213 citations · 264 across the 25 of their papers we have counts for
28 papers
Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents
Yutong Cheng, Wei Cheng, Wenchao Yu +2
A self-evolving agent rewrites its own harness and must decide which rewrites to keep, so its improvement signal is the check a rewrite has to pass. Verifying a rewrite by agent ro…
MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
ChengAo Shen, Wenchao Yu, Fangyu Wu +6
Time series forecasting (TSF) is evolving toward multimodal and agentic settings, yet using foundation models remains uneconomical in resource-constrained scenarios, where compact,…
Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement
Wangyang Ying, Yanchi Liu, Xujiang Zhao +5
Automatically extracting workflows as procedural graphs from natural language is promising yet underexplored, demanding both structural validity and logical alignment. While recent…
xTime: Extreme Event Prediction with Hierarchical Knowledge Distillation and Expert Fusion
Quan Li, Wenchao Yu, Suhang Wang +4
Extreme events frequently occur in real-world time series and often carry significant practical implications. In domains such as climate and healthcare, these events, such as flood…
Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
Cong Zeng, Shengkun Tang, Yuanzhou Chen +6
The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated text in digital communication.…
DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router
Minghao Guo, Qingcheng Zeng, Xujiang Zhao +5
Large Language Models (LLMs) excel at many reasoning tasks but struggle with knowledge-intensive queries due to their inability to dynamically access up-to-date or domain-specific…
Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting
ChengAo Shen, Wenchao Yu, Ziming Zhao +4
Time series, typically represented as numerical sequences, can also be transformed into images and texts, offering multi-modal views (MMVs) of the same underlying signal. These MMV…
Multi-modal Time Series Analysis: A Tutorial and Survey
Yushan Jiang, Kanghui Ning, Zijie Pan +7
Multi-modal time series analysis has recently emerged as a prominent research area in data mining, driven by the increasing availability of diverse data modalities, such as text, i…
TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents
Geon Lee, Wenchao Yu, Kijung Shin +2
Time series data is essential in various applications, including climate modeling, healthcare monitoring, and financial analytics. Understanding the contextual information associat…
TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
Yushan Jiang, Wenchao Yu, Geon Lee +5
Time series analysis provides essential insights for real-world system dynamics and informs downstream decision-making, yet most existing methods often overlook the rich contextual…
MixLLM: Dynamic Routing in Mixed Large Language Models
Xinyuan Wang, Yanchi Liu, Wei Cheng +5
Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own…
Scattered Forest Search: Smarter Code Space Exploration with LLMs
Jonathan Light, Yue Wu, Yiyou Sun +6
We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this…
PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization
Yuyang Ye, Lu-An Tang, Haoyu Wang +5
Achieving carbon neutrality within industrial operations has become increasingly imperative for sustainable development. It is both a significant challenge and a key opportunity fo…
InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration
Fali Wang, Runxue Bao, Suhang Wang +4
Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive kno…
PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
Yijia Xiao, Yiqiao Jin, Yushi Bai +10
The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless…
Interpretable Imitation Learning with Dynamic Causal Relations
Tianxiang Zhao, Wenchao Yu, Suhang Wang +6
Imitation learning, which learns agent policy by mimicking expert demonstration, has shown promising results in many applications such as medical treatment regimes and self-driving…
GLAD: Content-aware Dynamic Graphs For Log Anomaly Detection
Yufei Li, Yanchi Liu, Haoyu Wang +6
Logs play a crucial role in system monitoring and debugging by recording valuable system information, including events and states. Although various methods have been proposed to de…
Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations
Tianxiang Zhao, Wenchao Yu, Suhang Wang +6
Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, exi…
Personalized Federated Learning under Mixture of Distributions
Yue Wu, Shuaicheng Zhang, Wenchao Yu +5
The recent trend towards Personalized Federated Learning (PFL) has garnered significant attention as it allows for the training of models that are tailored to each client while mai…
Time Series Contrastive Learning with Information-Aware Augmentations
Dongsheng Luo, Wei Cheng, Yingheng Wang +8
Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been l…
Personalized Federated Learning via Heterogeneous Modular Networks
Tianchun Wang, Wei Cheng, Dongsheng Luo +5
Personalized Federated Learning (PFL) which collaboratively trains a federated model while considering local clients under privacy constraints has attracted much attention. Despite…
SEED: Sound Event Early Detection via Evidential Uncertainty
Xujiang Zhao, Xuchao Zhang, Wei Cheng +4
Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound e…
Unsupervised Document Embedding via Contrastive Augmentation
Dongsheng Luo, Wei Cheng, Jingchao Ni +8
We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-superv…
Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts
Junheng Hao, Muhao Chen, Wenchao Yu +2
Many large-scale knowledge bases simultaneously represent two views of knowledge graphs (KGs): an ontology view for abstract and commonsense concepts, and an instance view for spec…