Selecting Diverse SFT Traces Improves Post-RL Generalization Paper • 2609.33780 • Published 6 days ago • 37
Diluner/gpt54-mini-sequential-qwen3-4b-sft-s2-textcraft-20260920 Text Generation • 4B • Updated 12 days ago • 262
Diluner/gpt54-mini-sequential-qwen3-4b-sft-s2-textcraft-20260920 Text Generation • 4B • Updated 12 days ago • 262
Diluner/gpt54-mini-sequential-qwen3-4b-sft-s1-babyai-20260920 Text Generation • 4B • Updated 12 days ago • 247
Diluner/gpt54-mini-sequential-qwen3-4b-sft-s1-babyai-20260920 Text Generation • 4B • Updated 12 days ago • 247
Diluner/gpt54-mini-sequential-qwen3-4b-rose-s2-textcraft-20260920 Text Generation • 4B • Updated 12 days ago • 253
Diluner/gpt54-mini-sequential-qwen3-4b-rose-s2-textcraft-20260920 Text Generation • 4B • Updated 12 days ago • 253
Diluner/gpt54-mini-sequential-qwen3-4b-rose-s1-babyai-20260920 Text Generation • 4B • Updated 12 days ago • 264
Diluner/gpt54-mini-sequential-qwen3-4b-rose-s1-babyai-20260920 Text Generation • 4B • Updated 12 days ago • 264
Diluner/gpt54-mini-sequential-qwen3-1.7b-sft-s2-textcraft-20260920 Text Generation • 2B • Updated 12 days ago • 255
Diluner/gpt54-mini-sequential-qwen3-1.7b-sft-s2-textcraft-20260920 Text Generation • 2B • Updated 12 days ago • 255
Diluner/gpt54-mini-sequential-qwen3-1.7b-sft-s1-babyai-20260920 Text Generation • 2B • Updated 12 days ago • 247
Diluner/gpt54-mini-sequential-qwen3-1.7b-sft-s1-babyai-20260920 Text Generation • 2B • Updated 12 days ago • 247
Diluner/gpt54-mini-sequential-qwen3-1.7b-rose-s2-textcraft-20260920 Text Generation • 2B • Updated 12 days ago • 261
Diluner/gpt54-mini-sequential-qwen3-1.7b-rose-s2-textcraft-20260920 Text Generation • 2B • Updated 12 days ago • 261
Diluner/gpt54-mini-sequential-qwen3-1.7b-rose-s1-babyai-20260920 Text Generation • 2B • Updated 12 days ago • 255
Diluner/gpt54-mini-sequential-qwen3-1.7b-rose-s1-babyai-20260920 Text Generation • 2B • Updated 12 days ago • 255
Diluner/gpt54-mini-standalone-qwen3-4b-rose-textcraft-20260920 Text Generation • 4B • Updated 12 days ago • 249
Diluner/gpt54-mini-standalone-qwen3-4b-rose-textcraft-20260920 Text Generation • 4B • Updated 12 days ago • 249