84 papers
This paper addresses the challenges of evaluating Computer Graphics image quality by constructing a new dataset with systematic quality descriptions and proposing a retrieval-augmented, two-stream framework that significantly enhances Vision Language Models' ability to assess and explain CG quality.
This paper introduces HiFIVE, a data-management framework that addresses the NP-hard visualization-aware tile reduction problem through a two-stage triage and sparsification approach, enabling scalable, high-fidelity client-side geospatial visualization of terabyte-scale datasets while significantly reducing tile sizes.
This paper introduces K-Join, a simple parallel join algorithm that optimizes data transfer by selecting HyperCube shares as a linear combination of multiple vertex covers, achieving a load of based on a new hypergraph measure called the reduced quasi vertex-cover that matches or improves upon state-of-the-art performance.
This paper introduces EvoSchema, a comprehensive benchmark featuring a novel taxonomy of ten schema perturbation types to evaluate and enhance the robustness of text-to-SQL models against real-world database schema evolution, revealing that table-level changes significantly impact performance and demonstrating that training on diverse schema designs improves model resilience.
This paper establishes a theoretical foundation for querying multi-model databases by proposing and proving the equivalence of categorical calculus and categorical algebra, while also providing transformation rules for optimization and analyzing their expressive power and computational complexity.
The paper introduces STemDist, the first dataset distillation method designed for spatio-temporal forecasting that simultaneously compresses both spatial and temporal dimensions through a hybrid cluster-level and subset-based approach, achieving significantly faster training, reduced memory usage, and lower prediction errors compared to existing methods.
This paper introduces a novel framework for self-improving LLM agents that automatically extracts structured learnings from execution trajectories—categorizing them into strategy, recovery, and optimization tips—and injects them via adaptive memory retrieval to significantly boost task completion rates, particularly on complex scenarios.
This paper proposes a formal framework, architecture, and algorithms for constructing and incrementally maintaining materialized RDB2RDF views to enable efficient, semantically integrated access to legacy relational data within Enterprise Knowledge Graphs.
This paper presents SLER, a scalable system that combines standardized template enumeration with a learning-to-rank model to overcome the exponential search space and redundancy challenges of existing methods, successfully discovering over one million high-quality query rewrite rules for complex query plans.
This paper introduces the NP-hard Tag-specific Regret Minimization in Outdoor Advertising (TRMOA) problem, demonstrating that while standard greedy methods fail due to non-monotone and non-submodular regret models, fairness-aware greedy round-robin, randomized greedy, and local search algorithms effectively minimize regret and balance allocations using real-world datasets.
This paper proposes a novel formal framework and efficient algorithms to detect, analyze, and reformulate queries in order to extract relevant information from data sources that intentionally bias results due to conflicts of interest with users.
This paper presents and experimentally evaluates space-efficient B-tree variants optimized for memory-constrained flash-based embedded devices, demonstrating that storage-specific adaptations enable efficient on-device indexing and processing for IoT applications.
This paper introduces novel "Text-to-Big SQL" evaluation metrics to address the limitations of existing benchmarks in assessing production-level LLM agents, demonstrating that traditional Text-to-SQL metrics fail to capture critical cost, latency, and efficiency implications that arise when scaling to large datasets.
The paper introduces OMEGA, a K-generalizable learned top-K search method that leverages a base model trained on K=1 with trajectory-based features and a dynamic refinement procedure to achieve high accuracy and low latency for multi-K vector queries while significantly reducing preprocessing time compared to state-of-the-art methods.
The paper introduces KramaBench, a comprehensive benchmark featuring 104 real-world data-to-insight challenges across diverse domains, which reveals that current AI systems struggle to orchestrate end-to-end data pipelines over data lakes, achieving a maximum of only 55% accuracy despite strong performance in isolated tasks.
This paper introduces HCT-QA, a comprehensive benchmark comprising thousands of real-world and synthetic human-centric tables with natural language question-answer pairs, designed to evaluate and improve the performance of Large Language Models and Vision Language Models in querying complex tabular data.
This paper examines how the rapid advancement of AI, particularly with foundation models and unstructured data, introduces new challenges in latency, scalability, and interpretability for human-data interaction, arguing for a paradigm shift that redefines human-machine roles and integrates cognitive and perceptual principles to build more effective, human-centered analytical systems.
This paper introduces NGDBench, a comprehensive benchmark designed to evaluate neural models' ability to manage and query structured graph data across diverse domains using the full Cypher language, revealing significant current limitations in reasoning and robustness despite the models' success with unstructured text.
This paper presents O3-LSM, a novel disaggregated LSM-KVS architecture that maximizes write performance by implementing a three-layer offloading strategy—comprising dynamic memtable offloading, collaborative flush offloading, and shard-level optimization—to overcome the memory and throughput limitations of existing systems.
The paper introduces Bala-Join, an adaptive hash join framework for geo-distributed SQL databases that utilizes a Balanced Partition and Partial Replication (BPPR) algorithm and an online skewed key detector to effectively balance communication and computation loads, thereby significantly improving throughput and mitigating performance degradation caused by data skew in Wide Area Network deployments.