111 Jackrong/Qwopus3.5-27B-v3-GGUF Image-Text-to-Text • 27B • Updated Jul 9 • 682 • 352 Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published Apr 27 • 70
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published Apr 27 • 70
111 Jackrong/Qwopus3.5-27B-v3-GGUF Image-Text-to-Text • 27B • Updated Jul 9 • 682 • 352 Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published Apr 27 • 70
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published Apr 27 • 70
