Thinking in Streaming Video
Zikang Liu, Longteng Guo, Handong Li, Ru Zhen, Xingjian He, Ruyi Ji, Xiaoming Ren, Yanhao Zhang, Haonan Lu, Jing Liu

TL;DR
ThinkStream introduces an incremental streaming video reasoning framework that updates understanding in real-time, reducing latency and memory use for dynamic environments.
Contribution
The paper presents a novel Watch--Think--Speak paradigm, Reasoning-Compressed Streaming Memory, and Streaming Reinforcement Learning to enable efficient real-time video reasoning.
Findings
Outperforms existing online video models in accuracy and speed
Maintains low latency and memory usage in streaming scenarios
Supports long-horizon streaming reasoning
Abstract
Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video reasoning approaches follow a batch paradigm that defers reasoning until the full video context is observed, resulting in high latency and growing computational cost that are incompatible with streaming scenarios. In this paper, we introduce ThinkStream, a framework for streaming video reasoning based on a Watch--Think--Speak paradigm that enables models to incrementally update their understanding as new video observations arrive. At each step, the model performs a short reasoning update and decides whether sufficient evidence has accumulated to produce a response. To support long-horizon streaming, we propose Reasoning-Compressed Streaming Memory (RCSM), which treats intermediate reasoning traces as compact…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Reinforcement Learning in Robotics · Human Pose and Action Recognition
