AI Paper Atlas

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

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

Ganlin Yang, Tianyi Zhang, Haoran Hao, Weiyun Wang, Yibin Liu, Dehui Wang, Guanzhou Chen, Zijian Cai, Junting Chen, Weijie Su, Wengang Zhou, Yu Qiao and 6 more

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models

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
fine-tune on Vlaser-6M embodied reasoning dataInternVL3-2B · 12 embodied reasoning benchmarksnormalized average: 15.2 -> 45.3Improved
fine-tune on Vlaser-6M embodied reasoning dataInternVL3-8B · 12 embodied reasoning benchmarksnormalized average: 22.3 -> 51.3Improved
use 8B instead of 2B modelVlaser · point grounding vs planning and simulationbenchmark score: Where2place 74.0 (2B) vs 69.5 (8B); Ego-Plan2 38.3 (2B) vs 53.4 (8B)Mixed
initialize VLA from Vlaser-OOD (out-of-domain embodied reasoning data only) instead of InternVL3-2B (ablation)Vlaser VLA · SimplerEnv WidowXaverage success rate: 41.8% -> 43.2%No clear effect
initialize VLA from Vlaser-OOD instead of InternVL3-2B (ablation)Vlaser VLA · SimplerEnv Google Robot Variant Aggregationaverage success rate: 54.7% -> 51.3%Hurt
initialize VLA from Vlaser-OOD instead of InternVL3-2B (ablation)Vlaser VLA · RoboTwinaverage success rate: 55.8% -> 54.5%No clear effect
add in-domain QA data to VLM pretraining (ablation)Vlaser-2B VLA · SimplerEnv WidowXaverage success rate: 41.8% -> 62.6%Improved
add in-domain grounding data to VLM pretraining (ablation)Vlaser-2B VLA · SimplerEnv Google Robot Visual Matchingaverage success rate: 64.0% -> 73.6%Improved
add in-domain spatial data to VLM pretraining (ablation)Vlaser-2B VLA · SimplerEnv WidowXaverage success rate: 41.8% -> 60.8%Improved
combine QA, spatial and grounding in-domain data (Vlaser-All) vs single type (ablation)Vlaser-2B VLA · SimplerEnv WidowXaverage success rate: 62.6% (QA) -> 65.1% (All)Improved
combine all in-domain data (ablation)Vlaser-2B VLA · RoboTwinaverage success rate: 55.8% -> 67.5%Improved
shorten execute action length from 4 to 2 (ablation)Vlaser-QA VLA · SimplerEnv WidowXaverage success rate: 62.6% -> 51.1%Hurt

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