activity
20242026
collaborators

11 papers

cs.CV2026

IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views

Yuchuan Wu, Ke Niu, Haiyang Yu +3

Generating executable parametric CAD code from dimension-annotated orthographic drawings is a challenging task requiring geometric understanding, procedural reasoning, and precise…

cs.CV2026

AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition

Yuchuan Wu, Yinglian Zhu, Haiyang Yu +3

Ancient Chinese character recognition is a core capability for cultural heritage digitization, yet real-world workflows are inherently non-stationary: newly excavated materials are…

cs.CV2025

CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation

Ke Niu, Haiyang Yu, Zhuofan Chen +7

Computer-Aided Design (CAD) is essential in industrial design, but the complexity of traditional CAD modeling and workflows presents significant challenges for automating the gener…

cs.CV2025

OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and Understanding

Teng Fu, Mengyang Zhao, Ke Niu +2

LVLMs have been shown to perform excellently in image-level tasks such as VQA and caption. However, in many instance-level tasks, such as visual grounding and object detection, LVL…

cs.CV2025

CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning

Ke Niu, Zhuofan Chen, Haiyang Yu +5

Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing. Orthographic projection reasoning underpins the entire CAD workflow, encompassing design, manufacturin…

cs.LG2025

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

Ke Niu, Haiyang Yu, Zhuofan Chen +4

Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent adv…