| MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action | ✓ Link | 4.79 | MPCoT | 2026-06-04 |
| Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution | | 4.75 | Xiaomi-Robotics-0 | 2026-02-13 |
| Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation | | 4.73 | VITA | 2025-11-25 |
| AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention | | 4.65 | AVA-VLA | 2025-11-24 |
| MAST-VLA: Skill-Conditioned Adaptation with Trajectory-Affordance Priors for Multi-Skill Robot Manipulation | | 4.65 | MAST-VLA | 2026-10-23 |
| Variational Cognitive Memory Abstraction for Long-Horizon Vision-Language-Action Models | | 4.64 | CogMemory (ABC→D, Florence-2-L) | 2026-10-25 |
| TEMPO: Semantic-Action Decoupled RL Post-Training for Vision-Language-Action Models | | 4.59 | TEMPO | 2026-08-07 |
| OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation | | 4.57 | OASIS | 2026-05-25 |
| VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models | | 4.56 | VAMPO | 2026-03-19 |
| From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation | | 4.55 | MoLA | 2026-05-12 |
| LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding | | 4.52 | LIRA | 2026-08-06 |
| BICPO-VLA: Behavior-Identified Continuation Preference Optimization for Smooth Asynchronous Vision-Language-Action Control | | 4.52 | BICPO-VLA | 2026-08-14 |
| Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining | ✓ Link | 4.51 | DeFI | 2026-03-27 |
| VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model | ✓ Link | 4.50 | VLA-Adapter-Pro (CALVIN ABC→D) | 2025-09-11 |
| PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation | | 4.48 | PALM | 2026-01-11 |
| Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models | | 4.47 | Mind-VLA | 2026-08-05 |
| Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation | | 4.45 | OptimusVLA | 2026-02-22 |
| DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge | ✓ Link | 4.44 | DreamVLA | 2025-07-06 |
| X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model | | 4.43 | X-VLA | 2025-10-11 |
| Variational Cognitive Memory Abstraction for Long-Horizon Vision-Language-Action Models | | 4.42 | CogMemory (D→D, Florence-2-L) | 2026-10-25 |
| Unified Vision-Language-Action Model | | 4.41 | UniVLA | 2025-06-24 |
| From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors | | 4.40 | FALCON | 2025-10-20 |
| Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action Models | | 4.38 | SSM-VLA | 2025-09-30 |
| HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models | ✓ Link | 4.35 | HiF-VLA (CALVIN ABC→D) | 2025-12-10 |
| ChunkFlow: Towards Continuity-Consistent Chunked Policy Learning | | 4.30 | ChunkFlow | 2026-07-14 |
| Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations | ✓ Link | 4.29 | VPP | 2024-12-19 |
| MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models | | 4.29 | MemoryVLA++ | 2026-06-08 |
| Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models | ✓ Link | 4.25 | RoboVLMs | 2024-12-18 |
| TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging | | 4.19 | TS-Mask VLA | 2026-07-10 |
| VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models | | 4.142 | VLM4VLA (Qwen3VL-2B, CALVIN ABC-D) | 2026-01-06 |
| SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models | | 4.11 | SAM3D-VLA | 2026-07-28 |
| MoWM: Mixture-of-World-Models for Embodied Planning via Latent-to-Pixel Feature Modulation | ✓ Link | 4.10 | MoWM | 2025-09-26 |
| Pixel Motion Diffusion is What We Need for Robot Control | | 4.10 | DAWN | 2025-09-26 |
| UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent | | 4.08 | UP-VLA | 2025-01-31 |
| OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation | ✓ Link | 4.08 | Openhelix | 2025-05-06 |
| 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 |
| LLaDA-VLA: Vision Language Diffusion Action Models | | 4.01 | LLaDA-VLA | 2025-09-08 |
| PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning | | 4.01 | PMP | 2025-10-23 |
| ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver | | 3.95 | ReconVLA | 2025-08-14 |
| RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation | ✓ Link | 3.855 | RoboUniView | 2024-06-27 |
| UniVLA: Learning to Act Anywhere with Task-centric Latent Actions | ✓ Link | 3.80 | UniVLA | 2025-05-09 |
| ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation | | 3.73 | ProgressVLA | 2026-03-29 |
| Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline | | 3.68 | LLaVA-VLA | 2026-02-26 |
| CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding | ✓ Link | 3.67 | CEED-VLA (LLaVA-VLA, action chunk 5, CALVIN ABC→D) | 2025-06-16 |
| Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation | | 3.66 | RoboDual | 2024-10-10 |
| Diffusion Transformer Policy | ✓ Link | 3.61 | DiT Policy (CALVIN ABC→D) | 2024-10-21 |
| Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy | ✓ Link | 3.61 | Dita (CALVIN ABC→D) | 2025-03-25 |
| VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation | | 3.42 | VidMan | 2024-11-14 |
| Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning | | 3.39 | RD-VLA | 2026-02-08 |
| 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations | ✓ Link | 3.35 | 3DDA | 2024-02-18 |
| 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations | ✓ Link | 3.27 | 3D Diffusor Actor | 2024-02-18 |
| OpenVLA: An Open-Source Vision-Language-Action Model | ✓ Link | 3.27 | OpenVLA | 2024-06-13 |
| Variational Cognitive Memory Abstraction for Long-Horizon Vision-Language-Action Models | | 3.27 | CogMemory (D→D, PaliGemma) | 2026-10-25 |
| Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation | ✓ Link | 3.06 | GR-1 | 2023-12-20 |
| Variational Cognitive Memory Abstraction for Long-Horizon Vision-Language-Action Models | | 2.92 | CogMemory (ABC→D, PaliGemma) | 2026-10-25 |
| Vision-Language Foundation Models as Effective Robot Imitators | | 2.47 | Roboflamingo | 2023-11-02 |
| From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control | | 1.78 | LCB | 2024-05-08 |
| Learning Universal Policies via Text-Guided Video Generation | | 0.92 | Uni-Pi | 2023-01-31 |
| RT-1: Robotics Transformer for Real-World Control at Scale | ✓ Link | 0.90 | RT-1 | 2022-12-13 |