Ming-Yu Liu

Latest

• Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation
• Magic3D: High-Resolution Text-to-3D Content Creation
• Multimodal Conditional Image Synthesis with Product-of-Experts GANs
• GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds
• Domain Stylization: A Fast Covariance Matching Framework towards Domain Adaptation
• One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing
• On the Distance between Two Neural Networks and the Stability of Learning
• UFO2: A Unified Framework towards Omni-supervised Object Detection
• World-Consistent Video-to-Video Synthesis
• Instance-aware, Context-focused, and Memory-efficient Weakly-Supervised Object Detection
• UNAS: Differentiable Architecture Search Meets Reinforcement Learning