JeonghyeKim

beanie00's activity

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

authored a paper 6 days ago

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Paper • 2603.24472 • Published 7 days ago • 46

upvoted a paper 6 days ago

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Paper • 2603.24472 • Published 7 days ago • 46

submitted a paper to Daily Papers 6 days ago

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Paper • 2603.24472 • Published 7 days ago • 46

published a model 7 days ago

beanie00/math-SDPO-no-think-contents-Qwen3-8B-think-step-100

8B • Updated 10 days ago • 19

published a model 8 days ago

beanie00/math-GRPO-Qwen3-8B-think-step-100

8B • Updated 10 days ago • 18

updated a model 10 days ago

beanie00/math-SDPO-Qwen3-8B-think-off-step-100

8B • Updated 10 days ago • 22

updated a collection 10 days ago

self-distillation-analysis

Collection

8 items • Updated 7 days ago

published a model 10 days ago

beanie00/math-SDPO-Qwen3-8B-think-off-step-100

8B • Updated 10 days ago • 22

updated a model 10 days ago

beanie00/math-GRPO-Qwen3-8B-think-off-step-100

8B • Updated 10 days ago • 21

published a model 10 days ago

beanie00/math-GRPO-Qwen3-8B-think-off-step-100

8B • Updated 10 days ago • 21

updated a model 10 days ago

beanie00/math-GRPO-DeepSeek-Distill-7B-step-100

8B • Updated 10 days ago • 18

updated a collection 10 days ago

self-distillation-analysis

Collection

8 items • Updated 7 days ago

published a model 10 days ago

beanie00/math-GRPO-DeepSeek-Distill-7B-step-100

8B • Updated 10 days ago • 18

updated a model 10 days ago

beanie00/math-SDPO-no-think-contents-DeepSeek-Distill-7B-step-100

8B • Updated 10 days ago • 16

updated a collection 10 days ago

self-distillation-analysis

Collection

8 items • Updated 7 days ago

published a model 10 days ago

beanie00/math-SDPO-no-think-contents-DeepSeek-Distill-7B-step-100

8B • Updated 10 days ago • 16

updated a model 10 days ago

beanie00/math-SDPO-DeepSeek-Distill-7B-step-100

8B • Updated 10 days ago • 16

published a model 10 days ago

beanie00/math-SDPO-DeepSeek-Distill-7B-step-100

8B • Updated 10 days ago • 16