Fei Du

Lumos-Nexus is a training-efficient framework that enhances video generation quality by progressively bridging generation from a lightweight model to a high-fidelity generator in a shared latent space, without sacrificing reasoning capabilities.

The paper uses sparse autoencoders to identify specific latent features within LLM-based TTS models, enabling interpretable and fine-grained control over emotional expression by intervening in small subsets of these features.