Selecting Diverse SFT Traces Improves Post-RL Generalization Paper • 2609.33780 • Published Sep 27 • 38
Diluner/gpt54-mini-sequential-qwen3-4b-sft-s2-textcraft-20260920 Text Generation • 4B • Updated Sep 21 • 74
Diluner/gpt54-mini-sequential-qwen3-4b-sft-s2-textcraft-20260920 Text Generation • 4B • Updated Sep 21 • 74
Diluner/gpt54-mini-sequential-qwen3-4b-sft-s1-babyai-20260920 Text Generation • 4B • Updated Sep 21 • 32
Diluner/gpt54-mini-sequential-qwen3-4b-sft-s1-babyai-20260920 Text Generation • 4B • Updated Sep 21 • 32
Diluner/gpt54-mini-sequential-qwen3-4b-rose-s2-textcraft-20260920 Text Generation • 4B • Updated Sep 21 • 55
Diluner/gpt54-mini-sequential-qwen3-4b-rose-s2-textcraft-20260920 Text Generation • 4B • Updated Sep 21 • 55
Diluner/gpt54-mini-sequential-qwen3-4b-rose-s1-babyai-20260920 Text Generation • 4B • Updated Sep 21 • 75
Diluner/gpt54-mini-sequential-qwen3-4b-rose-s1-babyai-20260920 Text Generation • 4B • Updated Sep 21 • 75
Diluner/gpt54-mini-sequential-qwen3-1.7b-sft-s2-textcraft-20260920 Text Generation • 2B • Updated Sep 21 • 47
Diluner/gpt54-mini-sequential-qwen3-1.7b-sft-s2-textcraft-20260920 Text Generation • 2B • Updated Sep 21 • 47
Diluner/gpt54-mini-sequential-qwen3-1.7b-sft-s1-babyai-20260920 Text Generation • 2B • Updated Sep 21 • 34
Diluner/gpt54-mini-sequential-qwen3-1.7b-sft-s1-babyai-20260920 Text Generation • 2B • Updated Sep 21 • 34
Diluner/gpt54-mini-sequential-qwen3-1.7b-rose-s2-textcraft-20260920 Text Generation • 2B • Updated Sep 21 • 52
Diluner/gpt54-mini-sequential-qwen3-1.7b-rose-s2-textcraft-20260920 Text Generation • 2B • Updated Sep 21 • 52
Diluner/gpt54-mini-sequential-qwen3-1.7b-rose-s1-babyai-20260920 Text Generation • 2B • Updated Sep 21 • 47
Diluner/gpt54-mini-sequential-qwen3-1.7b-rose-s1-babyai-20260920 Text Generation • 2B • Updated Sep 21 • 47
Diluner/gpt54-mini-standalone-qwen3-4b-rose-textcraft-20260920 Text Generation • 4B • Updated Sep 21 • 61