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

Zheng Yuan

Zheng Yuan contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
math.CVComputation and Languagemath.AGArtificial IntelligenceMachine Learningphysics.opticsComputer VisionCryptography and Securitymath.ACquant-ph

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
23works
0followers
10topics
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

23 published item(s)

preprint2026arXiv

Multi-Dimensional Evaluation of LLMs for Grammatical Error Correction

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack comprehensive evaluation on grammar correction tasks; (2) whether combining these LLMs improves correction quality is unexplored; and (3) the extent to which reference-based metrics underestimate GEC system performance has not been adequately quantified. In this study, first, we evaluate latest-generation LLMs on edit precision, fluency preservation, and meaning retention, showing fine-tuned GPT-4o achieves state-of-the-art performance across all three dimensions. Second, through grammatical error type analysis we demonstrate that individual LLMs exhibit highly similar error correction patterns ($ρ=0.947$). Third, we show that reference-based metrics underestimate GEC performance with 73.76% of GPT-4o corrections different from gold standards being equally valid or even superior. These GEC evaluation findings equip educators with guidance for selecting GEC assistants that enhance rather than constrain student linguistic development. We make our data, code, and models publicly available.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

The existence of valuative interpolation at a singular point

The present paper studies the existence of valuative interpolation on the local ring of an irreducible analytic subvariety at singular points. We firstly develop the concepts and methods of Zhou weights and Tian functions near singular points of irreducible analytic subvarieties. By applying these tools, we establish the necessary and sufficient conditions for the existence of valuative interpolations on the rings of germs of holomorphic functions and weakly holomorphic functions at a singular point. As applications, we characterize the existence of valuative interpolations on the quotient ring of the ring of convergent power series in real variables. We also present separated necessary and sufficient conditions for the existence of valuative interpolations on the quotient ring of polynomial rings with complex coefficients and real coefficients. Furthermore, we show that the conditions become both necessary and sufficient under certain conditions on the zero set of the given polynomials.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

T2VAttack: Adversarial Attack on Text-to-Video Diffusion Models

The rapid evolution of Text-to-Video (T2V) diffusion models has driven remarkable advancements in generating high-quality, temporally coherent videos from natural language descriptions. Despite these achievements, their vulnerability to adversarial attacks remains largely unexplored. In this paper, we introduce T2VAttack, a comprehensive study of adversarial attacks on T2V diffusion models from both semantic and temporal perspectives. Considering the inherently dynamic nature of video data, we propose two distinct attack objectives: a semantic objective to evaluate video-text alignment and a temporal objective to assess the temporal dynamics. To achieve an effective and efficient attack process, we propose two adversarial attack methods: (i) T2VAttack-S, which identifies semantically or temporally critical words in prompts and replaces them with synonyms via greedy search, and (ii) T2VAttack-I, which iteratively inserts optimized words with minimal perturbation to the prompt. By combining these objectives and strategies, we conduct a comprehensive evaluation on the adversarial robustness of several state-of-the-art T2V models, including ModelScope, CogVideoX, Open-Sora, and HunyuanVideo. Our experiments reveal that even minor prompt modifications, such as the substitution or insertion of a single word, can cause substantial degradation in semantic fidelity and temporal dynamics, highlighting critical vulnerabilities in current T2V diffusion models.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Concavity property of minimal $L^{2}$ integrals with Lebesgue measurable gain VII -- Negligible weights

In this article, we present characterizations of the concavity property of minimal $L^2$ integrals with negligible weights degenerating to linearity on the fibrations over open Riemann surfaces and the fibrations over products of open Riemann surfaces. As applications, we obtain characterizations of the holding of equality in optimal jets $L^2$ extension problem with negligible weights on the fibrations over open Riemann surfaces and the fibrations over products of open Riemann surfaces.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

