Hao Sun

Holarissun's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 1 month ago

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities

Paper • 2507.13158 • Published Jul 17 • 24

upvoted a paper about 1 month ago

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities

Paper • 2507.13158 • Published Jul 17 • 24

commented a paper about 1 month ago

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities

Paper • 2507.13158 • Published Jul 17 • 24 •

2

upvoted 2 papers 6 months ago

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published Feb 20 • 106

Rethinking Diverse Human Preference Learning through Principal Component Analysis

Paper • 2502.13131 • Published Feb 18 • 38

updated 2 models about 1 year ago

Holarissun/SFT_gemma2b_hh-rlhf-helpful-gpt4_lr5e-06_epoch2-subset-1

Updated Jun 17, 2024 • 1

Holarissun/SFT_gemma2b_hh-rlhf-helpful_lr5e-06_epoch2-subset-1

Updated Jun 17, 2024 • 1

liked a model about 1 year ago

weqweasdas/RM-Mistral-7B

Text Classification • 7B • Updated Mar 31, 2024 • 936 • 23

updated 12 models about 1 year ago

Holarissun/REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Updated May 29, 2024 • 1

Holarissun/REPROD_dpo_harmlessharmless_gpt4_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Updated May 29, 2024 • 1

Holarissun/REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Updated May 29, 2024 • 1

Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Updated May 29, 2024 • 1

Holarissun/REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

Updated May 28, 2024 • 1

Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

Updated May 28, 2024 • 1

Holarissun/REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-05

Updated May 25, 2024 • 1

Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-05

Updated May 24, 2024 • 2

Holarissun/REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma2b_maxsteps10000_bz8_lr1e-05

Updated May 24, 2024 • 1

Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-06

Updated May 24, 2024 • 1

Holarissun/REPROD_dpo_helpfulhelpful_gpt3_subset-1_modelgemma2b_maxsteps10000_bz8_lr1e-05

Updated May 24, 2024 • 1 • 1

Holarissun/REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr1e-05

Updated May 24, 2024 • 1