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

Yuanbin Wu

Yuanbin Wu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and Languagenucl-thArtificial IntelligenceMachine Learningphysics.plasm-phComputer Visionhep-phInformation Retrievalphysics.atom-ph

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
13works
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

13 published item(s)

preprint2026arXiv

Logic-Regularized Verifier Elicits Reasoning from LLMs

Verifiers are crucial components for enhancing modern LLMs' reasoning capability. Typicalverifiers require resource-intensive superviseddataset construction, which is costly and faceslimitations in data diversity. In this paper, wepropose LOVER, an unsupervised verifier regularized by logical rules. LOVER treats theverifier as a binary latent variable, utilizinginternal activations and enforcing three logical constraints on multiple reasoning paths:negation consistency, intra-group consistency,and inter-group consistency (grouped by thefinal answer). By incorporating logical rulesas priors, LOVER can leverage unlabeled examples and is directly compatible with any offthe-shelf LLMs. Experiments on 10 datasetsdemonstrate that LOVER significantly outperforms unsupervised baselines, achieving performance comparable to the supervised verifier(reaching its 95% level on average). The sourcecode is publicly available at https://github.com/wangxinyufighting/llm-lover.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Off-axis vortex scattering of electron-positron annihilation into a photon pair

The off-axis triple-vortex scattering process of $e^-e^+\toγγ$ is studied theoretically, in which the positron is in a plane-wave state and the electron and photons are in vortex states. We develop a theoretical formalism for the process, which allows us to study the effects of various vortex parameters and scattering angle. We adopt a Bessel-Gaussian type wave packet for the initial vortex electron for the purpose of normalization. Numerical calculations are performed for an electron and a positron with a moderate energy around $1~\textrm{MeV}$. Our results demonstrate strong impacts of the scattering angle and the topological charges on the cross section and distributions in the energy and cone angles of the vortex photons. This could provide insight into off-axis vortex scattering and also a possible approach to distinguishing and detecting vortex electrons by off-axis vortex scattering.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Stabilizing LLM Supervised Fine-Tuning via Explicit Distributional Control

Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evidence suggests that this phenomenon is primarily driven by excessive distributional drift during optimization. Motivated by this perspective, we propose Anchored Learning, a simple framework that explicitly controls distributional updates during offline fine-tuning via a dynamically evolving moving anchor. Instead of matching a fixed reference distribution, the anchor interpolates between the current model and a frozen reference to construct an intermediate target that the model distills toward, transforming global fine-tuning into a sequence of local trust-region updates in distribution space. Theoretically, we prove this anchor-based update admits a linear KL-divergence upper bound per iteration, ensuring a stable transition between model distributions. Extensive experiments on iGSM, MedCalc, and IFEval show that Anchored Learning consistently lies on the Pareto frontier of gain-stability trade-offs, achieving near-optimal performance improvements while substantially reducing degradation compared to strong baselines. For example, while standard SFT suffers from over 53% performance degradation on iGSM and MedCalc, Anchored Learning slashes this drop to under 5% while maintaining near-optimal gains (e.g., 75.2% on iGSM).

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

Text2MDT: Extracting Medical Decision Trees from Medical Texts

Knowledge of the medical decision process, which can be modeled as medical decision trees (MDTs), is critical to build clinical decision support systems. However, the current MDT construction methods rely heavily on time-consuming and laborious manual annotation. In this work, we propose a novel task, Text2MDT, to explore the automatic extraction of MDTs from medical texts such as medical guidelines and textbooks. We normalize the form of the MDT and create an annotated Text-to-MDT dataset in Chinese with the participation of medical experts. We investigate two different methods for the Text2MDT tasks: (a) an end-to-end framework which only relies on a GPT style large language models (LLM) instruction tuning to generate all the node information and tree structures. (b) The pipeline framework which decomposes the Text2MDT task to three subtasks. Experiments on our Text2MDT dataset demonstrate that: (a) the end-to-end method basd on LLMs (7B parameters or larger) show promising results, and successfully outperform the pipeline methods. (b) The chain-of-thought (COT) prompting method \cite{Wei2022ChainOT} can improve the performance of the fine-tuned LLMs on the Text2MDT test set. (c) the lightweight pipelined method based on encoder-based pretrained models can perform comparably with LLMs with model complexity two magnititudes smaller. Our Text2MDT dataset is open-sourced at \url{https://tianchi.aliyun.com/dataset/95414}, and the source codes are open-sourced at \url{https://github.com/michael-wzhu/text2dt}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Few Clean Instances Help Denoising Distant Supervision

