AI Paper Atlas

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

ForeAct: Steering Your VLA with Efficient Visual Foresight Planning

Zhuoyang Zhang, Shang Yang, Qinghao Hu, Luke J. Huang, James Hou, Yufei Sun, Yao Lu, Song Han

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 10 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 visual foresight planning (imagined future observation + subtask text)pi0 + VLM · Real-world 11 tasksaverage success rate (%): 57.1 -> 87.4Improved
add VLM subtask planning to pi0pi0 · Real-world 11 tasksaverage success rate (%): 46.5 -> 57.1Improved
add foresight planning to pi0.5pi0.5 · Real-world tasksaverage success rate (%): 70.3 -> 88.2Improved
add foresight planning to pi0.5pi0.5 · LIBERO averagesuccess rate (%): 96.8 -> 97.5No clear effect
pretrain foresight generator on cross-embodiment data (ablation)foresight image generator · Out-of-distribution tasksfidelity: 0.00 -> 0.88Improved
pretrain foresight generator on cross-embodiment data (ablation)foresight image generator · In-distribution tasksfidelity: 0.18 -> 1.00Improved
use spatial text instruction instead of semantic text for pi0 (ablation)pi0 · Pick_Toolsuccess rate (%): 20.0 -> 46.8Improved
replace spatial text with foresight goal image (ours) (ablation)pi0 · Pick_Toolsuccess rate (%): 46.8 -> 93.4Improved
increase denoising steps for foresight generation beyond 8 (ablation)foresight generator · image quality / latencyvisual quality: 0.33 s at 8 stepsNo clear effect
reduce denoising steps to 1-2 (ablation)foresight generator · image qualityartifacts: 0.13s at 1 stepHurt
use ForeAct with less training data (20% of Clean_Rubb data)pi0 + ForeAct · Clean_Rubbsuccess rate (%): 79% at 20% dataImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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