AI Paper Atlas

Research map / 3D vision / 3D generation

ArtLLM: Generating Articulated Assets via 3D LLM

Penghao Wang, Siyuan Xie, Hongyu Yan, Xianghui Yang, Jingwei Huang, Chunchao Guo, Jiayuan Gu

CVPR 2026 · 3D vision › 3D generation · approach: Learning physics from video · 5 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 quantized discrete tokens for layout and joints (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)part IoU: 0.352 -> 0.473Improved
add quantized discrete tokens (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)joint axis error (lower better): 0.277 -> 0.141Improved
add multi-task SFT (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)joint type accuracy: 0.825 -> 0.898Improved
add multi-task SFT (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)joint axis error (lower better): 0.289 -> 0.141Mixed
add multi-task SFT (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)joint range IoU: 0.510 -> 0.582Improved
add random scaling and rotation augmentation (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)part IoU: 0.412 -> 0.473Improved
add augmentation (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)graph accuracy: 0.754 -> 0.780Improved
add multi-stage training with part-layout pretraining (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)joint pivot error (lower better): 0.175 -> 0.135Improved
add multi-stage training (ablation)ArtLLM · PartNet-Mobility ablation (144 objects, PartNet-Mobility training only)joint range IoU: 0.511 -> 0.582Improved
ArtLLM vs retrieval-based Articulate-AnythingArtLLM · PartNet-Mobility (7 categories, 77 objects)part mIoU: 0.3381 -> 0.6884Improved
ArtLLM vs Articulate-AnythingArtLLM · PartNet-Mobility (7 categories, 77 objects)time (s): 522 -> 19Improved
retrain SINGAPO on our larger dataset (ablation)SINGAPO · PartNet-Mobility (7 categories, 77 objects)joint type accuracy: 0.7649 -> 0.9065Improved

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