Scone
PulseAugur coverage of Scone — every cluster mentioning Scone across labs, papers, and developer communities, ranked by signal.
-
New ESPO method optimizes LLM prompts, boosting accuracy and reducing length
Researchers have developed ESPO (Error-Structured Prompt Optimization), a new method to improve the efficiency and accuracy of evolutionary prompt optimizers. ESPO addresses issues like prompt bloat by decomposing optim…
-
New SCoNE method improves RAG model robustness against retrieval noise
Researchers have introduced SCoNE, a novel training-free method designed to enhance the robustness of Retrieval-Augmented Generation (RAG) models against noisy retrieved information. SCoNE selectively edits context-awar…
-
New Scone model improves subject distinction in image generation
Researchers have introduced Scone, a novel method for subject-driven image generation that addresses the limitation of distinguishing between multiple subjects. Scone integrates composition and distinction capabilities,…