yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_110
4B • Updated • 5
Choi
yunhowhour
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? upvoted a paper 3 days ago
RobotValues: Evaluating Household Robots When Human Values Conflict upvoted a paper 21 days ago
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State ReplacementOrganizations
None yet
yunhowhour/Distill-1.5B_GRESO_batch_512_step_120
2B • Updated • 5
yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_w_o_global_norm_step_90
4B • Updated • 4
yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_w_o_global_norm_step_60
4B • Updated • 4
yunhowhour/CRRL_distill_1.5B_w_o_globalnorm_step_120
2B • Updated • 4
yunhowhour/CRRL_distill_1.5B_GRESO_step_90
2B • Updated • 6
yunhowhour/CRRL_batch_1024_step_50
4B • Updated • 3
yunhowhour/DAPO_batch_1024_step_90
4B • Updated • 4