AI Paper Atlas

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

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

Yi Chen, Yuying Ge, Weiliang Tang, Yizhuo Li, Yixiao Ge, Mingyu Ding, Ying Shan, Xihui Liu

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Multimodal prompt-driven manipulation · 59 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 latent motion token pre-training on video (ablation)Moto-GPT · CALVIN (ABC->D)average length: 2.14 -> 3.10Improved
add latent motion token pre-training on video (ablation)Moto-GPT · SIMPLER overallsuccess rate: 0.480 -> 0.614Improved
add latent motion token pre-training on video (ablation)Moto-GPT · Real-world tasks (avg)success rate (%): 23.33% -> 60%Improved
add motion token pre-training with only 1% of labeled data (ablation)Moto-GPT · CALVIN (ABC->D) data efficiencysuccess rate (%): 0% -> 52.5%Improved
add motion token pre-training under visual distractor and novel object (ablation)Moto-GPT · Real-world generalizationsuccess rate: +20% and +30%Improved
add human video (SSV2) to OXE pre-trainingMoto-GPT · SIMPLER Move Nearsuccess rateImproved
keep next-motion-token loss and motion tokens during fine-tuning (co-fine-tuning) (ablation)Moto-GPT · CALVIN (ABC->D)success rateImproved
use latent motion tokens instead of frames as video representation for classificationtoken classifier · CALVIN video classificationsemantic accuracy: 0.828 -> 0.797No clear effect
add 7 latent motion token chunks to initial framevideo classifier · CALVIN video classificationsemantic accuracy: 0.292 -> 0.797Improved
compare Moto (static RGB only) to GR-1 (extra gripper RGB and proprio)Moto · CALVIN (ABC->D)average length: 3.06 -> 3.10No clear effect

Later papers that compared with this method

2 later accepted papers report Moto as a baseline in their results tables; 2 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