LehongWu/mllm_lt_S6_v3_1_0416-gemini3flash_medium-0416_all256trajs_postgen_ecot-sft_qwen35_4b_0603_0238 Updated 4 days ago • 2
LehongWu/mllm_lt_S6_v3_1_0416-gemini3flash_medium-0416_all256trajs_postgen-sft_qwen35_4b_0602_2347 Updated 4 days ago • 2
LehongWu/mllm_lt_S6_v3_1_0416-gemini3flash_medium-0416_all256trajs_ours_ecot-sft_qwen35_4b_0602_0805 Updated 5 days ago • 3
LehongWu/mllm_lt_S6_v3_1_a256tj_x_S6R3_0521_s128tj-nt-sft_qwen35_4b_cotrain_sftthink_0602_0011 Updated 5 days ago • 15
LehongWu/mllm_lt_S6_v3_1_a256tj_x_S6R3_0521_s128tj-nt-sft_qwen35_4b_pretrain_sftthink_0602_0011 Updated 5 days ago • 9
LehongWu/grpo-v3a-qwen3_5_4b-S6R3_v3_1_0524_s128tj-base_sft_S6_prior_impl_a256tj-ent0_0528 Updated 8 days ago • 9
LehongWu/grpo-v3a-qwen3_5_4b-S6R3_v3_1_0524_s128tj-base_sft_S6_a64tj-ent0_0527 Updated 10 days ago • 5
LehongWu/grpo-v3a-qwen3_5_4b-S6R3_v3_1_prior_0524_s128tj-base_sft_prior_S6_a256tj-ent0_0525 Updated 12 days ago • 7
LehongWu/grpo-v3a-qwen3_5_4b-S6R3_v3_1_0524_s128tj-base_sft_S6_a256tj-ent0_0525 Updated 12 days ago • 7
LehongWu/mllm_lt_V_line_v3_1_no_prev-gemini3flash_medium-0524_all256trajs-sft_qwen35_4b_0524_2354 Updated 13 days ago • 3
LehongWu/mllm_lt_V_line_v3_1_to_noprev-gemini3flash_medium-0416_all256trajs-sft_qwen35_4b_0524_1516 Updated 14 days ago • 3
LehongWu/mllm_lt_V_line_v3_1-gemini3flash_medium-0416_all256trajs-sft_qwen35_4b_0524_1500 Updated 14 days ago • 3
LehongWu/mllm_lt_S6_v3_1_a256tj_x_S6R3_0521_s128tj-nt-sft_qwen35_4b_0524_1345 Updated 14 days ago • 12
LehongWu/mllm_lt_S6_v3_1_prior_implicit_0516-gem3f_med-0516_a256tj-sft_qwen35_4b_0523_1013 Updated 15 days ago • 7
LehongWu/mllm_lt_S6_v3_1_prior_0516-gem3f_med-0516_a256tj-sft_qwen35_4b_0523_0931 Updated 15 days ago • 6
LehongWu/mllm_lt_S6_v3_1_a256tj_x_S6R4_0521_s128tj-nt-sft_qwen35_4b_0523_0830 Updated 15 days ago • 3
LehongWu/mllm_lt_S6_013789_v3_1_0416-gem3f_med-0416_a64tj-sft_qwen35_4b_0522_0635 Updated 16 days ago • 7
LehongWu/mllm_lt_S6_013789_v3_1_0416-gem3f_med-0416_a256tj-nt-sft_qwen35_4b_0521_0552 Updated 17 days ago • 3
LehongWu/grpo-v3a-qwen3_5_4b-iip_only-v3_1-with_rep1-base_sft_6t_a500tj_0416_ep2_0521 Updated 17 days ago • 2
LehongWu/mllm_lt_S6_013789_v3_1_0416-gem3f_med-0416_a256tj-sft_qwen35_4b_0521_0313 Updated 17 days ago • 7
LehongWu/grpo-v3a-qwen3_5_4b-6t_s100_x_3t_s200_replctxt-v3_1-base_opsd_6t_a500tj_stu0.25-step400-0520 Updated 18 days ago • 2
LehongWu/grpo-v3a-qwen3_5_4b-iip_only-v3_1-with_rep0.1-base_sft_6t_a500tj_0416_ep2_0520 Updated 18 days ago • 3
LehongWu/opsd-collect_6t_013789_v3_1_0416-rep8_0416_a500tj-stu0.25-base_qwen35_4b-len1024-0519 Updated 18 days ago • 2
LehongWu/grpo-v3a-qwen3_5_4b-6t_s100_x_3t_s200_replctxt-v3_1-w_rep0.1-base_sft_6t_a500tj_0416_ep2_0519 Updated 19 days ago • 3
LehongWu/grpo-v3a-qwen3_5_4b-6t_s100_x_3t_s200_replctxt-v3_1-retemp_v3_3-base-ent0-len2048_0518 Updated 19 days ago • 4
LehongWu/opsd-collect_6t_013789_v3_1_0416-rep8_0416_a500tj-stu1-base_qwen35_4b-len1024-0519 Updated 19 days ago • 3