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

Yufeng Wu

Yufeng Wu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
eess.IVMultimediaArtificial IntelligenceComputation and LanguageComputer Visioncond-mat.mtrl-scics.CYMachine Learningmath.DSmath.NTphysics.app-phPopulations and Evolutionquant-ph

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
13topics
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

A Reproducible Multi-Architecture Baseline for Token-Level Chinese Metaphor Identification under the MIPVU Framework

Metaphor is pervasive in everyday language, yet token-level computational identification of metaphor-related words in Chinese under the MIPVU framework remains under-explored relative to English. This paper presents a reproducible multi-architecture baseline for token-level metaphor identification on the PSU Chinese Metaphor Corpus (PSU CMC), the only widely available MIPVU-annotated Chinese corpus. We systematically compare three model families: (i) encoder fine-tuning with Chinese RoBERTa-wwm-ext-large; (ii) MelBERT adapted to Chinese using a newly constructed basic-meaning resource derived from the Modern Chinese Dictionary, 7th edition (MCD7), comprising 74,823 entries with 71.51% PSU CMC vocabulary coverage; and (iii) Qwen3.5-9B fine-tuned with QLoRA as an instruction-tuned generative baseline. Across five fixed seeds, MelBERT MIP-only achieves the strongest performance at 0.7281 +/- 0.0050 test positive F1, marginally above MelBERT Full (0.7270 +/- 0.0069) and clearly above plain RoBERTa (0.7142 +/- 0.0121). The Qwen QLoRA generative configuration trails encoder baselines by approximately 11 F1 points (0.6157 +/- 0.0113). Three findings merit attention: (1) the SPV channel of MelBERT does not contribute reliable positive signal in Chinese, consistent with the dominance of conventional metaphor; (2) the Qwen-encoder gap is concentrated in recall, reflecting the discrete-commitment limitation of generative output; (3) several Qwen task formulations fail due to format design rather than model capacity. We release all split manifests, per-seed outputs, the MCD7 basic-meaning embedding pipeline, and training scripts to serve as a common reference for future Chinese metaphor identification research.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DDNet: A Dual-Stream Graph Learning and Disentanglement Framework for Temporal Forgery Localization

The rapid evolution of AIGC technology enables misleading viewers by tampering mere small segments within a video, rendering video-level detection inaccurate and unpersuasive. Consequently, temporal forgery localization (TFL), which aims to precisely pinpoint tampered segments, becomes critical. However, existing methods are often constrained by \emph{local view}, failing to capture global anomalies. To address this, we propose a \underline{d}ual-stream graph learning and \underline{d}isentanglement framework for temporal forgery localization (DDNet). By coordinating a \emph{Temporal Distance Stream} for local artifacts and a \emph{Semantic Content Stream} for long-range connections, DDNet prevents global cues from being drowned out by local smoothness. Furthermore, we introduce Trace Disentanglement and Adaptation (TDA) to isolate generic forgery fingerprints, alongside Cross-Level Feature Embedding (CLFE) to construct a robust feature foundation via deep fusion of hierarchical features. Experiments on ForgeryNet and TVIL benchmarks demonstrate that our method outperforms state-of-the-art approaches by approximately 9\% in AP@0.95, with significant improvements in cross-domain robustness.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

NiMark: A Non-intrusive Watermarking Framework against Screen-shooting Attacks

Unauthorized screen-shooting poses a critical data leakage risk. Resisting screen-shooting attacks typically requires high-strength watermark embedding, inevitably degrading the cover image. To resolve the robustness-fidelity conflict, non-intrusive watermarking has emerged as a solution by constructing logical verification keys without altering the original content. However, existing non-intrusive schemes lack the capacity to withstand screen-shooting noise. While deep learning offers a potential remedy, we observe that directly applying it leads to a previously underexplored failure mode, the Structural Shortcut: networks tend to learn trivial identity mappings and neglect the image-watermark binding. Furthermore, even when logical binding is enforced, standard training strategies cannot fully bridge the noise gap, yielding suboptimal robustness against physical distortions. In this paper, we propose NiMark, an end-to-end framework addressing these challenges. First, to eliminate the structural shortcut, we introduce the Sigmoid-Gated XOR (SG-XOR) estimator to enable gradient propagation for the logical operation, effectively enforcing rigid image-watermark binding. Second, to overcome the robustness bottleneck, we devise a two-stage training strategy integrating a restorer to bridge the domain gap caused by screen-shooting noise. Experiments demonstrate that NiMark consistently outperforms representative state-of-the-art methods against both digital attacks and screen-shooting noise, while maintaining zero visual distortion.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

Exploration of Adolescent Depression Risk Prediction Based on Census Surveys and General Life Issues

In contemporary society, the escalating pressures of life and work have propelled psychological disorders to the forefront of modern health concerns, an issue that has been further accentuated by the COVID-19 pandemic. The prevalence of depression among adolescents is steadily increasing, and traditional diagnostic methods, which rely on scales or interviews, prove particularly inadequate for detecting depression in young people. Addressing these challenges, numerous AI-based methods for assisting in the diagnosis of mental health issues have emerged. However, most of these methods center around fundamental issues with scales or use multimodal approaches like facial expression recognition. Diagnosis of depression risk based on everyday habits and behaviors has been limited to small-scale qualitative studies. Our research leverages adolescent census data to predict depression risk, focusing on children's experiences with depression and their daily life situations. We introduced a method for managing severely imbalanced high-dimensional data and an adaptive predictive approach tailored to data structure characteristics. Furthermore, we proposed a cloud-based architecture for automatic online learning and data updates. This study utilized publicly available NSCH youth census data from 2020 to 2022, encompassing nearly 150,000 data entries. We conducted basic data analyses and predictive experiments, demonstrating significant performance improvements over standard machine learning and deep learning algorithms. This affirmed our data processing method's broad applicability in handling imbalanced medical data. Diverging from typical predictive method research, our study presents a comprehensive architectural solution, considering a wider array of user needs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Can Multiple Phylogenetic Trees Be Displayed in a Tree-Child Network Simultaneously?

