AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models

Zirui Song, Guangxian Ouyang, Mingzhe Li, Yuheng Ji, Chenxi Wang, Zixiang Xu, Zeyu Zhang, Xiaoqing Zhang, Qian Jiang, Fengxian Ji, Zhenhao Chen, Zhongzhi Li and 1 more

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Multimodal prompt-driven manipulation · 42 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
train Qwen2.5-VL-3B with RLVR (structured rewards, 50% data) instead of SFT on full dataQwen2.5-VL-3B-Instruct · ShareRobot in-domain affordanceIoU: 12.69 -> 31.0Improved
train Qwen2.5-VL-3B with RLVR (50% data) instead of SFTQwen2.5-VL-3B-Instruct · ShareRobot in-domain trajectoryaverage of DFD/HD/RMSE: 126.77 -> 110.87Improved
RLVR instead of SFTQwen2.5-VL-3B-Instruct · VAIT trajectory (OOD)average of DFD/HD/RMSE: 179.45 -> 131.99Improved
RLVR instead of SFTQwen2.5-VL-3B-Instruct · UMD Part Affordance (OOD) graspIoU: 7.39 -> 34.65Improved
RLVR-trained 3B vs RoboBrain-7B (larger SFT model)ManipLVM-R1-3B · UMD Part Affordance (OOD) poundIoU: 12.75 -> 23.50Mixed
RLVR 3B vs Qwen2.5-VL-32B-Instruct zero-shotManipLVM-R1-3B · ShareRobot in-domain trajectoryaverage of DFD/HD/RMSE: 107.86 -> 110.87No clear effect

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