Real-world tasks real-world-tasks Leaderboard
Auto-discovered from papers reporting Real-world tasks (Success rate). · Metric: Success rate (higher is better) · 🟢 Updated 2h ago
| # | Model | Success rate | Paper |
|---|---|---|---|
| 1 | TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation | 100.00 | link |
| 2 | IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation | 85.00 | link |
| 3 | AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulation | 80.00 | link |
| 4 | Sparse2Act: Learning Action-Aligned Sparse 3D Representations for Cross-Domain Robot Manipulation | 72.50 | link |
| 5 | VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models | 65.00 | link |
| 6 | $\pi$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation | 50.00 | link |
| 7 | AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning | 44.00 | link |
| 8 | See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation | 43.30 | link |
| 9 | Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding | 20.00 | link |
| 10 | Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning | 11.00 | link |
| 11 | Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching | 5.00 | link |