| Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution | ✓ Link | 85.5 | Xiaomi-Robotics-0 (Visual Matching) | 2026-02-13 |
| NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards | ✓ Link | 82.8 | NORA-1.5 (DPO, Visual Matching) | 2025-11-18 |
| RLDX-1 Technical Report | ✓ Link | 81.5 | RLDX-1 (extra data) | 2026-05-05 |
| X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model | ✓ Link | 80.4 | X-VLA-0.9B (Google Robot Visual Matching) | 2025-10-11 |
| E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation | | 80.0 | MolmoAct + E-TTS | 2026-06-25 |
| Hume: Introducing System-2 Thinking in Visual-Language-Action Model | ✓ Link | 78.7 | Hume (Google Robot Visual Matching) | 2025-05-27 |
| MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation | | 77.7 | MemoryVLA (Google Robot Visual Matching) | 2025-08-26 |
| FM-Steer: Enhance Generalist Policies with Value-Guided Cascaded Denoising | | 76.6 | FM-Steer (π0) | 2026-06-03 |
| EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models | | 76.4 | EfficientVLA (L=28, T=112, Google Robot Visual Matching) | 2025-06-11 |
| Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning | ✓ Link | 76.2 | Vlaser-All (visual matching) | 2025-10-13 |
| StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing | ✓ Link | 76.0 | StarVLA-OFT (Google Robot Visual Matching) | 2026-04-06 |
| Less is More: Reducing Complexity in Vision-Language-Action Systems | ✓ Link | 76.0 | StarVLA-α (Specialist) | 2026-09-08 |
| SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration | | 75.05 | SP-VLA (Google Robot Visual Matching) | 2025-06-15 |
| CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation | | 74.8 | CogACT (Google Robot Visual Matching) | 2024-11-29 |
| SAFE-Pruner: Semantic Attention–Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation | ✓ Link | 74.5 | SAFE-Pruner (CogACT) | 2026-05-28 |
| VideoVLA: Video Generators Can Be Generalizable Robot Manipulators | | 73.1 | VideoVLA (Google Robot Visual Matching) | 2025-12-07 |
| Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies | ✓ Link | 71.2 | Discrete Diffusion VLA (Google Robot Visual Matching) | 2025-08-27 |
| Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy | ✓ Link | 68.7 | Dita (Google Robot Visual Matching) | 2025-03-25 |
| VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model | ✓ Link | 65.2 | VLA-JEPA | 2026-02-10 |
| Diffusion Transformer Policy | ✓ Link | 58.6 | DiT Policy (Google Robot Visual Matching) | 2024-10-21 |