Seungone Kim's picture

Seungone Kim PRO

seungone

AI & ML interests

Large Language Models, LLM-as-a-Judge, Reward Model Overoptimization, Personalized Alignment

Recent Activity

published a model 13 minutes ago
fusion-world-model/transformer_10m_g-residual
published a model 39 minutes ago
fusion-world-model/gru-dw_1m_e-joint
published a model about 1 hour ago
fusion-world-model/lstm_1m_g-residual
View all activity

Organizations

CMU-LTI's profile picture NeuLab @ LTI/CMU's profile picture KAIST AI's profile picture HAE-RAE's profile picture Mixture of Rewards's profile picture Human_Eval_RLHF's profile picture prometheus-eval's profile picture prometheus-vision's profile picture MPA human eval's profile picture Agora's profile picture multilingual-reward-bench's profile picture 11777-S25 Project's profile picture cot_encyclopedia_human_eval's profile picture cot_encyclopedia_human_eval's profile picture RefineBench's profile picture Carnegie Mellon University's profile picture ScholarCatalyst's profile picture Fusion World Models's profile picture