DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation Paper • 2610.04596 • Published 8 days ago • 20
semeru/code-code-galeras-code-completion-from-docstring-3k-deduped Viewer • Updated Oct 1, 2023 • 2.93k • 71 • 3
llmfan46/gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic Text Generation • 12B • Updated Jun 21 • 176 • • 15
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives Paper • 2610.07832 • Published 5 days ago • 12
BohdanPetryshyn/codellama-7b-openapi-completion-merged Text Generation • 7B • Updated May 2, 2024 • 123 • 6
Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory Paper • 2610.02521 • Published 10 days ago • 59
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution Paper • 2610.03675 • Published 9 days ago • 29
Smaller Models, Better Rejects: Preference Distillation Scaling Paper • 2609.38987 • Published 11 days ago • 31