README.md

---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-VL-4B-Instruct
tags:
- video-understanding
- streaming
- proactive
- activation-model
- masked-diffusion
- multimodal
- plug-and-play
language:
- en
pipeline_tag: video-classification
model-index:
- name: STRIDE-4B
  results:
  - task:
      type: video-classification
      name: Proactive Streaming Activation
    dataset:
      type: custom
      name: OVO-Bench
    metrics:
    - type: accuracy
      value: 60.27
      name: Overall (w/ Qwen3-VL-8B)
  - task:
      type: video-classification
      name: Proactive Streaming Activation
    dataset:
      type: custom
      name: StreamingBench
    metrics:
    - type: accuracy
      value: 59.98
      name: Overall (w/ Qwen3-VL-8B)
---

# STRIDE-4B

**STRIDE** (**S**tructured **T**emporal **R**efinement with **I**terative **DE**noising) is a lightweight proactive activation model for streaming video understanding.
It decides **when** a downstream Video-LLM should respond during a live video stream — without waiting for explicit user queries.

<p align="center">
  <a href="https://arxiv.org/abs/2603.27593"><img src="https://img.shields.io/badge/arXiv-2603.27593-b31b1b" alt="arXiv"></a>
  <a href="https://interlive-team.github.io/STRIDE"><img src="https://img.shields.io/badge/Project-Page-blue" alt="Project Page"></a>
  <a href="https://github.com/interlive-team/STRIDE"><img src="https://img.shields.io/badge/GitHub-Code-black" alt="GitHub"></a>
  <a href="https://huggingface.co/interlive"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Model_Collection-yellow" alt="HF"></a>
</p>

> **Paper**: *STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding*
>
> Junho Kim\*, Hosu Lee\*, James M. Rehg, Minsu Kim, Yong Man Ro
>
> UIUC, KAIST, Google DeepMind

## What is STRIDE?

Existing streaming Video-LLMs are **reactive** — they only respond when a user explicitly asks a question. STRIDE makes them **proactive** by adding a lightweight front-end that continuously monitors incoming frames and predicts coherent activation spans indicating *when* to trigger a response.

The key insight is that activation in streaming video is not a point-wise binary decision ("should I respond *now*?"), but a **span-structured** sequence modeling problem — the model must capture consistent onset (0 &rarr; 1), persistence (1 &rarr; 1), and offset (1 &rarr; 0) transitions. STRIDE achieves this through **masked diffusion** over a temporal activation window, jointly predicting and iteratively refining activation signals across the window.

### Two-Stage Architecture

```
Video Stream
  │
  ▼
[STRIDE Activation Model]  ← this model (4B)
  │
  │ trigger (only if active)
  ▼
[Downstream Video-LLM]     ← frozen, any off-the-shelf
  │
  ▼
Response
```

- **Stage 1 — Activation (STRIDE):** Monitors the stream at 1 FPS, maintains a sliding activation window, and iteratively denoises binary activation labels via masked diffusion.
- **Stage 2 — Response (Downstream LLM):** When triggered, the frozen downstream Video-LLM receives the accumulated frame cache and generates a response. STRIDE is fully **plug-and-play** — compatible with any off-the-shelf Video-LLM.

## Results

### OVO-Bench (Online Video Understanding)

| Method | Real-Time Perception | Backward Tracing | Forward Active Responding | Overall |
|---|:---:|:---:|:---:|:---:|
| Flash-VStream-7B | 28.37 | 27.38 | 45.09 | 33.61 |
| Dispider | 54.55 | 36.06 | 34.72 | 41.78 |
| TimeChat-Online-7B | 58.60 | 42.00 | 36.40 | 45.60 |
| QueryStream-7B | 61.40 | 42.10 | 39.03 | 47.51 |
| StreamAgent-7B | 61.30 | 41.70 | 45.40 | 49.40 |
| **STRIDE-4B** + Gemma3-4B | 60.58 | 34.60 | 57.57 | 50.92 |
| **STRIDE-4B** + InternVL3-8B | 66.63 | 47.77 | 57.33 | 57.24 |
| **STRIDE-4B** + Qwen3-VL-8B | 69.77 | 48.67 | 62.37 | **60.27** |

### StreamingBench (Streaming Comprehension)

| Method | Real-Time Visual | Omni-Source | Contextual | Overall |
|---|:---:|:---:|:---:|:---:|
| Flash-VStream-7B | 23.23 | 26.00 | 24.12 | 24.04 |
| VideoLLM-Online-8B | 35.99 | 28.45 | 26.55 | 32.48 |
| Dispider | 67.63 | 35.66 | 33.61 | 53.12 |
| StreamAgent-7B | 74.31 | 36.26 | 34.62 | 57.02 |
| **STRIDE-4B** + Gemma3-4B | 59.93 | 36.40 | 41.00 | 50.49 |
| **STRIDE-4B** + InternVL3-8B | 73.82 | 40.90 | 40.90 | 59.19 |
| **STRIDE-4B** + Qwen3-VL-8B | 76.01 | 40.00 | 39.90 | **59.98** |

## Usage

For the full streaming inference pipeline and evaluation scripts, please refer to the [STRIDE GitHub repository](https://github.com/interlive-team/STRIDE).

## Training

- **Architecture:** `Qwen3VLForSTRIDE` (Qwen3-VL backbone with a temporal activation head)
- **Base model:** [Qwen/Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct)
- **Training data:** Temporal activation annotations curated from eight publicly available video understanding datasets (ActivityNet-Captions, LITA, YouCook2, ET-Instruct, Charades, CharadesEgo, DiDeMo, Grounded-VideoLLM). STRIDE-4B is trained under the same data and training configuration as [STRIDE-2B](https://huggingface.co/interlive/STRIDE-2B).

## Model Variants

| Model | Params | Description |
|---|---|---|
| [STRIDE-2B](https://huggingface.co/interlive/STRIDE-2B) | 2B | Default activation model |
| [**STRIDE-4B**](https://huggingface.co/interlive/STRIDE-4B) (this) | 4B | Scaled variant with improved accuracy |

## Citation

```bibtex
@article{kim2026stride,
  title={STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding},
  author={Kim, Junho and Lee, Hosu and Rehg, James M. and Kim, Minsu and Ro, Yong Man},
  journal={arXiv preprint arXiv:2603.27593},
  year={2026}
}
```

## License

This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).