JeonghyeKim

beanie00's activity

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

authored a paper 18 days ago

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

Paper • 2603.24472 • Published 19 days ago • 53

upvoted a paper 19 days ago

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

Paper • 2603.24472 • Published 19 days ago • 53

submitted a paper to Daily Papers 19 days ago

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

Paper • 2603.24472 • Published 19 days ago • 53

published a model 19 days ago

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

8B • Updated 23 days ago • 38

published a model 21 days ago

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

8B • Updated 23 days ago • 82

updated a model 23 days ago

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

8B • Updated 23 days ago • 32

updated a collection 23 days ago

self-distillation-analysis

Collection

8 items • Updated 19 days ago

published a model 23 days ago

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

8B • Updated 23 days ago • 32

updated a model 23 days ago

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

8B • Updated 23 days ago • 42

published a model 23 days ago

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

8B • Updated 23 days ago • 42

updated a model 23 days ago

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

8B • Updated 23 days ago • 30

updated a collection 23 days ago

self-distillation-analysis

Collection

8 items • Updated 19 days ago

published a model 23 days ago

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

8B • Updated 23 days ago • 30

updated a model 23 days ago

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

8B • Updated 23 days ago • 31

updated a collection 23 days ago

self-distillation-analysis

Collection

8 items • Updated 19 days ago

published a model 23 days ago

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

8B • Updated 23 days ago • 31

updated a model 23 days ago

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

8B • Updated 23 days ago • 30

published a model 23 days ago

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

8B • Updated 23 days ago • 30