Michael Ryoo

6

Papers

120

Total Citations

Papers (6)

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

VicTR: Video-conditioned Text Representations for Activity Recognition

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

Adaptive Caching for Faster Video Generation with Diffusion Transformers

Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying