Iris L. Taylor

Hugodengland

4

·

AI & ML interests

ML enthusiast | open-source lover

Recent Activity

upvoted a paper 26 days ago

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

upvoted a paper about 1 month ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

upvoted a paper about 1 month ago

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

View all activity

Organizations

None yet

upvoted a paper 26 days ago

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

Paper • 2610.06647 • Published Oct 5 • 35

upvoted 2 papers about 1 month ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published Sep 29 • 168

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published Sep 30 • 150

upvoted a paper about 2 months ago

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

Paper • 2609.10715 • Published Sep 9 • 167