A binary phylogenetic network on a taxon set $X$ is a rooted acyclic digraph in which the degree of each nonleaf node is three and its leaves (i.e.degree-one nodes) are uniquely labeled with the taxa of $X$. It is tree-child if each nonleaf node has at least one child of indegree one. A set of binary phylogenetic trees may or may not be simultaneously displayed in a binary tree-child network. Necessary conditions for multiple phylogenetic trees being simultaneously displayed in a tree-child network are given here. In particular, it is proved that any two phylogenetic trees can always simultaneously be displayed in some tree-child network on the same taxa set. It is also proved that any set of multiple binary phylogenetic trees can always simultaneously be displayed in some non-binary tree-child network on the same taxa set, where each nonleaf node is of either indegree one and outdegree two or indegree at least two and outdegree out.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Rational numbers in $\times b$-invariant sets

Let $b \geq 2$ be an integer and $S$ be a finite non-empty set of primes not containing divisors of $b$. For any non-dense set $A \subset [0,1)$ such that $A \cap \mathbb{Q}$ is invariant under $\times b$ operation, we prove the finiteness of rational numbers in $A$ whose denominators can only be divided by primes in $S$. A quantitative result on the largest prime divisors of the denominators of rational numbers in $A$ is also obtained.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Dipolar Hole-Blocking Layers for Inverted Perovskite Solar Cells: Effects of Aggregation and Electron Transport Levels

Herein, we report on the synthesis and investigation of two triazino-isoquinoline tetrafluoroborate electrolytes as hole-blocking layers in methylammonium triiodide perovskite photovoltaic devices with fullerene electron extraction layer. We find that increasing the thickness of the dipolar hole-blocking layer results in a gradual increase in the open-circuit voltage suggesting that aggregation of the molecules can enhance the dipole induced by the layer. This finding is confirmed by theoretical calculations demonstrating that while both molecules exhibit a similar dipole moment in their isolated state, this dipole is significantly enhanced when they aggregate. Ultra-violet photoemission spectroscopy measurements show that both derivatives exhibit a high ionisation potential of 7 eV, in agreement with their effective hole-blocking nature demonstrated by the devices. However, each of the molecules shows a different electron affinity due to the increased conjugation of one of the derivatives. While the change in electron transport level between the two derivatives is as high as 0.3 eV, the difference in the open-circuit voltage of both types of devices is negligible, suggesting that the electron transport level plays only a minor role in determining the open-circuit voltage of the device. Numerical device simulations confirm that the increase in built-in potential, arising from the high dipole of the electrolyte layer, compensates for the non-ideal energetic alignment of the charge transport levels, resulting in high VOC for a range of electron transport levels. Our study demonstrates that the application of small molecule electrolytes as hole-blocking layer in inverted architecture perovskite solar cells is a powerful tool to enhance the open-circuit voltage of the devices and provides useful guidelines for designing future generations of such compounds.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Weak Texture Information Map Guided Image Super-resolution with Deep Residual Networks

Single image super-resolution (SISR) is an image processing task which obtains high-resolution (HR) image from a low-resolution (LR) image. Recently, due to the capability in feature extraction, a series of deep learning methods have brought important crucial improvement for SISR. However, we observe that no matter how deeper the networks are designed, they usually do not have good generalization ability, which leads to the fact that almost all of existing SR methods have poor performances on restoration of the weak texture details. To solve these problems, we propose a weak texture information map guided image super-resolution with deep residual networks. It contains three sub-networks, one main network which extracts the main features and fuses weak texture details, another two auxiliary networks extract the weak texture details fallen in the main network. Two part of networks work cooperatively, the auxiliary networks predict and integrates week texture information into the main network, which is conducive to the main network learning more inconspicuous details. Experiments results demonstrate that our method's performs achieve the state-of-the-art quantitatively. Specifically, the image super-resolution results of our method own more weak texture details.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Near-term performance of quantum repeaters with imperfect ensemble-based quantum memories

We study the feasibility of meaningful proof-of-principle demonstrations of several quantum repeater protocols with photon (single-photon and photon-pair) sources and atomic-ensemble based quantum memories. We take into account non-unit memory efficiencies that decay exponentially with time, which complicates the calculation of repeater rates. We discuss implementations based on quantum dots, parametric down-conversion, rare-earth-ion doped crystals, and Rydberg atoms. Our results provide guidance for the near-term implementation of long-distance quantum repeater demonstrations, suggesting that such demonstrations are within reach of current technology.

0 citations0 reviewsNo code linkedOpen access