Kyle

kylemartineziah

4 4

·

AI & ML interests

Into NLP, diffusion models and AI agents.

Recent Activity

updated a model 3 days ago

kylemartineziah/dino-demo

published a model 3 days ago

kylemartineziah/dino-demo

upvoted a paper 3 days ago

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

View all activity

Organizations

None yet

upvoted 3 papers 3 days ago

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

Paper • 2609.36484 • Published 5 days ago • 464

AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

Paper • 2609.38288 • Published 5 days ago • 129

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

Paper • 2609.34309 • Published 6 days ago • 406

upvoted a paper about 1 month ago

PAWBench: How Far Are We from Probabilistically Aligned World Modeling?

Paper • 2608.27345 • Published Aug 27 • 77