AI-powered metadata correction and harmonization

（翻译）AI 驱动的元数据修正与协调

Metadata harmonization (standardizing labels, identifiers, and formats so datasets can work together) is still largely manual. This post shows how AI-powered metadata correction works in practice, covering two approaches, human-in-the-loop validation and autonomous agent-driven workflows, plus gover

A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts

（翻译）巡天检测通道覆盖天文学基础模型中的像素，并使层析平均红移产生偏置

arXiv:2608.23626v1 Announce Type: new Abstract: Foundation models for astronomy are trained on survey pixels together with the catalogue products derived from those pixels. Those catalogues are incomplete at a measurable rate, and a model trained on both inherits that incompleteness as a systematic.

Do LLMs Understand Limit Order Book Dynamics?

（翻译）LLM 能理解限价订单簿动态吗？

Abstract page for arXiv paper 2608.23706: Do LLMs Understand Limit Order Book Dynamics?

A Formal Methodological Framework for Auditing Robustness and Fidelity in Explainable AI: From Application to Trust Certification

（翻译）审计可解释人工智能鲁棒性与保真度的形式化方法论框架：从应用到信任认证

Abstract page for arXiv paper 2608.23817: A Formal Methodological Framework for Auditing Robustness and Fidelity in Explainable AI: From Application to Trust Certification

Falcon TST 2.0获世界权威测评第一名，推动时间序列基础模型从通用预测走向金融应用

蚂蚁国际日前正式发布自研时序AI预测大模型“鹰序TST”2.0版。

Methodological and Conceptual Framework for 5D Multi-Table Analysis: A Unified Approach for Complex Data Reuse

（翻译）5D多表分析的方法论与概念框架：复杂数据复用的统一方法

Abstract page for arXiv paper 2608.26149: Methodological and Conceptual Framework for 5D Multi-Table Analysis: A Unified Approach for Complex Data Reuse

How Decathlon runs demand forecasting at scale with Chronos-2

（翻译）迪卡侬如何利用 Chronos-2 进行大规模需求预测

Decathlon, one of the world's largest sporting goods retailers, forecasts weekly demand for tens of thousands of products across multiple continents. Learn how they deployed Chronos-2 on AWS to improve forecast accuracy by 11-15 points while cutting operational complexity and running weekly inferenc

A Framework for Object-Centric Predictive Monitoring of Collaborative Processes

（翻译）一种用于协作流程的以对象为中心的预测监控框架

Abstract page for arXiv paper 2608.27671: A Framework for Object-Centric Predictive Monitoring of Collaborative Processes

When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation

（翻译）当预测误差不够时：评估因果估计中干扰函数的预测

Abstract page for arXiv paper 2609.00071: When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation

还在为大模型洗数据熬夜？蚂蚁拿下VLDB工业最佳论文，一套宽表搞定35PB语料，效率狂飙5.6倍

蚂蚁集团推出统一宽表系统OmniTable，论文获评VLDB 2026工业赛道最佳论文

BioSync: Transformer-Based Cross-Modal Fusion for a Multimodal Physiological Digital Biomarker

（翻译）BioSync：基于Transformer的跨模态融合用于多模态生理数字生物标志物

Abstract page for arXiv paper 2609.04504: BioSync: Transformer-Based Cross-Modal Fusion for a Multimodal Physiological Digital Biomarker

Govern models with MLflow and Amazon SageMaker AI Model Registry sync: Part 2

（翻译）使用 MLflow 与 Amazon SageMaker AI Model Registry 同步治理模型：第 2 部分

Governing models across accounts is the next step after automatic model registration. This post extends managed MLflow and Amazon SageMaker AI Model Registry sync to two cross-account governance topologies: a hub-and-spoke pattern that centralizes governance with AWS RAM, and a hybrid pattern that k

OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows

（翻译）OpenDiscoveryTrace：评估AI科学家工作流的过程轨迹

Abstract page for arXiv paper 2609.09203: OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows