ucla-cmllab/quac
Viewer • Updated • 12.6k • 8
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning
ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement
ucla-cmllab/ultrachat_200k
Viewer • Updated • 231k • 7
ucla-cmllab/vicuna_cleaned
Viewer • Updated • 94.1k • 41
ucla-cmllab/orca-chat-chat-format
Viewer • Updated • 198k • 35
ucla-cmllab/WizardLM_evol_instruct_V2_196k-chat-format
Viewer • Updated • 143k • 19
ucla-cmllab/ultrachat_100k
Viewer • Updated • 407k • 41
ucla-cmllab/oasst2_top4-chat-format
Viewer • Updated • 48.4k • 8