Back to home

Tag

transformer

Transformer is the sequence model behind many modern AI systems, from language generation and text-to-image diffusion to log anomaly detection. Coverage here focuses on attention, long-range dependencies, efficiency tradeoffs, and applied variants such as compressed-byte inference and diversity control.

2 articles

Humanoid-GPT scales motion tracking with a GPT-style model
Research/Jun 3

Humanoid-GPT scales motion tracking with a GPT-style model

Humanoid-GPT uses a GPT-style Transformer and 2B motion frames to improve zero-shot whole-body motion tracking.

Implicit Channel Estimation for Full-Duplex MIMO
Research/May 24

Implicit Channel Estimation for Full-Duplex MIMO

A transformer learns site-specific beams from few measurements, avoiding explicit self-interference channel estimation.