Apr 8, 2026 · Artificial Intelligence

Beyond Simple Motions: How SentiAvatar Redefines 3D Digital Human Action Generation

SentiAvatar introduces a two‑stage plan‑then‑infill framework that separates sentence‑level semantic planning from frame‑level prosody‑driven motion infill, leveraging a 200K‑sequence Motion Foundation Model and the newly released 21k‑clip SuSuInterActs dataset to achieve state‑of‑the‑art, real‑time expressive 3D digital human animation.

3D digital humansMotion Foundation ModelSentiAvatar

0 likes · 13 min read

Beyond Simple Motions: How SentiAvatar Redefines 3D Digital Human Action Generation

DataFunSummit

Nov 26, 2022 · Artificial Intelligence

Multimodal Digital Human Driving: Motionverse Engine and Metaverse Applications

This article introduces the evolution of digital human technology, explains the five maturity levels (L1‑L5), describes the Motionverse multimodal motion‑generation platform and its large‑scale data and AI models, and outlines SDK integration strategies for diverse metaverse scenarios.

Metaversemotion generationmultimodal AI

0 likes · 11 min read

Multimodal Digital Human Driving: Motionverse Engine and Metaverse Applications