Haoxuan Li

Causal Discovery in the Wild: A Voting-Theoretic Ensemble Approach

A Relative Error-Based Evaluation Framework of Heterogeneous Treatment Effect Estimators

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

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

Convergence Theory of Decentralized Diffusion Models via Pseudo-Non-Markov Analysis

LogiConBench: Benchmarking Logical Consistencies of LLMs

MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models

Treatment Responder Classification with Abstention

MTIR-SQL:Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL

FSMLP: Modelling Channel Dependencies With Simplex Theory Based Multi-Layer Perceptions In Frequency Domain

Rose-TTA: Reliable Online Structural Enhancement for Test-Time Adaptation

Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation

Rethinking the Flow-based Gradual Domain Adaption: A Semi-Dual Transport Perspective

MAD-Logic: Multi-Agent Debate Enhances Symbolic Translation and Reasoning

Partial Identification via Optimal Transport under Complex Constraints on Treatments and Potential Outcome Measures

From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training

Style Decomposition and Content Preservation for Artistic Style Transfer

Joint Learning Between Reference Image and Text Prompt for Fashion Image Editing

Identifying Outcome-Oriented Root Causes via Cross Regression

Spatiotemporal distributionally robust optimization for improved cross-patient EEG seizure analysis

T-GINEE: A Tensor-Based Multi-Graph Representation Learning

Graph Attribute Imputation via Generalized Wasserstein Balancing

Enhancing Logical Reasoning of Large Language Models via Phased Fine-Tuning

Estimating the Effects of Sample Training Orders for Large Language Models without Retraining

REL-RAG: Relation-Aware Retrieval-Augmented Generation for Generalizable Knowledge Graph Question Answering

Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models

On the Necessity of Step-Specific Representation Learning for Multi-Step Forecasting

Causal Discovery under Changing Mechanisms: A Unified Graphical Approach

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

Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference

Time-o1: Time-Series Forecasting Needs Transformed Label Alignment

IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector

Learning Counterfactual Outcomes Under Rank Preservation

Active Treatment Effect Estimation via Limited Samples

Optimal Transport for Time Series Imputation

FreDF: Learning to Forecast in the Frequency Domain

Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization

Counterfactual Implicit Feedback Modeling

Unveiling Extraneous Sampling Bias with Data Missing-Not-At-Random

Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning

OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain

Towards Accurate Time Series Forecasting via Implicit Decoding

Inverse Methods for Missing Data Imputation

Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness

Pruning Spurious Subgraphs for Graph Out-of-Distribtuion Generalization

Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning

Curious Causality-Seeking Agents Learn Meta Causal World

Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models

Learning without Isolation: Pathway Protection for Continual Learning

Attaining Human's Desirable Outcomes in Indirect Human-AI Interaction via Multi-Agent Influence Diagrams

Large Language Models are Demonstration Pre-Selectors for Themselves

Large Language Models are Demonstration Pre-Selectors for Themselves

Counterfactual Delayed Feedback Learning

Robust Heterogeneous Treatment Effect Estimation under Covariate Perturbation

Principle Counterfactual Fairness

Sampling Process Brings Additional Bias for Debiased Recommendation

Active Causal Learning for Conditional Average Treatment Effect Estimation

Counterfactual Learning under Rank Preservation

Mitigating Unobserved Confounding via Diffusion Probabilistic Models

Temporal Visiting-Monitoring Feature Interaction Learning for Modelling Structured Electronic Health Records

Do We Really Need Parameter-Isolation to Protect Task Knowledge?

Invariant Spatiotemporal Representation Learning for Cross-patient Seizure Classification