AI Paper Atlas

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

HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning

Quanxin Shou, Fangqi Zhu, Shuang Chen, Puxin Yan, Zhengyang Yan, Yikun Miao, Xiaoyi Pang, Zicong Hong, Ruikai Shi, Hao HUANG, Jie ZHANG, Song Guo

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 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 EM-CoT (text reasoning plus visual subgoal) to HALO (ablation)HALO · RoboTwin 2.0 Easyavg success rate (%): 75.3 -> 80.5Improved
add EM-CoT (text reasoning plus visual subgoal) to HALO (ablation)HALO · RoboTwin 2.0 Hardavg success rate (%): 21.2 -> 26.4Improved
add textual reasoning to EM-CoT (ablation)HALO · RoboTwin 2.0 Hardavg success rate (%): 18.3 -> 26.4Improved
add textual reasoning to EM-CoT (ablation)HALO · RoboTwin 2.0 Easyavg success rate (%): 77.8 -> 80.5Improved
add visual subgoal images to EM-CoT (ablation)HALO · RoboTwin 2.0 Hardavg success rate (%): 22.5 -> 26.4Improved
add visual subgoal images to EM-CoT (ablation)HALO · RoboTwin 2.0 Easyavg success rate (%): 76.1 -> 80.5Improved
add visual generation data to pretraining (ablation)HALO pretraining · RoboTwin 2.0 Hardavg success rate (%): 10.5 -> 21.2Improved
add visual generation data to pretraining (ablation)HALO pretraining · RoboTwin 2.0 Easyavg success rate (%): 58.2 -> 75.3Improved
add textual VQA data to pretraining (ablation)HALO pretraining · RoboTwin 2.0 Easyavg success rate (%): 42.9 -> 58.2Improved
add textual VQA data to pretraining (ablation)HALO pretraining · RoboTwin 2.0 Hardavg success rate (%): 3.9 -> 10.5Improved
add action prediction pretraining data (ablation)HALO pretraining · RoboTwin 2.0 Hardavg success rate (%): 0.0 -> 3.9Improved
add action prediction pretraining data (ablation)HALO pretraining · RoboTwin 2.0 Easyavg success rate (%): 32.4 -> 42.9Improved

Later papers that compared with this method

1 later accepted paper reports HALO as a baseline in their results tables; 1 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