| MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation | ✓ Link | 4.78 | MMaDA-VLA (CALVIN ABC→D) | 2026-03-26 |
| Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution | | 4.75 | Xiaomi-Robotics-0 | 2026-02-13 |
| GreenWAM: A World Foundation Model for Robotics | ✓ Link | 4.64 | GreenWAM | 2026-10-13 |
| FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies | ✓ Link | 4.53 | FLOWER (ABC→D, PrT) | 2025-09-05 |
| PAIR: Bridging Perception and Action in Vision-Language-Action Models | | 4.53 | VLA-Adapter + PAIR | 2026-10-06 |
| Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining | ✓ Link | 4.51 | DeFI | 2026-03-27 |
| LEAP-VLA: Latent-Enhanced Action Prototyping via Continuous Residual Latent Spaces for Vision-Language-Action Models | | 4.28 | LEAP-VLA | 2026-09-08 |
| AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation | ✓ Link | 4.22 | AffordanceWAM | 2026-10-18 |
| GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy | ✓ Link | 4.04 | GR-MG | 2024-08-26 |
| Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning | ✓ Link | 4.01 | MoDE | 2024-12-17 |
| Learning a Unified Latent Action Space from Videos with Action-centric Cycle Consistency | | 3.93 | CycleMimic | 2026-06-03 |
| OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams | ✓ Link | 3.885 | OmniStream-7B | 2026-03-12 |
| UniVLA: Learning to Act Anywhere with Task-centric Latent Actions | ✓ Link | 3.8 | UniVLA (Task-centric Latent Actions, CALVIN ABC→D) | 2025-05-09 |
| ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation | | 3.73 | ProgressVLA (Pretrained) | 2026-03-29 |
| EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training | | 3.714 | InternVL3.5-1B + EmbodiedMidtrain | 2026-04-21 |
| RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation | ✓ Link | 3.647 | RoboUniView | 2024-06-27 |
| Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning | ✓ Link | 3.39 | RD-VLA (0.5B) | 2026-02-08 |
| 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations | ✓ Link | 3.27 | 3D Diffuser Actor | 2024-02-18 |
| Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation | ✓ Link | 3.06 | GR-1 | 2023-12-20 |
| DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution | ✓ Link | 2.90 | DeeR w. online (CALVIN ABC→D) | 2024-11-04 |
| RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models | | 2.57 | RoboAlign | 2026-03-22 |