Existing distantly supervised relation extractors usually rely on noisy data for both model training and evaluation, which may lead to garbage-in-garbage-out systems. To alleviate the problem, we study whether a small clean dataset could help improve the quality of distantly supervised models. We show that besides getting a more convincing evaluation of models, a small clean dataset also helps us to build more robust denoising models. Specifically, we propose a new criterion for clean instance selection based on influence functions. It collects sample-level evidence for recognizing good instances (which is more informative than loss-level evidence). We also propose a teacher-student mechanism for controlling purity of intermediate results when bootstrapping the clean set. The whole approach is model-agnostic and demonstrates strong performances on both denoising real (NYT) and synthetic noisy datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Quantum effects on plasma screening for thermonuclear reactions in laser-generated plasmas

A quantum plasma screening model based on the density matrix formalism is used to investigate theoretically the thermonuclear reactions $^{13}$C($α$, $n$)$^{16}$O and $^2$H($d$, $n$)$^3$He in laser-generated plasmas over a large range of densities and temperatures. For cold and dense (solid-state density) plasmas, our results show that quantum effects can enhance the plasma screening for thermonuclear reactions up to one order of magnitude compared to the classical case. This result can have impact on nuclear astrophysics predictions, and also may play a role for fusion energy gain prospects. Our simulations allow us to identify the laser-generated plasma experimental setting in which the quantum effects on plasma screening could be confirmed at existing high-intensity laser facilities.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Dynamical control of nuclear isomer depletion via electron vortex beams

Long-lived excited states of atomic nuclei can act as energy traps. These states, known as nuclear isomers, can store a large amount of energy over long periods of time, with a very high energy-to-mass ratio. Under natural conditions, the trapped energy is only slowly released, limited by the long isomer lifetimes. Dynamical external control of nuclear state population has proven so far very challenging, despite ground-breaking incentives for a clean and efficient energy storage solution. Here, we describe a protocol to achieve the external control of the isomeric nuclear decay by using electrons whose wavefunction has been especially designed and reshaped on demand. Recombination of these electrons into the atomic shell around the isomer can lead to the controlled release of the stored nuclear energy. On the example of $^{93m}$Mo, we show that the use of tailored electron vortex beams increases the depletion by four orders of magnitude compared to the spontaneous nuclear decay of the isomer. Furthermore, specific orbitals can sustain an enhancement of the recombination cross section for vortex electron beams by as much as six orders of magnitude, providing a handle for manipulating the capture mechanism. These findings open new prospects for controlling the interplay between atomic and nuclear degrees of freedom, with potential energy-related and high-energy radiation sources applications.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Exploring laser-driven neutron sources for neutron capture cascades and the production of neutron-rich isotopes

The production of neutron-rich isotopes and the occurrence of neutron capture cascades via laser-driven (pulsed) neutron sources are investigated theoretically. The considered scenario involves the interaction of a laser-driven neutron beam with a target made of a single type of seed nuclide. We present a comprehensive study over $95$ seed nuclides in the range $3\le Z \le 100$ from $^7_3$Li to $^{255}_{100}$Fm. For each element, the heaviest sufficiently-long-lived (half life $> 1$ h) isotope whose data is available in the recent ENDF-B-VIII.0 neutron sublibrary is considered. We identify interesting seed nuclides with good performance in the production of neutron-rich isotopes where neutron capture cascades may occur. The effects of the neutron number per pulse, the neutron-target interaction size and the number of neutron pulses are also analyzed. Our results show the possibility of observing up to $4$ successive neutron capture events leading to neutron-rich isotopes with $4$ more neutrons than the original seed nuclide. This hints at new experimental possibilities to produce neutron-rich isotopes and simulate neutron capture nucleosynthesis in the laboratory. With several selected interesting seed nuclides in the region of the branching point of the $s$-process ($^{126}_{51}$Sb, $^{176}_{71}$Lu and $^{187}_{75}$Re) or the waiting point of the $r$-process (Lu, Re, Os, Tm, Ir and Au), we expect that laser-driven experiments can shed light on our understanding of nucleosynthesis.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

