Target-Guided Bayesian Flow Networks for Quantitatively Constrained CAD Generation

• URL: http://arxiv.org/abs/2510.25163v1
• Date: Wed, 29 Oct 2025 04:49:15 GMT
• Title: Target-Guided Bayesian Flow Networks for Quantitatively Constrained CAD Generation
• Abstract summary: We propose a novel framework for quantitatively constrained CAD generation, termed Target-Guided Bayesian Flow Network (TGBFN)<n>For the first time, TGBFN handles the multi-modality of CAD sequences in a unified continuous and differentiable parameter space rather than in the discrete data space.<n>We show that TGBFN achieves state-of-the-art performance in generating high-fidelity, condition-aware CAD sequences.
• Score: 21.976599517202914
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep generative models, such as diffusion models, have shown promising progress in image generation and audio generation via simplified continuity assumptions. However, the development of generative modeling techniques for generating multi-modal data, such as parametric CAD sequences, still lags behind due to the challenges in addressing long-range constraints and parameter sensitivity. In this work, we propose a novel framework for quantitatively constrained CAD generation, termed Target-Guided Bayesian Flow Network (TGBFN). For the first time, TGBFN handles the multi-modality of CAD sequences (i.e., discrete commands and continuous parameters) in a unified continuous and differentiable parameter space rather than in the discrete data space. In addition, TGBFN penetrates the parameter update kernel and introduces a guided Bayesian flow to control the CAD properties. To evaluate TGBFN, we construct a new dataset for quantitatively constrained CAD generation. Extensive comparisons across single-condition and multi-condition constrained generation tasks demonstrate that TGBFN achieves state-of-the-art performance in generating high-fidelity, condition-aware CAD sequences. The code is available at https://github.com/scu-zwh/TGBFN.

