Sizhong Qin — accepted AI-conference papers

2026

AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation

Milton Zhou, Sizhong Qin, Yongzhi Li, Quan Chen, Peng Jiang

CVPR 2026

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 and modality-specific, leading to high production costs and low overall efficiency. To address this issue, we propose Aut

Cited by 0 Source ↗code ↗Scholar ↗

2026

Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans

Sizhong Qin, Ramon Elias Weber, Xinzheng Lu

CVPR 2026

Architectural floor plan design demands joint reasoning over geometry, semantics, and spatial hierarchy, which remains a major challenge for current AI systems. Although recent diffusion and language models improve visual fidelity, they still struggle with coherent spatial reasoning and controllable

Cited by 0 Source ↗Scholar ↗