Papers
arxiv:2611.21366

ALIVE: Making Streaming Video Models Interactive

Published on Nov 16
ยท Submitted by
Jinzhao Li
on Nov 19
#2 Paper of the day
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

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.

Community

Paper submitter

๐Ÿš€ From Passive Video Understanding to Proactive, Interactive AI Assistants!

We introduce ALIVE, an interactive streaming video model that goes beyond simply watching and answering questions. ALIVE enables three key capabilities:

๐Ÿ”ต Proactive Monitoring: Continuously observe the world and respond when relevant events occur.
๐ŸŸฃ Streaming Task Coordination: Manage evolving user requests across multi-turn interactions.
๐ŸŸ  Feedback-Seeking Interaction: Proactively ask for missing information or user actions to complete tasks.

To achieve this, we introduce ALIVE-SFT-288K and ALIVE-RL-3K, combining contrastive supervised fine-tuning with reinforcement learning using Behavior-Aligned Credit Assignment (BACA). We also introduce FSI-Bench to evaluate feedback-seeking capabilities.

๐Ÿ† ALIVE achieves the highest overall scores among compared models across four public benchmarks and FSI-Bench.

A step toward AI assistants that don't just watch and answer, but proactively interact and collaborate with users!

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.21366 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.21366 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.21366 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.