linearizable's Scour Feed Today

HistoRAG: Embedding Historical Methodology in Retrieval-Augmented Generation Through Critical Technical Practice

arxiv.org·

IUU+DB: Tracking Illegal, Unreported, and Unregulated Fishing, Seafood Fraud, and Labor Abuse through LLM-driven Information Extraction

arxiv.org·

On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies

arxiv.org·

RSRank: Learning Relevance from Representational Shifts

arxiv.org·

Non-negative Elastic Net Decoding for Information Retrieval

arxiv.org·

Temporal Preference Optimization for Unsupervised Retrieval

arxiv.org·

Designing Recommendation Exposure and Favorite Lists: A Field Experiment in a Spot-Work Platform

arxiv.org·

Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search

arxiv.org·

Do Generative Recommenders Deepen the Information Cocoon? A Closed-Loop Simulation with LLM-powered User Simulators

aws.amazon.com·

Improve query performance with EXPLAIN plans in Amazon Aurora DSQL

percona.com·

Extending pt-archiver with a Partition-Aware Plug-in for Fast Retention Policy Enforcement

arxiv.org·

Transfer Learning for FHIR Questionnaire Terminology Binding

arxiv.org·

MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA

arxiv.org·

Directory-Aware Query and Maintenance in Vector Databases

arxiv.org·

RL-Index: Reinforcement Learning for Retrieval Index Reasoning

arxiv.org·

Filtered ANN as a Phase Transition: When Selectivity-Estimation Error Causes Plan Regret

arxiv.org·

S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents

arxiv.org·

Security updates for Wednesday

Understanding and Debugging Failures in N-Gram-Based Generative Retrieval

HistoRAG: Embedding Historical Methodology in Retrieval-Augmented Generation Through Critical Technical Practice

IUU+DB: Tracking Illegal, Unreported, and Unregulated Fishing, Seafood Fraud, and Labor Abuse through LLM-driven Information Extraction

On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies

RSRank: Learning Relevance from Representational Shifts

Non-negative Elastic Net Decoding for Information Retrieval

Temporal Preference Optimization for Unsupervised Retrieval

Designing Recommendation Exposure and Favorite Lists: A Field Experiment in a Spot-Work Platform

Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search

Do Generative Recommenders Deepen the Information Cocoon? A Closed-Loop Simulation with LLM-powered User Simulators

Improve query performance with EXPLAIN plans in Amazon Aurora DSQL

Extending pt-archiver with a Partition-Aware Plug-in for Fast Retention Policy Enforcement

Transfer Learning for FHIR Questionnaire Terminology Binding

MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA

Directory-Aware Query and Maintenance in Vector Databases

RL-Index: Reinforcement Learning for Retrieval Index Reasoning

Filtered ANN as a Phase Transition: When Selectivity-Estimation Error Causes Plan Regret

S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents

Understanding the Behaviors of Environment-aware Information Retrieval