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 about 7 hours ago

iaa01/qwen3-4b-elicit-pos-ckpt56

published a model about 7 hours ago

iaa01/qwen3-4b-elicit-pos-ckpt56

updated a model 13 days ago

iaa01/qwen3-1.7b-elicit-pos-ck40

View all activity

Organizations

Papers 1

arxiv:2502.04313

models 11

iaa01/qwen3-4b-elicit-pos-ckpt56

4B • Updated about 7 hours ago

iaa01/qwen3-1.7b-elicit-pos-ck40

2B • Updated 13 days ago • 83

iaa01/qwen3-4b-elicit-pos-ckpt72

4B • Updated 14 days ago • 336

iaa01/qwen3-4b-elicit-pos

4B • Updated 16 days ago • 32

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

8B • Updated Nov 28, 2025

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

8B • Updated Nov 28, 2025

iaa01/llama-8b-grpo-kl

8B • Updated Nov 28, 2025

iaa01/llama-8b-merge-alpha08-freq10

8B • Updated Nov 28, 2025

iaa01/llama-8b-merge-alpha05-freq10

8B • Updated Nov 28, 2025

iaa01/qwen3-1.7b-sft-grpo

2B • Updated May 20, 2025 • 1

datasets 0

None public yet