLM defense from rigid filtering to autonomous adaptive mitigation. Extensive evaluations across five representative open-source LLMs demonstrate that our method surpasses state-of-the-art (SOTA) baselines, achieving a superior average detection accuracy of 94\% across diverse and complex attack types.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models

The detection of sophisticated hallucinations in Large Language Models (LLMs) is hampered by a ``Detection Dilemma'': methods probing internal states (Internal State Probing) excel at identifying factual inconsistencies but fail on logical fallacies, while those verifying externalized reasoning (Chain-of-Thought Verification) show the opposite behavior. This schism creates a task-dependent blind spot: Chain-of-Thought Verification fails on fact-intensive tasks like open-domain QA where reasoning is ungrounded, while Internal State Probing is ineffective on logic-intensive tasks like mathematical reasoning where models are confidently wrong. We resolve this with a unified framework that bridges this critical gap. However, unification is hindered by two fundamental challenges: the Signal Scarcity Barrier, as coarse symbolic reasoning chains lack signals directly comparable to fine-grained internal states, and the Representational Alignment Barrier, a deep-seated mismatch between their underlying semantic spaces. To overcome these, we introduce a multi-path reasoning mechanism to obtain more comparable, fine-grained signals, and a segment-aware temporalized cross-attention module to adaptively fuse these now-aligned representations, pinpointing subtle dissonances. Extensive experiments on three diverse benchmarks and two leading LLMs demonstrate that our framework consistently and significantly outperforms strong baselines. Our code is available: https://github.com/peach918/HalluDet.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

High-Ti induced planar-fault transformation toward superlattice extrinsic stacking faults and microtwins in crept CoNi-based superalloys

Controlling planar fault shearing mechanisms is key for improving the high-temperature creep performance of gamma prime-strengthened high-temperature superalloys. This work examines how the Ti concentration in L12-strengthened CoNi-based alloys affects planar fault formation during creep. Interrupted compressive creep tests were conducted at 1223 K under air with a constant load stress of 241 MPa. We found, for the first time, that high Ti additions shift the dominant gamma prime shearing mode from antiphase boundaries (APBs) in Ti-free and low-Ti alloys to superlattice extrinsic stacking faults (SESFs). Systematic ab initio calculations show that in high-Ti alloys, the elevated APB energy renders APB-shearing mode unfavorable. Nevertheless, the SESF energy decreases relative to that in low-Ti compositions, and an increased ratio of complex intrinsic stacking fault (CISF) to SESF energy promote the transformation of high-energy CISFs into lower-energy SESFs. Chemical analysis using scanning transmission electron microscopy combined with energy-dispersive X-ray spectroscopy further reveals that, SESFs in high-Ti alloys are enriched in Ti, Mo and W, yet no grid-like ordering is observed. Together with the ab initio calculations, Mo and W additions in high Ti alloys could facilitate the transformation from L12 structure to low-energy D024 structure, indicating Mo and W segregation along SESFs is energetically favourable. Furthermore, the successive SESF thickening facilitates microtwinning in the absence of D024 ordering along SESFs, as an additional big carrier for creep strain. These new findings clarify the role of Ti in controlling planar fault shearing mechanisms, providing new insights for optimizing the creep performance of next-generation CoNi-based superalloys.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training data, linguistic ambiguity, and generative uncertainty. It further differentiates between hallucinations and jailbreaks in terms of intent and triggering mechanisms. We propose a three-dimensional survey framework: (1) Attack dimension-including template/encoding-based, in-context learning manipulation, reinforcement/adversarial learning, LLM-assisted and fine-tuned attacks, as well as prompt- and image-level perturbations and agent-based transfer in VLMs; (2) Defense dimension-encompassing prompt-level obfuscation, output evaluation, and model-level alignment or fine-tuning; and (3) Evaluation dimension-covering metrics such as Attack Success Rate (ASR), toxicity score, query/time cost, and multimodal Clean Accuracy and Attribute Success Rate. Compared with prior works, this survey spans the full spectrum from text-only to multimodal settings, consolidating shared mechanisms and proposing unified defense principles: variant-consistency and gradient-sensitivity detection at the perception layer, safety-aware decoding and output review at the generation layer, and adversarially augmented preference alignment at the parameter layer. Additionally, we summarize existing multimodal safety benchmarks and discuss future directions, including automated red teaming, cross-modal collaborative defense, and standardized evaluation.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Long-time behavior of the Hermitian-Yang-Mills flow on non-Kähler manifolds

