arxiv:2508.12680
y_zha
yzha
AI & ML interests
None yet
Recent Activity
updated
a model
17 days ago
yzha/grpo_qwen3_8b_sysprompt_workflow2_step160
published
a model
17 days ago
yzha/grpo_qwen3_8b_sysprompt_workflow2_step160
updated
a model
18 days ago
yzha/qwen3_8b_new_prompt_orig_otcm_rwd_w_choice_ratio
Organizations
None yet
models
9
yzha/grpo_qwen3_8b_sysprompt_workflow2_step160
8B
•
Updated
•
57
yzha/qwen3_8b_new_prompt_orig_otcm_rwd_w_choice_ratio
8B
•
Updated
•
104
yzha/grpo_qwen3_8b_sysprompt_workflow2
8B
•
Updated
•
454
yzha/vision-g1
Image-Text-to-Text
•
8B
•
Updated
•
791
yzha/tklt-virl-400step
8B
•
Updated
yzha/virl_39k_step200
8B
•
Updated
yzha/tklt-step200
8B
•
Updated
yzha/Align
Updated
•
1
yzha/AlignScore
Updated
•
5