Pipelines, warehouses, feature stores and the query engines that feed everything above.
arXiv:2610.01039v1 Announce Type: new Abstract: While recent video generative models can synthesize high-fidelity videos, they struggle to portray plausible physical interactions and the resulting st...
Enterprise Representation Simplification (ERS) proposes reducing unnecessary representational complexity in enterprise information while preserving essential data within a defined scope. The paper introduces Enterprise Representation Complexity (ERC), a representation‑neutral model that measures complexity across four dimensions—Objects, Interactions, Behaviors, and Supporting Sources—at both representation and task levels. ERC enables comparison of architectural simplification versus retrieval optimization, supports an economic model of maintenance costs, and demonstrates that lower task‑level ERC can improve AI reasoning accuracy, as shown in Text‑to‑SQL research.
BudgetSchemaBench is a diagnostic tool for evaluating how different schema‑context budgets affect text‑to‑SQL systems. It automatically derives relevance labels from gold SQL, tests four budgets across 80 databases, and compares three schema representations while keeping table rankings fixed. The study shows that increasing the budget improves execution accuracy, especially for lexical retrieval, and that dense retrieval already captures most needed tables at low budgets.
arXiv:2610.01064v1 Announce Type: cross Abstract: Retrieving the right tables is a prerequisite for Text-to-SQL over realistic databases. Dense table retrievers rank schema elements independently, bu...
arXiv:2610.02122v1 Announce Type: cross Abstract: Real-world enterprise data science and analytics workflows require reasoning across dozens of tables, performing statistical analyses, and acting on...
arXiv:2610.01352v1 Announce Type: new Abstract: Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven da...
arXiv:2610.00873v1 Announce Type: cross Abstract: In many industrial applications, 1) tabular data is scarce and imbalanced and thus requires synthetic expansion; 2) input distributions drift between...
arXiv:2510.24046v2 Announce Type: replace-cross Abstract: Existing tabular data generation methods primarily focus on matching statistical distributions between real and synthetic data, often overloo...
arXiv:2609.39257v1 Announce Type: cross Abstract: Accurate forecasting of electricity production is essential for maintaining the operational efficiency and strategic planning of energy utilities. In...
arXiv:2609.39640v1 Announce Type: cross Abstract: Cross-lingual transfer describes how knowledge in a source language benefits a target language. Measuring it quantitatively requires broad multilingu...
The paper introduces a co‑evolving framework where a target agent improves by learning from its own failures, and a separate failure agent is trained to generate hard negative trajectories. These hard negatives, derived from plausible but incorrect attempts, help the target agent better distinguish successful behavior from subtle errors. Experiments on online shopping, scientific reasoning, and interactive SQL querying show a 5.7% average reward improvement over baseline methods.
arXiv:2605.07111v3 Announce Type: replace-cross Abstract: Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides greater represe...
arXiv:2601.12310v2 Announce Type: replace Abstract: Self-training systems often degenerate due to the lack of an external criterion for judging data quality, leading to reward hacking and semantic dr...
arXiv:2609.39371v1 Announce Type: new Abstract: In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements refe...
InsightMap is a framework that uses top‑down maps as explicit spatial memory and action‑conditioned prediction targets for language‑guided navigation. It links historical views to labeled map locations and employs a shared multimodal backbone to jointly learn navigation action prediction and post‑action map generation, providing auxiliary training supervision. The approach supports a unified RGB‑D pipeline for navigation, visual question answering, situated reasoning, and 3D grounding, achieving state‑of‑the‑art results on R2R‑CE, RxR‑CE, ScanQA, SQA3D, ScanRefer, and outperforming baselines on the Unitree Go2 platform.
arXiv:2609.37705v1 Announce Type: cross Abstract: Goodness-of-fit testing is a basic tool for assessing whether a fitted procedure has captured the systematic information contained in the covariates....
arXiv:2604.22893v2 Announce Type: replace-cross Abstract: Traditional ``row-count $\times$ quality coefficient'' approaches fail to capture the nonlinear utility of data for Large Language Model (LLM...
IronLLM-0.6B is a 654‑million‑parameter language model engineered for efficient on‑device inference, featuring a hybrid attention architecture, X‑MTP multi‑token prediction, and a lightweight verification head that yields a 1.48× decoding speedup. Trained on roughly 6.2 trillion tokens with a quality‑oriented pipeline and further refined via Multi‑Domain On‑Policy Distillation, the model adopts an Instruct‑Only design to meet low‑latency requirements. A lighter variant, IronLLM‑0.6B‑Light, replaces RMSNorm with Dynamic Tanh and streamlines costly components to enhance inference and quantization efficiency, offering a strong performance‑efficiency trade‑off for resource‑constrained deployment.
arXiv:2609.35917v1 Announce Type: new Abstract: Graph neural networks are increasingly applied to road-level crash prediction, but the stability of their reported gains has received little scrutiny....
arXiv:2512.00329v2 Announce Type: replace-cross Abstract: Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task...