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

Kexin Yang

Kexin Yang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and Languagecond-mat.mtrl-sciArtificial Intelligencephysics.soc-phPopulations and EvolutionSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
8works
0followers
6topics
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

8 published item(s)

preprint2026arXiv

NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs

While Large Language Models (LLMs) have demonstrated remarkable proficiency in generating standalone charts, synthesizing comprehensive dashboards remains a formidable challenge. Existing end-to-end paradigms, which typically treat dashboard generation as a direct code generation task (e.g., raw HTML), suffer from two fundamental limitations: representation redundancy due to massive tokens spent on visual rendering, and low controllability caused by the entanglement of analytical reasoning and presentation. To address these challenges, we propose NL2Dashboard, a lightweight framework grounded in the principle of Analysis-Presentation Decoupling. We introduce a structured intermediate representation (IR) that encapsulates the dashboard's content, layout, and visual elements. Therefore, it confines the LLM's role to data analysis and intent translation, while offloading visual synthesis to a deterministic rendering engine. Building upon this framework, we develop a multi-agent system in which the IR-driven algorithm is instantiated as a suite of tools. Comprehensive experiments conducted with this system demonstrate that NL2Dashboard significantly outperforms state-of-the-art baselines across diverse domains, achieving superior visual quality, significantly higher token efficiency, and precise controllability in both generation and modification tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

On Predicting the Post-training Potential of Pre-trained LLMs

The performance of Large Language Models (LLMs) on downstream tasks is fundamentally constrained by the capabilities acquired during pre-training. However, traditional benchmarks like MMLU often fail to reflect a base model's plasticity in complex open-ended scenarios, leading to inefficient model selection. We address this by introducing a new task of predicting post-training potential - forecasting a base model's performance before post-training. We propose RuDE (Rubric-based Discriminative Evaluation), a unified framework that bypasses the generation gap of base models by leveraging response discrimination. Guided by our systematic 4C Taxonomy, RuDE constructs controlled contrastive pairs across diverse domains by fine-grained rubric violations. Extensive experiments demonstrate a correlation greater than 90% with post-training performance. Crucially, validation via Reinforcement Learning (RL) confirms that RuDE effectively identifies high-potential smaller models that outperform larger counterparts, offering a compute-efficient mechanism for foundation model development.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Draft, Command, and Edit: Controllable Text Editing in E-Commerce

Product description generation is a challenging and under-explored task. Most such work takes a set of product attributes as inputs then generates a description from scratch in a single pass. However, this widespread paradigm might be limited when facing the dynamic wishes of users on constraining the description, such as deleting or adding the content of a user-specified attribute based on the previous version. To address this challenge, we explore a new draft-command-edit manner in description generation, leading to the proposed new task-controllable text editing in E-commerce. More specifically, we allow systems to receive a command (deleting or adding) from the user and then generate a description by flexibly modifying the content based on the previous version. It is easier and more practical to meet the new needs by modifying previous versions than generating from scratch. Furthermore, we design a data augmentation method to remedy the low resource challenge in this task, which contains a model-based and a rule-based strategy to imitate the edit by humans. To accompany this new task, we present a human-written draft-command-edit dataset called E-cEdits and a new metric "Attribute Edit". Our experimental results show that using the new data augmentation method outperforms baselines to a greater extent in both automatic and human evaluations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Personalized recommendation system based on social relationships and historical behaviors

Previous studies show that recommendation algorithms based on historical behaviors of users can provide satisfactory recommendation performance. Many of these algorithms pay attention to the interest of users, while ignore the influence of social relationships on user behaviors. Social relationships not only carry intrinsic information of similar consumption tastes or behaviors, but also imply the influence of individual to its neighbors. In this paper, we assume that social relationships and historical behaviors of users are related to the same factors. Based on this assumption, we propose an algorithm to focus on social relationships useful for recommendation systems through mutual constraints from both types of information. We test the performance of our algorithm on four types of users, including all users, active users, inactive users and cold-start users. Results show that the proposed algorithm outperforms benchmarks in four types of scenarios subject to recommendation accuracy and diversity metrics. We further design a randomization model to explore the contribution of social relationships to recommendation performance, and the result shows that the contribution of social relationships in the proposed algorithm depends on the coupling strength of social relationships and historical behaviors.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation

