arxiv:2505.13444
Wenxuan D
wenwenD
AI & ML interests
None yet
Organizations
models 76
wenwenD/qwen3-8b-codeexp_additive_v14_grpo_wprior_think_step400_0505_2009_nvidia
8B • Updated • 4
wenwenD/qwen3-8b-codeexp_additive_v14_grpo_wprior_think_step350_0505_2009_nvidia
8B • Updated • 4
wenwenD/qwen3-8b-codeexp_additive_v14_grpo_wprior_think_step300_0505_2009_nvidia
8B • Updated • 3
wenwenD/qwen3-8b-codeexp_additive_v14_grpo_wprior_think_step250_0505_2009_nvidia
8B • Updated • 3
wenwenD/qwen3-8b-codeexp_additive_v14_grpo_wprior_think_step200_0505_2009_nvidia
8B • Updated • 1
wenwenD/qwen3-8b-codeexp_additive_v14_grpo_wprior_think_step150_0505_2009_nvidia
8B • Updated • 5
wenwenD/qwen3-8b-codeexp_additive_v14_grpo_wprior_think_step100_0505_2009_nvidia
8B • Updated • 3
wenwenD/qwen3-8b-codeexp_additive_v14_grpo_wprior_think_step50_0505_2009_nvidia
8B • Updated • 2
wenwenD/nemotron-3-nano-4b-bf16-codeexp_grpo_wprior_think_step250_0503_0420_nvidia_balanced_v3
4B • Updated • 2
wenwenD/nemotron-3-nano-4b-bf16-codeexp_grpo_wprior_think_step225_0503_0420_nvidia_balanced_v3
4B • Updated • 2