Hugging Face Papers ↗ · 2026-11-16
ALIVE:让流式视频模型变得具有交互性
媒体报道 Hugging Face Papers 原文语言:中文
研究团队推出了 ALIVE,这是一个支持主动监控、流式任务协调和寻求反馈交互的交互式流式视频模型。该研究构建了 ALIVE-SFT-288K 和 ALIVE-RL-3K 用于两阶段训练,并在四个公共基准测试以及新推出的 FSI-Bench 上取得了最高总分。
全文
Streaming video LLMs can continuously observe the world, yet often handle user requests in isolation. We introduce ALIVE, an interactive streaming video model supporting proactive monitoring, streaming task coordination, and feedback-seeking interaction. We construct ALIVE-SFT-288K and ALIVE-RL-3K for two-stage training. Contrastive supervised fine-tuning teaches when and how to respond, while reinforcement learning with Behavior-Aligned Credit Assignment (BACA) combines trajectory-level and local advantages to refine decisions, responses, and silence across multi-turn interactions. We also introduce FSI-Bench to evaluate feedback seeking and subsequent task completion. ALIVE achieves the highest overall scores among the compared models on four public benchmarks and FSI-Bench, demonstrating strong streaming understanding and interactive capabilities.
View arXiv page View PDF Project page GitHub 17 Add to collection
正文以来源语言显示。