AI Paper Atlas

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

Towards Long-Horizon Vision-Language-Action System: Reasoning, Acting and Memory

Daixun Li, Yusi Zhang, Mingxiang Cao, Donglai Liu, Weiying Xie, Tianlin Hui, Lunkai Lin, Zhiqiang Xie, Yunsong Li

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 2 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 cold-start curriculum SFT (ablation)Qwen2-VL-7B reasoning layer · Coarse-grained long-horizon tasksaccuracy (%): 29.00 -> 62.00Improved
add cold-start curriculum SFT (ablation)Qwen2-VL-7B reasoning layer · Zero-shot generalizationaccuracy (%): 19.00 -> 43.00Improved
add iterative DPO iteration 1 (ablation)reasoning layer after cold start · Zero-shot generalizationaccuracy (%): 43.00 -> 55.00Improved
add iterative DPO iteration 3 after iteration 2 (ablation)reasoning layer · Zero-shot generalizationaccuracy (%): 64.00 -> 73.00Improved
add iterative DPO iteration 3 after iteration 2 (ablation)reasoning layer · Coarse-grained long-horizon tasksaccuracy (%): 75.00 -> 87.00Improved
add iterative DPO iteration 3 after iteration 2 (ablation)reasoning layer · Intensive instruction following tasksROUGE L (%): 70.23 -> 70.23No clear effect
add reasoning layer on top of acting layer with memory (ablation)MindExplore · 8 tasks, cruising and obstacle avoidanceaverage success rate (%): 60.00 -> 76.25Improved
add memory mechanism (ablation)MindExplore · 8 tasks, cruising and obstacle avoidanceaverage success rate (%): 76.25 -> 92.50Improved
use point cloud instead of channel-concatenated 2D depth+RGB (ablation)Base Expert · Moving to a Target Locationsuccess rate: 32/50 -> 42/50Improved
add depth point cloud to RGB (ablation)Arm Expert · Grasping a Specified Objectsuccess rate: 23/50 -> 40/50Improved
add RGB to LiDAR+Depth point cloud (ablation)Base Expert · Moving to a Target Locationsuccess rate: 37/50 -> 42/50Improved
use expert-specific MMDP (BE/AE) instead of ACT (ablation)acting layer · meta-action averagesuccess rate (%): 36.86 -> 87.12Improved

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