arxiv:2505.13444
Wenxuan D
wenwenD
AI & ML interests
None yet
Recent Activity
updated
a model
1 day ago
wenwenD/qwen3-4b-codeexp_grpo_no_prior_think_step280_2026-01-25_06-29-13_nvidia_balanced
published
a model
1 day ago
wenwenD/qwen3-4b-codeexp_grpo_no_prior_think_step280_2026-01-25_06-29-13_nvidia_balanced
updated
a model
1 day ago
wenwenD/qwen3-4b-codeexp_grpo_w_prior_think_step280_2026-01-25_06-28-54_nvidia_balanced
Organizations
models
22
wenwenD/qwen3-4b-codeexp_grpo_no_prior_think_step280_2026-01-25_06-29-13_nvidia_balanced
4B
•
Updated
•
9
wenwenD/qwen3-4b-codeexp_grpo_w_prior_think_step280_2026-01-25_06-28-54_nvidia_balanced
4B
•
Updated
•
10
wenwenD/qwen3-4b-codeexp_grpo_with_prior_think_step280_2026-01-24_07-19-57_nvidia
4B
•
Updated
•
14
wenwenD/qwen3-4b-codeexp_grpo_no_prior_think_step280_2026-01-24_07-21-36_nvdia
4B
•
Updated
•
14
wenwenD/qwen3-4b-codeexp_grpo_w_prior_think_discount_always1_step175_2026_01_23_21_40_33
4B
•
Updated
•
8
wenwenD/qwen3-1.7b-csv_explorer_grpo_noprior_step75_12_16-07-10
2B
•
Updated
•
12
wenwenD/qwen3-1.7b-csv_explorer_grpo_step100
2B
•
Updated
•
10
wenwenD/qwen3-8B_csv_format_sft_10epcs
8B
•
Updated
•
14
wenwenD/qwen3-8B_500_rej_extend_final_checkpoint-1065_correctformat
8B
•
Updated
wenwenD/qwen3-8B_500_rej_extend_final_checkpoint-426_correctformat
8B
•
Updated
•
2
datasets
0
None public yet