Emotional Reasoning on EmoSet In-domain
77.15AccuracySFT
Evaluation Results
| Method | Links | |
|---|---|---|
| SFTBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=-, Post-training=true2026.02 | 77.15 | |
| EMO-R3Backbone=Qwen2.5-VL-3B-Instruct, Roll-out=8, Post-training=true2026.02 | 76.4 | |
| EMO-R3Backbone=Qwen2.5-VL-3B-Instruct, Roll-out=4, Post-training=true2026.02 | 75.5 | |
| GRPOBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=8, Post-training=true2026.02 | 75.45 | |
| GRPOBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=4, Post-training=true2026.02 | 74.6 | |
| DAPOBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=8, Post-training=true2026.02 | 70.21 | |
| DAPOBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=4, Post-training=true2026.02 | 68.99 | |
| SEPM*Backbone=LLaVA1.5-7B, Roll-out=-, Post-training=false2026.02 | 56.04 | |
| Vanilla*Backbone=LLaVA1.5-7B, Roll-out=-, Post-training=false2026.02 | 52.77 | |
| Vanilla*Backbone=Qwen2.5-VL-3B-Instruct, Roll-out=-, Post-training=false2026.02 | 51.55 |