MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence

• URL: http://arxiv.org/abs/2511.17647v1
• Date: Thu, 20 Nov 2025 07:39:10 GMT
• Title: MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence
• Abstract summary: MamTiff-CAD is a novel CAD parametric command sequences generation framework.<n>We use a Transformer-based diffusion model for multi-scale latent representations.<n>Experiments demonstrate that MamTiff-CAD achieves state-of-the-art performance on both reconstruction and generation tasks.
• Score: 34.89364653219628
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parametric Computer-Aided Design (CAD) is crucial in industrial applications, yet existing approaches often struggle to generate long sequence parametric commands due to complex CAD models' geometric and topological constraints. To address this challenge, we propose MamTiff-CAD, a novel CAD parametric command sequences generation framework that leverages a Transformer-based diffusion model for multi-scale latent representations. Specifically, we design a novel autoencoder that integrates Mamba+ and Transformer, to transfer parameterized CAD sequences into latent representations. The Mamba+ block incorporates a forget gate mechanism to effectively capture long-range dependencies. The non-autoregressive Transformer decoder reconstructs the latent representations. A diffusion model based on multi-scale Transformer is then trained on these latent embeddings to learn the distribution of long sequence commands. In addition, we also construct a dataset that consists of long parametric sequences, which is up to 256 commands for a single CAD model. Experiments demonstrate that MamTiff-CAD achieves state-of-the-art performance on both reconstruction and generation tasks, confirming its effectiveness for long sequence (60-256) CAD model generation.

Related papers

• IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing [31.86100517851177]
  IterCAD is a unified multimodal agent framework for closed-loop, interactive CAD generation and editing.<n>It achieves highly competitive performance across multiple benchmarks, significantly outperforming existing approaches in both code executability and geometric precision.
  arXiv  Detail & Related papers  (2026-06-11T13:53:21Z)
• Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion [10.432531054049681]
  Boundary Representation (BRep) is the standard format for Computer-Aided Design (CAD)<n>We present Img2CADSeq, a multi-stage pipeline that overcomes limitations by encoding CAD sequences into a three-level hierarchical codebook.
  arXiv  Detail & Related papers  (2026-05-13T10:06:41Z)
• GeoFusion-CAD: Structure-Aware Diffusion with Geometric State Space for Parametric 3D Design [10.120364226524417]
  Parametric Computer-Aided Design (CAD) is fundamental to modern 3D modeling.<n>Existing methods struggle to generate long command sequences.<n>We propose GeoFusion-CAD, an end-to-end diffusion framework for scalable and structure-aware generation.
  arXiv  Detail & Related papers  (2026-03-23T13:41:39Z)
• Mamba-CAD: State Space Model For 3D Computer-Aided Design Generative Modeling [18.65998676457976]
  We introduce Mamba-CAD, a self-supervised generative modeling for complex CAD models in the industry.<n>We utilize the learned representation to guide a generative adversarial network to produce the fake representation of CAD models.<n>To train Mamba-CAD, we create a new dataset consisting of 77,078 CAD models with longer parametric CAD sequences.
  arXiv  Detail & Related papers  (2026-02-28T03:38:26Z)
• ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models [16.220781575918256]
  ReCAD is a reinforcement learning (RL) framework that bootstraps pretrained large models (PLMs) to generate precise parametric computer-aided design (CAD) models from multimodal inputs.<n>We employ a hierarchical primitive learning process to teach structured and compositional skills under a unified reward function.<n>ReCAD sets a new state-of-the-art in both text-to-CAD and image-to-CAD tasks, significantly improving geometric accuracy across in-distribution and out-of-distribution settings.
  arXiv  Detail & Related papers  (2025-12-06T07:12:56Z)
• GenCAD-3D: CAD Program Generation using Multimodal Latent Space Alignment and Synthetic Dataset Balancing [3.5539239472975583]
  We introduce GenCAD-3D, a multimodal generative framework to generate 3D CAD programs.<n>We also present SynthBal, a synthetic data augmentation strategy designed to balance and expand datasets.<n>Our experiments show that SynthBal significantly boosts reconstruction accuracy, reduces the generation of invalid CAD models, and markedly improves performance on high-complexity geometries.
  arXiv  Detail & Related papers  (2025-09-17T19:10:44Z)
• CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images [69.7768227804928]
  CADCrafter is an image-to-parametric CAD model generation framework that trains solely on synthetic textureless CAD data.<n>We introduce a geometry encoder to accurately capture diverse geometric features.<n>Our approach can robustly handle real unconstrained CAD images, and even generalize to unseen general objects.
  arXiv  Detail & Related papers  (2025-04-07T06:01:35Z)
• CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM [39.113795259823476]
  We introduce the CAD-MLLM, the first system capable of generating parametric CAD models conditioned on the multimodal input.<n>We use advanced large language models (LLMs) to align the feature space across diverse multi-modalities data and CAD models' vectorized representations.<n>Our resulting dataset, named Omni-CAD, is the first multimodal CAD dataset that contains textual description, multi-view images, points, and command sequence for each CAD model.
  arXiv  Detail & Related papers  (2024-11-07T18:31:08Z)
• PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting [82.03373838627606]
  Self-attention mechanism in Transformer architecture requires positional embeddings to encode temporal order in time series prediction. We argue that this reliance on positional embeddings restricts the Transformer's ability to effectively represent temporal sequences. We present a model integrating PRE with a standard Transformer encoder, demonstrating state-of-the-art performance on various real-world datasets.
  arXiv  Detail & Related papers  (2024-08-20T01:56:07Z)
• MatFormer: Nested Transformer for Elastic Inference [91.45687988953435]
  MatFormer is a novel Transformer architecture designed to provide elastic inference across diverse deployment constraints.<n>MatFormer achieves this by incorporating a nested Feed Forward Network (FFN) block structure within a standard Transformer model.<n>We show that a 850M decoder-only MatFormer language model (MatLM) allows us to extract multiple smaller models spanning from 582M to 850M parameters.
  arXiv  Detail & Related papers  (2023-10-11T17:57:14Z)
• FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification [53.55504611255664]
  FormerTime is a hierarchical representation model for improving the classification capacity for the multivariate time series classification task. It exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism.
  arXiv  Detail & Related papers  (2023-02-20T07:46:14Z)
• SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks [37.33746656109331]
  We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences. Autoregressive Transformer decoders generate CAD construction sequences sharing certain properties specified by the codebook vectors.
  arXiv  Detail & Related papers  (2022-07-11T05:10:51Z)
• Visual Saliency Transformer [127.33678448761599]
  We develop a novel unified model based on a pure transformer, Visual Saliency Transformer (VST), for both RGB and RGB-D salient object detection (SOD) It takes image patches as inputs and leverages the transformer to propagate global contexts among image patches. Experimental results show that our model outperforms existing state-of-the-art results on both RGB and RGB-D SOD benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-25T08:24:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.