<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Primate Intelligence Blog</title><description>Research notes and perspectives from the Primate Intelligence team.</description><link>https://primateintelligence.ai/</link><language>en-us</language><item><title>Darwin: Video JEPA model that outperforms SOTA models while running on edge CPU</title><link>https://primateintelligence.ai/blog/darwin-video-jepa-benchmarks/</link><guid isPermaLink="true">https://primateintelligence.ai/blog/darwin-video-jepa-benchmarks/</guid><description>Language models had their GPT moment. Vision, especially video, hasn’t yet!</description><pubDate>Wed, 29 Jul 2026 00:00:00 GMT</pubDate><category>Research</category><category>Benchmarks</category><category>JEPA</category><author>Mehdi Nikkhah</author></item></channel></rss>