Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning
cs.CV, cs.AI
Submitted: 2026-10-11
Updated: 2026-10-11
Code: https://github.com/hiyouga/EasyR1
Terminology
Sources
- Generating CAD Code with Vision-Language Models for 3D Designs
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- CodeBERT: A Pre-Trained Model for Programming and Natural Languages
- CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
- GPT-4o System Card
- cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning
- ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models
- From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- DINOv3
- OpenAI GPT-5 System Card
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- LLaMA: Open and Efficient Foundation Language Models
- NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling
- CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
- SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks
- Group Sequence Policy Optimization
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models