Modelpublic

TencentARC/TimeLens-8B

sourceHugging Faceotherupdated 5mo agoView on Hugging Face

19likes1.2kdownloads

Model Card

TimeLens-8B

📑 **Paper** | 💻 **Code** | 🏠 **Project Page** | 🤗 **Model & Data**

✨ Model Description

TimeLens-8B is an MLLM with state-of-the-art video temporal grounding performance among open-source models, finetuned from Qwen3-VL-8B-Instruct. It is trained with carefully crafted RLVR (reinforcement learning with verifiable rewards) recipe proposed in our paper, utilizing our high-quality VTG training dataset TimeLens-100K.

📊 Performance

TimeLens-8B achieves state-of-the-art video temporal grounding performance among open-source models:

<table> <thead> <tr> <th rowspan="2" align="center">Model</th> <th colspan="4" align="center">Charades-TimeLens</th> <th colspan="4" align="center">ActivityNet-TimeLens</th> <th colspan="4" align="center">QVHighlights-TimeLens</th> </tr> <tr> <th align="center">R1 @0.3</th> <th align="center">R1 @0.5</th> <th align="center">R1 @0.7</th> <th align="center">mIoU</th> <th align="center">R1 @0.3</th> <th align="center">R1 @0.5</th> <th align="center">R1 @0.7</th> <th align="center">mIoU</th> <th align="center">R1 @0.3</th> <th align="center">R1 @0.5</th> <th align="center">R1 @0.7</th> <th align="center">mIoU</th> </tr> </thead> <tbody> <tr> <td><a href="https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct">Qwen2.5-VL-7B-Instruct</a></td> <td align="center">59.7</td> <td align="center">37.8</td> <td align="center">16.6</td> <td align="center">39.3</td> <td align="center">44.1</td> <td align="center">31.0</td> <td align="center">16.1</td> <td align="center">31.4</td> <td align="center">41.5</td> <td align="center">27.8</td> <td align="center">15.2</td> <td align="center">31.6</td> </tr> <tr> <td><a href="https://huggingface.co/TencentARC/TimeLens-7B">TimeLens-7B🚀</a></td> <td align="center">70.5</td> <td align="center">55.6</td> <td align="center">28.4</td> <td align="center">48.8</td> <td align="center">62.8</td> <td align="center">51.0</td> <td align="center">32.6</td> <td align="center">46.2</td> <td align="center">74.1</td> <td align="center">62.7</td> <td align="center">43.1</td> <td align="center">56.0</td> </tr> <tr> <td><a href="https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct">Qwen3-VL-8B-Instruct</a></td> <td align="center">69.2</td> <td align="center">53.4</td> <td align="center">27.5</td> <td align="center">48.3</td> <td align="center">62.1</td> <td align="center">51.2</td> <td align="center">34.4</td> <td align="center">46.8</td> <td align="center">74.2</td> <td align="center">64.6</td> <td align="center">49.3</td> <td align="center">59.4</td> </tr> <tr> <td><a href="https://huggingface.co/TencentARC/TimeLens-8B">TimeLens-8B🚀</a></td> <td align="center">76.6</td> <td align="center">63.0</td> <td align="center">35.2</td> <td align="center">55.2</td> <td align="center">68.9</td> <td align="center">58.4</td> <td align="center">40.6</td> <td align="center">53.2</td> <td align="center">80.2</td> <td align="center">71.6</td> <td align="center">55.5</td> <td align="center">65.5</td> </tr> </tbody> </table>

For detailed comparison with other models, please refer to the 🏆 Leaderboard.

🚀 Usage

Install the following packages:

bash

pip install transformers==4.57.1 accelerate==1.6.0 torch==2.6.0 torchvision==0.21.0
pip install qwen-vl-utils[decord]==0.0.14
# use Flash-Attention 2 to speed up generation
pip install flash-attn==2.7.4.post1 --no-build-isolation --no-cache-dir

Using 🤗Transformers for Inference:

python

import requests
import os
import torch
from transformers import AutoModelForImageTextToText, AutoProcessor
from qwen_vl_utils import process_vision_info


def download_video(url):
    save_path = os.path.basename(url)
    if not os.path.exists(save_path):
        print(f"Downloading video from {url}...")
        response = requests.get(url, stream=True)
        response.raise_for_status()
        with open(save_path, 'wb') as f:
            for chunk in response.iter_content(chunk_size=8192):
                f.write(chunk)
    return save_path

# Load model and processor
model = AutoModelForImageTextToText.from_pretrained(
    "TencentARC/TimeLens-8B",
    dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    device_map="auto",
)

processor = AutoProcessor.from_pretrained(
    "TencentARC/TimeLens-8B",
    padding_side="left",
    do_resize=False,
)

# Prepare input
query = "A man drinks water with a glass"
video_path = download_video("https://huggingface.co/datasets/JungleGym/TimeLens-Assets/resolve/main/2Y8XQ.mp4")

GROUNDER_PROMPT = "Please find the visual event described by the sentence '{}', determining its starting and ending times. The format should be: 'The event happens in <start time> - <end time> seconds'."

messages = [{
    'role': 'user',
    'content': [
        {
            'type': 'video',
            'video': video_path,
            'min_pixels': 64 * 32 * 32,
            'total_pixels': 14336 * 32 * 32,
            'fps': 2,
        },
        {
            'type': 'text',
            'text': GROUNDER_PROMPT.format(query)
        }
    ]
}]

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,
)

videos, video_metadatas = zip(*videos)
videos, video_metadatas = list(videos), list(video_metadatas)

inputs = processor(
  text=[text],
  images=images,
  videos=videos,
  video_metadata=video_metadatas,
  padding=True,
  return_tensors='pt',
  **video_kwargs,
).to("cuda")

output_ids = model.generate(
    **inputs,
    do_sample=False,
    max_new_tokens=512,
)

generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, output_ids)
]
answer = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]
print(f"Answer: {answer}")

Citation

If you find our work helpful for your research and applications, please cite our paper:

bibtex

@article{zhang2025timelens,
  title={TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs},
  author={Zhang, Jun and Wang, Teng and Ge, Yuying and Ge, Yixiao and Li, Xinhao and Shan, Ying and Wang, Limin},
  journal={arXiv preprint arXiv:2512.14698},
  year={2025}
}