Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-level encoders, specialized segmentation decoders, and incompatible training objectives. To address these challenges, we present SAMTok, a discrete mask tokenizer that converts any region mask into two special tokens and reconstructs the mask using these tokens with high fidelity. By treating masks as new language tokens, SAMTok enables base MLLMs (such as the QwenVL series) to learn pixel-wise capabilities through standard next-token prediction and simple reinforcement learning, without architectural modifications and specialized loss design. SAMTok builds on SAM2 and is trained on 209M diverse masks using a mask encoder and residual vector quantizer to produce discrete, compact, and information-rich tokens. With 5M SAMTok-formatted mask understanding and generation data samples, QwenVL-SAMTok attains state-of-the-art or comparable results on region captioning, region VQA, grounded conversation, referring segmentation, scene graph parsing, and multi-round interactive segmentation. We further introduce a textual answer-matching reward that enables efficient reinforcement learning for mask generation, delivering substantial improvements on GRES and GCG benchmarks. Our results demonstrate a scalable and straightforward paradigm for equipping MLLMs with strong pixel-wise capabilities. Our code and models are available.

翻译：像素级能力对于构建交互式智能系统至关重要。然而，由于复杂的区域级编码器、专门的分割解码器以及不兼容的训练目标，像素级多模态大语言模型（MLLMs）仍然难以扩展。为解决这些挑战，我们提出了SAMTok，一种离散掩码分词器，可将任意区域掩码转换为两个特殊标记，并利用这些标记以高保真度重建掩码。通过将掩码视为新的语言标记，SAMTok使得基础MLLMs（例如QwenVL系列）能够通过标准的下一个标记预测和简单的强化学习来掌握像素级能力，而无需修改架构或设计专门的损失函数。SAMTok基于SAM2构建，利用掩码编码器和残差向量量化器在2.09亿个多样化掩码上进行训练，以生成离散、紧凑且信息丰富的标记。通过500万个SAMTok格式的掩码理解与生成数据样本，QwenVL-SAMTok在区域描述、区域视觉问答、指代对话、参考分割、场景图解析以及多轮交互式分割任务上取得了最先进或可比的结果。我们进一步引入了一种文本答案匹配奖励机制，使得掩码生成的强化学习更加高效，在GRES和GCG基准测试中带来了显著提升。我们的结果展示了一种可扩展且直接的范式，能够为MLLMs赋予强大的像素级能力。我们的代码与模型均已开源。