TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
Paper
•
2412.03069
•
Published
•
29
Unified MLLM
Unified model that generate Text, Image, Video
-
-
Are Emergent Abilities of Large Language Models a Mirage?
Paper • 2304.15004 • Published • 6 -
Scaling Image Tokenizers with Grouped Spherical Quantization
Paper • 2412.02632 • Published • 9 -
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
Paper • 2410.13848 • Published • 30 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 96 -
Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
Paper • 2412.04432 • Published • 12