Source link : https://tech365.info/xpeng-unveils-the-world-model-accelerator-x-cache-which-requires-no-coaching-is-plug-and-play-and-boosts-inference-pace-by-2-7-occasions/
Assist CleanTechnica’s work by way of a Substack subscription or on Stripe.
Guangzhou, Might 6, 2026 — XPENG (NYSE: XPEV, HKEX: 9868), a number one China-based high-tech firm, beforehand launched the X-World technical report and demonstrated the sensible worth of this know-how in XPENG’s autonomous driving. Lately, XPENG as soon as once more introduced developments in world mannequin know-how, the X-Cache technical report.
X-Cache leverages the continuity of the bodily world to establish reusable picture areas whereas making certain security, thereby decreasing redundant computations. It may be instantly utilized to world fashions in a quick and light-weight method (with out requiring retraining), reaching as much as 2.7 instances quicker denoising inference acceleration for world fashions. This considerably enhances effectivity and reduces useful resource consumption.
Reductive but Dependable, Exploiting Bodily Continuity for Cross-Section Characteristic Reuse
As autonomous driving enters the model-driven period, high-fidelity simulation of the true world has grow to be a cornerstone for the continual evolution of driving fashions. Whereas autoregressive video diffusion-based world fashions provide high-fidelity, multi-view video technology capabilities, their inference value and latency stay bottlenecks constraining real-time interplay and large-scale deployment.
XPENG employs fewer steps to refine visuals that carefully mirror the true world (a method often…
—-
Author : tech365
Publish date : 2026-05-08 05:21:00
Copyright for syndicated content belongs to the linked Source.
—-
1 – 2 – 3 – 4 – 5 – 6 – 7 – 8