AutoRegressive Generation with B-rep Holistic Token Sequence Representation

• URL: http://arxiv.org/abs/2601.16771v1
• Date: Fri, 23 Jan 2026 14:15:02 GMT
• Title: AutoRegressive Generation with B-rep Holistic Token Sequence Representation
• Authors: Jiahao Li, Yunpeng Bai, Yongkang Dai, Hao Guo, Hongping Gan, Yilei Shi,
• Abstract summary: We propose BrepARG, the first attempt to encode B-rep's geometry and topology into a holistic token sequence representation.<n>Specifically, BrepARG encodes B-rep into 3 types of tokens: geometry and position tokens representing geometric features, and face index tokens representing topology.<n> Experiments demonstrate that BrepARG achieves state-of-the-art (SOTA) performance.
• Score: 31.0473553479822
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Previous representation and generation approaches for the B-rep relied on graph-based representations that disentangle geometric and topological features through decoupled computational pipelines, thereby precluding the application of sequence-based generative frameworks, such as transformer architectures that have demonstrated remarkable performance. In this paper, we propose BrepARG, the first attempt to encode B-rep's geometry and topology into a holistic token sequence representation, enabling sequence-based B-rep generation with an autoregressive architecture. Specifically, BrepARG encodes B-rep into 3 types of tokens: geometry and position tokens representing geometric features, and face index tokens representing topology. Then the holistic token sequence is constructed hierarchically, starting with constructing the geometry blocks (i.e., faces and edges) using the above tokens, followed by geometry block sequencing. Finally, we assemble the holistic sequence representation for the entire B-rep. We also construct a transformer-based autoregressive model that learns the distribution over holistic token sequences via next-token prediction, using a multi-layer decoder-only architecture with causal masking. Experiments demonstrate that BrepARG achieves state-of-the-art (SOTA) performance. BrepARG validates the feasibility of representing B-rep as holistic token sequences, opening new directions for B-rep generation.

Related papers

• Trie-Aware Transformers for Generative Recommendation [18.901863061905825]
  We propose TrieRec, a trie-aware generative recommendation method that augments Transformers with structural inductive biases.<n>We implement TrieRec within three representative GR backbones, achieving notably improvements of 8.83% on average across four real-world datasets.
  arXiv  Detail & Related papers  (2026-02-25T08:25:16Z)
• ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation [64.84095852784714]
  Residual Tokenizer (ResTok) is a 1D visual tokenizer that builds hierarchical residuals for both image tokens and latent tokens.<n>We show that restoring hierarchical residual priors in visual tokenization significantly improves AR image generation, achieving a gFID of 2.34 on ImageNet-256 with only 9 sampling steps.
  arXiv  Detail & Related papers  (2026-01-07T14:09:18Z)
• BrepLLM: Native Boundary Representation Understanding with Large Language Models [15.988259787552629]
  Current token-sequence-based Large Language Models (LLMs) are not well-suited for processing 3D Boundary Representation (Brep) models.<n>We propose BrepLLM, the first framework that enables LLMs to parse and reason over raw Brep data.<n> Experiments show that BrepLLM achieves state-of-the-art (SOTA) results on 3D object classification and captioning tasks.
  arXiv  Detail & Related papers  (2025-12-18T11:09:49Z)
• AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry [13.357641924794402]
  The boundary representation (B-Rep) is the standard data structure used in Computer-Aided Design (CAD) for defining solid models.<n>This paper presents AutoBrep, a novel Transformer model that autoregressively generates B-Reps with high quality and validity.
  arXiv  Detail & Related papers  (2025-12-02T18:46:25Z)
• BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch [61.20046418942948]
  Boundary representation (B-rep) is the de facto standard for CAD model representation in modern industrial design.<n>We present BrepGPT, a single-stage autoregressive framework for B-rep generation.
  arXiv  Detail & Related papers  (2025-11-27T07:16:53Z)
• Spanning Tree Autoregressive Visual Generation [51.7635842702602]
  We present Spanning Tree Autoregressive (STAR) modeling, which can incorporate prior knowledge of images, such as center bias and locality, to maintain sampling performance.
  arXiv  Detail & Related papers  (2025-11-21T09:45:17Z)
• Seg-VAR: Image Segmentation with Visual Autoregressive Modeling [60.79579744943664]
  We propose a novel framework that rethinks segmentation as a conditional autoregressive mask generation problem.<n>This is achieved by replacing the discriminative learning with the latent learning process.<n>Our method incorporates three core components: (1) an image encoder generating latent priors from input images, (2) a spatial-aware seglat (a latent expression of segmentation mask) encoder that maps segmentation masks into discrete latent tokens, and (3) a decoder reconstructing masks from these latents.
  arXiv  Detail & Related papers  (2025-11-16T13:36:19Z)
• BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry [24.779824909395245]
  BrepGen is a diffusion-based generative approach that directly outputs a Boundary representation (Brep) Computer-Aided Design (CAD) model. BrepGen represents a B-rep model as a novel structured latent geometry in a hierarchical tree.
  arXiv  Detail & Related papers  (2024-01-28T04:07:59Z)
• GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding [52.14832976759585]
  Grammatical error correction (GEC) is an important NLP task that is usually solved with autoregressive sequence-to-sequence models. We propose a novel non-autoregressive approach to GEC that decouples the architecture into a permutation network. We show that the resulting network improves over previously known non-autoregressive methods for GEC.
  arXiv  Detail & Related papers  (2023-11-14T14:24:36Z)
• Unfolding Projection-free SDP Relaxation of Binary Graph Classifier via GDPA Linearization [59.87663954467815]
  Algorithm unfolding creates an interpretable and parsimonious neural network architecture by implementing each iteration of a model-based algorithm as a neural layer. In this paper, leveraging a recent linear algebraic theorem called Gershgorin disc perfect alignment (GDPA), we unroll a projection-free algorithm for semi-definite programming relaxation (SDR) of a binary graph. Experimental results show that our unrolled network outperformed pure model-based graph classifiers, and achieved comparable performance to pure data-driven networks but using far fewer parameters.
  arXiv  Detail & Related papers  (2021-09-10T07:01:15Z)

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.