Tag
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。
Vivix Labs 发布实时交互式视频模型 W1，定价仅 $0.003/秒，价格约为 Seedance 2.5 单条片段的八十分之一，有望让实时交互视频成为常态。
The article describes the creation of an interactive digital avatar by a TechCrunch author using Synthesia's AI technology, showcasing its use for personalized PR and training applications.
Light Interaction introduces a training-free inference acceleration framework for interactive video world models, using adaptive context management, denoising cache acceleration, and 3D block sparse attention to achieve up to 2.59x speedup while maintaining competitive visual quality.
Incantation presents an interactive video world model that uses natural language as the action interface for fine-grained multi-entity control and cross-entity generalization, achieving high performance and real-time streaming through novel attention and distillation techniques.
Echo-Forcing introduces a scene memory framework for interactive long video generation, using hierarchical temporal memory, scene recall frames, and difference-aware memory decay to handle prompt switching and long-term recall. The method is training-free and achieves strong performance on VBench-Long.