AI Paper Atlas

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

CycleManip: Enabling Cycle-based Manipulation via Effective History Perception and Understanding

Yi-Lin Wei, Haoran Liao, Yuhao Lin, Pengyue Wang, Zhizhao Liang, Guiliang Liu, Wei-Shi Zheng

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation

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 cost-aware history sampling (dense proprioception, sparse binary/exponential visual frames) (ablation)DP3 · real-world cyclic tasks (block hammering)success rate (%): 37.5 -> 62.5Improved
add cost-aware history sampling (ablation)DP3 · real-world drum beating (bi-gripper)success rate (%): 0 -> 60Improved
add progress-prediction multi-task learning (historical understanding) (ablation)CycleManip w/o Task · real-world block hammeringsuccess rate (%): 62.5 -> 93.75Improved
add progress-prediction multi-task learning (ablation)CycleManip w/o Task · real-world table cleaning (bi-dexterous)success rate (%): 40 -> 100Improved
add progress-prediction multi-task learning (ablation)CycleManip w/o Task · real-world tire pumping (humanoid)success rate (%): 20 -> 50Improved
add progress-prediction multi-task learning (ablation)CycleManip w/o Task · real-world bottle shakingcycle count deviation: 1.31 -> 0.375Improved
replace Pi-0 baseline with CycleManip history encoding plugged into Pi-0Pi-0 · CycleManip sim: bottle shakingsuccess rate (%): 19 -> 72Improved
plug CycleManip into Pi-0Pi-0 · CycleManip sim: dual-knife choppingsuccess rate (%): 1 -> 41Improved
apply CycleManip to general manipulation tasksDP3 · RoboTwin 2.0 Place Bread Basketsuccess rate (%): 26 -> 61Improved
apply CycleManip to general manipulation tasksDP3 · RoboTwin 2.0 Turn Switchsuccess rate (%): 46 -> 64Improved
add CycleManip history sampling and multi-task headDP3 · CycleManip sim: carrot cuttingefficiency: Time_test 0.0893 -> 0.0953; Suc. 38 -> 86Mixed
use baselines with short observation windows (Pi-0 with 1-frame observation)Pi-0 · CycleManip sim: dual-knife choppingsuccess rate (%): 1Hurt

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