Feng

Yunzhen's activity

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

upvoted 2 papers about 2 months ago

The Art of Scaling Reinforcement Learning Compute for LLMs

Paper • 2510.13786 • Published Oct 15 • 30

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting

Paper • 2510.08696 • Published Oct 9 • 14

commented a paper about 2 months ago

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting

Paper • 2510.08696 • Published Oct 9 • 14 •

3

upvoted a paper 2 months ago

Rethinking Thinking Tokens: LLMs as Improvement Operators

Paper • 2510.01123 • Published Oct 1 • 5

commented a paper 2 months ago

Rethinking Thinking Tokens: LLMs as Improvement Operators

Paper • 2510.01123 • Published Oct 1 • 5 •

2

upvoted a paper 3 months ago

Soft Tokens, Hard Truths

Paper • 2509.19170 • Published Sep 23 • 15

authored a paper 3 months ago

What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

Paper • 2509.19284 • Published Sep 23 • 22

upvoted a paper 3 months ago

What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

Paper • 2509.19284 • Published Sep 23 • 22

commented a paper 3 months ago

What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

Paper • 2509.19284 • Published Sep 23 • 22 •

2

upvoted 2 papers 10 months ago

DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails

Paper • 2502.05163 • Published Feb 7 • 23

PILAF: Optimal Human Preference Sampling for Reward Modeling

Paper • 2502.04270 • Published Feb 6 • 11

commented a paper 10 months ago

PILAF: Optimal Human Preference Sampling for Reward Modeling

Paper • 2502.04270 • Published Feb 6 • 11 •

2

upvoted a paper almost 2 years ago

Teaching Large Language Models to Reason with Reinforcement Learning

Paper • 2403.04642 • Published Mar 7, 2024 • 50

authored a paper almost 2 years ago

A Tale of Tails: Model Collapse as a Change of Scaling Laws

Paper • 2402.07043 • Published Feb 10, 2024 • 16