psp-dada/TableVerse-5K
Viewer • Updated • 4.84k • 541
Peng Shangpin
psp-dada
AI & ML interests
Multimodal Large Language Models, Preference Optimization Algorithm, Reinforcement Learning
Recent Activity
authored a paper 1 day ago
$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training updated a dataset 3 days ago
psp-dada/TableVerse-5KOrganizations