SeanWang0027 PRO

SeanWang0027

·

https://haojinw0027.github.io/

AI & ML interests

LLM Post-Training

Recent Activity

published a model about 12 hours ago

SeanWang0027/qwen3-4b-nemotron-if-off-sft-v1

updated a model about 20 hours ago

SeanWang0027/qwen3-4b-nemotron-if-off-sft-v1

updated a model 2 days ago

SeanWang0027/rose-opd-implementation

View all activity

Organizations

SeanWang0027 's datasets 52

SeanWang0027/polaris_rose_rollouts_olmo3-7b_from_qwen3-30b-a3b_cutoff4096_240steps

Viewer • Updated 5 days ago • 61.7k • 15

SeanWang0027/student_partial_sciworld

Viewer • Updated 11 days ago • 2.12k • 33

SeanWang0027/sciworld-agentgym-qwen3-1p7b-rollouts

Updated 15 days ago • 43

SeanWang0027/rose-tinker-s25-eval-rollouts

Preview • Updated 16 days ago • 45

SeanWang0027/rose-tinker-step1-rollouts

Viewer • Updated 16 days ago • 256 • 41

SeanWang0027/sciworld-newsplit-rollouts

Updated 17 days ago • 68

SeanWang0027/scienceworld-tcod-split

Viewer • Updated 18 days ago • 3.6k • 70

SeanWang0027/sciworld-teacher32b-sft-partial

Viewer • Updated 19 days ago • 352 • 66

SeanWang0027/rlve-eval-rollouts

Updated 22 days ago • 114

SeanWang0027/rlve-32b-k1024-sft

Viewer • Updated 23 days ago • 9k • 40

SeanWang0027/Multi-Turn

Viewer • Updated 25 days ago • 10 • 519

SeanWang0027/rlve_rose_opd_4096

Updated Jul 2 • 3

SeanWang0027/physics_hard_questions

Updated May 29 • 20

SeanWang0027/polaris_hard_POPE

Updated May 20 • 3

SeanWang0027/polaris_hard_sampling

Viewer • Updated May 18 • 15.4k • 11

SeanWang0027/polaris_Qwen3-1_7B_prefix_4K

Viewer • Updated May 17 • 14.4k • 21

SeanWang0027/polaris_pope_prefix_40K

Viewer • Updated May 16 • 40k • 21

SeanWang0027/polaris_offline_40K

Viewer • Updated May 16 • 40k • 7

SeanWang0027/polaris_warmup_40K

Viewer • Updated May 16 • 40k • 3

SeanWang0027/polaris_hard

Viewer • Updated May 15 • 15.4k • 24

SeanWang0027/math_pope_mix_1018

Viewer • Updated May 10 • 1.02k • 7

SeanWang0027/sft_full_math_hard_9000

Viewer • Updated May 10 • 9k • 7

SeanWang0027/extreme_hard_4B

Viewer • Updated May 8 • 5.27k • 5

SeanWang0027/rlve_mixed_20envs_stitch_full

Viewer • Updated Apr 20 • 16k • 11

SeanWang0027/verl_mask_training

Updated Apr 19 • 452

SeanWang0027/rlve_30b_qwen_1.7b_mixed_20envs_10

Viewer • Updated Apr 18 • 16k • 6

SeanWang0027/teacher_prefix_sudoku_10K_sequential_qwen3_4b_thinking_continual_nemotron-cascade-8b

Updated Apr 16 • 6

SeanWang0027/student_prefix_sequential

Viewer • Updated Apr 14 • 3k • 31 • 1

SeanWang0027/RAGEN

Updated Apr 11 • 415

SeanWang0027/mixed_sdft_solution_sequential_minesweeper_kukurasu_qwen3_4b_thinking

Updated Apr 9 • 27