TimeLens2-8B

TimeLens2-8B 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-8B-Instruct and achieves 48.0 average mIoU across seven temporal grounding benchmarks.

TimeLens2-8B sets a new state of the art on this seven-benchmark suite, with strong performance across short-, long-, and egocentric-video grounding.

Benchmark Results

Inference

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

from pathlib import Path

from qwen_vl_utils import process_vision_info
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "MCG-NJU/TimeLens2-8B"
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])