GenTUS reformulates table union search as constrained generative retrieval over semantic table identifiers, achieving top retrieval quality on seven benchmarks with lower latency and storage costs.
hub Canonical reference
In41st IEEE International Conference on Data Engineering, ICDE 2025, Hong Kong, May 19-23
Canonical reference. 100% of citing Pith papers cite this work as background.
23
Pith papers citing it
2
external citations · external index
Background
100% of classified citations
hub tools
citation-role summary
background 8
citation-polarity summary
roles
background 6polarities
background 6representative citing papers
Releases a large real-world dataset of dirty postal addresses with ground truth for benchmarking data cleaning algorithms.
The bi-channel paradigm separates database networking into a high-performance UDP data path and a TCP control path to reduce kernel overhead while preserving reliability on fast cloud networks.
A machine-learned router predicts per-query recall for filtered ANN methods and selects the recall-QPS optimal one, outperforming fixed baselines on five unseen datasets.
PerfEvolve equips LLM agents with executable skills from expert methods to enable dynamic, version-consistent, workload-specific tuning in PostgreSQL, outperforming documentation baselines by up to 35.2% on TPC-C and TPC-H.
FliX flips the indexing paradigm by mapping GPU compute to data buckets and using batch binary search, delivering up to 6.5x lower query latency and 4x better throughput per memory than leading GPU B-trees and LSM-trees.
A survey of 55 agentic VA systems proposes a co-evolutionary framework defining four agent roles (PLANNER, CREATOR, REVIEWER, CONTEXT MANAGER) mapped to visual analytics pipeline stages along with design guidelines.
NL2SQLBench is a new modular benchmarking framework that evaluates LLM NL2SQL methods across three core modules on existing datasets, exposing large accuracy gaps and computational inefficiency.
Learned static functions combine per-key ML-predicted prefix codes with classic static function storage to compress static key-value mappings beyond zero-order entropy limits.
Spectral aggregate tests prune up to 51% of candidates in CSM but leave enumeration intermediates unchanged beyond initial bindings across tested workloads.
HKVM-RAG uses key-value-separated hypergraphs to organize LLM evidence tuples into answer-path hyperedges, yielding F1 gains over KG-PPR on two multi-hop QA benchmarks and further gains when combined with dense retrievers.
SynLearner lets LLMs improve synthetic data generation on later tasks in a stream by learning reusable patterns and balancing quality with diversity from feedback on earlier tasks.
StructuredSemanticSearch uses table discovery operators and orientation-aware integration on model-card tables to improve evidence coverage and diversity in model recommendation queries over a semantic baseline.
The paper defines a bounded reference architecture for LLM-orchestrated hybrid retrieval in dataset search using BM25, dense embeddings, reciprocal rank fusion, and metadata augmentation with pseudo-queries.
A modular systemisation plus practitioner objectives framework organises DP graph release methods and yields an open social-network benchmark of SotA edge- and node-DP algorithms.
chart-plot is an agentic harness using style-aware code generation from venue figures, a LaTeX-aware render-and-revise loop, and structured edit handles to produce top-venue-ready academic charts.
HRNN combines a navigation graph, ranked KNN graph, and reverse-neighbor lists with proxy-based candidate generation and materialized kNN-radii to achieve up to 10x higher throughput for approximate RkNN on datasets up to 10M vectors.
AgentReputation proposes separating AI agent task execution, reputation management, and secure record-keeping into distinct layers, with context-specific reputation cards and a risk-based policy engine to handle verification in decentralized settings.
MegaTrain enables reliable full-precision training of up to 120B parameter LLMs on one H200 GPU with 1.5TB host memory via host-memory streaming, pipelined double-buffered execution, and stateless layer templates, achieving 1.84x throughput over DeepSpeed ZeRO-3 for 14B models.
A survey of LLMs for graph computation introduces a role-based taxonomy of executors versus planners and concludes that current models suit simple small-scale tasks but remain unreliable for large-scale exact computation.
AnnoRetrieve induces annotation schemas from documents and answers queries via structured retrieval, reporting F1 0.87 with lower LLM cost than graph/LLM baselines but higher cost than QUEST and vector search.
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.
A self-supervised GNN model on cloud logs flags suspicious events with far fewer alerts than rule-based baselines but cannot estimate missed threats.
citing papers explorer
-
A Case for Agentic Tuning: From Documentation to Action in PostgreSQL
PerfEvolve equips LLM agents with executable skills from expert methods to enable dynamic, version-consistent, workload-specific tuning in PostgreSQL, outperforming documentation baselines by up to 35.2% on TPC-C and TPC-H.
-
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.