# DiffusionAnything: End-to-End In-context Diffusion Learning for Unified Navigation and Pre-Grasp Motion

arXiv: https://arxiv.org/abs/2603.26322 · HTML: https://mlsanity.com/paper/2603.26322/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2026.

## Built on by (most cited first, 1 of 1)

- [CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain](https://mlsanity.com/paper/2606.16048/) (2026)

## Abstract (arXiv)

Efficiently predicting motion plans directly from vision remains a fundamental challenge in robotics, where planning typically requires explicit goal specification and task-specific design. Recent vision-language-action (VLA) models infer actions directly from visual input but demand massive computational resources, extensive training data, and fail zero-shot in novel scenes. We present a unified image-space diffusion policy handling both meter-scale navigation and centimeter-scale manipulation via multi-scale feature modulation, with only 5 minutes of self-supervised data per task. Three key innovations drive the framework: (1) Multi-scale FiLM conditioning on task mode, depth scale, and spatial attention enables task-appropriate behavior in a single model; (2) trajectory-aligned depth prediction focuses metric 3D reasoning along generated waypoints; (3) self-supervised attention from AnyTraverse enables goal-directed inference without vision-language models and depth sensors. Operating purely from RGB input (2.0 GB memory, 10 Hz), the model achieves robust zero-shot generalization to novel scenes while remaining suitable for onboard deployment.