Search papers, labs, and topics across Lattice.
Tuna-2, a unified multimodal model, directly encodes pixels using patch embeddings, bypassing the need for separate vision encoders for understanding and generation. This architecture achieves state-of-the-art performance on multimodal benchmarks, demonstrating that pixel-space modeling can compete with latent-space approaches for image generation. While encoder-based models converge faster initially, Tuna-2's encoder-free design scales better for multimodal understanding, especially on tasks requiring fine-grained visual perception.
Ditching the vision encoder actually *improves* multimodal understanding at scale, proving that pixel embeddings alone can achieve state-of-the-art results in unified multimodal models.
Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the representation encoder. Experiments show that Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception. These results show that pretrained vision encoders are not necessary for multimodal modelling, and end-to-end pixel-space learning offers a scalable path toward stronger visual representations for both generation and perception.
