Ilze Amanda Auzina's picture

3

Ilze Amanda Auzina

iaa01

·

https://ilzeamandaa.github.io/

AI & ML interests

RL Post-Training | Reasoning and Exploration | Open-ended

Recent Activity

updated a model 13 days ago

iaa01/llama-8b-merge-alpha1-freq10

published a model 13 days ago

iaa01/llama-8b-merge-alpha1-freq10

updated a model 13 days ago

iaa01/llama-8b-grpo-no-kl

View all activity

Organizations

upvoted 3 papers 10 months ago

Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs

Paper • 2502.19413 • Published Feb 26 • 21

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

Paper • 2502.19414 • Published Feb 26 • 20

Great Models Think Alike and this Undermines AI Oversight

Paper • 2502.04313 • Published Feb 6 • 33