Zixuan Ke

ZixuanKe

·

https://vincent950129.github.io/

AI & ML interests

NLP, Language Modeling, Continual Learning

Organizations

Collections 7

View 7 collections

Papers 9

arxiv:2609.04280

arxiv:2606.13003

arxiv:2601.14652

arxiv:2505.14996

models 9

ZixuanKe/harmony-medium-grpo-7b-hotpot-global-step-270

ZixuanKe/harmony-medium-grpo-7b-browse-comp-plus-global-step-160

ZixuanKe/harmony-grpo-7b-global-step-260

ZixuanKe/hotpotqa-grpo-7b-gpt-oss-120b

8B • Updated Apr 12 • 9

ZixuanKe/browsecomp-grpo-7b-gpt-oss-120b

8B • Updated Apr 12 • 7

ZixuanKe/deepscaler_grpo_7b_gpt_oss_120b

8B • Updated Apr 12 • 10

ZixuanKe/harmony-grpo-7b-global-step-180

ZixuanKe/harmony-medium-grpo-7b-browse-comp-plus-global-step-140

ZixuanKe/harmony-medium-grpo-7b-hotpot-global-step-250

Updated Apr 1 • 1

datasets 788

ZixuanKe/evovling_agents

Viewer • Updated Sep 10 • 3.33k • 5.45k

ZixuanKe/evovling_skills

Viewer • Updated Sep 10 • 3.36k • 2.64k

ZixuanKe/evovling_tools

Viewer • Updated Sep 10 • 4.63k • 1.53k • 1

ZixuanKe/Frames_All

Viewer • Updated Sep 18, 2025 • 824 • 39

ZixuanKe/Frames_MAS_Zero

Viewer • Updated Sep 16, 2025 • 82 • 35

ZixuanKe/GSM8K_MAS_Zero

Viewer • Updated Jul 2, 2025 • 100 • 55

ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1.1_genrm_qwen3-32b_stepwise_dpo_binarized_F2048

Viewer • Updated Jun 30, 2025 • 16.5k • 65

ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1.1_genrm_qwen3-32b_dpo_binarized_F2048

Viewer • Updated Jun 30, 2025 • 16.9k • 34

ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1.1_genrm_qwen3-32b_dpo_binarized_filter2048

Viewer • Updated Jun 30, 2025 • 16.9k • 31

ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1.1_genrm_qwen3-32b_stepwise_dpo_binarized

Viewer • Updated Jun 30, 2025 • 16.9k • 39

View 788 datasets