In this paper, we study the long-time behavior of the Hermitian-Yang-Mills flow over compact Hermitian manifolds. We obtain the monotonicity of lower bound and upper bound of the eigenvalues of the mean curvature along the Hermitian-Yang-Mills flow. In the Gauduchon case, we show that the eigenvalues of the mean curvature converge to geometric invariants determined by the Harder-Narasimhan type. Furthermore, we generalize the Atiyah-Bott-Bando-Siu question to the non-Kähler case.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SecMoE: Communication-Efficient Secure MoE Inference via Select-Then-Compute

Privacy-preserving Transformer inference has gained attention due to the potential leakage of private information. Despite recent progress, existing frameworks still fall short of practical model scales, with gaps up to a hundredfold. A possible way to close this gap is the Mixture of Experts (MoE) architecture, which has emerged as a promising technique to scale up model capacity with minimal overhead. However, given that the current secure two-party (2-PC) protocols allow the server to homomorphically compute the FFN layer with its plaintext model weight, under the MoE setting, this could reveal which expert is activated to the server, exposing token-level privacy about the client's input. While naively evaluating all the experts before selection could protect privacy, it nullifies MoE sparsity and incurs the heavy computational overhead that sparse MoE seeks to avoid. To address the privacy and efficiency limitations above, we propose a 2-PC privacy-preserving inference framework, \SecMoE. Unifying per-entry circuits in both the MoE layer and piecewise polynomial functions, \SecMoE obliviously selects the extracted parameters from circuits and only computes one encrypted entry, which we refer to as Select-Then-Compute. This makes the model for private inference scale to 63$\times$ larger while only having a 15.2$\times$ increase in end-to-end runtime. Extensive experiments show that, under 5 expert settings, \SecMoE lowers the end-to-end private inference communication by 1.8$\sim$7.1$\times$ and achieves 1.3$\sim$3.8$\times$ speedup compared to the state-of-the-art (SOTA) protocols.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

VReID-XFD: Video-based Person Re-identification at Extreme Far Distance Challenge Results

Person re-identification (ReID) across aerial and ground views at extreme far distances introduces a distinct operating regime where severe resolution degradation, extreme viewpoint changes, unstable motion cues, and clothing variation jointly undermine the appearance-based assumptions of existing ReID systems. To study this regime, we introduce VReID-XFD, a video-based benchmark and community challenge for extreme far-distance (XFD) aerial-to-ground person re-identification. VReID-XFD is derived from the DetReIDX dataset and comprises 371 identities, 11,288 tracklets, and 11.75 million frames, captured across altitudes from 5.8 m to 120 m, viewing angles from oblique (30 degrees) to nadir (90 degrees), and horizontal distances up to 120 m. The benchmark supports aerial-to-aerial, aerial-to-ground, and ground-to-aerial evaluation under strict identity-disjoint splits, with rich physical metadata. The VReID-XFD-25 Challenge attracted 10 teams with hundreds of submissions. Systematic analysis reveals monotonic performance degradation with altitude and distance, a universal disadvantage of nadir views, and a trade-off between peak performance and robustness. Even the best-performing SAS-PReID method achieves only 43.93 percent mAP in the aerial-to-ground setting. The dataset, annotations, and official evaluation protocols are publicly available at https://www.it.ubi.pt/DetReIDX/ .

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Machine Learning based Enterprise Financial Audit Framework and High Risk Identification

In the face of global economic uncertainty, financial auditing has become essential for regulatory compliance and risk mitigation. Traditional manual auditing methods are increasingly limited by large data volumes, complex business structures, and evolving fraud tactics. This study proposes an AI-driven framework for enterprise financial audits and high-risk identification, leveraging machine learning to improve efficiency and accuracy. Using a dataset from the Big Four accounting firms (EY, PwC, Deloitte, KPMG) from 2020 to 2025, the research examines trends in risk assessment, compliance violations, and fraud detection. The dataset includes key indicators such as audit project counts, high-risk cases, fraud instances, compliance breaches, employee workload, and client satisfaction, capturing both audit behaviors and AI's impact on operations. To build a robust risk prediction model, three algorithms - Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN) - are evaluated. SVM uses hyperplane optimization for complex classification, RF combines decision trees to manage high-dimensional, nonlinear data with resistance to overfitting, and KNN applies distance-based learning for flexible performance. Through hierarchical K-fold cross-validation and evaluation using F1-score, accuracy, and recall, Random Forest achieves the best performance, with an F1-score of 0.9012, excelling in identifying fraud and compliance anomalies. Feature importance analysis reveals audit frequency, past violations, employee workload, and client ratings as key predictors. The study recommends adopting Random Forest as a core model, enhancing features via engineering, and implementing real-time risk monitoring. This research contributes valuable insights into using machine learning for intelligent auditing and risk management in modern enterprises.

0 citations0 reviewsNo code linkedOpen access