UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding
This addresses the challenge of harmonizing multimodal tasks for AI researchers, though it appears incremental as it builds on existing visual representation methods.
The paper tackles the problem of integrating visual understanding and image generation by proposing UniToken, a model that uses unified visual encoding with discrete and continuous representations, achieving state-of-the-art performance on various benchmarks.
We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation tasks. Unlike previous approaches that rely on unilateral visual representations, our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information that empowers heterogeneous tasks to selectively assimilate domain-specific knowledge based on their inherent characteristics. Through in-depth experiments, we uncover key principles for developing a unified model capable of both visual understanding and image generation. Extensive evaluations across a diverse range of prominent benchmarks demonstrate that UniToken achieves state-of-the-art performance, surpassing existing approaches. These results establish UniToken as a robust foundation for future research in this domain. The code and models are available at https://github.com/SxJyJay/UniToken.