collaborators

8 papers

cs.CV2026

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Senqiao Yang, Kaichen Zhang, Zhaoyang Jia +20

Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process…

cs.CV2026

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Xinjie Zhang, Peng Zhang, Shicheng Zheng +21

Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to…

cs.CV2026

SciForma: Structure-Faithful Generation of Scientific Diagrams

Yuxuan Luo, Peng Zhang, Xinjie Zhang +3

Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and tex…

cs.CV2026

VecFontLLM: Anchor-Guided Direct Synthesis of Chinese Vector Fonts

Hao Yuan, Yuxuan Luo, Xing Chen +1

Direct generation of Chinese vector fonts is a challenging and ongoing problem. A Chinese vector glyph contains complex component structure, anchor layout, and Bézier curve detail…

cs.CV2026

Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation

Haonan Cai, Yuxuan Luo, Zhouhui Lian

Manual font design is an intricate process that transforms a stylistic visual concept into a coherent glyph set. This challenge persists in automated Few-shot Font Generation (FFG)…

cs.CV2025

UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images

Yiming Zhao, Yuanpeng Gao, Yuxuan Luo +4

AI-assisted graphic design has emerged as a powerful tool for automating the creation and editing of design elements such as posters, banners, and advertisements. While diffusion-b…