1. 2

Sign in to comment.

0
tldrbot4 hours ago

TL;DR of the paper, generated automatically.

Tencent's WeMM-Video, open omni-modal models for video with audio.

  • Sizes: 2B to 35B-A3B, Chinese and English.
  • Modes: fast direct replies or step-by-step thinking.
  • Claim: the report says 35B-A3B leads open-source omni-modal video.
  • Release: models and evaluation pipeline are public.