AI Paper Atlas

Research map / 3D vision / 3D generation

RoboTron-Mani: All-in-One Multimodal Large Model for Robotic Manipulation

Feng Yan, Fanfan Liu, Yiyang Huang, Zechao Guan, Liming Zheng, Yufeng Zhong, Chengjian Feng, Lin Ma

ICCV 2025 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations · 29 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 frame-by-frame action (FFA) output (ablation)RoboTron-Mani · CALVINaverage length: 1.77 -> 2.37Improved
add image output on top of FFA (ablation)RoboTron-Mani · CALVINaverage length: 2.37 -> 3.13Improved
add UVFormer on top of FFA (ablation)RoboTron-Mani · CALVINaverage length: 2.37 -> 2.88Improved
add UVFormer to FFA plus image output (ablation)RoboTron-Mani · CALVINaverage length: 3.13 -> 3.21Improved
add occupancy (OCC) supervision on FFA plus UVFormer (ablation)RoboTron-Mani · CALVINaverage length: 2.88 -> 3.18Improved
add OCC to FFA, image and UVFormer (ablation)RoboTron-Mani · CALVINaverage length: 3.21 -> 3.31Improved
replace MLP action head with DiT action head (ablation)RoboTron-Mani · CALVINaverage length: 3.31 -> 3.51Improved
train on aligned RoboData instead of non-aligned (ablation)RoboTron-Mani · LIBEROsuccess rate: 64.2% -> 90.7%Improved
train on aligned RoboData instead of non-aligned (ablation)RoboTron-Mani · CALVINsuccess rate: 74.7% -> 91.0%Improved
train on aligned data instead of non-aligned (ablation)RoboTron-Mani · Meta-Worldsuccess rate: 79.3% -> 78.6%No clear effect
align data for a 2D-input model (ablation)RoboFlamingo* · LIBEROsuccess rate: 69.1% -> 72.1%No clear effect
use 3D perception model over 2D RoboFlamingo on real robotRoboTron-Mani · Real-world Hardsuccess rate: 6.6% -> 46.6%Improved

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