arxiv:2505.13291
🔄 In a Training Loop
Michał Wiliński
MWilinski
AI & ML interests
Machine Learning, Reinforcement Learning
Recent Activity
updated a model 5 days ago
MWilinski/qwen2.5-3b-gail updated a model 6 days ago
MWilinski/qwen2.5-3b-gail-helpsteer3 updated a model 6 days ago
MWilinski/qwen2.5-3b-sft-helpsteer3Organizations
models 12
MWilinski/qwen2.5-3b-gail-helpsteer3
Updated
MWilinski/qwen2.5-3b-sft-helpsteer3
Updated
MWilinski/qwen2.5-3b-gail-pirate
Updated
MWilinski/qwen2.5-3b-sft-pirate
Updated
MWilinski/qwen2.5-3b-gail-frozen
Updated
MWilinski/qwen2.5-3b-gail-unfrozen
Updated
MWilinski/qwen2.5-3b-dpo-irl
Updated
MWilinski/qwen2.5-3b-sft-irl
Updated
MWilinski/qwen2.5-3b-gail
Updated
MWilinski/dro-v-qwen3-1.7b-paperlike
Updated
datasets 19
MWilinski/rlhf-irl-pirate-expert
Viewer • Updated • 6k • 9
MWilinski/rlhf-irl
Viewer • Updated • 14k • 40
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-oss-20b-diverse-openrouter
Viewer • Updated • 200 • 53
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-oss-20b-diverse-openrouter
Viewer • Updated • 200 • 80
MWilinski/hh-rlhf-irl
Viewer • Updated • 10k • 4
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-policy
Viewer • Updated • 2k • 20
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-policy
Viewer • Updated • 2k • 24
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-child
Viewer • Updated • 1.5k • 25
MWilinski/hh-rlhf-helpful-base-rollouts-gpt-5.1-adult
Viewer • Updated • 1.5k • 15
MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-adult
Viewer • Updated • 1.5k • 26