AI Paper Atlas

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

X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

Jinliang Zheng, Jianxiong Li, Zhihao Wang, Dongxiu Liu, Xirui Kang, Yuchun Feng, Yinan Zheng, Jiayin Zou, Yilun Chen, Jia Zeng, Tai Wang, Ya-Qin Zhang and 2 more

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 281 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 heterogeneous pretraining naively (ablation)X-VLA baseline · Simpler-WidowXadaptation success rate: 39.6 -> 25.0Hurt
add custom learning rate for the VLM (ablation)X-VLA baseline (no pretraining) · Simpler-WidowXadaptation success rate: 4.1 -> 39.6Improved
add action alignment, intention abstraction and balanced sampling (ablation)X-VLA · Simpler-WidowXadaptation success rate: 25.0 -> 50.0Improved
replace DiT with Transformer encoder (ablation)X-VLA · Simpler-WidowXadaptation success rate: 50.0 -> 47.9No clear effect
add encoding pipeline (ablation)X-VLA · Simpler-WidowXadaptation success rate: 47.9 -> 64.6Improved
add soft prompt (ablation)X-VLA · Simpler-WidowXadaptation success rate: 64.6 -> 73.8Improved
add scaling up to 0.9B (ablation)X-VLA · Simpler-WidowXadaptation success rate: 73.8 -> 89.6Improved
add two-step adaptation (ablation)X-VLA · Simpler-WidowXadaptation success rate: 89.6 -> 95.8Improved
add soft prompt (ablation)X-VLA · Simpler-WidowXpretraining validation error: 0.053 -> 0.041Improved
use 10 demos instead of 50 in PEFTX-VLA-0.9B · LIBERO-Goal PEFTsuccess rate: 92.8 -> 91.1No clear effect
use pretrained frozen prompts instead of random frozen prompts (ablation)X-VLA PEFT · Simpler-WidowXsuccess rateImproved

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