Pengcheng Xu

ryan-superman

·

AI & ML interests

None yet

Recent Activity

liked a model 8 days ago

explcre/omegagenome-distilled-students

commentedon a paper 19 days ago

UOPD: Uncertainty-Aware Intervention for On-Policy Distillation of Multi-Turn Agents

upvoted a paper 19 days ago

UOPD: Uncertainty-Aware Intervention for On-Policy Distillation of Multi-Turn Agents

View all activity

Organizations

None yet

ryan-superman 's models 418

ryan-superman/nt-2.5b-lora-teachers-r48

ryan-superman/tcod-weights-alfworld_tcod_b2f_1p5b_20260916012014-7cf9fc

ryan-superman/tcod-resume-alfworld_tcod_b2f_1p5b-f4c452

ryan-superman/tcod-resume-alfworld_tcod_f2b_1p5b_20260915141050-5b269a

ryan-superman/tcod-resume-search_sacd_1p5B_mt8_bs64_s123_k1_q0.30-0.30_b1.0_sftplain_lazy_-f84070

ryan-superman/tcod-weights-search_sacd_1p5B_mt8_bs64_s123_k1_q0.30-0.30_b1.0_sftplain_lazy_-f84070

ryan-superman/tcod-runlog-search_sacd_1p5B_mt8_bs64_s123_k1_fx1.0_b1.0_sftplain_lazy_teach-b65cb7

ryan-superman/tcod-runlog-search_sacd_1p5B_mt8_bs64_s123_k1_q0.30-0.30_b1.0_sftplain_lazy_-f84070

ryan-superman/tcod-resume-search_sacd_3B_mt8_bs64_s42_k1_q0.40-0.05_b1.0_sftplain_lazy_stu-c5fd0b

Updated Sep 14 • 1

ryan-superman/tcod-resume-search_tcod_b2f___mt8_bs64_s123_ee3f0c50-0182f7

ryan-superman/tcod-resume-alfworld_sacd_3b_confidence_tau1.28_beta1.0_sftplain_lazy_teache-9c2842

ryan-superman/tcod-resume-alfworld_sacd_3b_confidence_tau1.28_beta1.0_sftplain_lazy_teache-3cdfc5

ryan-superman/tcod-weights-alfworld_sacd_3b_confidence_tau1.28_beta1.0_sftplain_lazy_teache-b6701a

ryan-superman/tcod-weights-alfworld_sacd_1p5b_confidence_tau1.28_beta1.0_sftplain_lazy_teac-09ef4c

ryan-superman/tcod-weights-alfworld_sacd_1p5b_confidence_tau1.28_beta1.0_sftplain_lazy_teac-b31f03

ryan-superman/tcod-resume-search_tcod_f2b_1p5B_mt8_bs64_s42_3df379a6-e4ec47

ryan-superman/tcod-resume-search_sacd___mt8_bs64_s42_confidence_q0.30-0.05_b1.0_sftplain_l-097c9b

ryan-superman/tcod-weights-search_sacd_1p5B_mt8_bs64_s42_k1_q0.50-0.50_b1.0_sftplain_lazy_t-e161b0

ryan-superman/tcod-weights-search_sacd_1p5B_mt8_bs64_s42_k1_q0.30-0.30_b1.0_sftplain_lazy_t-f3e61b

ryan-superman/tcod-runlog-alfworld_sacd_1p5b_confidence_tau1.28_beta1.0_sftplain_lazy_teac-1d9230

ryan-superman/tcod-runlog-alfworld_sacd_3b_confidence_tau1.28_beta1.0_sftplain_lazy_teache-b6701a

ryan-superman/tcod-runlog-alfworld_sacd_3b_confidence_tau1.28_beta1.0_sftplain_lazy_teache-4923b1

ryan-superman/tcod-runlog-search_sacd_1p5B_mt8_bs64_s42_k1_q0.30-0.30_b1.0_sftplain_lazy_t-f3e61b

ryan-superman/tcod-weights-search_sacd_1p5B_mt8_bs16_s42_k1_q0.50-0.50_b1.0_sftplain_lazy_t-941c4c

ryan-superman/tcod-weights-search_sacd_1p5B_mt8_bs16_s42_k1_q0.30-0.30_b1.0_sftplain_lazy_t-233ed2

ryan-superman/tcod-runlog-search_sacd_1p5B_mt8_bs16_s42_k1_q0.30-0.30_b1.0_sftplain_lazy_t-233ed2

ryan-superman/tcod-runlog-search_sacd_1p5B_mt8_bs16_s42_k1_q0.50-0.50_b1.0_sftplain_lazy_t-941c4c

ryan-superman/tcod-weights-search_sacd___mt8_bs64_s42_confidence_q0.30-0.05_b1.0_sftplain_l-097c9b

ryan-superman/tcod-runlog-search_sacd___mt8_bs64_s42_confidence_q0.30-0.05_b1.0_sftplain_l-097c9b

ryan-superman/tcod-weights-search_sacd_1p5B_mt8_bs64_s42_k1_q0.30-0.05_b1.0_sftplain_lazy_t-bc609f