Zenglin Xu

Researcher@Shanghai Academy of AI for Science·中国·OpenReview

研究方向

Agentic AI · federated learning · time series analysis · Trustworthy AI · tensor networks · Bayesian nonparametrics · Kernel Methods · Semi-supervised Learning

Zenglin Xu

Bandit Learning in Matching Markets Robust to Adversarial Corruptions

SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC

SONATA: Synergistic Coreset Informed Adaptive Temporal Tensor Factorization

Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization

PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting

FinEvo: From Isolated Backtests to Ecological Market Games for Multi-Agent Financial Strategy Evolution

IndexNet: Timestamp and Variable-Aware Modeling for Time Series Forecasting

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

Geometric Compression in Grokking: The Three-Stage Modular Dynamics of Transformers

DockedAC: A Dataset with Comprehensive 3D Protein-ligand Complexes for Activity Cliff Analysis

RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching

Efficient Network Automatic Relevance Determination

IDInit: A Universal and Stable Initialization Method for Neural Network Training

InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions

DockedAC: Empowering Deep Learning Models With 3D Protein-ligand Data For Activity Cliff Analysis

On the Power of Federated Learning for Online Sparse Linear Regression with Decentralized Data

Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification

FedCVD: The First Real-World Federated Learning Benchmark on Cardiovascular Disease Data

MME-FINANCE: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning

PDETime: Rethinking Long-term Multivariate Time Series Forecasting from the Perspective of Partial Differential Equations