Budgeted ultrasound evidence selection with Qwen3-VL and GRPO: audited experiments, dataset suitability, and transparent development results.
-
Updated
Oct 12, 2026 - Python
Budgeted ultrasound evidence selection with Qwen3-VL and GRPO: audited experiments, dataset suitability, and transparent development results.
CEBRA: State-Aware Chunk Reduction for Efficient Context Construction in Multi-Hop RAG
CPU reproducibility artifacts for Complex Utility, Simple Calibration (WSDM 2027 Findings)
CognitiveRAG backend for OpenClaw: multi-layer memory, evidence selection, and explainable context construction.
Clean research implementation of Bactrainus for modular multi-hop question answering.
To associate your repository with the evidence-selection topic, visit your repo's landing page and select "manage topics."