🏢 University of Hong Kong

Goku: a novel family of joint image-and-video generation models uses rectified flow Transformers, achieving industry-leading performance with a robust data pipeline and training infrastructure.

LLMs learn to critique and refine their output via reinforcement learning, significantly improving code generation.

GameFactory uses AI to generate entirely new games within diverse, open-domain scenes by learning action controls from a small dataset and transferring them to pre-trained video models.

FashionComposer revolutionizes fashion image creation through flexible composition of garments, faces, and poses.

UniReal: a universal framework for image generation and editing, unifying diverse tasks via learning real-world dynamics from video data, achieving highly realistic and versatile results.

Moto: Bridging language for robot manipulation using latent motion tokens, achieving superior performance with limited data.

TEXGen: A groundbreaking generative diffusion model creates high-resolution 3D mesh textures directly from text and image prompts, exceeding prior methods in quality and efficiency.

SAMPart3D: Zero-shot 3D part segmentation across granularities, scaling to large datasets & handling part ambiguity.