TAO HUANG

Overall Research Framework

以多模态智能为核心，以视觉生成建模世界，以具身智能交互现实

Multimodal Intelligence at the Core,
Visual Generation for Modeling the World,
Embodied Intelligence for Interacting with Reality

Research highlights:

1 Efficient Foundation Architectures

Kairos-3.0 (World Model)

• A Pure Temporally-Linear DiT Architecture
We replace standard quadratic temporal attention with a hybrid design composed of linear- and local-attention mechanisms. This enables efficient modeling of long video sequences while maintaining strong temporal coherence and causal reasoning ability.

MiniMax-01 (LLM)

• Innovative Linear Attention Architecture
For the first time on a large scale, we have implemented a mixture of linear and softmax attention architecture. This model has 456B parameters and a MoE structure with 45.9B parameters activated per inference.

Mamba for Vision

2 Knowledge Distillation

DIST

3 Embodied AI