AI.info

Kun Gai

Explore Kun Gai on AI.info.

• TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
• SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
• FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
• Monet: Reasoning in Latent Visual Space Beyond Images and Language
• Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization