AI Paper Atlas

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

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

Tao Lin, Yilei Zhong, Yuxin Du, Jingjing Zhang, Jiting Liu, Yinxinyu Chen, Encheng Gu, Ziyan Liu, Hongyi Cai, Yanwen Zou, Lixing Zou, Zhaoye Zhou and 2 more

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 33 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
use two-stage training (freeze VLM first) instead of single-stage joint training (ablation)Evo-1 · Meta-Worldsuccess rateImproved
use mid-layer cross-attention integration (Module A) instead of Modules B-D (ablation)Evo-1 · LIBERO-Longsuccess rateImproved
keep only first 14 layers of the language branch (ablation)Evo-1 · design choicesuccess rateNo clear effect
use Evo-1 compact design vs larger SmolVLA on Meta-WorldEvo-1 · Meta-Worldsuccess rate: 68.2 -> 80.6Improved
Evo-1 vs pi0 on LIBERO-SpatialEvo-1 · LIBERO Spatialsuccess rate: 96.8 -> 92.7Hurt
Evo-1 vs pi0 on LIBERO averageEvo-1 · LIBEROsuccess rate: 94.2 -> 94.8Improved
Evo-1 vs pi0 on real-world tasksEvo-1 · Real-world xArm6success rate: 73 -> 78Improved
Evo-1 vs SmolVLA under unseen distractorEvo-1 · Real-world Pick and Place Cansuccess rate: 65% -> 80%Improved
Evo-1 vs SmolVLA at 30 mm higher targetEvo-1 · Real-world Pick and Place Cansuccess rate: 60% -> 70%Improved
Evo-1 smaller model vs pi0 on memoryEvo-1 · Inference RTX 4090dGPU memory (GB): 17.9 -> 2.3Improved

Later papers that compared with this method

2 later accepted papers report Evo-1 as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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