AI Paper Atlas

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

EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation

Min Lin, Xiwen Liang, Bingqian Lin, Jingzhi Liu, Zijian Jiao, Kehan Li, Ziang Yan, Yu Sun, Weijia Liufu, Yuhan Ma, Jiarui Hu, Yuecheng Liu and 3 more

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 34 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 RGB input (ablation)EchoVLA · PnP Counter to Stove (mobile)success rate: 0.02 -> 0.17Improved
add point cloud input (ablation)EchoVLA · PnP Counter to Stove (mobile)success rate: 0.08 -> 0.17Improved
add point cloud input (ablation)EchoVLA · PnP Counter to Stove (static)success rate: 0.15 -> 0.21Improved
add scene memory (ablation)EchoVLA · PnP Counter to Stove (mobile)success rate: 0.09 -> 0.17Improved
add scene memory (ablation)EchoVLA · PnP Counter to Stove (static)success rate: 0.16 -> 0.21Improved
add episodic memory (ablation)EchoVLA · PnP Counter to Stove (mobile)success rate: 0.14 -> 0.17Improved
add episodic memory (ablation)EchoVLA · PnP Counter to Stove (static)success rate: 0.13 -> 0.21Improved
raise episodic window size from 2 to 8 (ablation)EchoVLA · PnPC2S (mobile)success rate: 0.08 -> 0.17Improved
raise episodic window size from 8 to 16 (ablation)EchoVLA · PnPC2S (mobile)success rate: 0.17 -> 0.15Hurt
raise update threshold tau from 0.1 to 0.5 (ablation)EchoVLA · PnPC2S (mobile)success rate: 0.11 -> 0.17Improved
raise update threshold tau from 0.5 to 0.7 (ablation)EchoVLA · PnPC2S (mobile)success rate: 0.17 -> 0.13Hurt
use EchoVLA instead of pi0.5EchoVLA · RoboCasa manipulation/navigationAvg SR: 0.32 -> 0.52Improved

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