ConClick-8B
Model for ConClick: Element-wise Contrastive Learning Improves GUI Grounding. ConClick trains on target–distractor examples with coordinate supervision, listwise ranking, and pairwise margin losses.
| Inference | ScreenSpot-Pro | MMBench-GUI L2 | OSWorld-G |
|---|---|---|---|
| Direct | 66.03 | 86.28 | 70.20 |
| + ReClick | 72.36 | 87.28 | 71.76 |
Contains the LoRA adapter, selection head, and visual-merger state for Qwen/Qwen3-VL-8B-Instruct. Use the ConClick repository to install dependencies, run inference, evaluate, or train.
- Downloads last month
- 14
Model tree for ruotian/ConClick-8B
Base model
Qwen/Qwen3-VL-8B-Instruct