TimeLens2-35B-A3B is a video temporal grounding model based on Qwen/Qwen3.6-35B-A3B. Given a video and a text query, it predicts the relevant time intervals in seconds.
Paper · Code & Usage · Collection
| Benchmark | mIoU (%) |
|---|---|
| Charades-STA | 60.73 |
| ActivityNet Captions | 63.34 |
| QVHighlights | 70.53 |
| VUE-TR | 51.85 |
| VUE-TR-v2 | 51.90 |
| MomentSeeker | 30.79 |
| Ego4D-NLQ-v2 | 23.61 |
| Average | 50.39 |
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/TimeLens2-35B-A3B as the model path.
model-00008-of-00017.safetensors 4.6 GBmodel-00006-of-00017.safetensors 4.6 GBmodel-00004-of-00017.safetensors 4.5 GBmodel-00002-of-00017.safetensors 4.5 GBmodel-00014-of-00017.safetensors 4.5 GBmodel-00010-of-00017.safetensors 4.5 GBmodel-00016-of-00017.safetensors 4.5 GBmodel-00012-of-00017.safetensors 4.5 GBmodel-00001-of-00017.safetensors 4.3 GBmodel-00013-of-00017.safetensors 4.0 GBmodel-00003-of-00017.safetensors 3.9 GBmodel-00015-of-00017.safetensors 3.9 GBmodel-00009-of-00017.safetensors 3.9 GBmodel-00011-of-00017.safetensors 3.9 GBmodel-00005-of-00017.safetensors 3.8 GBmodel-00007-of-00017.safetensors 3.8 GBmodel-00017-of-00017.safetensors 2.5 GBQwen/Qwen3.6-35B-A3B