In-Order Chart-Based Constituent Parsing

We propose a novel in-order chart-based model for constituent parsing. Compared with previous CKY-style and top-down models, our model gains advantages from in-order traversal of a tree (rich features, lookahead information and high efficiency) and makes a better use of structural knowledge by encoding the history of decisions. Experiments on the Penn Treebank show that our model outperforms previous chart-based models and achieves competitive performance compared with other discriminative single models.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Span-based Linearization for Constituent Trees

We propose a novel linearization of a constituent tree, together with a new locally normalized model. For each split point in a sentence, our model computes the normalizer on all spans ending with that split point, and then predicts a tree span from them. Compared with global models, our model is fast and parallelizable. Different from previous local models, our linearization method is tied on the spans directly and considers more local features when performing span prediction, which is more interpretable and effective. Experiments on PTB (95.8 F1) and CTB (92.4 F1) show that our model significantly outperforms existing local models and efficiently achieves competitive results with global models.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Neutron production from thermonuclear reactions in laser-generated plasmas

The production of intense neutron beams via thermonuclear reactions in laser-generated plasmas is investigated theoretically. So far, state-of-the-art neutron beams are produced via laser-induced particle acceleration leading to high-energy particle beams that subsequently interact with a secondary target. Here we show that neutron beams of two orders of magnitude narrower bandwidth can be obtained from thermonuclear reactions in plasmas generated by Petawatt-class lasers. The intensity of such neutron beams is about one or two orders of magnitude lower than the one of the state-of-the-art laser-driven neutron beams. We study to this end the reaction $^2$H($d$, $n$)$^3$He in plasmas generated by Petawatt-class lasers interacting with D$_2$ gas jet targets and CD$_2$ solid-state targets. The results also shows the possibility of direct measurements of reaction rates at low temperatures of astrophysical interests. In addition, the use of CD$_2$ solid-state targets can also lead to great enhancements on the plasma screening compared to the case of D$_2$ gas jet targets, opening new possibilities to study this so far unsolved issue in the field of astrophysics.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Relational Reflection Entity Alignment

Entity alignment aims to identify equivalent entity pairs from different Knowledge Graphs (KGs), which is essential in integrating multi-source KGs. Recently, with the introduction of GNNs into entity alignment, the architectures of recent models have become more and more complicated. We even find two counter-intuitive phenomena within these methods: (1) The standard linear transformation in GNNs is not working well. (2) Many advanced KG embedding models designed for link prediction task perform poorly in entity alignment. In this paper, we abstract existing entity alignment methods into a unified framework, Shape-Builder & Alignment, which not only successfully explains the above phenomena but also derives two key criteria for an ideal transformation operation. Furthermore, we propose a novel GNNs-based method, Relational Reflection Entity Alignment (RREA). RREA leverages Relational Reflection Transformation to obtain relation specific embeddings for each entity in a more efficient way. The experimental results on real-world datasets show that our model significantly outperforms the state-of-the-art methods, exceeding by 5.8%-10.9% on Hits@1.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Visual Attack and Defense on Text

Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of generating such visual text attack and show that the attacked text are readable by humans but mislead a neural classifier greatly. We ap-ply a vision-based model and adversarial training to defense the attack without losing the ability to understand normal text. Our results also show that visual attack is extremely sophisticated and diverse, more work needs to be done to solve this.

0 citations0 reviewsNo code linkedOpen access