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.
Woicik, Abdurrahman Ghanem, Marco Serafini, Ashraf Aboulnaga, and Michael Stonebraker
11 Pith papers cite this work, alongside 42 external citations. Polarity classification is still indexing.
11
Pith papers citing it
42
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 11roles
background 1polarities
background 1representative citing papers
Repetition rate mismatch between small-scale proxies and target budgets is the main reason data mixture experiments do not scale; a subsampling procedure that equalizes repetition rates recovers optimal mixtures from 1/16-scale experiments.
GRAB-ANNS is a new GPU graph index that achieves up to 240x higher hybrid search throughput via bucket layouts and hybrid intra/inter-bucket edges.
IGSTGNN adds incident-context spatial fusion and temporal impact decay modules to model how events alter traffic patterns, achieving state-of-the-art results on a new time-aligned incident-traffic dataset.
Unconstrained LLM rewriting of RDF dataset metadata maximizes retrieval gains but is least faithful; profile-grounded rewriting best balances effectiveness and grounding.
An open-source tool extracts freeway networks from OSM into station-referenced format with corridor querying and validation, tested on 359.6 miles in Orange County at ~41 seconds per mile.
SPA trains LLMs via plan-aware RL with adaptive reward shaping and self-improvement on slowdowns to produce faster query rewrites than rule-based or standard LLM methods on IID and OOD workloads.
SOLANET is a distributed GPU toolkit for neighbor graph construction that reports 11X speedup on 512 APUs for 1B points and 6.9X for 2B points.
Maximizing reachability in k-path temporal graphs via budgeted shifts is FPT when parameterized by k and b together or by k alone, but intractable in most other parameterizations with matching XP algorithms.
A vision for a cloud SmartNIC that hides Parquet decoding costs by offloading parsing and filters directly on the network datapath, backed by DuckDB performance estimates.
MF-CKGE separates temporal old and new knowledge into distinct embedding spaces with semantic decoupling and adaptive importance scoring to improve continual link prediction.
citing papers explorer
-
Generative Retrieval for Table Union Search
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.
-
Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them
Repetition rate mismatch between small-scale proxies and target budgets is the main reason data mixture experiments do not scale; a subsampling procedure that equalizes repetition rates recovers optimal mixtures from 1/16-scale experiments.
-
GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing
GRAB-ANNS is a new GPU graph index that achieves up to 240x higher hybrid search throughput via bucket layouts and hybrid intra/inter-bucket edges.
-
Incident-Guided Spatiotemporal Traffic Forecasting
IGSTGNN adds incident-context spatial fusion and temporal impact decay modules to model how events alter traffic patterns, achieving state-of-the-art results on a new time-aligned incident-traffic dataset.
-
Faithful or Findable? Evaluating LLM-Generated Metadata for RDF Dataset Search
Unconstrained LLM rewriting of RDF dataset metadata maximizes retrieval gains but is least faithful; profile-grounded rewriting best balances effectiveness and grounding.
-
An Open-Source Tool for Reproducible Freeway Network Extraction from OpenStreetMap
An open-source tool extracts freeway networks from OSM into station-referenced format with corridor querying and validation, tested on 359.6 miles in Orange County at ~41 seconds per mile.
-
SPA: A SQL-Plan-Aware Reinforcement Learning Framework for Query Rewriting with LLMs
SPA trains LLMs via plan-aware RL with adaptive reward shaping and self-improvement on slowdowns to produce faster query rewrites than rule-based or standard LLM methods on IID and OOD workloads.
-
SOLANET: Distributed Neighbor Graph Construction on GPU-Accelerated Systems
SOLANET is a distributed GPU toolkit for neighbor graph construction that reports 11X speedup on 512 APUs for 1B points and 6.9X for 2B points.
-
Maximizing Reachability via Shifting of Temporal Paths
Maximizing reachability in k-path temporal graphs via budgeted shifts is FPT when parameterized by k and b together or by k alone, but intractable in most other parameterizations with matching XP algorithms.
-
Should I Hide My Duck in the Lake?
A vision for a cloud SmartNIC that hides Parquet decoding costs by offloading parsing and filters directly on the network datapath, backed by DuckDB performance estimates.
-
Multi-Faceted Continual Knowledge Graph Embedding for Semantic-Aware Link Prediction
MF-CKGE separates temporal old and new knowledge into distinct embedding spaces with semantic decoupling and adaptive importance scoring to improve continual link prediction.