Qihang Yu

8

Papers

143

Total Citations

Papers (8)

MaskBit: Embedding-free Image Generation via Bit Tokens

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

COCONut: Modernizing COCO Segmentation

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

ViTamin: Designing Scalable Vision Models in the Vision-Language Era

Randomized Autoregressive Visual Generation

FlowTok: Flowing Seamlessly Across Text and Image Tokens

Leveraging Panoptic Scene Graph for Evaluating Fine-Grained Text-to-Image Generation