$ \text{T}^3 $OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area

Smart Internet of Vehicles (IoVs) combined with Artificial Intelligence (AI) will contribute to vehicle decision-making in the Intelligent Transportation System (ITS). Multi-Vehicle Pursuit games (MVP), a multi-vehicle cooperative ability to capture mobile targets, is becoming a hot research topic gradually. Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games. We define an Observation-constrained MVP (OMVP) problem in this paper and propose a Transformer-based Time and Team Reinforcement Learning scheme ($ \text{T}^3 $OMVP) to address the problem. First, a new multi-vehicle pursuit model is constructed based on decentralized partially observed Markov decision processes (Dec-POMDP) to instantiate this problem. Second, by introducing and modifying the transformer-based observation sequence, QMIX is redefined to adapt to the complicated road structure, restricted moving spaces and constrained observations, so as to control vehicles to pursue the target combining the vehicle's observations. Third, a multi-intersection urban environment is built to verify the proposed scheme. Extensive experimental results demonstrate that the proposed $ \text{T}^3 $OMVP scheme achieves significant improvements relative to state-of-the-art QMIX approaches by 9.66%~106.25%. Code is available at https://github.com/pipihaiziguai/T3OMVP.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Automatic Biomedical Term Clustering by Learning Fine-grained Term Representations

Term clustering is important in biomedical knowledge graph construction. Using similarities between terms embedding is helpful for term clustering. State-of-the-art term embeddings leverage pretrained language models to encode terms, and use synonyms and relation knowledge from knowledge graphs to guide contrastive learning. These embeddings provide close embeddings for terms belonging to the same concept. However, from our probing experiments, these embeddings are not sensitive to minor textual differences which leads to failure for biomedical term clustering. To alleviate this problem, we adjust the sampling strategy in pretraining term embeddings by providing dynamic hard positive and negative samples during contrastive learning to learn fine-grained representations which result in better biomedical term clustering. We name our proposed method as CODER++, and it has been applied in clustering biomedical concepts in the newly released Biomedical Knowledge Graph named BIOS.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model

Pretrained language models have served as important backbones for natural language processing. Recently, in-domain pretraining has been shown to benefit various domain-specific downstream tasks. In the biomedical domain, natural language generation (NLG) tasks are of critical importance, while understudied. Approaching natural language understanding (NLU) tasks as NLG achieves satisfying performance in the general domain through constrained language generation or language prompting. We emphasize the lack of in-domain generative language models and the unsystematic generative downstream benchmarks in the biomedical domain, hindering the development of the research community. In this work, we introduce the generative language model BioBART that adapts BART to the biomedical domain. We collate various biomedical language generation tasks including dialogue, summarization, entity linking, and named entity recognition. BioBART pretrained on PubMed abstracts has enhanced performance compared to BART and set strong baselines on several tasks. Furthermore, we conduct ablation studies on the pretraining tasks for BioBART and find that sentence permutation has negative effects on downstream tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

BIOS: An Algorithmically Generated Biomedical Knowledge Graph

Biomedical knowledge graphs (BioMedKGs) are essential infrastructures for biomedical and healthcare big data and artificial intelligence (AI), facilitating natural language processing, model development, and data exchange. For decades, these knowledge graphs have been developed via expert curation; however, this method can no longer keep up with today's AI development, and a transition to algorithmically generated BioMedKGs is necessary. In this work, we introduce the Biomedical Informatics Ontology System (BIOS), the first large-scale publicly available BioMedKG generated completely by machine learning algorithms. BIOS currently contains 4.1 million concepts, 7.4 million terms in two languages, and 7.3 million relation triplets. We present the methodology for developing BIOS, including the curation of raw biomedical terms, computational identification of synonymous terms and aggregation of these terms to create concept nodes, semantic type classification of the concepts, relation identification, and biomedical machine translation. We provide statistics on the current BIOS content and perform preliminary assessments of term quality, synonym grouping, and relation extraction. The results suggest that machine learning-based BioMedKG development is a viable alternative to traditional expert curation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Boundary points, minimal $L^2$ integrals and concavity property II: on weakly pseudoconvex Kähler manifolds

In this article, we consider minimal $L^2$ integrals on the sublevel sets of plurisubharmonic functions on weakly pseudoconvex Kähler manifolds with Lebesgue measurable gain related to modules at boundary points of the sublevel sets, and establish a concavity property of the minimal $L^2$ integrals. As applications, we present a necessary condition for the concavity degenerating to linearity, a concavity property related to modules at inner points of the sublevel sets, an optimal support function related to the modules, a strong openness property of the modules and a twisted version, an effectiveness result of the strong openness property of the modules.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Boundary points, minimal $L^2$ integrals and concavity property V -- vector bundles

In this article, for singular hermitian metrics on holomorphic vector bundles, we consider minimal $L^2$ integrals on sublevel sets of plurisubharmonic functions on weakly pseudoconvex Kähler manifolds related to modules at boundary points of the sublevel sets, and establish a concavity property of the minimal $L^2$ integrals. As applications, we present a necessary condition for the concavity degenerating to linearity, a strong openness property of the modules and a twisted version, an effectiveness result of the strong openness property of the modules, and an optimal support function related to the modules.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding

Automatic ICD coding is defined as assigning disease codes to electronic medical records (EMRs). Existing methods usually apply label attention with code representations to match related text snippets. Unlike these works that model the label with the code hierarchy or description, we argue that the code synonyms can provide more comprehensive knowledge based on the observation that the code expressions in EMRs vary from their descriptions in ICD. By aligning codes to concepts in UMLS, we collect synonyms of every code. Then, we propose a multiple synonyms matching network to leverage synonyms for better code representation learning, and finally help the code classification. Experiments on the MIMIC-III dataset show that our proposed method outperforms previous state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Concavity property of minimal $L^2$ integrals with Lebesgue measurable gain IV: product of open Riemann surfaces

In this article, we present characterizations of the concavity property of minimal $L^2$ integrals degenerating to linearity in the case of products of analytic subsets on products of open Riemann surfaces. As applications, we obtain characterizations of the holding of equality in optimal jets $L^2$ extension problem from products of analytic subsets to products of open Riemann surfaces, which implies characterizations of the product versions of the equality parts of Suita conjecture and extended Suita conjecture, and the equality holding of a conjecture of Ohsawa for products of open Riemann surfaces.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Concavity property of minimal $L^2$ integrals with Lebesgue measurable gain VI: fibrations over products of open Riemann surfaces

In this article, we present characterizations of the concavity property of minimal $L^2$ integrals degenerating to linearity in the case of fibrations over products of open Riemann surfaces. As applications, we obtain characterizations of the holding of equality in optimal jets $L^2$ extension problem from fibers over products of analytic subsets to fibrations over products of open Riemann surfaces, which implies characterizations of the equality parts of Suita conjecture and extended Suita conjecture for fibrations over products of open Riemann surfaces.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching

The expansion of renewable energy could help realizing the goals of peaking carbon dioxide emissions and carbon neutralization. Some existing grid dispatching methods integrating short-term renewable energy prediction and reinforcement learning (RL) have been proved to alleviate the adverse impact of energy fluctuations risk. However, these methods omit the long-term output prediction, which leads to stability and security problems on the optimal power flow. This paper proposes a confidence estimation Transformer for long-term renewable energy forecasting in reinforcement learning-based power grid dispatching (Conformer-RLpatching). Conformer-RLpatching predicts long-term active output of each renewable energy generator with an enhanced Transformer to boost the performance of hybrid energy grid dispatching. Furthermore, a confidence estimation method is proposed to reduce the prediction error of renewable energy. Meanwhile, a dispatching necessity evaluation mechanism is put forward to decide whether the active output of a generator needs to be adjusted. Experiments carried out on the SG-126 power grid simulator show that Conformer-RLpatching achieves great improvement over the second best algorithm DDPG in security score by 25.8% and achieves a better total reward compared with the golden medal team in the power grid dispatching competition sponsored by State Grid Corporation of China under the same simulation environment. Codes are outsourced in https://github.com/buptlxh/Conformer-RLpatching.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition

Nested entities are observed in many domains due to their compositionality, which cannot be easily recognized by the widely-used sequence labeling framework. A natural solution is to treat the task as a span classification problem. To learn better span representation and increase classification performance, it is crucial to effectively integrate heterogeneous factors including inside tokens, boundaries, labels, and related spans which could be contributing to nested entities recognition. To fuse these heterogeneous factors, we propose a novel triaffine mechanism including triaffine attention and scoring. Triaffine attention uses boundaries and labels as queries and uses inside tokens and related spans as keys and values for span representations. Triaffine scoring interacts with boundaries and span representations for classification. Experiments show that our proposed method outperforms previous span-based methods, achieves the state-of-the-art $F_1$ scores on nested NER datasets GENIA and KBP2017, and shows comparable results on ACE2004 and ACE2005.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuning

