Di Weng

Residual-triggered active sensitivity estimation for topology-changes detection and voltage control with MAPO-SOP

Youzhuo Zheng, Yutao Xu, Yekui Yang, Yuchu Lu et autres

cn, in (code pays fourni par la source)

A Supply Chain Coordination Control Method for New Energy Grid Connected Power Systems Based on Data Analysis

Anjiang Liu, Youzhuo Zheng, Di Weng, Hengrong Zhang et autres

Renewable energy variability and unpredictability hinder supply chain coordination in grid-connected systems; thus, a data-based control approach is designed. All-phase Fourier transform is applied to extract features of renewable generation for enhanced decision making with supply chain data. The transportation, inventory, and …

BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations

Yunfan Zhou, Qiming Shi, Yizhou Yang, Di Weng et autres

While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user queries implicitly rely on domain-specific knowledge, such as business logic, data conventions, and analytical practices, that is neither captured by the schema nor explicitly …

AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis

Yangtian Liu, Yan Miao, Shuhan Liu, Yunfan Zhou et autres

Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows become more autonomous, conventional interfaces no longer provide adequate support for two critical requirements: observability for understanding …

POEM: Phase-Aware $\mathrm{SO}(2)$ Feature Rotation for Time Series Forecasting Under Periodicity Drift

Jiawen Zhu, Shuhan Liu, Shengxuan Li, Qiming Shi et autres

Deep learning has advanced time series forecasting, but periodicity drift, in which cycle timing and phase vary over time, remains a challenging problem. Existing methods predominantly model these sequences on fixed time grids, suffering from a limited ability to accommodate phase-related variation. …

cn (code pays fourni par la source)

Analysis of the microgrid’s frequency resilience using a lightweight selfish sheep optimisation algorithm

Anjiang Liu, Youzhuo Zheng, Di Weng, Hengrong Zhang et autres

The lightweighting problem in microgrid (MG) simulation models is first officially described in this paper as an optimisation assignment with the goal of minimising the disturbances to the microgrid frequency robustness. This paper formally presents the lightweighting problem in microgrid (MG) simulations …

Research on abnormal detection of transmission lines in high-risk areas on the distribution network side under extreme weather conditions

Anjiang Liu, Youzhuo Zheng, Di Weng, Hengrong Zhang et autres

This paper presents an integrated electric-gas energy system fault recovery method based on bidirectional coupled devices. Simulation examples of an IEEE 13-node electric system and a 6-node natural gas system are used to validate the effectiveness of the method. YALMIP is used …

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

Qiming Shi, Yulong Tao, Linbo Jin, Zhaolu Kang et autres

Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments often require Long-Term Coherence, the capacity to preserve purposeful behavior across extended horizons while adapting decisions to accumulated …

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

Qiming Shi, Yulong Tao, Linbo Jin, Zhaolu Kang et autres

Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments often require Long-Term Coherence, the capacity to preserve purposeful behavior across extended horizons while adapting decisions to accumulated …

cn, ca (code pays fourni par la source)

SKILL-KD: Contrastive Skill Distillation for LLM Agents

Qiming Shi, Yibo Dou, Jiawen Zhu, Yulong Tao et autres

Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summaries, memory entries, or direct summaries of successful demonstrations. This creates a mismatch for weaker student agents: when …

SKILL-KD: Contrastive Skill Distillation for LLM Agents

Qiming Shi, Yibo Dou, Jiawen Zhu, Yulong Tao et autres

Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summaries, memory entries, or direct summaries of successful demonstrations. This creates a mismatch for weaker student agents: when …

cn, us (code pays fourni par la source)

GeoAnimation: a grammar for animated geographic visualization

Jie Yu, Zhenning Chen, Di Weng, Y N Wu

cn (code pays fourni par la source)