# Human-video and latent-action pretraining

Area: [Vision-language-action models](https://mlsanity.com/vla/index.md). HTML: https://mlsanity.com/vla/human-video-and-latent-action-pretraining/

## Key facts

- Human-video and latent-action pretraining: 103 papers on arXiv since 2024 (data through 7 Oct 2026).
- 43 of its 103 mapped papers (42%) cite “Latent Action Pretraining from Videos” (2024, arXiv 2410.11758).
- 36 of its 103 mapped papers (35%) cite “UniVLA: Learning to Act Anywhere with Task-centric Latent Actions” (2025, arXiv 2505.06111).
- 11 new papers 17 Sep–7 Oct.

## Most cited here

- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024), cited by 43 papers here
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025), cited by 36 papers here
- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025), cited by 17 papers here
- [Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos](https://mlsanity.com/paper/2507.15597/) (2025), cited by 17 papers here
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024), cited by 13 papers here
- [DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping](https://mlsanity.com/paper/2502.20900/) (2025), cited by 9 papers here
- [GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data](https://mlsanity.com/paper/2505.03233/) (2025), cited by 9 papers here
- [Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos](https://mlsanity.com/paper/2510.21571/) (2025), cited by 8 papers here
- [Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization](https://mlsanity.com/paper/2601.12993/) (2026), cited by 7 papers here
- [mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs](https://mlsanity.com/paper/2512.15692/) (2025), cited by 5 papers here

## New (17 Sep–7 Oct)

- [YUBI-STAG: Contact and Semantic-Rich Alignment for VLAs via Automated Video-Language Grounding](https://mlsanity.com/paper/2610.09718/) (2026-10-07)
- [ESP: Energy-Score Policy for One-Step Multimodal Action Generation](https://mlsanity.com/paper/2610.07696/) (2026-10-06)
- [NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields](https://mlsanity.com/paper/2610.00981/) (2026-10-01)
- [FineART: Fine-Grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation](https://mlsanity.com/paper/2609.36416/) (2026-09-30)
- [CrossSafe: Towards Cross-Embodiment Latent Safety Filters](https://mlsanity.com/paper/2609.28984/) (2026-09-24)
- [ActGaze: Learning Action-Grounded Gaze through Counterfactual Visual Interventions for High-Precision Manipulation](https://mlsanity.com/paper/2609.28955/) (2026-09-24)
- [Direction-Scale Decomposition in Action Representation: Rethinking What to Tokenize for Vision-Language-Action Models](https://mlsanity.com/paper/2609.28865/) (2026-09-24)
- [SCULPT-VLA: Learning Structured Control through Staged Action Grounding](https://mlsanity.com/paper/2609.23275/) (2026-09-20)
- [GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments](https://mlsanity.com/paper/2609.21948/) (2026-09-18)
- [A Sim-to-Real Integration Pipeline for Training and Deployment of Chunk-Based VLA Manipulation Policies](https://mlsanity.com/paper/2609.21817/) (2026-09-18)
- [HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface](https://mlsanity.com/paper/2609.20659/) (2026-09-17)