arxiv:2607.05297
Jinhe Bi
Jinhe
AI & ML interests
None yet
Organizations
models 11
Jinhe/ReflectRL-Qwen2.5-3B-Instruct-GRPO-ReflectRL
Text Generation • 3B • Updated • 37
Jinhe/ReflectRL-Qwen2.5-1.5B-Instruct-GRPO-ReflectRL
Text Generation • 2B • Updated • 21
Jinhe/ReflectRL-Llama-3.1-8B-Instruct-GRPO
Text Generation • 8B • Updated • 19
Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO
Text Generation • 8B • Updated • 15
Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL
Text Generation • 8B • Updated • 29
Jinhe/ReflectRL-Llama-3.1-8B-Instruct-GRPO-ReflectRL
Text Generation • 8B • Updated • 20
Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO
Text Generation • 8B • Updated • 21
Jinhe/ReflectRL-Qwen2.5-3B-Instruct-GRPO
Text Generation • 3B • Updated • 20
Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL
Text Generation • 8B • Updated • 27
Jinhe/ReflectRL-Qwen2.5-1.5B-Instruct-GRPO
Text Generation • 2B • Updated • 37