Related papers

• Fast Cross-Scenario Adaptation of CSI Models via Channel Conditional Parameter Generation [71.49439535846827]
  Conditional Channel Generation (CCPG) is an end-to-end pipeline for rapid deployment of CSI models in dynamic wireless environments.<n> CCPG identifies scene-sensitive adaptation bottlenecks through component-freezing experiments and generates only lightweight LoRA weights.<n>Experiments on DeepMIMO and WAIR-D for CSI feedback and channel estimation show that CCPG adapts to new scenarios in about 3 seconds with a single forward pass.
  arXiv  Detail & Related papers  (2026-06-22T13:20:01Z)
• Unlocking Feature Learning in Gated Delta Networks at Scale [52.705562336559446]
  Training and scaling Large Language Models demand enormous computational resources.<n>We derive the scaling rules for Gated Delta Network.<n> Experiments on language-model pre-training confirm that our configurations enable stable learning-rate transfer.
  arXiv  Detail & Related papers  (2026-06-02T08:45:24Z)
• 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)
• Computer-Aided Design Generation by Cascaded Discrete Diffusion Model [42.90502940340903]
  We propose a cascaded discrete diffusion framework for CAD generation.<n>Unlike isotropic Gaussian perturbation, the forward process of our approach operates directly over categorical token distributions.<n> Experiments on the DeepCAD dataset show that the proposed approach surpasses existing autoregressive and continuous diffusion models.
  arXiv  Detail & Related papers  (2026-05-06T15:26:11Z)
• Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting [79.37674445572462]
  Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends.<n>Treating reshaped tensors as static images results in a topological mismatch.<n> relying on uniform fixed-size representations allocates modeling capacity inefficiently.<n>TimeGS is a novel framework that fundamentally shifts the forecasting paradigm from regression to 2D generative rendering.
  arXiv  Detail & Related papers  (2026-02-10T14:13:36Z)
• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• BladeSDF : Unconditional and Conditional Generative Modeling of Representative Blade Geometries Using Signed Distance Functions [4.188806282965805]
  This paper introduces a domain-specific implicit generative framework for turbine blade geometry using DeepSDF.<n>By integrating constraints, objectives, and performance metrics, this approach advances beyond traditional 2D-guided or unconstrained 3D pipelines.
  arXiv  Detail & Related papers  (2026-01-19T23:02:33Z)
• AGDC: Autoregressive Generation of Variable-Length Sequences with Joint Discrete and Continuous Spaces [33.91616464118993]
  Transformer-based autoregressive models excel in data generation but are inherently constrained by their reliance on discretized tokens.<n>We analyze the scalability limitations of existing discretization-based approaches for generating hybrid discrete-continuous sequences.<n>We propose AGDC, a novel unified framework that jointly models discrete and continuous values for variable-length sequences.
  arXiv  Detail & Related papers  (2026-01-09T09:57:12Z)
• MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence [34.89364653219628]
  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.
  arXiv  Detail & Related papers  (2025-11-20T07:39:10Z)
• PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction [87.33016661440202]
  Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality.<n>We propose PointNSP, a coarse-to-fine generative framework that preserves global shape structure at low resolutions.<n> Experiments on ShapeNet show that PointNSP establishes state-of-the-art (SOTA) generation quality for the first time within the autoregressive paradigm.
  arXiv  Detail & Related papers  (2025-10-07T06:31:02Z)
• Time Series Based Network Intrusion Detection using MTF-Aided Transformer [3.265773263570237]
  We introduce a novel approach to time series classification using a Markov Transition Field (MTF)-aided Transformer model, specifically designed for Software-Defined Networks (SDNs)<n>We evaluate the model's performance using the InSDN dataset, demonstrating that our model outperforms baseline classification models.
  arXiv  Detail & Related papers  (2025-08-22T01:54:35Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• Revisiting CAD Model Generation by Learning Raster Sketch [17.853025952444437]
  We introduce RECAD, a novel framework that generates Raster sketches and 3D Extrusions for CAD models.<n>By combining two diffusion networks, RECAD effectively generates sketch-and-extrude CAD models.
  arXiv  Detail & Related papers  (2025-03-02T15:11:35Z)
• Parallel Sequence Modeling via Generalized Spatial Propagation Network [80.66202109995726]
  Generalized Spatial Propagation Network (GSPN) is a new attention mechanism for optimized vision tasks that inherently captures 2D spatial structures.<n>GSPN overcomes limitations by directly operating on spatially coherent image data and forming dense pairwise connections through a line-scan approach.<n>GSPN achieves superior spatial fidelity and state-of-the-art performance in vision tasks, including ImageNet classification, class-guided image generation, and text-to-image generation.
  arXiv  Detail & Related papers  (2025-01-21T18:56:19Z)
• Recurrent Diffusion for Large-Scale Parameter Generation [52.98888368644455]
  We introduce Recurrent Diffusion for Large Scale Generation (RPG), a novel framework that generates full neural network parameters up to hundreds of millions on a single GPU.<n>RPG serves as a critical advance in AI generating AI, potentially enabling efficient weight generation at scales previously deemed infeasible.
  arXiv  Detail & Related papers  (2025-01-20T16:46:26Z)
• CCDM: Continuous Conditional Diffusion Models for Image Generation [22.70942688582302]
  Conditional Diffusion Models (CDMs) offer a promising alternative to Continuous Conditional Generative Modeling (CCGM)<n>CDMs address existing limitations with specially designed conditional diffusion processes, a novel hard vicinal image denoising loss, and efficient conditional sampling procedures.<n>We demonstrate that CCDMs outperform state-of-the-art CCGM models, establishing a new benchmark.
  arXiv  Detail & Related papers  (2024-05-06T15:10:19Z)
• Differentially-Private Multi-Tier Federated Learning [14.725823723623213]
  We propose Multi-Tier Federated Learning with Multi-Tier Differential Privacy (M2FDP) M2FDP is a DP-enhanced FL methodology for jointly optimizing privacy and performance in hierarchical networks.
  arXiv  Detail & Related papers  (2024-01-21T20:46:21Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)

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.