AI Paper Atlas

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

FM-Steer: Enhance Generalist Policies with Value-Guided Cascaded Denoising

Haoming Song, Delin Qu, Yuanqi Yao, Qizhi Chen, Jiarui Li, Qi Lv, Yiwen Tang, Li Kang, Heng Zhou, Xianqiang Gao, Yuhang Tang, Xiaofan Li and 6 more

CVPR 2026 · 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
replace learned flow verifier with random flow-point selection (ablation)FM-Steer (π0) · LIBEROsuccess rate (%): 98.6 -> 84.9Hurt
add Lite-Flow denoiser to complete remaining flow matching (ablation)FM-Steer (π0) · LIBEROsuccess rate (%): 89.8 -> 98.6Improved
add repeat sampling of multiple flow points (ablation)FM-Steer (π0) · LIBEROsuccess rate (%): 93.8 -> 98.6Improved
add cascaded denoising (noise bound T below 1) so candidates differ in noise level (ablation)FM-Steer (π0) · LIBEROsuccess rate (%): 95.9 -> 98.6Improved
add value-guided sampling and cascaded denoising on top of π0π0 · LIBERO overallsuccess rate (%): 94.2 -> 98.6Improved
add FM-Steer to π0π0 · SimplerEnv WidowX overallsuccess rate (%): 69.2 -> 79.5Improved
add FM-Steer to GR00T N1GR00T N1 · LIBERO overallsuccess rate (%): 93.9 -> 97.3Improved
replace flow verifier with random selection (ablation)FM-Steer (π0) · SimplerEnv (OXE mixture)success rate (%): 75.1 -> 61.4Hurt
remove Lite-Flow denoiser (ablation)FM-Steer (π0) · real-world robot taskssuccess rate: -63%Hurt
replace flow verifier with random selection (ablation)FM-Steer (π0) · real-world robot taskssuccess rate: -78%Hurt
apply test-time verification to autoregressive VLAs (V-GPS, RoboMonkey) vs FM-Steer on flow VLAOpenVLA · SimplerEnv WidowX overallsuccess rate (%): 37.7 -> 37.0 (V-GPS), 47.8 (RoboMonkey)Mixed
asynchronous cascaded denoising with Lite-Flow denoiserFM-Steer · real-world WidowXcontrol frequency: 4Hz verifier, 90Hz denoiserImproved

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