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

arXiv: https://arxiv.org/abs/2506.00568 · HTML: https://mlsanity.com/paper/2506.00568/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 31 May 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 21 of 21)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM](https://mlsanity.com/paper/2411.04954/) (2024)
- [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://mlsanity.com/paper/2503.07065/) (2025)
- [CAD-Recode: Reverse Engineering CAD Code from Point Clouds](https://mlsanity.com/paper/2412.14042/) (2024)
- [CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers](https://mlsanity.com/paper/2412.13810/) (2024)
- [CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images](https://mlsanity.com/paper/2504.04753/) (2025)
- [ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models](https://mlsanity.com/paper/2502.19958/) (2025)
- [From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach](https://mlsanity.com/paper/2412.11892/) (2024)
- [UMIT: Unifying Medical Imaging Tasks via Vision-Language Models](https://mlsanity.com/paper/2503.15892/) (2025)
- [RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generation](https://mlsanity.com/paper/2503.18549/) (2025)
- [EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models](https://mlsanity.com/paper/2503.04058/) (2025)
- [PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning](https://mlsanity.com/paper/2503.18147/) (2025)
- [GaussianCAD: Robust Self-Supervised CAD Reconstruction from Three Orthographic Views Using 3D Gaussian Splatting](https://mlsanity.com/paper/2503.05161/) (2025)
- [Large Language Model-Based Intelligent Antenna Design System](https://mlsanity.com/paper/2504.18271/) (2025)

## Built on by (most cited first, 8 of 8)

- [MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement](https://mlsanity.com/paper/2508.09670/) (2025)
- [From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation](https://mlsanity.com/paper/2508.10118/) (2025)
- [Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection](https://mlsanity.com/paper/2603.04337/) (2026)
- [RB-FT: Rationale-Bootstrapped Fine-Tuning for Video Classification](https://mlsanity.com/paper/2511.15923/) (2025)
- [Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision](https://mlsanity.com/paper/2606.29301/) (2026)
- [CrossProjection: Geometric Grounding Beyond Viewpoint Change in Architectural Drawings](https://mlsanity.com/paper/2608.00473/) (2026)
- [IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views](https://mlsanity.com/paper/2608.24020/) (2026)
- [LED-BENCH: A Benchmark for Large-format Engineering Drawing Understanding](https://mlsanity.com/paper/2610.19571/) (2026)

## Abstract (arXiv)

Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing. Orthographic projection reasoning underpins the entire CAD workflow, encompassing design, manufacturing, and simulation. However, prevailing deep-learning approaches employ standard 3D reconstruction pipelines as an alternative, which often introduce imprecise dimensions and limit the parametric editability required for CAD workflows. Recently, some researchers adopt vision-language models (VLMs), particularly supervised fine-tuning (SFT), to tackle CAD-related challenges. SFT shows promise but often devolves into pattern memorization, yielding poor out-of-distribution performance on complex reasoning tasks. To address these gaps, we introduce CReFT-CAD, a two-stage fine-tuning paradigm that first employs a curriculum-driven reinforcement learning stage with difficulty-aware rewards to build reasoning ability steadily, and then applies supervised post-tuning to hone instruction following and semantic extraction. Complementing this, we release TriView2CAD, the first large-scale, open-source benchmark for orthographic projection reasoning, comprising 200,000 synthetic and 3,000 real-world orthographic projections with precise dimension annotations and six interoperable data modalities. We benchmark leading VLMs on orthographic projection reasoning and demonstrate that CReFT-CAD substantially improves reasoning accuracy and out-of-distribution generalizability in real-world scenarios, offering valuable insights for advancing CAD reasoning research.