# Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learning

arXiv: https://arxiv.org/abs/2512.00074 · HTML: https://mlsanity.com/paper/2512.00074/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2025.

## Built on by (most cited first, 3 of 3)

- [Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assembly](https://mlsanity.com/paper/2609.07534/) (2026)
- [ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation](https://mlsanity.com/paper/2609.16586/) (2026)
- [Native Action-Prior Learning from Videos for World Action Models](https://mlsanity.com/paper/2610.03391/) (2026)

## Abstract (arXiv)

Despite strong results on recognition and segmentation, current 3D visual pre-training methods often underperform on robotic manipulation. We attribute this gap to two factors: the lack of state-action-state dynamics modeling and the unnecessary redundancy of explicit geometric reconstruction. We introduce AFRO, a self-supervised framework that learns dynamics-aware 3D representations without action or reconstruction supervision. AFRO casts state prediction as a generative diffusion process and jointly models forward and inverse dynamics in a shared latent space to capture causal transition structure. To prevent feature leakage in action learning, we employ feature differencing and inverse-consistency supervision, improving the quality and stability of visual features. When combined with Diffusion Policy, AFRO substantially increases manipulation success rates across 16 simulated and 4 real-world tasks, outperforming existing pre-training approaches. The framework also scales favorably with data volume and task complexity. Qualitative visualizations indicate that AFRO learns semantically rich, discriminative features, offering an effective pre-training solution for 3D representation learning in robotics. Project page: https://kolakivy.github.io/AFRO/