arxiv:2504.20073
Zihan Wang PRO
ZihanWang314
AI & ML interests
None yet
Organizations
models 36
ZihanWang314/metamathqa_llama32_3b_single_turn_grpo_1attempt_1turn_global_step_200
3B • Updated • 6
ZihanWang314/metamathqa_llama32_3b_single_turn_grpo_1attempt_1turn_global_step_150
3B • Updated • 8
ZihanWang314/metamathqa_llama32_3b_single_turn_grpo_1attempt_1turn_global_step_100
3B • Updated • 4
ZihanWang314/metamathqa_llama32_3b_single_turn_grpo_1attempt_1turn_global_step_50
3B • Updated • 5
ZihanWang314/exp1_Countdown_no_retry_global_step_200
3B • Updated • 4
ZihanWang314/exp1_Countdown_no_retry_global_step_150
3B • Updated • 7
ZihanWang314/exp1_SimpleSokoban_no_retry_global_step_200
3B • Updated • 5
ZihanWang314/exp1_Countdown_no_retry_global_step_100
3B • Updated • 6
ZihanWang314/exp1_SimpleSokoban_no_retry_global_step_150
3B • Updated • 4
ZihanWang314/exp1_Countdown_no_retry_global_step_50
3B • Updated • 6