AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

AutoRegressive Generation with B-rep Holistic Token Sequence Representation

Jiahao Li, Yunpeng Bai, Yongkang Dai, Hao Guo, Hongping Gan, Yilei Shi

CVPR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Biological sequence transformers · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DFS face ordering instead of random order (ablation)BrepARG · DeepCAD unconditionalValidity (%): 67.92 -> 87.60Improved
add DFS face ordering instead of BFS (ablation)BrepARG · DeepCAD unconditionalValidity (%): 85.94 -> 87.60Improved
add DFS face ordering instead of ZYX centroid ordering (ablation)BrepARG · DeepCAD unconditionalValidity (%): 83.12 -> 87.60Improved
add DFS face ordering instead of spectral ordering (ablation)BrepARG · DeepCAD unconditionalValidity (%): 79.38 -> 87.60Improved
add MAX-IDX-A edge ordering instead of random (ablation)BrepARG · DeepCAD unconditionalValidity (%): 85.43 -> 87.60Improved
add MAX-IDX-A edge ordering instead of random (ablation)BrepARG · DeepCAD unconditionalCOV (%): 74.25 -> 75.45Improved
increase VQ-VAE codebook size from 512 to 4096 (ablation)Face-Edge VQ-VAE · DeepCAD unconditionalValidity (%): 69.8% -> 87.5%Improved
lower nucleus sampling p from 0.95 to 0.6 (ablation)BrepARG · DeepCAD unconditionalValidity (%): 82.85 -> 90.25Mixed
lower nucleus sampling p from 0.9 to 0.6 (ablation)BrepARG · DeepCAD unconditionalCOV (%): 75.45 -> 63.50Hurt
use deep-learning quantization of bounding boxes (best scheme 2) instead of uniform scalar quantization (ablation)position tokenization · bounding box reconstructionAcc: 99.4%Hurt
use BrepARG instead of DTGBrepGenDTGBrepGen · DeepCAD unconditionalValidity (%): 79.80 -> 87.60Improved
use BrepARG instead of DTGBrepGenDTGBrepGen · ABC unconditionalValidity (%): 57.59 -> 67.54Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy