<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Streaming-Inference on Noureddine RAMDI</title><link>https://ramdi.fr/tags/streaming-inference/</link><description>Recent content in Streaming-Inference on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 23 May 2026 20:41:27 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/streaming-inference/index.xml" rel="self" type="application/rss+xml"/><item><title>Streaming 3D scene reconstruction with LingBot-Map’s geometric context transformer</title><link>https://ramdi.fr/github-stars/streaming-3d-scene-reconstruction-with-lingbot-maps-geometric-context-transformer/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/streaming-3d-scene-reconstruction-with-lingbot-maps-geometric-context-transformer/</guid><description>LingBot-Map performs streaming 3D reconstruction from long image sequences at ~20 FPS using a geometric context transformer and paged KV cache attention for efficient memory management.</description></item></channel></rss>