Peng Dengyun

AnsOfTi's activity

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

updated 3 models about 1 month ago

LARG/DRSAF-Qwen3-8B-distill

8B • Updated Nov 17 • 4

LARG/DRSAF-Qwen2.5-7B-distill

8B • Updated Nov 17 • 8

LARG/DRSAF-Qwen2.5-7B-distill-extreme

8B • Updated Nov 17 • 3

upvoted 2 papers 2 months ago

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

Paper • 2510.15110 • Published Oct 16 • 15

AutoPR: Let's Automate Your Academic Promotion!

Paper • 2510.09558 • Published Oct 10 • 51

upvoted a paper 6 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2 • 187