Guilin Liu

Latest

• Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
• Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• DiffiT: Diffusion Vision Transformers for Image Generation
• Partial Convolution for Padding, Inpainting, and Image Synthesis
• Coupled Segmentation and Edge Learning Using Dynamic Graph Propagation
• Coupled Segmentation and Edge Learning via Dynamic Graph Propagation
• DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
• Dual Contrastive Loss and Attention for GANs
• View Generalization for Single Image Textured 3D Models
• Neural FFTs for Universal Texture Image Synthesis
• Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter