Kelvin Ito

itokelvin00

4

·

kofinowak

AI & ML interests

Fine-tuning models for fun and profit.

Recent Activity

upvoted a paper 3 days ago

REMORY: Learning Residual Memory for Context Compaction

upvoted a paper 16 days ago

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

upvoted a paper 16 days ago

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

View all activity

Organizations

None yet

upvoted a paper 3 days ago

REMORY: Learning Residual Memory for Context Compaction

Paper • 2610.11287 • Published 12 days ago • 166

upvoted 2 papers 16 days ago

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

Paper • 2609.36484 • Published 21 days ago • 548

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

Paper • 2609.39102 • Published 20 days ago • 643

upvoted a paper 19 days ago

MaLiang-Harness: A Programmable Path to Image and Video Generation

Paper • 2609.34309 • Published 22 days ago • 368