Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

About this episode

🤗 Upvotes: 37 | cs.CV, cs.AI

        <strong>Authors:</strong><br />
        Inferix Team, Tianyu Feng, Yizeng Han, Jiahao He, Yuanyu He, Xi Lin, Teng Liu, Hanfeng Lu, Jiasheng Tang, Wei Wang, Zhiyuan Wang, Jichao Wu, Mingyang Yang, Yinghao Yu, Zeyu Zhang, Bohan Zhuang</p>

        <strong>Title:</strong><br />
        Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation</p>

        <strong>Arxiv:</strong><br />
        <a href="http://arxiv.org/abs/2511.20714v1">http://arxiv.org/abs/2511.20714v1</a></p>

        <strong>Abstract:</strong><br />
        World models serve as core simulators for fields such as agentic AI, embodied AI, and gaming, capable of generating long, physically realistic, and interactive high-quality videos. Moreover, scaling these models could unlock emergent capabilities in visual perception, understanding, and reasoning, paving the way for a new paradigm that moves beyond current LLM-centric vision foundation models. A key breakthrough empowering them is the semi-autoregressive (block-diffusion) decoding paradigm, which merges the strengths of diffusion and autoregressive methods by generating video tokens in block-applying diffusion within each block while conditioning on previous ones, resulting in more coherent and stable video sequences. Crucially, it overcomes limitations of standard video diffusion by reintroducing LLM->