Entities lie in the heart of biomedical natural language understanding, and the biomedical entity linking (EL) task remains challenging due to the fine-grained and diversiform concept names. Generative methods achieve remarkable performances in general domain EL with less memory usage while requiring expensive pre-training. Previous biomedical EL methods leverage synonyms from knowledge bases (KB) which is not trivial to inject into a generative method. In this work, we use a generative approach to model biomedical EL and propose to inject synonyms knowledge in it. We propose KB-guided pre-training by constructing synthetic samples with synonyms and definitions from KB and require the model to recover concept names. We also propose synonyms-aware fine-tuning to select concept names for training, and propose decoder prompt and multi-synonyms constrained prefix tree for inference. Our method achieves state-of-the-art results on several biomedical EL tasks without candidate selection which displays the effectiveness of proposed pre-training and fine-tuning strategies.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Manipulating propagation and evolution of polarization singularities in composite Bessel-like fields

Structured optical fields embedded with polarization singularities (PSs) have attracted extensive attention due to their capability to retain topological invariance during propagation. Many advances in PSs research have been made over the past 20 years in the areas of mathematical description, generation and detection technologies, propagation dynamics, and applications. However, one of the most crucial and difficult tasks continues to be manipulating PSs with multiple degrees of freedom, especially in three-dimensional (3D) tailored optical fields. We propose and demonstrate the longitudinal PS lines obtained by superimposing Bessel-like modes with orthogonal polarization states on composite vector optical fields (VOFs). The embedded PSs in the fields can be manipulated to propagate robustly along arbitrary trajectories, or to annihilate, revive, and transform each other at on-demand positions in 3D space, allowing complex PSs topological morphology and intensity pattern to be flexibly customized. Our findings could spur further research into singular optics and help with applications such as micromanipulation, microstructure fabrication, and optical encryption.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Quantum Meet-in-the-Middle Attack on Feistel Construction

Inspired by Hosoyamada et al.'s work [14], we propose a new quantum meet-in-the-middle (QMITM) attack on $r$-round ($r \ge 7$) Feistel construction to reduce the time complexity. Similar to Hosoyamada et al.'s work, our attack on 7-round Feistel is also based on Guo et al.'s classical meet-in-the-middle (MITM) attack [13]. The classic MITM attack consumes a lot of time mainly in three aspects: construct the lookup table, query data and find a match. Therefore, parallel Grover search processors are used to reduce the time of constructing the lookup table. And we adjust the truncated differentials of the 5-round distinguisher proposed by Guo et al. to balance the complexities between constructing the lookup table and querying data. Finally, we introduce a quantum claw finding algorithm to find a match for reducing time. The subkeys can be recovered by this match. Furthermore, for $r$-round ($r > 7$) Feistel construction, we treat the above attack on the first 7 rounds as an inner loop and use Grover's algorithm to search the last $r-7$ rounds of subkeys as an outer loop. In summary, the total time complexity of our attack on $r$-round ($r \ge 7$) is only $O(2^{2n/3+(r-7)n/4})$ less than classical and quantum attacks. Moreover, our attack belongs to Q1 model and is more practical than other quantum attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Versatile Non-diffracting Perfect Vortex Beams

The rapid scale broadening and divergence increasing of vortex beams (VBs) with orbital angular momentum (OAM), e.g., Laguerre-Gaussian beams, severely impede the wide applications of VBs ranging from optical manipulation to high-dimensional quantum information communications, which call for VBs to have the same transverse scale and divergence for distinct OAM or even the small vortex ring for large OAM. Non-diffracting beams, on the other hand, that are capable of overcoming diffraction without divergence, are very evocative and indeed appealing in numerous applications including atom optics and medical imaging. Here, we propose theoretically and demonstrate experimentally a brand new type of VB having OAM-independent radii meanwhile holding propagation-invariant without divergence as well as self-healing properties, named non-diffracting perfect vortex beam (NDPVB). We work out a versatile toolkit based on Fourier-space analysis to multidimensionally customize NDPVBs at will so that it is of propagating intensity and phase controllability with intriguing customizable behaviors of self-accelerating, self-similar, and self-rotating. This goes beyond tailoring the transverse plane to the higher-dimensional propagating characteristics in structured light beams. A deeper insight into the internal flow revealed and confirmed that the multidimensional customization of NDPVBs is dominated by inducing corresponding multidimensional internal flow, facilitating our understanding of how our design scheme of propagating properties manipulates the internal flows, unveiling the nature of structure formation and behavior transformation of structured light beams.

0 citations0 reviewsNo code linkedOpen access