Liang-Chieh Chen

4

Papers

94

Total Citations

Papers (4)

MaskBit: Embedding-free Image Generation via Bit Tokens

COCONut: Modernizing COCO Segmentation

ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation

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