hermes-ai.netis an unofficial, independent community guide to Hermes Agent, with localized docs, release notes, desktop notes, and practical setup paths.

modelVideo Open Source

UC Berkeley's VDN-H3 Generates 14-Second Videos Faster Than You Can Watch

VDN-H3 replaces most of MiniMax H3's quadratic attention with a linear branch, rendering a 14.4-second 768p clip in 11.23 seconds on 8 B200s.

Source

AlphaSignal

Published

Sep 7, 2026, 7:56 AM

Author

AlphaSignal Newsroom

Read

1 min read

VDN-H3 replaces most of MiniMax H3's quadratic attention with a linear branch, rendering a 14.4-second 768p clip in 11.23 seconds on 8 B200s.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

AlphaSignal · repo

CozyClay Lets You Direct AI Video Shots in 3D Without Writing Prompts

AlphaSignal · model

Community LoRA Sharpens MiniMax H3 Videos Without Hosted 2K API

AlphaSignal · repo

Next reads

CozyClay Lets You Direct AI Video Shots in 3D Without Writing Prompts

Community LoRA Sharpens MiniMax H3 Videos Without Hosted 2K API

Amap's ABot-Recon Rebuilds 3D Worlds From Live Video Using Under 7GB