AI Paper Atlas

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

EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought

Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin, Bin Wang, Jifeng Dai, Yu Qiao, Ping Luo

NeurIPS 2023 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents

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 closed-loop link from planning to low-level control (ablation)EmbodiedGPT · Franka Kitchen, 10 demossuccess rate: 38.6 -> 50.8Improved
add closed-loop link (ablation)EmbodiedGPT · Franka Kitchen, 25 demossuccess rate: 47.3 -> 58.5Improved
add closed-loop link (ablation)EmbodiedGPT · Meta-World, 10 demossuccess rate: 62.7 -> 76.4Improved
add closed-loop link (ablation)EmbodiedGPT · Meta-World, 25 demossuccess rate: 64.9 -> 81.2Improved
add EgoCOT chain-of-thought training (ablation)EmbodiedGPT · Franka Kitchen, 10 demossuccess rate: 26.2 -> 50.8Improved
add EgoCOT chain-of-thought training (ablation)EmbodiedGPT · Franka Kitchen, 25 demossuccess rate: 36.4 -> 58.5Improved
add EgoCOT chain-of-thought training (ablation)EmbodiedGPT · Meta-World, 10 demossuccess rate: 55.2 -> 76.4Improved
add EgoCOT chain-of-thought training (ablation)EmbodiedGPT · Meta-World, 25 demossuccess rate: 58.7 -> 81.2Improved
increase demonstrations from 10 to 25EmbodiedGPT · Franka Kitchensuccess rate: 50.8 -> 58.5Improved
increase demonstrations from 10 to 25EmbodiedGPT · Meta-Worldsuccess rate: 76.4 -> 81.2Improved
use EmbodiedGPT (7B LM) instead of LLaVA-13BLLaVA-13B · image input user studyobject recognition score: 8.5 -> 8.4No clear effect
use EmbodiedGPT instead of LLaVA-13BLLaVA-13B · image input user studyplan executable score: 7.6 -> 8.4Improved

Later papers that compared with this method

3 later accepted papers report EmbodiedGPT as a baseline in their results tables; 3 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