1 4 5

SeanWang0027 PRO

SeanWang0027

https://haojinw0027.github.io/

AI & ML interests

LLM Post-Training

Recent Activity

published a dataset about 2 hours ago

CL-From-Nothing/physics_8B_1K_Qwen3-32B_pass8

upvoted a paper 1 day ago

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models

updated a model 2 days ago

SeanWang0027/polaris_warmup_polaris

View all activity

Organizations

Collections 3

View 3 collections

Papers 2

arxiv:2602.01058

arxiv:2505.16964

models 56

SeanWang0027/polaris_warmup_polaris

Updated 2 days ago

SeanWang0027/polaris_warmup_polaris_ROSE_warmup_Qwen3_1_7B_40K-parquet_qwen3-1.7b_epoch_1_mask

2B • Updated 2 days ago • 16

SeanWang0027/rl_warm_up_mixed_minesweeper_correct_thinking-parquet_qwen3-1.7b_epoch_3_mask_k4096

Updated 11 days ago

SeanWang0027/rl_warm_up_mixed_minesweeper_correct_thinking-parquet_qwen3-1.7b_epoch_3_mask

Updated 12 days ago

SeanWang0027/grpo_minesweeper

Updated 13 days ago

View 56 models

datasets 39

SeanWang0027/polaris_hard_POPE

Updated 3 days ago • 16

SeanWang0027/polaris_hard_sampling

Viewer • Updated 5 days ago • 15.4k • 23

SeanWang0027/polaris_Qwen3-1_7B_prefix_4K

Viewer • Updated 6 days ago • 14.4k • 24

SeanWang0027/polaris_pope_prefix_40K

Viewer • Updated 7 days ago • 40k • 25

SeanWang0027/polaris_offline_40K

Viewer • Updated 7 days ago • 40k • 25

SeanWang0027/polaris_warmup_40K

Viewer • Updated 8 days ago • 40k • 28

SeanWang0027/polaris_hard

Viewer • Updated 9 days ago • 15.4k • 41

SeanWang0027/math_pope_mix_1018

Viewer • Updated 14 days ago • 1.02k • 31

SeanWang0027/sft_full_math_hard_9000

Viewer • Updated 14 days ago • 9k • 32

SeanWang0027/extreme_hard_4B

Viewer • Updated 16 days ago • 5.27k • 36

View 39 datasets

SeanWang0027 PRO

AI & ML interests

Recent Activity

Organizations

Collections 3

SeanWang0027/olmo-7b-synlogic-sudoku-easy-grpo

SeanWang0027/olmo-7b-synlogic-sudoku-easy-hard-grpo

SeanWang0027/olmo-7b-synlogic-survo-sft

SeanWang0027/olmo-7b-synlogic-survo-space_reasoning-sft

SeanWang0027/olmo-7b-synlogic-survo-space_reasoning-math_path-sft

SeanWang0027/sci-10k-olmo-7b-synlogic-survo-space_reasoning-math_path-sft

SeanWang0027/olmo-7b-synlogic-sudoku-easy-grpo

SeanWang0027/olmo-7b-synlogic-sudoku-easy-hard-grpo

SeanWang0027/olmo-7b-synlogic-survo-sft

SeanWang0027/olmo-7b-synlogic-survo-space_reasoning-sft

SeanWang0027/olmo-7b-synlogic-survo-space_reasoning-math_path-sft

SeanWang0027/sci-10k-olmo-7b-synlogic-survo-space_reasoning-math_path-sft

Papers 2

models 56

SeanWang0027/polaris_warmup_polaris

SeanWang0027/polaris_warmup_polaris_ROSE_warmup_Qwen3_1_7B_40K-parquet_qwen3-1.7b_epoch_1_mask

SeanWang0027/token_reward_direct_math_hard_509

SeanWang0027/rl_warm_up_0519

SeanWang0027/polaris_warmup_polaris_offline_40K-parquet_qwen3-1.7b_epoch_1_mask

SeanWang0027/polaris_warmup_polaris_warmup_40K-parquet_qwen3-4b_epoch_1_mask

SeanWang0027/token_reward_direct

SeanWang0027/rl_warm_up_mixed_minesweeper_correct_thinking-parquet_qwen3-1.7b_epoch_3_mask_k4096

SeanWang0027/rl_warm_up_mixed_minesweeper_correct_thinking-parquet_qwen3-1.7b_epoch_3_mask

SeanWang0027/grpo_minesweeper

datasets 39

SeanWang0027/polaris_hard_POPE

SeanWang0027/polaris_hard_sampling

SeanWang0027/polaris_Qwen3-1_7B_prefix_4K

SeanWang0027/polaris_pope_prefix_40K

SeanWang0027/polaris_offline_40K

SeanWang0027/polaris_warmup_40K

SeanWang0027/polaris_hard

SeanWang0027/math_pope_mix_1018

SeanWang0027/sft_full_math_hard_9000

SeanWang0027/extreme_hard_4B

SeanWang0027 PRO

AI & ML interests

Recent Activity

Organizations

Collections 3

Papers 2

models 56 Sort: Recently updated

datasets 39 Sort: Recently updated

models 56

datasets 39