TimeLens2-9B

TimeLens2-9B is a video temporal grounding model based on Qwen/Qwen3.5-9B. Given a video and a text query, it predicts the relevant time intervals in seconds.

Paper · Code & Usage · Collection

Benchmark Results

Benchmark mIoU (%)
Charades-STA 60.56
ActivityNet Captions 61.97
QVHighlights 70.28
VUE-TR 54.04
VUE-TR-v2 52.19
MomentSeeker 30.23
Ego4D-NLQ-v2 22.69
Average 50.28

The two VUE benchmarks use the available-video subsets. The average is the unweighted mean over the seven benchmarks.

For inference and evaluation, follow the official TimeLens2 repository and use ZhuYuhan/TimeLens2-9B as the model path.

Downloads last month
54
Safetensors
Model size
9B params
Tensor type
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ZhuYuhan/TimeLens2-9B

Finetuned
Qwen/Qwen3.5-9B
Finetuned
(1,433)
this model
Quantizations
1 model

Paper for ZhuYuhan/TimeLens2-9B