Michael Zhang's picture

Michael Zhang PRO

mzio

·

AI & ML interests

None yet

Recent Activity

updated a dataset about 7 hours ago

mzio/ff-main-ec-online_mind2web_cc-gc-chat_claude-mc-hf_qwen3_4b_inst_2507-lc-claude_agent_so-r0

updated a dataset about 15 hours ago

mzio/aprm-sft_thinkact-Einsurance_default-G1-S1-Rinsurance_aprm_1_mc-ap1-train_all-b060

published a dataset about 15 hours ago

mzio/aprm-sft_thinkact-Einsurance_default-G1-S1-Rinsurance_aprm_1_mc-ap1-train_all-b060

View all activity

Organizations

mzio 's datasets 485

mzio/aprm-sft_genthinkact-ENtw_coin_collector-GEaprm_qwen3_ap-SE42-RE1-ap1-b0019

Viewer • Updated Jan 22 • 3.2k • 1

mzio/aprm-sft_genthinkact-ENtw_coin_collector-GEaprm_qwen3_ap-SE42-RE1-ap1-b0009

Viewer • Updated Jan 22 • 3.2k • 1

mzio/aprm-sft_act_only-ENtextworld_coin_collector-GEaprm_qwen3_ap-SE42-RE1

Viewer • Updated Jan 21 • 400 • 2

mzio/aprm_sft_thought_action_rollouts-ENtextworld_treasure_hunter-GEaprm_qwen3_ap-SE42-RE1-ap1_0099

Viewer • Updated Jan 21 • 3.2k • 2

mzio/aprm-sft_genthinkact-ENtextworld_treasure_hunter-GEaprm_qwen3_ap-SE42-RE0-ap1-b0000

Viewer • Updated Jan 21 • 3.2k • 2

mzio/sft-ENtextworld_cooking_game-GEaprm_qwen3_ap-SE42-RE1

Viewer • Updated Jan 21 • 1.26k • 2

mzio/sft-ENtextworld_treasure_hunter-GEaprm_qwen3_ap-SE42-RE1

Viewer • Updated Jan 21 • 400 • 1

mzio/sft-ENtextworld_coin_collector-GEaprm_qwen3_ap-SE42-RE1

Viewer • Updated Jan 21 • 400 • 2

mzio/sft-ENtextworld_cooking_game-GEaprm_qwen3_ap-SE42-RE0

Viewer • Updated Jan 21 • 1.26k • 2

mzio/sft-ENtextworld_treasure_hunter-GEaprm_qwen3_ap-SE42-RE0

Viewer • Updated Jan 21 • 400 • 2

mzio/sft-ENtextworld_coin_collector-GEaprm_qwen3_ap-SE42-RE0

Viewer • Updated Jan 21 • 400 • 3

mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_gpt5_gen4s_GEaprm_qwen3_ap_SE42_RE4-ap1_best_0020

Viewer • Updated Jan 19 • 1.59k • 3

mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_gpt5_gen4s_GEaprm_qwen3_ap_SE42_RE4-ap1_0019

Viewer • Updated Jan 19 • 1.59k • 3

mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_default_GEaprm_qwen3_ap_SE42_RE5-ap1_best_0040

Viewer • Updated Jan 19 • 12.7k • 3

mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_default_GEaprm_qwen3_ap_SE42_RE5-ap1_0039

Viewer • Updated Jan 19 • 12.7k • 3

mzio/act_prm-gpt5_low-hotpotqa_mc_gpt5_gen-v2397-tools

Viewer • Updated Jan 19 • 2.4k • 26

mzio/act_prm-gpt5_low-hotpotqa_mc_gpt5_gen-v5-tools

Viewer • Updated Jan 19 • 5 • 17

mzio/rb_last-cql-mc_oai_gpt5_low-ec_hotpotqa_mc_gpt5-ds_train-spp1-gbs1-s42-r_0-v5649-tools

Viewer • Updated Jan 19 • 5.65k • 17

mzio/hotpotqa_mc-llama3_2_3b_inst-full_obs-tools-v546

Viewer • Updated Jan 19 • 546 • 4

mzio/hotpotqa_mc-llama3_2_3b_inst-full_obs-tools-v1082

Viewer • Updated Jan 19 • 1.08k • 4

mzio/hotpotqa_mc-llama3_2_3b_inst-full_obs_v1082

Viewer • Updated Jan 19 • 1.08k • 3

mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0020

Viewer • Updated Jan 19 • 9.91k • 117

mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0010

Viewer • Updated Jan 19 • 9.91k • 113

mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0000

Viewer • Updated Jan 18 • 9.91k • 107

mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_1-ap_rl0000

Viewer • Updated Jan 18 • 9.91k • 114

mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0080

Viewer • Updated Jan 18 • 1.02k • 8

mzio/aprm_sft-act_prm_browsecomp_100_aprm_qwen3_ap_42_debug-0020

Viewer • Updated Jan 18 • 2.12k • 101

mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0070

Viewer • Updated Jan 18 • 4.06k • 2

mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0070

Viewer • Updated Jan 18 • 4.06k • 6

mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0060

Viewer • Updated Jan 18 • 1.02k • 2