AI Paper Atlas

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

Octopus: Embodied Vision-Language Programmer from Environmental Feedback

Jingkang Yang, Yuhao Dong, Shuai Liu, Bo Li, Ziyue Wang, ChenCheng Jiang, Haoran Tan, Jiamu Kang, Yuanhan Zhang, Kaiyang Zhou, Ziwei Liu

ECCV 2024 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 64 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 RLEF (PPO with environmental-feedback reward model) after SFT (ablation)Octopus · OctoGibson all taskstask completion rate: 0.15 -> 0.18Improved
add RLEF after SFT (ablation)Octopus · OctoGibson reasoning taskstask completion rate: 0.13 -> 0.20Improved
add RLEF after SFT (ablation)Octopus · OctoMC unseen taskstask completion rate: 0.20 -> 0.20No clear effect
add RLEF after SFT (ablation)Octopus · OctoGTA alltask completion rate: 0.18 -> 0.20Improved
randomize order of FPV and BEV image inputsOctopus · OctoGibsontask performanceHurt
reduce model size from 7B to 3BOctopus · OctoGibsontask performanceHurt
finetune language decoder in addition to connector (ablation)Octopus · OctoGibson (60 tasks)successful tasks: 4 -> 5 out of 60Improved
use code-specialized CodeLLaMA instead of general LLaMA as blind LLMblind LLM planners · OctoGibsonexecutable code rate: 24% -> 92%Improved
replace MPT backbone with CodeLLaMA in OctopusOctopus · OctoGibsonoutput qualityHurt
compare Octopus (SFT+RLEF) to GPT-4 and GPT-4VOctopus · OctoGibson alltask completion rate: 0.18 vs 0.43 (GPT-4)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