Examples of tasks we designed in https://arxiv.org/abs/2504.15266
Chen Wu PRO
ChenWu98
AI & ML interests
Generative models
Organizations
None yet
models 49
ChenWu98/grpo_generator_both_Qwen-Qwen3-8B_lr1e-6
Updated
ChenWu98/grpo_generator_easy_Qwen-Qwen3-8B_lr1e-6
Updated
ChenWu98/grpo_generator_partial_solution_hard_Qwen-Qwen3-8B_lr1e-6_p50_init2800
Updated
ChenWu98/opd_grpo_verifier_hard_Qwen-Qwen3-1.7B_alpha0.5_lr1e-6_opd1.0_pg0.1_k3_qwen3_8bgen
Updated
ChenWu98/grpo_generator_feedback_hard_Qwen-Qwen3-8B_lr1e-6_k1_init2800
Updated
ChenWu98/grpo_generator_feedback_hard_Qwen-Qwen3-8B_lr1e-6_k3_init2800
Updated
ChenWu98/grpo_generator_standard_hard_Qwen-Qwen3-8B_lr1e-6_longer
Updated
ChenWu98/grpo_generator_feedback_hard_Qwen-Qwen3-8B_lr1e-6_k1
Updated
ChenWu98/opd_grpo_verifier_hard_Qwen-Qwen3-8B_alpha0.5_lr1e-6_opd1.0_pg1.0_k3_initrlgen
Updated
ChenWu98/opd_grpo_verifier_hard_Qwen-Qwen3-8B_alpha0.5_lr1e-6_opd1.0_pg0.1_k3_o_r5_initrlgen
Updated
datasets 12
ChenWu98/dapo17k_en_rollout
Viewer • Updated • 41.2k • 53
ChenWu98/Countdown-N4T200-2048
Viewer • Updated • 163k • 16
ChenWu98/Countdown-N4T200-val
Viewer • Updated • 1k • 9
ChenWu98/STP_Lean_0320_statement-cosine-similarity-rank
Viewer • Updated • 810k • 44
ChenWu98/NuminaMath-CoT-2048-cosine-similarity-rank
Viewer • Updated • 858k • 45
ChenWu98/stack-v2-python-normal-only
Viewer • Updated • 1.28M • 479
ChenWu98/stack-v2-python-flexible-orders
Viewer • Updated • 2.42M • 162
ChenWu98/line.10.9.10.10000
Viewer • Updated • 11k • 14
ChenWu98/circle.10.9.10.10000
Viewer • Updated • 11k • 21
ChenWu98/triangle.10
Viewer • Updated • 16k • 23