Wei Cheng

Trajectory Graph Copilot: Pre-Action Error Diagnosis in LLM Agents

When Evolution Meets Momentum: Orchestrating Goal-oriented and Process-oriented reasoning for LLM Inference Scaling

LM$^2$otifs: An Explainable Framework for Machine-Generated Texts Detection

On the Effect of Sampling Diversity in Scaling LLM Inference

Exploring Data-Driven Models for Compound Flood Forecasting: A comprehensive benchmark

DISC: Dynamic Decomposition Improves LLM Inference Scaling

F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI

TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop

SFS: Smarter Code Space Search improves LLM Inference Scaling

Chain-of-region: Visual Language Models Need Details for Diagram Analysis

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors

Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection

Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop

Explanation-Assisted Data Augmentation for Graph Learning

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search