Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2505.07538 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913860837965824 |
|---|---|
| author | Wang, Bohan Yue, Zhongqi Zhang, Fengda Chen, Shuo Bi, Li'an Zhang, Junzhe Song, Xue Chan, Kennard Yanting Pan, Jiachun Wu, Weijia Zhou, Mingze Lin, Wang Pan, Kaihang Zhang, Saining Jia, Liyu Hu, Wentao Zhao, Wei Zhang, Hanwang |
| author_facet | Wang, Bohan Yue, Zhongqi Zhang, Fengda Chen, Shuo Bi, Li'an Zhang, Junzhe Song, Xue Chan, Kennard Yanting Pan, Jiachun Wu, Weijia Zhou, Mingze Lin, Wang Pan, Kaihang Zhang, Saining Jia, Liyu Hu, Wentao Zhao, Wei Zhang, Hanwang |
| contents | We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design core, we compose an autoregressive (AR) prior -- mirroring the causal structure of language -- into visual tokens by using the reverse diffusion process of image generation. The AR property makes Selftok fundamentally distinct from traditional spatial tokens in the following two key ways: - Selftok offers an elegant and minimalist approach to unify diffusion and AR for vision-language models (VLMs): By representing images with Selftok tokens, we can train a VLM using a purely discrete autoregressive architecture -- like that in LLMs -- without requiring additional modules or training objectives. - We theoretically show that the AR prior satisfies the Bellman equation, whereas the spatial prior does not. Therefore, Selftok supports reinforcement learning (RL) for visual generation with effectiveness comparable to that achieved in LLMs. Besides the AR property, Selftok is also a SoTA tokenizer that achieves a favorable trade-off between high-quality reconstruction and compression rate. We use Selftok to build a pure AR VLM for both visual comprehension and generation tasks. Impressively, without using any text-image training pairs, a simple policy gradient RL working in the visual tokens can significantly boost the visual generation benchmark, surpassing all the existing models by a large margin. Therefore, we believe that Selftok effectively addresses the long-standing challenge that visual tokens cannot support effective RL. When combined with the well-established strengths of RL in LLMs, this brings us one step closer to realizing a truly multimodal LLM. Project Page: https://selftok-team.github.io/report/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07538 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning Wang, Bohan Yue, Zhongqi Zhang, Fengda Chen, Shuo Bi, Li'an Zhang, Junzhe Song, Xue Chan, Kennard Yanting Pan, Jiachun Wu, Weijia Zhou, Mingze Lin, Wang Pan, Kaihang Zhang, Saining Jia, Liyu Hu, Wentao Zhao, Wei Zhang, Hanwang Computer Vision and Pattern Recognition We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design core, we compose an autoregressive (AR) prior -- mirroring the causal structure of language -- into visual tokens by using the reverse diffusion process of image generation. The AR property makes Selftok fundamentally distinct from traditional spatial tokens in the following two key ways: - Selftok offers an elegant and minimalist approach to unify diffusion and AR for vision-language models (VLMs): By representing images with Selftok tokens, we can train a VLM using a purely discrete autoregressive architecture -- like that in LLMs -- without requiring additional modules or training objectives. - We theoretically show that the AR prior satisfies the Bellman equation, whereas the spatial prior does not. Therefore, Selftok supports reinforcement learning (RL) for visual generation with effectiveness comparable to that achieved in LLMs. Besides the AR property, Selftok is also a SoTA tokenizer that achieves a favorable trade-off between high-quality reconstruction and compression rate. We use Selftok to build a pure AR VLM for both visual comprehension and generation tasks. Impressively, without using any text-image training pairs, a simple policy gradient RL working in the visual tokens can significantly boost the visual generation benchmark, surpassing all the existing models by a large margin. Therefore, we believe that Selftok effectively addresses the long-standing challenge that visual tokens cannot support effective RL. When combined with the well-established strengths of RL in LLMs, this brings us one step closer to realizing a truly multimodal LLM. Project Page: https://selftok-team.github.io/report/. |
| title | Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.07538 |