streaming-video-generation

StreamEval 是一个面向交互式流视频生成的统一基准，涵盖五个任务和 300 个测试用例，评估了 37 个模型，发现高视觉质量并不等于可靠的任务执行与状态一致性，请求执行仍是主要挑战。

This paper introduces Causal-rCM, a unified teacher-forcing and self-forcing framework for autoregressive diffusion distillation in streaming video generation and interactive world models, achieving state-of-the-art performance with fast convergence.

TurboServe is a serving system designed for streaming video generation workloads, using an online scheduling approach that coordinates session placement and GPU provisioning to reduce latency and cost.

StreamForce is a causal, unified video generation model that provides real-time, physically grounded responses to time-varying forces through a distillation pipeline and autoregressive architecture, achieving state-of-the-art performance in force adherence and motion realism.

StreamDiffusionV2 received the Best Research Paper Award at MLSys26, introducing an open-source streaming system for real-time interactive video generation that treats video generation as a streaming pipeline rather than a turn-based process.