Haifeng Chen

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

The Power of Order: Fooling LLMs with Adversarial Table Permutation

LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis

DISC: Dynamic Decomposition Improves LLM Inference Scaling

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

SFS: Smarter Code Space Search improves LLM Inference Scaling

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors

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

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

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

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

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

LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis

OCEAN: Online Multi-modal Root Cause Analysis for Microservice Systems