# Vision-language-action models

1,509 papers in 13 research directions. Data through 7 Oct 2026.
HTML: https://mlsanity.com/vla/

## Directions (largest first)

- [Generalist VLA models and benchmarks](https://mlsanity.com/vla/generalist-vla-models-and-benchmarks/index.md): 276 papers, 0 new this week
- [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/index.md): 237 papers, 4 new this week
- [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/index.md): 173 papers, 4 new this week
- [Reasoning and chain-of-thought in VLA](https://mlsanity.com/vla/reasoning-and-chain-of-thought-in-vla/index.md): 137 papers, 1 new this week
- [3D and spatial-aware VLA](https://mlsanity.com/vla/3d-and-spatial-aware-vla/index.md): 129 papers, 0 new this week
- [Failure recovery and robustness](https://mlsanity.com/vla/failure-recovery-and-robustness/index.md): 109 papers, 5 new this week
- [Human-video and latent-action pretraining](https://mlsanity.com/vla/human-video-and-latent-action-pretraining/index.md): 103 papers, 2 new this week
- [VLA for autonomous driving](https://mlsanity.com/vla/vla-for-autonomous-driving/index.md): 101 papers, 1 new this week
- [World model-based VLA](https://mlsanity.com/vla/world-model-based-vla/index.md): 76 papers, 3 new this week
- [Safety and adversarial attacks](https://mlsanity.com/vla/safety-and-adversarial-attacks/index.md): 58 papers, 1 new this week
- [Tactile, force-aware and humanoid VLA](https://mlsanity.com/vla/tactile-force-aware-and-humanoid-vla/index.md): 50 papers, 1 new this week
- [VLA architectures and generalization](https://mlsanity.com/vla/vla-architectures-and-generalization/index.md): 43 papers, 3 new this week
- [Aerial and drone VLA](https://mlsanity.com/vla/aerial-and-drone-vla/index.md): 17 papers, 1 new this week