AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning

Mingi Kim, Yongjun Kim, Jungwoo Kang, Hyungki Kim

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 4 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 Phase 1 B-rep-code alignment before LLM integration (vs end-to-end training) (ablation)BrepCoder · DeepCAD reverse engineeringMedian Chamfer Distance (x1e-3): 124.18 -> 0.464Improved
train encoder from scratch instead of segmentation pre-trained weights (ablation)BrepCoder · DeepCAD reverse engineeringMedian Chamfer Distance (x1e-3): 0.499 -> 0.464Improved
use UV-Net instead of AAGNet encoder (finer 10x10 UV sampling) (ablation)BrepCoder · DeepCAD reverse engineeringMedian Chamfer Distance (x1e-3): 3.99 -> 0.464Improved
use CoCa (contrastive plus captioning loss) instead of CLIP alignment (ablation)BrepCoder · DeepCAD reverse engineeringACC_param: 78.09 -> 82.01Improved
freeze the B-rep encoder when integrating with LLM (ablation)BrepCoder · DeepCAD reverse engineeringMedian Chamfer Distance (x1e-3): 0.516 -> 0.464Improved
scale LLM backbone from 0.5B to 1.5B (ablation)BrepCoder · DeepCAD reverse engineeringMedian Chamfer Distance (x1e-3): 0.612 -> 0.464Improved
swap Qwen-2.5 1.5B backbone for Llama-3.2 1B (ablation)BrepCoder · DeepCAD reverse engineeringMedian Chamfer Distance (x1e-3): 0.464 -> 0.467No clear effect
use 3-layer projector instead of 2-layer (ablation)BrepCoder · DeepCAD reverse engineeringACC_param: 80.15 -> 82.01Improved
use 3-layer projector instead of 1-layer (ablation)BrepCoder · DeepCAD reverse engineeringACC_param: 80.66 -> 82.01Improved
add Stage 1 reverse engineering pre-training (ablation)BrepCoder · CAD-QA (SGP-Bench)accuracy (%): 71% -> 79%Improved
add Stage 1 reverse engineering pre-training (ablation)BrepCoder · Error correction (DeepCAD)Median Chamfer Distance (x1e-3): 0.405 -> 0.335Improved
add Stage 1 reverse engineering pre-training (ablation)BrepCoder · Error correction (DeepCAD)ACC_cmd: 99.43 -> 99.08Hurt

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