Zixuan Ke
ZixuanKe
AI & ML interests
NLP, Language Modeling, Continual Learning
Recent Activity
authored a paper about 22 hours ago
EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness? authored a paper about 22 hours ago
The Illusion of Multi-Agent Advantage authored a paper about 22 hours ago
MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled BenchmarksOrganizations
models 9
ZixuanKe/harmony-medium-grpo-7b-hotpot-global-step-270
Updated
ZixuanKe/harmony-medium-grpo-7b-browse-comp-plus-global-step-160
Updated
ZixuanKe/harmony-grpo-7b-global-step-260
Updated
ZixuanKe/hotpotqa-grpo-7b-gpt-oss-120b
8B • Updated • 7
ZixuanKe/browsecomp-grpo-7b-gpt-oss-120b
8B • Updated • 2
ZixuanKe/deepscaler_grpo_7b_gpt_oss_120b
8B • Updated • 4
ZixuanKe/harmony-grpo-7b-global-step-180
Updated
ZixuanKe/harmony-medium-grpo-7b-browse-comp-plus-global-step-140
Updated
ZixuanKe/harmony-medium-grpo-7b-hotpot-global-step-250
Updated • 1
datasets 788
ZixuanKe/evovling_agents
Viewer • Updated • 3.33k • 267
ZixuanKe/evovling_skills
Viewer • Updated • 3.36k • 448
ZixuanKe/evovling_tools
Viewer • Updated • 4.63k • 836 • 1
ZixuanKe/Frames_All
Viewer • Updated • 824 • 4
ZixuanKe/Frames_MAS_Zero
Viewer • Updated • 82 • 11
ZixuanKe/GSM8K_MAS_Zero
Viewer • Updated • 100 • 12
ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1.1_genrm_qwen3-32b_stepwise_dpo_binarized_F2048
Viewer • Updated • 16.5k • 20
ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1.1_genrm_qwen3-32b_dpo_binarized_F2048
Viewer • Updated • 16.9k • 8
ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1.1_genrm_qwen3-32b_dpo_binarized_filter2048
Viewer • Updated • 16.9k • 24
ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1.1_genrm_qwen3-32b_stepwise_dpo_binarized
Viewer • Updated • 16.9k • 14