Youngrok Park PRO

yr-park's activity

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

upvoted a paper 3 days ago

PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

Paper • 2608.30597 • Published 17 days ago • 26

upvoted a paper 8 days ago

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published 9 days ago • 94

upvoted a paper 14 days ago

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published 15 days ago • 75

updated a model 14 days ago

yr-park/reverse_distill_assets

Updated 14 days ago • 5

New activity in raymin0223/reverse_distill_assets about 2 months ago

Remove obsolete SFT100 experiment checkpoints: 260728-rcd-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2-sftstep100-260731

1

#2 opened about 2 months ago by

yr-park

Remove obsolete SFT100 experiment checkpoints: 260728-grpo-knights_knaves-q3-1p7b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2-sftstep100-260731

1

#1 opened about 2 months ago by

yr-park

Remove obsolete SFT100 experiment checkpoints: 260728-rcd-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2-sftstep100-260731

1

#2 opened about 2 months ago by

yr-park

Remove obsolete SFT100 experiment checkpoints: 260728-grpo-knights_knaves-q3-1p7b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2-sftstep100-260731

1

#1 opened about 2 months ago by

yr-park

updated a model about 2 months ago

yr-park/reverse_distill_assets

Updated 14 days ago • 5

upvoted a paper 2 months ago

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

Paper • 2607.04412 • Published Jul 5 • 36

updated a model 2 months ago

yr-park/reverse_distill_assets

Updated 14 days ago • 5