LegendaryDawn/mbpo-adv_dpo001-shard2-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 4B • Updated 4 days ago • 17
LegendaryDawn/mbpo-adv_neg_replace-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 4B • Updated 5 days ago • 47
LegendaryDawn/mbpo-adv_dpo001-shard-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 4B • Updated 6 days ago • 46
LegendaryDawn/mbpo-adv_dpo001-shard-adv_8_64_rankmix20-grpo-n5-qwen2_5_vl_3b-step300 4B • Updated 7 days ago • 76
LegendaryDawn/mbpo-clean_negative_reweight-resrl_quantile-adv_8_64-qwen2_5_vl_3b-step302 4B • Updated 13 days ago • 75
LegendaryDawn/mbpo-clean_negative_reweight-rank_power-adv_8_64-qwen2_5_vl_3b-step302 4B • Updated 13 days ago • 70
LegendaryDawn/mbpo-clean_negative_reweight-budget_exp-adv_8_64-qwen2_5_vl_3b-step302 4B • Updated 13 days ago • 110
LegendaryDawn/mbpo-adv_masked_grpo-balanced-adv_8_64-qwen2_5_vl_3b-step302 4B • Updated 15 days ago • 88
LegendaryDawn/SDRL-icml_rebuttal-debateLength-freq-Qwen2.5-3B-majority_n4_l4096-DAPO_n8_bs256_long8-step200 3B • Updated 22 days ago • 20
LegendaryDawn/SDRL-icml_rebuttal-2turn-freq-Qwen2.5-3B-majority_n4_l2048-DAPO_n8_bs256_long8-step200 3B • Updated 23 days ago • 129
LegendaryDawn/SDRL-icml_rebuttal-freq-Qwen2.5-3B-majority_n8_l2048-DAPO_n8_bs256_long8-step200 3B • Updated 24 days ago • 142
LegendaryDawn/SDRL-freq-Qwen3-4B-Base-majority_n8_l2048-GRPO_n8_bs256_long8-step200 4B • Updated about 1 month ago • 120
LegendaryDawn/SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long12-yarn2-step200 8B • Updated Feb 17 • 1
LegendaryDawn/SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long12-yarn2-step125 8B • Updated Feb 15 • 1
LegendaryDawn/SDRL-rand-Qwen3-8B-Base-random_n8_l4096-DAPO_n8_bs256_long12-yarn2-step125 8B • Updated Feb 15 • 1
LegendaryDawn/SDRL-rand-Qwen3-8B-Base-random_n8_l4096-DAPO_n8_bs256_long12-yarn2-step200 8B • Updated Feb 13 • 1
LegendaryDawn/SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long8-step200 8B • Updated Feb 5 • 6
LegendaryDawn/SDRL-rand-Qwen3-8B-Base-random_n8_l4096-DAPO_n8_bs256_long8-step200 8B • Updated Feb 4 • 6
LegendaryDawn/SDRL-rand-Qwen3-4B-Base-icml-self-debate-random_n8_l2048-DAPO_n8_bs256_long8-step200 4B • Updated Jan 27 • 389
LegendaryDawn/SDRL-freq-Qwen3-4B-Base-icml-self-debate-exp-majority_n8_l2048-DAPO_n8_bs256_long8-run2-step200 4B • Updated Jan 25 • 772
LegendaryDawn/SDRL-rand-Qwen2.5-3B-icml-self-debate-ablation-random_n4_l2048-DAPO_n8_bs256_long8-step200 3B • Updated Jan 25 • 370