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 23 hours ago

iaa01/qwen3-4b-elicit-pos

published a model about 23 hours ago

iaa01/qwen3-4b-elicit-pos

updated a model about 1 month ago

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

View all activity

Organizations

Papers 1

arxiv:2502.04313

models 8

iaa01/qwen3-4b-elicit-pos

4B • Updated about 23 hours ago • 26

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

8B • Updated Nov 28, 2025 • 3

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

8B • Updated Nov 28, 2025 • 3

iaa01/llama-8b-grpo-kl

8B • Updated Nov 28, 2025 • 2

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

8B • Updated Nov 28, 2025 • 3

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

8B • Updated Nov 28, 2025 • 4

iaa01/qwen3-1.7b-sft-grpo

2B • Updated May 20, 2025 • 5

iaa01/qwen-2.5-3b-multi_step

3B • Updated Mar 20, 2025 • 8

datasets 0

None public yet