Grounded Referring Expression Comprehension on GREC (testA)
75.7N-accMimoVL-7B + MRSI + CVO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MimoVL-7B + MRSI + CVOBackbone=MimoVL-7B, Training Configuration=MRSI + Constraint-guided Verifiable Optimization (CVO)2026.02 | 75.7 | 90.4 | |
| Qwen2.5VL-7B + MRSI + CVOBackbone=Qwen2.5VL-7B, Training Configuration=MRSI + Constraint-guided Verifiable Optimization (CVO)2026.02 | 74.7 | 90.4 | |
| Qwen2.5VL-7B + MRSIBackbone=Qwen2.5VL-7B, Training Configuration=Multi-style Reasoning Schema Injection (MRSI)2026.02 | 74.2 | 89.1 | |
| MimoVL-7B + MRSIBackbone=MimoVL-7B, Training Configuration=Multi-style Reasoning Schema Injection (MRSI)2026.02 | 72.6 | 89.4 | |
| Qwen2.5VL-7B + SFTBackbone=Qwen2.5VL-7B, Training Configuration=Supervised Fine-Tuning (SFT)2026.02 | 70.6 | 81.1 | |
| MimoVL-7B + SFTBackbone=MimoVL-7B, Training Configuration=Supervised Fine-Tuning (SFT)2026.02 | 65.7 | 66.1 |