AI Paper Atlas

Research map / Point clouds / Point cloud classification

Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds

Xianzhe Fan, Shengliang Deng, Xiaoyang Wu, Yuxiang Lu, Zhuoling Li, Mi Yan, Yujia Zhang, Zhizheng Zhang, He Wang, Hengshuang Zhao

ICML 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 0 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
lift depth to point clouds and fuse with 2D patches instead of 2D-onlyVLA · Simulation pilotSingle-Trial SR: 45.3 -> 61.1Improved
point cloud fusion instead of RGBD image-plane depthVLA · Simulation pilotSingle-Trial SR: 56.8 -> 61.1Improved
point cloud fusion instead of implicit-3D (VGGT) encoderVLA · Simulation pilotSingle-Trial SR: 46.3 -> 61.1Improved
add depth-pretrained encoder branch (implicit depth) to 2D-onlyVLA · Simulation pilotSingle-Trial SR: 45.3 -> 55.8Improved
add 2D branch to 3D-only (ablation)Any3D-VLA · Simulation ablationSingle-Trial SR: 44.2 -> 61.1Improved
add 2D branch to 3D-only (ablation)Any3D-VLA · Simulation ablationGrasp SR: 91.6 -> 89.5Hurt
use DINOv2-L in addition to SigLIP instead of DINOv2-S (ablation)Any3D-VLA · Simulation ablationTest SR: 72.6 -> 80.0Improved
add DINOv2 to 3D + SigLIP (ablation)Any3D-VLA · Simulation ablationSingle-Trial SR: 42.1 -> 61.1Improved
hybrid point cloud training instead of simulator-only (ablation)Any3D-VLA · Real-world zero-shot (DA3)Average SR: 60.0 -> 62.5Improved
hybrid point cloud training instead of simulator-only (ablation)Any3D-VLA · Simulation (DA3 inference)Test SR: 78.9 -> 82.1Improved
hybrid point cloud training instead of simulator-only (ablation)Any3D-VLA · Simulation (Simulator inference)Test SR: 80.0 -> 81.1No clear effect
hybrid point cloud training instead of sensor-only (ablation)Any3D-VLA · Real-world Task 1 (DA3 inference)SR: 80.0 -> 93.3Improved

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