LehongWu/verl-lt-vqa_class1-train_seed0_0124
Updated • 12
Lehong Wu
LehongWu
·
AI & ML interests
None yet
Recent Activity
updated a dataset about 19 hours ago
LehongWu/tmp updated a model 1 day ago
LehongWu/grpo-vlmjg_v2c-V_suc500_0409-repl_cntxt-norep-base_sft_group_x_line_all1k_0409_ep2_0421 published a model 1 day ago
LehongWu/grpo-vlmjg_v2c-V_suc500_0409-repl_cntxt-norep-base_sft_group_x_line_all1k_0409_ep2_0421Organizations
LehongWu/verl-lt-vqa_class1-eval_seed1m_1230
Updated • 11
LehongWu/verl-lt-vqa_class1-vqa_train_seed0-group_seed0_0113_0903.old
Updated • 7
LehongWu/verl-lt-vqa_class1-vqa_eval_seed1m-group_seed1000000_1230_0347.old
Updated • 4
LehongWu/vis-infer_only-cmp_judge_qwenv2c-gem3f
Viewer • Updated • 1.08k • 8
LehongWu/vis-infer_only-qwen_sft_gem3f-human_data
Viewer • Updated • 541 • 7
LehongWu/vis-infer_only-gem3f-human_data
Viewer • Updated • 541 • 3
LehongWu/vis-infer_only-cmp_judge_qwenv2c-sft_gem3f_eval64task_0310_ep1
Viewer • Updated • 400 • 3
LehongWu/tmp_debug_gold_dataset
Viewer • Updated • 64 • 10
LehongWu/vis-infer_only-cmp_judge_gem3fllm_vs_8bv0-grpo_judge_gem3f_0302
Viewer • Updated • 600 • 5
LehongWu/vis-infer_only-cmp_judge_gem3fllm-grpo_judge_gem3f_0302
Viewer • Updated • 400 • 4
LehongWu/vis-infer_only-qwen3vl8b_grpo_judge_gem3f_0302-human_data
Viewer • Updated • 200 • 6
LehongWu/vis-infer_only-cmp_judge_8bv0_vs_8bv2b_vs_8bv2c-grpo_v2b_0227
Viewer • Updated • 800 • 11
LehongWu/vis-infer_only-cmp_judge_8bv0_vs_8bv2b-grpo_v2b_0227
Viewer • Updated • 1.62k • 6
LehongWu/vis-infer_only-qwen3vl8b_grpo_vlmjudge_v2b_0227-human_data
Viewer • Updated • 541 • 13
LehongWu/vis-infer_only-cmp_judge_8bv0_vs_8bv2_vs_8bv2b-grpo_v2
Viewer • Updated • 252 • 11
LehongWu/vis-infer_only-cmp_judge_8bv0_vs_8bv2_vs_32bv2_vs_gemini3flash-grpo_v2
Viewer • Updated • 315 • 11
LehongWu/vis-infer_only-cmp_judge_8bv0_vs_8bv2_vs_32bv2-grpo_v2
Viewer • Updated • 252 • 11
LehongWu/vis-infer_only-cmp_judge_8bv0_vs_8bv2-grpo_v2
Viewer • Updated • 189 • 3
LehongWu/vis-infer_only-qwen3vl8b_grpo_vlmjudge_v2_0221-human_data-scored
Viewer • Updated • 1.62k • 7
LehongWu/vis-infer_only-qwen3vl8b_grpo_vlmjudge_v2_0221-human_data
Viewer • Updated • 541 • 6
LehongWu/vis-infer_only-qwen3vl8b_base-human_data-scored
Viewer • Updated • 600 • 7
LehongWu/vis-infer_only-qwen3vl8b_base-human_data
Viewer • Updated • 200 • 4
LehongWu/eval_custom_line_color-qwen3vl8b-base-repeat4_0202
Viewer • Updated • 634k • 12
LehongWu/language-table-outputs-backup-0201
Viewer • Updated • 148k • 8
LehongWu/verl-lt-vqa_class2-instruction_6types_seed0_0126
Updated • 3
LehongWu/verl-lt-vqa_class2-instruction_6types_seed1m_0125
Updated • 4
LehongWu/human_reason_process_notebook-backup-0123
Viewer • Updated • 4.18k • 5
LehongWu/verl-lt-vqa_class2-line_color_qwen3vl8b_base_1223
Updated • 4
LehongWu/language-table-outputs-backup-0116
Updated • 5