Meta presents Tuna-2 Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation paper: https://
huggingface.co/papers/2604.24
763
…
Meta Introduces Tuna-2: Pixel Embeddings for Multimodal AI
By
–
By
–
Meta presents Tuna-2 Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation paper: https://
huggingface.co/papers/2604.24
763
…