Xiao Luo

Assistant Professor@University of Wisconsin - Madison·中国·OpenReview

研究方向

large language model · deep learning · bioinformatics · graph neural networks · information retrieval · graph machine learning · AI for science · dynamical system

Xiao Luo

Hierarchical Encoding Tree with Modality Mixup for Cross-modal Hashing

Sample Lottery: Unsupervised Discovery of Critical Instances for LLM Reasoning

G-Merging: Graph Models Merging for Parameter-Efficient Multi-Task Knowledge Consolidation

PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning

PRISM: Partial-label Relational Inference with Spatial and Spectral Cues

Conformalized Hierarchical Calibration for Uncertainty-Aware Adaptive Hashing

Out-of-Distribution Graph Models Merging

FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation

RISE: A Statistical Perspective for Adversarial Attacks against Closed-Source MLLMs

Twin Evolution with Meta Preference Optimization for Semi-Supervised Learning of Large Language Models

Learn to Merge: Meta-Learning for Adaptive Multi-Task Model Merging

SE-Diff: Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation

CARE: Contextual Affinity Exploration with Twin Concordance for Graph Out-Of-Distribution Detection

PURE: Prototypical Mutual Prompting Enhancement for Zero-shot Text-attributed Graph Learning

DREAM: Decoupled Reinforcement Learning with Reward Measurement for Large Language Model Test-time Training

Text-guided Group Mixup with Canonical Mining for Imbalanced Graph Clustering

CAUSAL REASONING WITH LARGE FOUNDATION MOD- ELS TO GUIDE DYNAMIC SYSTEM FORECASTING

DoMiNO: Down-scaling Molecular Dynamics with Neural Graph Ordinary Differential Equations

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models

Prototypical Environment-aware Proxy with Coordinated Optimization for Multi-agent Dynamics Modeling

Multi-agent System with Individual Optimized Expertise for Retrieval Augmented Generation

POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimization

LIGHT: LLM-guided Graph Expert Routing for Semi-supervised Domain Generalization

Learning Universal Sample Difficulty with Pathology Foundation Models in Histopathology Image Analysis

Permutation-Invariant Hierarchical Representation Learning for Reinforcement-Guided Feature Transformation

GREAT: GROUP-ACQUIRED BIPARTITE ALIGNMENT FOR GRAPH FAIRNESS ADAPTATION

GRACE: A Generalizable Method For Multi-agent System Security Evaluation

Court Simulation with Multifaceted Agent Judgment for LLM Jailbreak Evaluation

RAGCell: Retrieval-Augmented Generation as Supervision for Versatile Single-cell Analysis

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs

Rethink GraphODE Generalization within Coupled Dynamical System

DANCE: Dual Unbiased Expansion with Group-acquired Alignment for Out-of-distribution Graph Fairness Learning

SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision

Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning

Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

GCAL: Adapting Graph Models to Evolving Domain Shifts

Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation

Flow Field Reconstruction with Sensor Placement Policy Learning

Towards Continuous Reuse of Graph Models via Holistic Memory Diversification

Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes

CellDJBench: Benchmark Datasets for Data-Driven Biological Fluid Simulation

Iterative Feature Space Optimization through Incremental Adaptive Evaluation

A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizability

Joint Modeling of Spatial and Temporal Multiscales in Molecular Dynamics

GRACE: Towards Realistic Multimodal Single-Cell Data Matching