AI Paper Atlas

Research map / 3D vision / 3D generation

NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation

Cheng Wan, Yongsen Mao, Wenzheng Wu, Yuxuan Xie, Chucheng Xiang, Runze Wang, Xiang Zhang, zhongyuan liu, Rushi Dai, Yuan Liu

ECCV 2026 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 3 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
encode asset and room point clouds natively into the LLM instead of text/boxes (ablation)NaLA · layout generationavg AI score: 2.82 -> 3.53 (text-only vs full, standard input)Improved
add point cloud training, evaluated with text-only input at test (ablation)NaLA · layout generationavg AI score: 3.21 (text-only trained) vs 3.22 (full)No clear effect
use coarse-to-fine anchoring + residual tokens instead of text coordinates (ablation)NaLA · layout generationavg AI score: 3.12 -> 3.53Improved
add pose anchoring tokens to residual-only output (ablation)NaLA · layout generationcollision ratio (%): 19.19 -> 0.86Improved
add pose residual tokens to anchoring-only output (ablation)NaLA · layout generationavg AI score: 3.30 -> 3.53Improved
use grid B=20 instead of 5 (ablation)NaLA · layout generationavg AI score: 2.58 -> 3.53Improved
use grid B=20 instead of 100 (ablation)NaLA · layout generationavg AI score: 2.76 -> 3.53Improved
add input asset sequence shuffling (ablation)NaLA · layout generationavg AI score: 2.46 -> 3.53Improved
add asset replacement augmentation (ablation)NaLA · layout generationavg AI score: 2.60 -> 3.53Improved
add scene rotation augmentation (ablation)NaLA · layout generationavg AI score: 2.84 -> 3.53Improved
use two-stage training (3D-FRONT then Imaginarium) instead of 3D-FRONT only (ablation)NaLA · layout generationavg AI score: 2.90 -> 3.53Improved
use two-stage training instead of joint mixed training (ablation)NaLA · layout generationavg AI score: 3.31 -> 3.53Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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