List your company
ResearchFormerly WizWand

Curiosity on G2U Curiosity

1.402MeanV-JEPA2
-0.056080.322460.7011.07954Nov 19, 2025
Updated 6mo ago

Evaluation results

MethodLinks
V-JEPA2Paradigm=World Model Group, Optimization Objective (@)=curiosity2025.111.40215.616.5
GenieReduxParadigm=World Model Group, Optimization Objective (@)=curiosity2025.111.37412.59.8
GenieReduxParadigm=World Model Group, Optimization Objective (@)=utility2025.111.24812.414.6
GenieReduxParadigm=World Model Group, Optimization Objective (@)=survival2025.111.19812.511
Qwen3-VL-8BParadigm=Interactive Physical Reasoner Group, Interactive Physical Reasoner (IPR) Status=w/ IPR2025.111.17313.113.4
DreamerV3Paradigm=World Model Group, Optimization Objective (@)=curiosity2025.111.16113.114
V-JEPA2Paradigm=World Model Group, Optimization Objective (@)=survival2025.111.1515.617.7
V-JEPA2Paradigm=World Model Group, Optimization Objective (@)=utility2025.111.13614.522.6
DreamerV3Paradigm=World Model Group, Optimization Objective (@)=survival2025.111.1212.516.5
HumanParadigm=Control Group2025.1117.914
DreamerV3Paradigm=World Model Group, Optimization Objective (@)=utility2025.110.96415.411
Qwen3-VL-30B-A3BParadigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=curiosity2025.110.87820.52.4
DQNParadigm=Reinforcement Learning (RL) Group, Optimization Objective (@)=survival2025.110.85614.48.5
Qwen3-VL-8B-BCParadigm=Imitation Learning (IL) Group2025.110.81212.89.1
ACT-BCParadigm=Imitation Learning (IL) Group2025.110.79315.112.8
DQNParadigm=Reinforcement Learning (RL) Group, Optimization Objective (@)=curiosity2025.110.77213.47.9
DQNParadigm=Reinforcement Learning (RL) Group, Optimization Objective (@)=utility2025.110.6214.24.9
Qwen3-VL-30B-A3BParadigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=utility2025.110.52821.34.9
GPT-4oParadigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=curiosity2025.110.36815.35.5
Qwen3-VL-30B-A3BParadigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=survival2025.110.325230
Qwen3-VL-8BParadigm=Interactive Physical Reasoner Group, Interactive Physical Reasoner (IPR) Status=w/o IPR2025.110.325154.3
GPT-4oParadigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=utility2025.110.31914.63.7
GPT-5Paradigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=curiosity2025.110.29816.47.3
PPOParadigm=Reinforcement Learning (RL) Group, Optimization Objective (@)=survival2025.110.23316.53.7
PPOParadigm=Reinforcement Learning (RL) Group, Optimization Objective (@)=utility2025.110.2216.83
PPOParadigm=Reinforcement Learning (RL) Group, Optimization Objective (@)=curiosity2025.110.1917.32.4
GPT-5Paradigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=utility2025.110.18516.50.6
GPT-5Paradigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=survival2025.110.12718.31.8
GPT-4oParadigm=Multimodal Large Language Model (MLLM) Group, Optimization Objective (@)=survival2025.110.03917.20.6
RandomParadigm=Control Group2025.11018.13