AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

BrepLLM: Enabling Large Language Models to Understand Boundary Representations

Liyuan Deng, Hao Guo, Yongkang Dai, Yunpeng Bai, Yifan Zhu, Yuanyuan Gao, Huaxi Huang, Yilei Shi

ECCV 2026 · Large language models › Instruction and fine-tuning · approach: Calibration and knowledge in LLM tuning · 10 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
feed native B-rep via BrepEncoder instead of point clouds or rendered imagesBrepLLM · Brep2Text captioningQwen3-30B score: 56.58 -> 61.36 (vs MiniGPT-3D)Improved
feed native B-rep to LLMBrepLLM · Brep2Text classificationaverage accuracy: 56.25 -> 60.0Improved
B-rep input vs point cloud input (human eval)BrepLLM · Brep2Text captioninghallucination count: 0.86 -> 0.83Improved
add adaptive UV sampling (ablation)BrepLLM · Brep2Text captioningQwen3-30B score: 59.21 -> 61.36Improved
add hierarchical BrepEncoder (ablation)BrepLLM · Brep2Text captioningQwen3-30B score: 57.39 -> 61.36Improved
add Stage II (LoRA 3D-language alignment) after Stage I (ablation)BrepLLM · Brep2Text captioningQwen3-30B score: 43.83 -> 61.36Improved
add Stage I (MLP bridging) before Stage II (ablation)BrepLLM · Brep2Text captioningQwen3-30B score: 59.12 -> 61.36Improved

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