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

Kun Yan

Kun Yan contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer Visioncond-mat.mtrl-sciArtificial Intelligence

Trust snapshot

Quick read

Trust 17 - UnverifiedVerification L1Unclaimed author
4works
0followers
3topics
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

4 published item(s)

preprint2026arXiv

Qwen-Image-2.0 Technical Report

We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress, existing models still struggle with ultra-long text rendering, multilingual typography, high-resolution photorealism, robust instruction following, and efficient deployment, especially in text-rich and compositionally complex scenarios. Qwen-Image-2.0 addresses these challenges by coupling Qwen3-VL as the condition encoder with a Multimodal Diffusion Transformer for joint condition-target modeling, supported by large-scale data curation and a customized multi-stage training pipeline. This enables strong multimodal understanding while preserving flexible generation and editing capabilities. The model supports instructions of up to 1K tokens for generating text-rich content such as slides, posters, infographics, and comics, while significantly improving multilingual text fidelity and typography. It also enhances photorealistic generation with richer details, more realistic textures, and coherent lighting, and follows complex prompts more reliably across diverse styles. Extensive human evaluations show that Qwen-Image-2.0 substantially outperforms previous Qwen-Image models in both generation and editing, marking a step toward more general, reliable, and practical image generation foundation models.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Angle-resolved polarized Raman spectroscopy for distinguishing stage-I graphite intercalation compounds with Thorium, Uranium and Plutonium

Graphite intercalation compounds (GICs) with the geometrical anisotropy and strong electron-phonon coupling are in full swing and have shown their great potential for applications in nanodevices. I selected representative three elements in actinide group with valence electron arrangement: Thorium (Th) ([Rn]6d27s2), Uranium (U) ([Rn]5f36d17s2), Plutonium (Pu) ([Rn]5f67s2). I calculated their phonon spectra and demonstrated the atomic-scale microstructure identification of actinide graphite intercalation compounds by angle-resolved polarized Raman spectroscopy.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Unique electronic structure and the shape-change effect of stage-I graphite intercalation compounds with Thorium, Uranium and Plutonium

GICs doped with elements containing d and f orbitals have been studied rarely. We control the distribution and density of intercalated actinide metals (Th, U and Pu), and consider the effect of changing the distance of two adjacent carbon layers on the electronic structure so as to infer the physical properties of such materials under high pressure or high temperature - which is of great significance in fundamental research. According to band schemas, those GICs are all metallic. The projected density of states (PDOS) indicates that the metal atoms first undergo hybridization of its s, p, d, and f orbitals, and then bond with the carbon's pz orbitals of the nearest-neighbor octagons. The electron orbital spin up of C and Th is symmetrical with spin down, so there is no electron spin polarization. However, the s, p, d, and f orbitals of U and Pu all exhibit electron spin polarization, which leads to the magnetic properties of the material and make the p orbits of C appear spin polarization around Fermi level. In addition, these three selected elements are the most commonly used raw materials in nuclear fission, so such GICs are expected to become novel nuclear energy storage materials.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Few-shot Image Classification with Multi-Facet Prototypes

The aim of few-shot learning (FSL) is to learn how to recognize image categories from a small number of training examples. A central challenge is that the available training examples are normally insufficient to determine which visual features are most characteristic of the considered categories. To address this challenge, we organize these visual features into facets, which intuitively group features of the same kind (e.g. features that are relevant to shape, color, or texture). This is motivated from the assumption that (i) the importance of each facet differs from category to category and (ii) it is possible to predict facet importance from a pre-trained embedding of the category names. In particular, we propose an adaptive similarity measure, relying on predicted facet importance weights for a given set of categories. This measure can be used in combination with a wide array of existing metric-based methods. Experiments on miniImageNet and CUB show that our approach improves the state-of-the-art in metric-based FSL.

0 citations0 reviewsNo code linkedOpen access