yzha/grpo_qwen3_8b_sysprompt_workflow2_step160
8B • Updated
y_zha
yzha
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
CocoaBench: Evaluating Unified Digital Agents in the Wild updated a model 7 months ago
yzha/grpo_qwen3_8b_sysprompt_workflow2_step160 published a model 7 months ago
yzha/grpo_qwen3_8b_sysprompt_workflow2_step160Organizations
None yet
yzha/qwen3_8b_new_prompt_orig_otcm_rwd_w_choice_ratio
8B • Updated • 1
yzha/grpo_qwen3_8b_sysprompt_workflow2
8B • Updated
yzha/vision-g1
Image-Text-to-Text • 8B • Updated • 16
yzha/tklt-virl-400step
8B • Updated
yzha/virl_39k_step200
8B • Updated
yzha/tklt-step200
8B • Updated
yzha/Align
Updated • 1
yzha/AlignScore
Updated • 6