📊 Showing 3 results | 📏 Metric: chair_i
| Rank | Model | Paper | chair_i | Date | Code |
|---|---|---|---|---|---|
| 1 | RLHF-V | RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback | 7.50 | 2023-12-01 | 📦 openbmb/minicpm-v 📦 rlhf-v/rlhf-v 📦 tidedra/vl-rlhf 📦 exgc/r1v-free |
| 2 | RLAIF-V 7B | RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness | 4.30 | 2024-05-27 | 📦 openbmb/minicpm-v 📦 openbmb/omnilmm 📦 OpenBMB/MiniCPM-o 📦 rlhf-v/rlaif-v 📦 rlhf-v/rlhf-v |
| 3 | RLAIF-V 12B | RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness | 1.80 | 2024-05-27 | 📦 openbmb/minicpm-v 📦 openbmb/omnilmm 📦 OpenBMB/MiniCPM-o 📦 rlhf-v/rlaif-v 📦 rlhf-v/rlhf-v |