---
license: apache-2.0
library_name: transformers
pipeline_tag: video-text-to-text
base_model: Qwen/Qwen3-VL-4B-Instruct
tags:
  - video
  - temporal-grounding
  - qwen3-vl
---

# TimeLens2-4B

TimeLens2-4B is a video multimodal large language model for temporal grounding. Given a video and a text query, it returns the time interval containing the relevant visual evidence.

The model is built on [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) and achieves **47.7 average mIoU** across seven temporal grounding benchmarks.

Despite its compact size, **TimeLens2-4B delivers state-of-the-art performance among similarly sized models** and outperforms substantially larger open and proprietary baselines.

## Paper

[TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs](https://arxiv.org/abs/2607.17423)

## Benchmark Results

![Temporal grounding benchmark results](https://huggingface.co/MCG-NJU/TimeLens2-4B/resolve/main/assets/benchmark_results.svg)

## Inference

```bash
pip install -U torch torchvision "transformers>=4.57.0" accelerate "qwen-vl-utils[decord]>=0.0.14"
pip install -U flash-attn --no-build-isolation
```

```python
from pathlib import Path

from qwen_vl_utils import process_vision_info
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "MCG-NJU/TimeLens2-4B"
video_path = "/path/to/video.mp4"
query = "A man opens the refrigerator."

model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    attn_implementation="flash_attention_2",
)
processor = AutoProcessor.from_pretrained(model_id)

prompt = (
    f'Given the query: "{query}", return ALL time spans (in seconds) where the query is relevant.\n'
    "Output format MUST be a JSON array of [start, end] pairs.\n"
)
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "video",
                "video": Path(video_path).resolve().as_uri(),
                "fps": 2.0,
                "min_pixels": 32 * 32,
                "max_pixels": 480 * 480,
                "total_pixels": 128000 * 32 * 32,
            },
            {"type": "text", "text": prompt},
        ],
    }
]

text = processor.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
images, videos, video_kwargs = process_vision_info(
    messages,
    image_patch_size=16,
    return_video_kwargs=True,
    return_video_metadata=True,
)

if videos is not None:
    videos, video_metadatas = zip(*videos)
    videos, video_metadatas = list(videos), list(video_metadatas)
else:
    video_metadatas = None

inputs = processor(
    text=text,
    images=images,
    videos=videos,
    video_metadata=video_metadatas,
    do_resize=False,
    return_tensors="pt",
    **video_kwargs,
).to(model.device)

output_ids = model.generate(
    **inputs,
    max_new_tokens=4096,
    temperature=0.01,
    top_p=0.001,
    top_k=1,
    repetition_penalty=1.0,
)
output_ids = [
    output[len(input_ids) :]
    for input_ids, output in zip(inputs.input_ids, output_ids)
]
response = processor.batch_decode(
    output_ids,
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False,
)
print(response[0])
```

## Citation

```bibtex
@misc{zhu2026timelens2,
      title={TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs},
      author={Yuhan Zhu and Changlian Ma and Xiangyu Zeng and Xinhao Li and Zhiqiu Zhang and Songze Li and Jun Zhang and Tianxiang Jiang and Yuandong Yang and Ziang Yan and Zikang Wang and Xinyu Chen and Haoran Chen and Shaowei Zhang and Limin Wang},
      year={2026},
      eprint={2607.17423},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2607.17423},
}
```