RoboTwin 2.0

'RoboTwin 2.0' is a benchmark dataset used to evaluate robotic manipulation tasks, specifically focusing on spatial-temporal interactions and geometric constraints in action execution.

Papers using RoboTwin 2.0 (36)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning2025 · 83 citesBridge-WA: Predicting Where and How the World Changes for Robotic Action2026Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision2026Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models2026ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation2026Feat2Go: Visual Feature-Grounded Value Estimation for Embodied Reinforcement Learning2026PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking2026Light-WAM: Efficient World Action Models with State-Fusion Action Decoding2026GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation2026Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based Robotic Manipulation2026Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination2026See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation2026Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control2026PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models2026Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation2026RotVLA: Rotational Latent Action for Vision-Language-Action Model2026AttenA+: Rectifying Action Inequality in Robotic Foundation Models2026Key-Gram: Extensible World Knowledge for Embodied Manipulation2026SANTS: A State-Adaptive Scheduler for World Action Models20263DVLA: Enhancing Vision-Language-Action Models via 3D Spatial and Instance Understanding2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing2026AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps2026STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation2026MotuBrain: An Advanced World Action Model for Robot Control2026SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation2026One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies2026VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning2026MemoAct: Atkinson-Shiffrin-Inspired Memory-Augmented Visuomotor Policy for Robotic Manipulation2026VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation2026HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matching2026JEPA-VLA: Video Predictive Embedding is Needed for VLA Models2026HoloBrain-0 Technical Report2026Universal Pose Pretraining for Generalizable Vision-Language-Action Policies2026Information Filtering via Variational Regularization for Robot Manipulation2026PocketDP3: Efficient Pocket-Scale 3D Visuomotor Policy2026PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation2026