Shusheng Xu

xssstory's activity

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

authored 2 papers 22 days ago

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Paper • 2404.10719 • Published Apr 16, 2024 • 5

On Designing Effective RL Reward at Training Time for LLM Reasoning

Paper • 2410.15115 • Published Oct 19, 2024

liked a dataset 22 days ago

inclusionAI/AReaL-boba-Data

Preview • Updated 24 days ago • 419 • 12

updated a collection 22 days ago

AReaL-boba

Collection

4 items • Updated 22 days ago • 6

published 2 models 23 days ago

inclusionAI/AReaL-boba-SFT-32B

Updated 23 days ago • 75 • 7

inclusionAI/AReaL-boba-RL-7B

Updated 23 days ago • 164 • 4

published a dataset 23 days ago

inclusionAI/AReaL-boba-Data

Preview • Updated 24 days ago • 419 • 12

updated 2 models 23 days ago

inclusionAI/AReaL-boba-SFT-32B

Updated 23 days ago • 75 • 7

inclusionAI/AReaL-boba-RL-7B

Updated 23 days ago • 164 • 4

updated a dataset 24 days ago

inclusionAI/AReaL-boba-Data

Preview • Updated 24 days ago • 419 • 12

updated a dataset 25 days ago

inclusionAI/AReaL-RL-Data

Preview • Updated 25 days ago • 629 • 1

published a dataset about 2 months ago

inclusionAI/AReaL-RL-Data

Preview • Updated 25 days ago • 629 • 1

published 3 models about 2 months ago

inclusionAI/AReaL-1.5B-Preview-Stage-3

Updated Feb 24 • 12 • 1

inclusionAI/AReaL-1.5B-Preview-Stage-2

Updated Feb 24 • 8 • 1

inclusionAI/AReaL-1.5B-Preview-Stage-1

Updated Feb 24 • 2 • 1

updated 2 models about 2 months ago

inclusionAI/AReaL-1.5B-Preview-Stage-3

Updated Feb 24 • 12 • 1

inclusionAI/AReaL-1.5B-Preview-Stage-2

Updated Feb 24 • 8 • 1