4 papers
StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows
Sizhong Qin, Yi Gu, Yao Jiang +13
Addressing a structural-engineering request requires more than a single answer; it requires a chain of interdependent artifacts: interpreted requirements, a computable model, valid…
AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation
Milton Zhou, Sizhong Qin, Yongzhi Li +2
Short-form videos have become a primary medium for digital advertising, requiring scalable and efficient content creation. However, current workflows and AI tools remain disjoint a…
Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans
Sizhong Qin, Ramon Elias Weber, Xinzheng Lu
Architectural floor plan design demands joint reasoning over geometry, semantics, and spatial hierarchy, which remains a major challenge for current AI systems. Although recent dif…
ChatHouseDiffusion: Prompt-Guided Generation and Editing of Floor Plans
Sizhong Qin, Chengyu He, Qiaoyun Chen +4
The generation and editing of floor plans are critical in architectural planning, requiring a high degree of flexibility and efficiency. Existing methods demand extensive input inf…