4 papers
The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
Hongyuan Liu, Qinli Yang, Wen Li +6
Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the m…
LaTCoder: Converting Webpage Design to Code with Layout-as-Thought
Yi Gui, Zhen Li, Zhongyi Zhang +10
Converting webpage designs into code (design-to-code) plays a vital role in User Interface (UI) development for front-end developers, bridging the gap between visual design and fun…
UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs
Yi Gui, Zhen Li, Zhongyi Zhang +8
Automating the synthesis of User Interfaces (UIs) plays a crucial role in enhancing productivity and accelerating the development lifecycle, reducing both development time and manu…
Judge Anything: MLLM as a Judge Across Any Modality
Shu Pu, Yaochen Wang, Dongping Chen +10
Evaluating generative foundation models on open-ended multimodal understanding (MMU) and generation (MMG) tasks across diverse modalities (e.g., images, audio, video) poses signifi…