RoboMimic

The 'RoboMimic' dataset/benchmark contains a variety of robotic manipulation tasks and is used to evaluate the performance of robotic control algorithms in real-time scenarios.

Papers using RoboMimic (17)

StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception2026SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution2026Aligning Flow Map Policies with Optimal Q-Guidance2026Feedback World Model Enables Precise Guidance of Diffusion Policy2026GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks2026Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations2026ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching2026Gated Memory Policy2026PPGuide: Steering Diffusion Policies with Performance Predictive Guidance2026PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning2026STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction2026Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation2026One Step Is Enough: Dispersive MeanFlow Policy Optimization2026Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition2025DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation2025Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising2025Imagination at Inference: Synthesizing In-Hand Views for Robust Visuomotor Policy Inference2025