Zhixuan Chu

Associate Professor@Zhejiang University·中国·OpenReview

研究方向

LLM · foundation model · graph learning · time series · explanation · multimodal · prompt learning · generative language model · causal inference · treatment effect estimation · representation learning · deep learning · continual learning · incremental learning

Zhixuan Chu

DistDF: Time-series Forecasting Needs Joint-distribution Wasserstein Alignment

Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models

Towards Real-world Debiasing: Rethinking Evaluation, Challenge, and Solution

Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets

V2P: Visual Attention Calibration for GUI Grounding via Background Suppression and Center Peaking

Graph Attribute Imputation via Generalized Wasserstein Balancing

CARP: Causal Alignment of Reward Models via Response-to-Prompt Prediction

CollabMask: Explainable Neuron Collaboration with Gradient Masks for LLM Fine-Tuning

ZeroSecBench: Fine-grained and Robust Evaluation for Secure Code Generation

TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

FAMMA: A Benchmark for Financial Multilingual Multimodal Question Answering

Towards Real World Debiasing: A Fine-grained Analysis On Spurious Correlation

Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models

A Comprehensive Deepfake Detector Assessment Platform

DB-GPT-Hub: Towards Open Benchmarking Text-to-SQL Empowered by Large Language Models