AI Paper Atlas

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

RoboOmni: Actions Are Just Another Modality for Vision-Language Models

Dong Wang, Zilong Chen, Jirong Liu, Ziqing Qiao, Xin Xiao, Bingyi Kang, Hongtao Wu, Xiao Ma, Tao Kong, Huaping Liu

ICML 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
add Multi-Token Action Prediction (MTAP) to FAST tokenizer (ablation)RoboOmni(FAST) · CALVIN ABCD->D5-task success rate: 80.1% -> 88.1%Improved
add MTAP to Bin tokenizer (ablation)RoboOmni(Bin) · CALVIN ABCD->D5-task success rate: 67.9% -> 83.4%Improved
add MTAP parallel decoding to Bin tokenizer for speed (ablation)RoboOmni(Bin) · CALVINinference time (ms/action): 107 -> 12.1Improved
increase history window from 1 to 5 (ablation)RoboOmni(Bin) · CALVIN ABCD->D5-task success rate: 81.3% -> 83.4%Improved
increase history window from 5 to 10 (ablation)RoboOmni(Bin) · CALVIN ABCD->Daverage task length: 4.64 -> 4.55No clear effect
scale backbone from 2B to 7B (ablation)RoboOmni(Bin) · CALVIN ABCD->D5-task success rate: 77.6% -> 83.4%Improved
add VLM data co-training (ablation)RoboOmni(Bin) · CALVIN ABCD->Daverage task length: 4.53 -> 4.64Improved
add sequence packing (ablation)RoboOmni(Bin) · CALVIN ABCD->Daverage task length: 4.46 -> 4.64Improved
add classifier-free guidance training (drop language 20%) (ablation)RoboOmni(Bin) · CALVIN ABCD->Daverage task length: 4.48 -> 4.64Improved
use 1024 action bins instead of 256 (ablation)RoboOmni(Bin) · CALVIN ABCD->D5-task success rate: 83.4% -> 79.0%Hurt
use 128 action bins instead of 256 (ablation)RoboOmni(FAST) · CALVIN ABCD->D5-task success rate: 88.1% -> 86.1%Hurt
use 128 bins instead of 256 for Bin tokenizer (ablation)RoboOmni(Bin) · CALVIN ABCD->D5-task success rate: 83.4% -> 83.7%No clear effect

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