List your company

Embodied Task Planning on VoTa-Bench 1.0 (Unseen)

82.27Examine&Light SRD2PO
-0.337221.108942.55564.0011Mar 13, 2025

Evaluation results

MethodLinks
D2POBackbone=LLaMA-3.2 (11B)2025.0382.2766.4764.4755.347.145.6953.151.5258.0957.5957.855.7957.5952.27
D2POBackbone=Qwen2-VL (7B)2025.0377.362.6756.5849.5611.438.6655.7555.7572.7972.7968.8168.5161.4657.16
D2POBackbone=LLaVA-1.6 (7B)2025.0377.358.9860.5349.314.2910.3860.1860.1869.1268.965.1464.4661.6155.78
DPOBackbone=LLaVA-1.6 (7B)2025.0375.8951.5360.5345.257.144.6256.6456.2165.4464.6163.363.1258.8251.23
DPOBackbone=LLaMA-3.2 (11B)2025.0374.4761.464.4754.167.145.6345.1343.7651.4750.3353.2151.4152.3247.39
DPOBackbone=Qwen2-VL (7B)2025.0373.7660.1753.9546.957.145.1552.2152.2166.1866.1866.9766.9757.5953.65
LLaMA-3.2 (11B)Mode=SFT2025.0370.9258.7553.9546.257.144.6151.3350.0247.0646.8552.2950.8150.3146.02
Qwen2-VL (7B)Mode=SFT2025.0368.7956.9352.6344.464.292.6143.3643.3762.562.2949.5447.3850.7746.7
LLaVA-1.6 (7B)Mode=SFT2025.0364.5452.4157.8951.394.29342.4841.6156.6256.1644.0443.5148.1444.33
Qwen2-VL (7B)Mode=ICL2025.0326.9512.23.951.69000000006.352.86
Qwen2-VL (7B)Mode=Base2025.0325.539.3415.799.58000000007.433.18
LLaMA-3.2 (11B)Mode=Base2025.0312.062.100000000002.630.46
LLaMA-3.2 (11B)Mode=ICL2025.039.221.485.260.83000000002.630.42
LLaVA-1.6 (7B)Mode=Base2025.034.260.776.581.14000000001.70.3
LLaVA-1.6 (7B)Mode=ICL2025.032.840.452.631.07000000000.930.23