Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing
研究通过训练一个紧凑的开放权重规划器RefineCut来解决实际视频编辑中的决策层问题，该方法通过结构化补丁和验证器优化视频编辑计划。
0 citationsRead paper
Selected work
Representative Papers
AIMold: An Autonomous AI-based Pipeline for Complex Mold Design
This study addresses the longstanding reliance on expert knowledge in designing injection molds for complex plastic parts, a process hindered by the absence of automated methods and publicly available data. To bridge this gap, the authors introduce MoldCAD, the first large-scale structured CAD dataset dedicated to complex mold design, comprising 4,934 parts and 3,850 complete mold assemblies. They further propose an end-to-end AI pipeline that leverages deep learning to predict parting directions, generate parting surfaces, identify auxiliary components, and perform assembly reasoning—directly producing manufacturing-ready mold designs. The method successfully generates over 23,000 fabricable mold components, achieving, for the first time, fully automatic translation from part geometry to complete mold assembly and advancing the frontier of manufacturing-aware CAD generation.
0 citationsRead paper
Recent publications
Latest Papers
Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing
研究通过训练一个紧凑的开放权重规划器RefineCut来解决实际视频编辑中的决策层问题，该方法通过结构化补丁和验证器优化视频编辑计划。
0 citationsRead paper
AIMold: An Autonomous AI-based Pipeline for Complex Mold Design
This study addresses the longstanding reliance on expert knowledge in designing injection molds for complex plastic parts, a process hindered by the absence of automated methods and publicly available data. To bridge this gap, the authors introduce MoldCAD, the first large-scale structured CAD dataset dedicated to complex mold design, comprising 4,934 parts and 3,850 complete mold assemblies. They further propose an end-to-end AI pipeline that leverages deep learning to predict parting directions, generate parting surfaces, identify auxiliary components, and perform assembly reasoning—directly producing manufacturing-ready mold designs. The method successfully generates over 23,000 fabricable mold components, achieving, for the first time, fully automatic translation from part geometry to complete mold assembly and advancing the frontier of manufacturing-aware CAD generation.
0 citationsRead paper