Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

• URL: http://arxiv.org/abs/2604.24763v1
• Date: Mon, 27 Apr 2026 17:59:56 GMT
• Title: Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
• Abstract summary: Tuna-2 is a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings.<n>Experiments show that Tuna-2 achieves state-of-the-art performance in multimodal benchmarks.
• Score: 108.23557570345356
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder [17.494692126897434]
  We present textbf Omni-Encoder, a unified Transformer backbone designed to co-embed visual and audio signals at a symmetrical 25 fps within a shared latent space.<n> Experiments demonstrate that, compared to the modality-specific baseline Qwen2.5- Omni, Omni-Encoder delivers substantial gains on visual continuous understanding tasks.<n>These results suggest that unified omnivorous encoding offers a promising direction for building omni-modal models.
  arXiv  Detail & Related papers  (2026-05-02T15:55:03Z)
• TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models [96.41974190202642]
  Unified multimodal models (UMMs) aim to jointly perform multimodal understanding and generation within a single framework.<n>We present TUNA, a native UMM that builds a unified continuous visual representation by cascading a VAE encoder with a representation encoder.
  arXiv  Detail & Related papers  (2025-12-01T18:59:51Z)
• Show-o2: Improved Native Unified Multimodal Models [57.34173415412808]
  Show-o2 is a native unified multimodal models that leverage autoregressive modeling and flow matching.<n>Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion.
  arXiv  Detail & Related papers  (2025-06-18T15:39:15Z)
• Multimodal Autoregressive Pre-training of Large Vision Encoders [85.39154488397931]
  We present AIMV2, a family of generalist vision encoders characterized by a straightforward pre-training process. Our encoders excel not only in multimodal evaluations but also in vision benchmarks such as localization, grounding, and classification.
  arXiv  Detail & Related papers  (2024-11-21T18:31:25Z)
• Distilled Dual-Encoder Model for Vision-Language Understanding [50.42062182895373]
  We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks. We show that applying the cross-modal attention distillation for both pre-training and fine-tuning stages achieves further improvements.
  arXiv  Detail & Related papers  (2021-12-16T09:21:18Z)
• Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network [14.796204921975733]
  Dual-view snapshot compressive imaging (SCI) aims to capture videos from two field-of-views (FoVs) in a single snapshot. It is challenging for existing model-based decoding algorithms to reconstruct each individual scene. We propose an optical flow-aided recurrent neural network for dual video SCI systems, which provides high-quality decoding in seconds.
  arXiv  Detail & Related papers  (2021-09-11T14:24:44Z)
• Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach [104.02201472370801]
  We come up with a novel image coding framework by leveraging both the compressive and the generative models. By introducing advanced generative models, we train a flexible network to reconstruct images from compact feature representations and the reference pixels. Experimental results demonstrate the superiority of our framework in both human visual quality and facial landmark detection.
  arXiv  Detail & Related papers  (2020-01-09T10:37:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.