Streaming World Model Recurrent Memory Diagram
Overview
A numbered four-step horizontal flow for spatial memory in a streaming world model: (1) observe views x₁–x₃ from moving cameras, (2) accumulate spatial context into a fixed-size recurrent state S with camera encoding and a KDA update, (3) a context-aware query attends over explicit history tokens and highlights co-visible ones with an attention-mass bar chart, (4) a softmax readout recovers a consistent revisit view. It is an editable PowerPoint diagram adapted from the original paper figure under CC BY 4.0.
What the diagram shows
Every box, arrow, label and math term is a native shape you can recolor, resize and relabel for your own slides, posters or papers.
File format
The download contains .pptx (1 slide, 16.00 × 5.15 in; opens in PowerPoint, Keynote, WPS and LibreOffice Impress; Google Slides works too, but complex freeforms may shift slightly), .svg and .drawio. Includes preview.png (full resolution) and a 1200 px web preview.
Shapes and editing
The file has 149 native editable shapes: 89 auto-shapes, 20 text boxes, 40 freeforms, 0 lines/connectors. 17 embedded images (see below). You can edit all text and math (x₁, x₂, x₃, S), native camera icons, the 6×6 state matrix cells, the circular update arrow, the query pill, 12 curved attention arrows, dotted guides, the attention-mass bars and all frame outlines.
Embedded images and fonts
17 items are embedded images: the scene photos and the 12 history-token thumbnails. Text uses Times New Roman, which is preinstalled on Windows and macOS (LibreOffice uses the metric-compatible Liberation Serif). Sub- and superscripts are real formatted text runs, not equation objects. The SVG keeps text as text; the draw.io file is a shape-by-shape conversion and may need small nudges. This is a faithful redraw for reuse, not the authors' original source file.
Source & license Adapted from Figure 3 of LOCI: Spatial Linear Memory for Streaming World Models by Ji Xia, Tingting Liao, Xuezhi Liang, Hao Li, Guangyi Liu (arXiv:2609.40222, https://arxiv.org/abs/2609.40222; code: https://github.com/xiaji2021/LOCI). Licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Redrawn as editable shapes; changes made by 叫我Alonzo就好了/alonzolab. Not endorsed by the original authors. Attribution to the original paper is required when you publish or share the figure; the exact credit line is in LICENSE-ATTRIBUTION.txt inside each download.