Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.20714 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910175182454784 |
|---|---|
| author | Inferix Team Feng, Tianyu Han, Yizeng He, Jiahao He, Yuanyu Lin, Xi Liu, Teng Lu, Hanfeng Tang, Jiasheng Wang, Wei Wang, Zhiyuan Wu, Jichao Yang, Mingyang Yu, Yinghao Zhang, Zeyu Zhuang, Bohan |
| author_facet | Inferix Team Feng, Tianyu Han, Yizeng He, Jiahao He, Yuanyu Lin, Xi Liu, Teng Lu, Hanfeng Tang, Jiasheng Wang, Wei Wang, Zhiyuan Wu, Jichao Yang, Mingyang Yu, Yinghao Zhang, Zeyu Zhuang, Bohan |
| contents | 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-style KV Cache management, enabling efficient, variable-length, and high-quality generation.
Therefore, Inferix is specifically designed as a next-generation inference engine to enable immersive world synthesis through optimized semi-autoregressive decoding processes. This dedicated focus on world simulation distinctly sets it apart from systems engineered for high-concurrency scenarios (like vLLM or SGLang) and from classic video diffusion models (such as xDiTs). Inferix further enhances its offering with interactive video streaming and profiling, enabling real-time interaction and realistic simulation to accurately model world dynamics. Additionally, it supports efficient benchmarking through seamless integration of LV-Bench, a new fine-grained evaluation benchmark tailored for minute-long video generation scenarios. We hope the community will work together to advance Inferix and foster world model exploration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20714 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation Inferix Team Feng, Tianyu Han, Yizeng He, Jiahao He, Yuanyu Lin, Xi Liu, Teng Lu, Hanfeng Tang, Jiasheng Wang, Wei Wang, Zhiyuan Wu, Jichao Yang, Mingyang Yu, Yinghao Zhang, Zeyu Zhuang, Bohan Computer Vision and Pattern Recognition Artificial Intelligence 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-style KV Cache management, enabling efficient, variable-length, and high-quality generation. Therefore, Inferix is specifically designed as a next-generation inference engine to enable immersive world synthesis through optimized semi-autoregressive decoding processes. This dedicated focus on world simulation distinctly sets it apart from systems engineered for high-concurrency scenarios (like vLLM or SGLang) and from classic video diffusion models (such as xDiTs). Inferix further enhances its offering with interactive video streaming and profiling, enabling real-time interaction and realistic simulation to accurately model world dynamics. Additionally, it supports efficient benchmarking through seamless integration of LV-Bench, a new fine-grained evaluation benchmark tailored for minute-long video generation scenarios. We hope the community will work together to advance Inferix and foster world model exploration. |
| title | Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.20714 |