Jiho Kang
jihokang02
ยท
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
liked a dataset about 11 hours ago
n1ghtf4l1/Agentic-Diagnostic-Reasoning-with-Multimodal-SLMs-via-Reinforcement-Learning upvoted a paper about 11 hours ago
StudentSim: Training LLM-based Student Simulators upvoted a paper about 11 hours ago
MemBodied: Recurrent Associative Memory for Vision-Language-Action ModelsOrganizations
None yet