# AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation

arXiv: https://arxiv.org/abs/2609.22332 · HTML: https://mlsanity.com/paper/2609.22332/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 11 of its 44 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 11 of 11)

- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data](https://mlsanity.com/paper/2602.16710/) (2026)
- [Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising](https://mlsanity.com/paper/2604.26694/) (2026)
- [Native Video-Action Pretraining for Generalizable Robot Control](https://mlsanity.com/paper/2607.08639/) (2026)
- [EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data](https://mlsanity.com/paper/2607.08436/) (2026)
- [HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos](https://mlsanity.com/paper/2605.24934/) (2026)
- [AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding](https://mlsanity.com/paper/2606.06155/) (2026)
- [AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment](https://mlsanity.com/paper/2605.17517/) (2026)

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

- [GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed](https://mlsanity.com/paper/2609.39600/) (2026)
- [GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives](https://mlsanity.com/paper/2609.39601/) (2026)
- [OpenWAM: An Open Framework for Composable World-Action Models](https://mlsanity.com/paper/2610.07922/) (2026)

## Abstract (arXiv)

Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act. Action-labeled robot videos directly supervise control but are costly and limited in diversity, whereas egocentric human videos capture diverse interactions but lack robot actions and differ in embodiment and appearance. We introduce AffordanceWAM, an affordance-aware generative World Action Model that represents object-centric spatiotemporal affordance through Scalar Affordance and Affordance Heatmap, within the generated future World. This representation grounds visual prediction in task-relevant objects and interaction regions for action generation, and provides shared interaction targets across human and robot videos. Built on a pretrained video diffusion Transformer, AffordanceWAM uses separately parameterized World and Action Experts, coupled through Masked Joint Self-Attention, to jointly predict future RGB observations, Scalar Affordance fields, Affordance Heatmaps, and continuous robot actions under a unified flow-matching objective. Human videos supervise all three future-World streams, whereas robot trajectories additionally provide action supervision, enabling transfer without human action labels or retargeting. Experiments on RoboCasa, CALVIN ABCrightarrowD, and real-world manipulation demonstrate consistent gains over RGB-only and robot-data-only baselines. Under fixed robot supervision, RoboCasa performance improves monotonically as affordance-annotated human video scales. These results support affordance as an effective interface for both vision-language-action learning and human-to-robot transfer.