Julia Kempe

Knykny's activity

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

upvoted a paper 4 months ago

Efficient RL Training for LLMs with Experience Replay

Paper • 2604.08706 • Published Apr 9 • 23

upvoted 2 papers 7 months ago

Likelihood-Based Reward Designs for General LLM Reasoning

Paper • 2602.03979 • Published Feb 3 • 8

Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published Jan 26 • 44

upvoted 2 papers 10 months ago

Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation

Paper • 2510.21891 • Published Oct 24, 2025 • 2

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

Paper • 2510.08696 • Published Oct 9, 2025 • 15

upvoted a paper 11 months ago

Soft Tokens, Hard Truths

Paper • 2509.19170 • Published Sep 23, 2025 • 16

upvoted a paper over 1 year ago

PILAF: Optimal Human Preference Sampling for Reward Modeling

Paper • 2502.04270 • Published Feb 6, 2025 • 12

upvoted a paper almost 2 years ago

Emergent properties with repeated examples

Paper • 2410.07041 • Published Oct 9, 2024 • 8

upvoted a paper over 2 years ago

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

Paper • 2402.07043 • Published Feb 10, 2024 • 15