SplatRAG 3, a retrieval system using local Gaussian-splat memory, achieved a SciFact (BEIR test, 300 claims, k=10) recall@10 of 0.8804 and nDCG@10 of 0.7624 on a store that also contains 5,000 Urban D…
A new experiment by Dylan Castillo comparing Matryoshka Representation Learning (MRL) and Principal Component Analysis (PCA) for reducing embedding dimensions found that both methods preserve retrieva…
Researchers introduced RAGuard, a layered defense framework for retrieval-augmented generation (RAG) systems against data poisoning, achieving a 0.000% attack success rate in all defended configuratio…
A developer built raven-retrieval, an open-source framework that benchmarks 19 retrieval pipelines on BEIR datasets with Bonferroni-corrected significance tests. The key finding is that top pipelines …
Researchers from Apple propose amortized maximum inner product search (MIPS) using neural networks to predict optimal keys, significantly improving efficiency on the BEIR benchmark. The method trains …
Recent AI research introduces RL-driven agentic optimization using dense token-level supervision and progress advantage signals to stabilize training. PhysiFormer injects 3D geometric reasoning into d…
A developer identifies the 'index distribution problem' as a fundamental flaw in agent-based search systems, where retrieval indexes encode past relevance judgments rather than semantic truth, causing…
Researchers have developed RICE-PO, a policy optimization framework that converts retrieval interactions into localized learning signals for training reasoning-based retrieval agents. The framework ad…