cs.IR
PulseAugur coverage of cs.IR — every cluster mentioning cs.IR across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New research proposes efficient context management for AI research agents
A new research paper introduces marginal value estimation as a method to improve the efficiency of deep research agents. These agents, used for complex, open-ended tasks, often struggle with rapidly growing context wind…
-
New Lakehouse Method Enhances Vector Search with File Pruning
Researchers have developed a novel method for integrating approximate nearest-neighbor (ANN) search with structured data filtering within an open lakehouse table format, specifically Apache Iceberg over Parquet. This ap…
-
New research establishes near-optimal dimension lower bounds for single-vector embeddings
Researchers have developed a new method to establish near-optimal dimension lower bounds for single-vector embeddings used in maximum inner product similarity. This work addresses a gap in previous research by providing…
-
New RAMP method boosts ad prediction accuracy with limited user data
Researchers have developed a new method called RAMP (Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment Pathways) to improve the accuracy of click-through rate (CTR) and c…
-
New TRUST framework improves temporal session-based recommendations
Researchers have developed a new framework called TRUST for temporal session-based recommendation systems. Unlike previous methods that used absolute time intervals, TRUST calibrates each interval relative to the specif…
-
New NNN decoding method enhances information retrieval beyond dense retrieval
Researchers have introduced Non-Negative Elastic Net (NNN) decoding as a novel approach to information retrieval, moving beyond the standard inner-product scoring of dense retrieval methods. This new technique treats re…