Attribute-based Controlled Text Generation (CTG) refers to generating sentences that satisfy desirable attributes (e.g., emotions and topics). Existing works often utilize fine-tuning or resort to extra attribute classifiers, yet suffer from storage and inference time increases. To address these concerns, we explore attribute-based CTG in a prompt-based manner. In short, the proposed Tailor represents each attribute as a pre-trained continuous vector (i.e., single-attribute prompt) and guides the generation of a fixed PLM switch to a pre-specified attribute. We experimentally find that these prompts can be simply concatenated as a whole to multi-attribute CTG without any re-training, yet raises problems of fluency decrease and position sensitivity. To this end, Tailor provides a multi-attribute prompt mask and a re-indexing position-ids sequence to bridge the gap between the training (one prompt for each task) and testing stage (concatenating more than one prompt). To further enhance such single-attribute prompt combinations, Tailor also introduces a trainable prompt connector, which can be concatenated with any two single-attribute prompts to multi-attribute text generation. Experiments on 11 attribute-specific generation tasks demonstrate strong performances of Tailor on both single-attribute and multi-attribute CTG, with 0.08\% training parameters of a GPT-2.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Magnetocrystalline anisotropy of the easy-plane metallic antiferromagnet Fe$_2$As

Magnetocrystalline anisotropy is a fundamental property of magnetic materials that determines the dynamics of magnetic precession, the frequency of spin waves, the thermal stability of magnetic domains, and the efficiency of spintronic devices. We combine torque magnetometry and density functional theory calculations to determine the magnetocrystalline anisotropy of the metallic antiferromagnet Fe$_2$As. Fe$_2$As has a tetragonal crystal structure with the Néel vector lying in the (001) plane. We report that the four-fold magnetocrystalline anisotropy in the (001)-plane of Fe$_2$As is extremely small, ${K_{22}} = - 150~{\rm{ J/}}{\rm{m}^{\rm{3}}}$ at T = 4 K, much smaller than perpendicular magnetic anisotropy of ferromagnetic structure widely used in spintronics device. ${K_{22}}$ is strongly temperature dependent and close to zero at T > 150 K. The anisotropy ${K_1}$ in the (010) plane is too large to be measured by torque magnetometry and we determine ${K_1} = -830~{\rm{ kJ/}}{\rm{m}^{\rm{3}}}$ using first-principles density functional theory. Our simulations show that the contribution to the anisotropy from classical magnetic dipole-dipole interactions is comparable to the contribution from spin-orbit coupling. The calculated four-fold anisotropy in the (001) plane ${K_{22}}$ ranges from $- 292~{\rm{ J/}}{\rm{m}^{\rm{3}}}$ to $280~{\rm{ J/}}{\rm{m}^{\rm{3}}}$, the same order of magnitude as the measured value. We use ${K_1}$ from theory to predict the frequency and polarization of the lowest frequency antiferromagnetic resonance mode and find that the mode is linearly polarized in the (001)-plane with $f = $ 670 GHz.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Preliminary prediction of the basic reproduction number of the Wuhan novel coronavirus 2019-nCoV

Objectives.--To estimate the basic reproduction number of the Wuhan novel coronavirus (2019-nCoV). Methods.--Based on the susceptible-exposed-infected-removed (SEIR) compartment model and the assumption that the infectious cases with symptoms occurred before January 25, 2020 are resulted from free propagation without intervention, we estimate the basic reproduction number of 2019-nCoV according to the reported confirmed cases and suspected cases, as well as the theoretical estimated number of infected cases by other research teams, together with some epidemiological determinants learned from the severe acute respiratory syndrome. Results The basic reproduction number falls between 2.8 to 3.3 by using the real-time reports on the number of 2019-nCoV infected cases from People's Daily in China, and falls between 3.2 and 3.9 on the basis of the predicted number of infected cases from colleagues. Conclusions.--The early transmission ability of 2019-nCoV is closed to or slightly higher than SARS. It is a controllable disease with moderate-high transmissibility. Timely and effective control measures are needed to suppress the further transmissions. Notes Added.--Using a newly reported epidemiological determinants for early 2019-nCoV, the estimated basic reproduction number is in the range [2.2,3.0].

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Magneto-optic Response of the Metallic Antiferromagnet Fe$_{2}$As to Ultrafast Temperature Excursions

The linear magneto-optical Kerr effect (MOKE) is often used to probe magnetism of ferromagnetic materials, but MOKE cannot be applied to collinear antiferromagnets (AFs) due to the cancellation of sub-lattice magnetization. Magneto-optical constants that are quadratic in magnetization, however, provide an approach for studying AFs on picosecond time scales. Here, we combine transient measurements of optical reflectivity and birefringence to study the linear optical response of Fe$_{2}$As to small ultrafast temperature excursions. We performed temperature dependent pump-probe measurements on crystallographically isotropic (001) and anisotropic (010) faces of Fe$_{2}$As bulk crystals. We find the largest optical signals arise from changes in the index of refraction along the $z$-axis, i.e. perpendicular to the Néel vector. Both real and imaginary parts of the time-resolved optical birefringence rotation signal approximately follow the temperature dependence of the magnetic heat capacity, as expected if the changes in dielectric constants are dominated by contributions of exchange interactions to the dielectric constant. We conclude that under our experimental conditions, changes in the exchange interaction contribute more strongly to the temperature dependence of the magneto-optic constants than the Voigt effect.

0 citations0 reviewsNo code linkedOpen access