| 2026 |
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments |
End-to-End VLA |
arXiv |
| 2026 |
Membership Inference Attacks on Vision-Language-Action Models |
End-to-End VLA |
arXiv |
| 2026 |
Learning Diffusion Policy from Primitive Skills for Robot Manipulation |
Diffusion Policy |
arXiv |
| 2026 |
Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation |
End-to-End VLA |
arXiv |
| 2026 |
InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation |
End-to-End VLA |
ICLR |
| 2026 |
A Survey of Language-Conditioned Robot Manipulation |
End-to-End VLA |
IJRR |
| 2025 |
VLAS: VLA Model With Speech Instructions |
Multimodal Ecology |
ICLR |
| 2025 |
pi_0.5: VLA with Open-World Generalization |
Diffusion Policy |
arXiv |
| 2025 |
SmolVLA |
Imitation Learning |
arXiv |
| 2025 |
Tactile-VLA |
Multimodal Ecology |
CoRL |
| 2025 |
DexVLA |
End-to-End VLA |
arXiv |
| 2025 |
OpenHelix |
End-to-End VLA |
arXiv |
| 2025 |
SpatialVLA |
End-to-End VLA |
arXiv |
| 2025 |
LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks |
High-Level Planning |
arXiv |
| 2025 |
EO-1: Interleaved Vision-Text-Action Pretraining for General Robot Control |
End-to-End VLA |
arXiv |
| 2025 |
RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI |
Datasets & Benchmarks |
arXiv |
| 2025 |
LLaDA-VLA: Vision Language Diffusion Action Models |
End-to-End VLA |
arXiv |
| 2025 |
Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning |
End-to-End VLA |
arXiv |
| 2025 |
X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model |
End-to-End VLA |
arXiv |
| 2025 |
Embodiment Transfer Learning for Vision-Language-Action Models |
End-to-End VLA |
arXiv |
| 2025 |
HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies |
End-to-End VLA |
arXiv |
| 2025 |
Asynchronous Fast-Slow Vision-Language-Action Policies for Whole-Body Robotic Manipulation |
End-to-End VLA |
arXiv |
| 2025 |
Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review |
End-to-End VLA |
arXiv |
| 2025 |
Toward Embodied AGI: A Review of Embodied AI and the Road Ahead |
End-to-End VLA |
arXiv |
| 2025 |
Embodied Navigation Foundation Model |
End-to-End VLA |
arXiv |
| 2025 |
MiMo-Embodied: X-Embodied Foundation Model Technical Report |
End-to-End VLA |
arXiv |
| 2025 |
LACY: A Vision-Language Model-based Language-Action Cycle for Self-Improving Robotic Manipulation |
End-to-End VLA |
arXiv |
| 2025 |
Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy |
Datasets & Benchmarks |
ICRA |
| 2024 |
OpenVLA: An Open-Source Vision-Language-Action Model |
End-to-End VLA |
CoRL |
| 2024 |
RoboFlamingo |
High-Level Planning |
ICLR |
| 2024 |
Octo: An Open-Source Generalist Robot Policy |
End-to-End VLA |
RSS |
| 2024 |
GR-2: Generative Video-Language-Action Model |
End-to-End VLA |
arXiv |
| 2024 |
TinyVLA |
End-to-End VLA |
RA-L |
| 2024 |
TraceVLA: Visual Trace Prompting |
End-to-End VLA |
ICLR |
| 2024 |
DeepSeek-VL: Towards Real-World Vision-Language Understanding |
VLM Foundation |
arXiv |
| 2024 |
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks |
VLM Foundation |
CVPR |
| 2024 |
Improved Baselines with Visual Instruction Tuning |
VLM Foundation |
CVPR |
| 2024 |
What matters when building vision-language models? |
VLM Foundation |
NeurIPS |
| 2024 |
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling |
VLM Foundation |
arXiv |
| 2024 |
LLaVA-NeXT-Interleave |
VLM Foundation |
arXiv |
| 2024 |
LLaVA-OneVision: Easy Visual Task Transfer |
VLM Foundation |
arXiv |
| 2024 |
Pixtral 12B |
VLM Foundation |
arXiv |
| 2024 |
UniSim |
World Model & Video Policy |
ICLR |
| 2024 |
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation |
End-to-End VLA |
arXiv |
| 2024 |
AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents |
Datasets & Benchmarks |
arXiv |
| 2024 |
AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding |
Multimodal Ecology |
arXiv |
| 2024 |
DISCO: Language-Guided Manipulation with Diffusion Policies and Constrained Inpainting |
Diffusion Policy |
arXiv |
| 2024 |
A call for embodied AI |
VLM Foundation |
ICML |
| 2023 |
LLaVA: Visual Instruction Tuning |
VLM Foundation |
NeurIPS |
| 2023 |
PaLM-E: An Embodied Multimodal Language Model |
High-Level Planning |
ICML |
| 2023 |
VoxPoser |
High-Level Planning |
CoRL |
| 2023 |
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control |
End-to-End VLA |
CoRL |
| 2023 |
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models |
VLM Foundation |
ICML |
| 2023 |
OBELICS |
Multimodal Ecology |
NeurIPS |
| 2023 |
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond |
VLM Foundation |
arXiv |
| 2023 |
Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis |
World Model & Video Policy |
arXiv |
| 2022 |
X-VLM: Multi-Grained Vision Language Pre-Training |
Multimodal Ecology |
ICML |