---
title: "AHA-WAM"
description: "World-action model for RoboTwin 2.0: video + action experts, six-frame history, 16×14 chunks. MIT license. A100 Workspace validated; not a closed-loop score."
modelId: "ahawam"
pageSource: authored
---

AHA-WAM is a **world-action model** for manipulation: a video expert and an action expert share a **mixture cache** so the policy can use predictive world modeling at infer time. WorldFoundry runs the exact video/action experts, mixture-cache editor, **six-frame** history, two-phase chunk inference, Wan VAE, and UMT5 encoder **in process**. Trainers, simulators, and deployment servers are excluded. Pipeline: `AHAWAMPipeline`. Aliases `aha-wam` and `aha-wam-robotwin` resolve here.

<ModelPaperFigures modelId="ahawam" locale="en" />

The official paper is on [arXiv 2606.09811](https://arxiv.org/abs/2606.09811). Project: [serene-sivy.github.io/aha-wam](https://serene-sivy.github.io/aha-wam/). Code: [Serene-SIVY/AHA-WAM](https://github.com/Serene-SIVY/AHA-WAM). License: **MIT**. Recorded policy: `SereneC/AHA-WAM-RoboTwin2.0` (`robotwin_ahawam.pt`). VAE and UMT5 come from `DiffSynth-Studio/Wan-Series-Converted-Safetensors`.

The released RoboTwin 2.0 checkpoint completed real **A100** Workspace inference from **three ALOHA views** plus a **14-D** state and returned a finite **16×14** open-loop chunk. Catalog runner is still unset — that is numerical checkpoint validation, not a closed-loop simulator score.

<ModelCommandBuilder modelId="ahawam" locale="en" />

## What it is for

AHA-WAM RoboTwin chunk from three ALOHA views plus state.

Launch `worldfoundry-eval run ahawam`.

Score on [RoboTwin 2.0](/docs/evaluation/benchmark-hub/robotwin) — the released checkpoint is trained for RoboTwin 2.0.

## Runtime contract

Required: `image` and `prompt`; optional: `model_id`, `state`, `preferred_cameras`, `image_size`, `configured_action_horizon`, `action_chunk_size`, and `default_chunks_per_video_prefill`; artifacts: `action_trace` and `ahawam_action_trace.json`.

| Knob | Recorded value |
| --- | --- |
| Image size | **384×320** |
| Action horizon | **64** |
| Chunk size | **16** |
| Video prefill chunks | **2** (then KV refresh; up to six earlier prefill entries kept) |

## Run in WorldFoundry

Status: **Verified**. Unified environment `worldfoundry-unified-cu128` (Python 3.11, CUDA 12.8). Stage `SereneC/AHA-WAM-RoboTwin2.0`, `DiffSynth-Studio/Wan-Series-Converted-Safetensors`, and `Wan-AI/Wan2.1-T2V-1.3B` locally — missing files fail at load, nothing is downloaded. Run `worldfoundry-eval run ahawam`. Catalog VRAM is unset.

<ModelRelatedRecipes modelId="ahawam" locale="en" />