arxiv:2502.04313
Ilze Amanda Auzina
iaa01
AI & ML interests
RL Post-Training | Reasoning and Exploration | Open-ended
Organizations
models 11
iaa01/CIA-1.7B
2B • Updated • 13 • 1
iaa01/CIA-4B
4B • Updated • 34 • 3
iaa01/qwen3-4b-elicit-pos-ckpt72
4B • Updated
iaa01/qwen3-4b-elicit-pos
4B • Updated • 3
iaa01/llama-8b-merge-alpha1-freq10
8B • Updated
iaa01/llama-8b-grpo-no-kl
8B • Updated • 2
iaa01/llama-8b-grpo-kl
8B • Updated • 2
iaa01/llama-8b-merge-alpha08-freq10
8B • Updated • 1
iaa01/llama-8b-merge-alpha05-freq10
8B • Updated
iaa01/qwen3-1.7b-sft-grpo
2B • Updated
datasets 0
None public yet