Zihan Liu

zihanliu's activity

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

New activity in nvidia/AceReason-1.1-SFT 15 days ago

Add task_categories and library_name to metadata

#1 opened 16 days ago by

nielsr

updated a collection 16 days ago

AceReason

Collection

Math and Code reasoning model trained through reinforcement learning (RL) • 7 items • Updated about 18 hours ago • 13

upvoted a paper 16 days ago

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy

Paper • 2506.13284 • Published 17 days ago • 23

commented a paper 16 days ago

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy

Paper • 2506.13284 • Published 17 days ago • 23 •

4

liked a dataset 16 days ago

nvidia/AceReason-Math

Viewer • Updated 15 days ago • 49.6k • 1.66k • 17

authored 2 papers 16 days ago

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models

Paper • 2504.06214 • Published Apr 8

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Paper • 2505.16400 • Published May 22 • 31

liked a dataset 16 days ago

nvidia/AceReason-1.1-SFT

Viewer • Updated 15 days ago • 3.96M • 2.95k • 60

liked a model 16 days ago

nvidia/AceReason-Nemotron-1.1-7B

Text Generation • 8B • Updated 16 days ago • 21.4k • • 49

published a model 16 days ago

nvidia/AceReason-Nemotron-1.1-7B

Text Generation • 8B • Updated 16 days ago • 21.4k • • 49

published a dataset 16 days ago

nvidia/AceReason-1.1-SFT

Viewer • Updated 15 days ago • 3.96M • 2.95k • 60

updated a model 16 days ago

nvidia/AceReason-Nemotron-1.1-7B

Text Generation • 8B • Updated 16 days ago • 21.4k • • 49

updated a dataset 16 days ago

nvidia/AceReason-1.1-SFT

Viewer • Updated 15 days ago • 3.96M • 2.95k • 60

upvoted a collection 16 days ago

AceReason

Collection

Math and Code reasoning model trained through reinforcement learning (RL) • 7 items • Updated about 18 hours ago • 13

updated a collection 16 days ago

AceReason

Collection

Math and Code reasoning model trained through reinforcement learning (RL) • 7 items • Updated about 18 hours ago • 13

upvoted a paper 16 days ago

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Paper • 2505.16400 • Published May 22 • 31

liked 2 models about 1 month ago

nvidia/AceReason-Nemotron-7B

Text Generation • 8B • Updated 16 days ago • 38.7k • • 18

nvidia/AceReason-Nemotron-14B

Text Generation • 15B • Updated 15 days ago • 46.4k • • 84

upvoted a collection 2 months ago

AceMath-RL

Collection

Math reasoning models trained through reinforcement learning (RL) • 1 item • Updated about 18 hours ago • 4