Zizhuo Zhang PRO

resistz's activity

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

updated a model 5 days ago

resistz/GT-GRPO_Llama-3.2-3B-Instruct_NQ-HotpotQA

Updated 5 days ago

published a model 5 days ago

resistz/GT-GRPO_Llama-3.2-3B-Instruct_NQ-HotpotQA

Updated 5 days ago

updated a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Llama-3.2-3B-Instruct-DAPO14k

4B • Updated 6 days ago • 16

updated a collection 6 days ago

Co-rewarding

Collection

Co-rewarding is a novel self-supervised RL framework that improves training stability by seeking complementary supervision from another views. • 75 items • Updated 6 days ago • 1

published a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Llama-3.2-3B-Instruct-DAPO14k

4B • Updated 6 days ago • 16

updated a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Qwen3-4B-Base-DAPO14k

4B • Updated 6 days ago • 16

published a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Qwen3-4B-Base-DAPO14k

4B • Updated 6 days ago • 16

updated a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Qwen3-8B-Base-DAPO14k

8B • Updated 6 days ago • 13

updated a collection 6 days ago

Co-rewarding

Collection

Co-rewarding is a novel self-supervised RL framework that improves training stability by seeking complementary supervision from another views. • 75 items • Updated 6 days ago • 1

published a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Qwen3-8B-Base-DAPO14k

8B • Updated 6 days ago • 13

updated a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Llama-3.2-3B-Instruct-MATH

4B • Updated 6 days ago • 20

published a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Llama-3.2-3B-Instruct-MATH

4B • Updated 6 days ago • 20

updated a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Qwen3-4B-Base-MATH

4B • Updated 6 days ago • 15

published a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Qwen3-4B-Base-MATH

4B • Updated 6 days ago • 15

updated a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Qwen3-8B-Base-MATH

8B • Updated 6 days ago • 12

published a model 6 days ago

TMLR-Group-HF/Co-rewarding-III-Qwen3-8B-Base-MATH

8B • Updated 6 days ago • 12