# UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

arXiv: https://arxiv.org/abs/2604.19734 · HTML: https://mlsanity.com/paper/2604.19734/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Humanoid and legged locomotion world models, one of 11 directions in World models.
- Builds on 37 of its 41 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- World models / [Humanoid and legged locomotion world models](https://mlsanity.com/wm/humanoid-and-legged-locomotion-world-models/)

## Builds on (most cited first, 30 of 37)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [Real-World Robot Learning with Masked Visual Pre-training](https://mlsanity.com/paper/2210.03109/) (2022)
- [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025)
- [Unified Video Action Model](https://mlsanity.com/paper/2503.00200/) (2025)
- [EgoMimic: Scaling Imitation Learning via Egocentric Video](https://mlsanity.com/paper/2410.24221/) (2024)
- [Ctrl-World: A Controllable Generative World Model for Robot Manipulation](https://mlsanity.com/paper/2510.10125/) (2025)
- [Behavior Generation with Latent Actions](https://mlsanity.com/paper/2403.03181/) (2024)
- [Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers](https://mlsanity.com/paper/2409.20537/) (2024)
- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025)
- [FLARE: Robot Learning with Implicit World Modeling](https://mlsanity.com/paper/2505.15659/) (2025)
- [IRASim: A Fine-Grained World Model for Robot Manipulation](https://mlsanity.com/paper/2406.14540/) (2024)
- [Humanoid Policy ~ Human Policy](https://mlsanity.com/paper/2503.13441/) (2025)
- [VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers](https://mlsanity.com/paper/2507.01016/) (2025)
- [Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos](https://mlsanity.com/paper/2412.04445/) (2024)
- [QueST: Self-Supervised Skill Abstractions for Learning Continuous Control](https://mlsanity.com/paper/2407.15840/) (2024)
- [H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation](https://mlsanity.com/paper/2507.23523/) (2025)

## Built on by (most cited first, 10 of 10)

- [ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?](https://mlsanity.com/paper/2606.19531/) (2026)
- [Wall-OSS-0.5 Technical Report](https://mlsanity.com/paper/2605.30877/) (2026)
- [X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining](https://mlsanity.com/paper/2606.14752/) (2026)
- [Towards Predictive, Aligned, and Scalable Robot Learning](https://mlsanity.com/paper/2607.11270/) (2026)
- [AnyWorld: Factorized Egocentric World Models for Cross-Embodiment Generalization](https://mlsanity.com/paper/2608.29242/) (2026)
- [PhiZero: A World Model Built Around Physical Language](https://mlsanity.com/paper/2607.28624/) (2026)
- [GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments](https://mlsanity.com/paper/2609.21948/) (2026)
- [GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives](https://mlsanity.com/paper/2609.39601/) (2026)
- [SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models](https://mlsanity.com/paper/2610.06598/) (2026)
- [VioLA: Learning Generalist Humanoid Control Policies from Human Data](https://mlsanity.com/paper/2610.12435/) (2026)

## Abstract (arXiv)

Scaling humanoid foundation models is bottlenecked by the scarcity of robotic data. While massive egocentric human data offers a scalable alternative, bridging the cross-embodiment chasm remains a fundamental challenge due to kinematic mismatches. We introduce UniT (Unified Latent Action Tokenizer via Visual Anchoring), a framework that establishes a unified physical language for human-to-humanoid transfer. Grounded in the philosophy that heterogeneous kinematics share universal visual consequences, UniT employs a tri-branch cross-reconstruction mechanism: actions predict vision to anchor kinematics to physical outcomes, while vision reconstructs actions to filter out irrelevant visual confounders. Concurrently, a fusion branch synergies these purified modalities into a shared discrete latent space of embodiment-agnostic physical intents. We validate UniT across two paradigms: 1) Policy Learning (VLA-UniT): By predicting these unified tokens, it effectively leverages diverse human data to achieve state-of-the-art data efficiency and robust out-of-distribution (OOD) generalization on both humanoid simulation benchmark and real-world deployments, notably demonstrating zero-shot task transfer. 2) World Modeling (WM-UniT): By aligning cross-embodiment dynamics via unified tokens as conditions, it realizes direct human-to-humanoid action transfer. This alignment ensures that human data seamlessly translates into enhanced action controllability for humanoid video generation. Ultimately, by inducing a highly aligned cross-embodiment representation (empirically verified by t-SNE visualizations revealing the convergence of human and humanoid features into a shared manifold), UniT offers a scalable path to distill vast human knowledge into general-purpose humanoid capabilities.