# LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant

Source: [LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant](<https://www.sota2.com/research/paper/68fa774c1e209131cea725d7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:15:51.701Z

Authors: Wei Li, Bing Hu, Rui Shao, Leyang Shen, Liqiang Nie

Published: 2025-03-05T16:52:34.000Z

## Abstract

First-person video assistants are highly anticipated to enhance our daily lives through online video dialogue. However, existing online video assistants often sacrifice assistant efficacy for real-time efficiency by processing low-frame-rate videos with coarse-grained visual features.To overcome the trade-off between efficacy and efficiency, we propose "Fast & Slow Video-Language Thinker" as an onLIne videO assistaNt, LION-FS, achieving real-time, proactive, temporally accurate, and contextually precise responses. LION-FS adopts a two-stage optimization strategy: 1)Fast Path: Routing-Based Response Determination evaluates frame-by-frame whether an immediate response is necessary. To enhance response determination accuracy and handle higher frame-rate inputs efficiently, we employ Token Aggregation Routing to dynamically fuse spatiotemporal features without increasing token numbers, while utilizing Token Dropping Routing to eliminate redundant features. 2)Slow Path: Multi-granularity Keyframe Augmentation optimizes keyframes during response generation. To provide comprehensive and detailed responses beyond atomic actions constrained by training data, fine-grained spatial features and human-environment interaction features are extracted through multi-granular pooling. These features are further integrated into a meticulously designed multimodal Thinking Template to guide more precise response generation. Comprehensive evaluations on online video tasks demonstrate that LION-FS achieves state-of-the-art efficacy and efficiency.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Streaming Narration on Ego4D](<https://www.sota2.com/research/sota/streaming-narration-on-ego4d.md>): Streaming Narration; Ego4D; Perplexity (PPL): 2.09.

- [Video Narration on Ego4D Narration Stream (Offline)](<https://www.sota2.com/research/sota/video-narration-on-ego4d-narration-stream-offline.md>): Video Narration; Ego4D Narration Stream (Offline); Perplexity (PPL): 2.09.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.03663>)

[PDF](<https://arxiv.org/pdf/2503.03663.pdf>)