Chameleon: Mixed-Modal Early-Fusion Foundation Models
Paper
•
2405.09818
•
Published
•
125
Multimodal
-
-
Matryoshka Multimodal Models
Paper • 2405.17430 • Published • 30
Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
Paper • 2406.02430 • Published • 29Note (instruction+原稿の入力token)をTransformerでspeech tokenに変換した後、DMでより詳細な情報を肉付けする
-
An Image is Worth 32 Tokens for Reconstruction and Generation
Paper • 2406.07550 • Published • 55 -
ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
Paper • 2407.04172 • Published • 22 -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 115 -
Seed-Music: A Unified Framework for High Quality and Controlled Music Generation
Paper • 2409.09214 • Published • 45