$RTRV retrieval

Latest papers

1. Latent Compaction with Test-Time Training cs.CL · 14 Oct · 2 hits

   …compared with 40.0% for KVZip+. The method also transfers across model scales and families, with retrieval gains on both Qwen3 and MiniCPM5. These results show that treating the KV cache as a neural network…

2. ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models cs.CL · 14 Oct · 1 hit

   …method, to the best of our knowledge, to leverage HLA recurrent states for position-specific context retrieval during drafting. ReaDy equips each draft position with a learned query to retrieve supplementary…

3. Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks cs.CL · 14 Oct · 3 hits

   Retrieval-Augmented Generation (RAG) models have become almost a cornerstone of open-domain question…

4. Cascaded Retrieval with Cross-Modal Query Refinement for Efficient Visual Document Search cs.CL · 14 Oct · 4 hits

   …costs that grow with corpus size and are impractical to scale. We propose SCOUT, a cascaded two-track retrieval framework that separates retrieval performance from exhaustive search. The visual track first uses…

5. CASI: Credit Assignment via Set Intervention for Agentic Retrieval cs.AI · 14 Oct · 3 hits

   Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the resulting set.…

6. Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference cs.CL · 14 Oct · 9 hits

   …biomedical evidence to improve factual trustworthiness and reasoning accuracy. However, indiscriminate retrieval can introduce noise and latency, raising a critical retrieval-timing problem: at each reasoning…

7. Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection cs.LG · 14 Oct · 3 hits

   …(OOD) settings. In this paper, we tackle the aforementioned limitation and propose RAMSAD, a retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our…

8. HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation cs.AI · 14 Oct · 1 hit

   …Gap 2, we introduce a safety-aware medication set generation module, which integrates dual-level experience retrieval with safety-aware set decoding to produce clinically relevant, safer, and locally adaptive…