影响力指数

97.72/100

前 0.1%

全站排名 #67

发表论文60 篇

平均评分5.3

年均产出20.0 篇/年

Yang Wang

Full Professor@University of Science and Technology of China·中国·OpenReview

研究方向

Spatiotemporal data mining and its interdisciplinary studies · AI for Science · Long-tailed Learning · Graph Learning

6.0

PepBenchmark: A Standardized Benchmark for Peptide Machine Learning

ICLR 2026Poster

通讯

5.5

One for Two: A Unified Framework for Imbalanced Graph Classification via Dynamic Balanced Prototype

ICLR 2026Oral

通讯

5.5

FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning

ICLR 2026Poster

通讯

5.5

PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting

ICLR 2026Poster

通讯

5.3

Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspective

ICLR 2026Poster

通讯

5.0

STORM: Synergistic Cross-Scale Spatio-Temporal Modeling for Weather Forecasting

ICLR 2026Poster

通讯

5.0

Long-tailed Test-Time Adaptation for Vision-Language Models

ICLR 2026Poster

通讯

4.7

DATR: DDI-Aware Therapeutic Structure Reconstruction for Safer Medication Recommendation

ICLR 2026Withdrawn

三作

4.5

I2Mole: Interaction-aware Invariant Molecular Learning For Generalizable Property Prediction

ICLR 2026Poster

通讯

4.0

IBGraphRAG: Enhancing Medical Knowledge Graph Retrieval Based on Semantic Consistency and Information Bottleneck

ICLR 2026Withdrawn

通讯

4.0

SymSpectra: Symmetric Information Bottleneck Framework for Molecular Structure Recognition under Imbalanced Settings

ICLR 2026Withdrawn

通讯

4.0

ReTaMTSF: Retrieval-Based Multimodal Framework for Multivariate Time Series Forecasting

ICLR 2026Withdrawn

通讯

4.0

MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning

ICLR 2026Withdrawn

通讯

4.0

GeoCMON: Operator Learning on Deformable Domains via Disentangled Geometric Conditioning

ICLR 2026Withdrawn

通讯

4.0

Fusing LLMs with Scientific Literature for Heuristic Discovery

ICLR 2026Rejected

通讯

3.5

MSpecTmol: A Multi-Modal Spectroscopic Learning Framework for Molecular Structure Identification

ICLR 2026Withdrawn

通讯

3.0

Graph-Guided Reconstruction Diffusion for Multivariate Time Series Anomaly Detection

ICLR 2026Withdrawn

通讯

3.0

CBFlownet: Generating Higher-Quality Candidates via Combinatorial Bandits

ICLR 2026Withdrawn

通讯

2.7

LAMP: Long-tailed Multimodal Prompt Learning for Vision-Language Models

ICLR 2026Rejected

通讯

2.5

MG2FlowNet: Accelerating High-Reward Sample Generation via Enhanced MCTS and Greediness Control

ICLR 2026Withdrawn

通讯

2.5

Cross-Domain Adaptive Multi-Scale Representation Learning for Unified Time Series Anomaly Detection

ICLR 2026Rejected

通讯

2.5

UniErase: Towards Balanced and Precise Unlearning in Language Models

ICLR 2026Withdrawn

通讯

8.2

Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation

NeurIPS 2025Poster

通讯

8.2

Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery

NeurIPS 2025Spotlight

通讯

7.3

MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling

NeurIPS 2025Poster

通讯

7.3

TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition

NeurIPS 2025Poster

通讯

7.2

Robust Spatio-Temporal Centralized Interaction for OOD Learning

ICML 2025Poster

通讯

7.2

SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation

ICML 2025Spotlight

通讯

7.2

Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data

ICML 2025Poster

通讯

7.2

Enhancing Graph Invariant Learning from a Negative Inference Perspective

ICML 2025Poster

通讯

6.8

Dynamic and Chemical Constraints to Enhance the Molecular Masked Graph Autoencoders

NeurIPS 2025Poster

三作

6.8

Integrating Drug Substructures and Longitudinal Electronic Health Records for Personalized Drug Recommendation

NeurIPS 2025Poster

通讯

6.6

TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting

ICML 2025Spotlight

通讯

6.5

Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck

ICLR 2025Poster

通讯

6.4

Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting

NeurIPS 2025Poster

通讯

6.4

Bridging the Gap Between Cross-Domain Theory and Practical Application: A Case Study on Molecular Dissolution

NeurIPS 2025Poster

通讯

6.4

Less but More: Linear Adaptive Graph Learning Empowering Spatiotemporal Forecasting

NeurIPS 2025Poster

通讯

6.3

Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics

ICLR 2025Poster

通讯

6.0

STOP! A Out-of-Distribution Processor with Robust Spatiotemporal Interaction

ICLR 2025Rejected

通讯

5.8

Capturing substructure interactions by invariant Information Bottle Theory for Generalizable Property Prediction

ICLR 2025Rejected

5.7

COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation

ICLR 2025Poster

通讯

5.3

Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data

ICLR 2025Rejected

通讯

5.0

Exploring Complex Trade-offs in Information Bottleneck through Multi-Objective Optimization

ICLR 2025Rejected

通讯

3.3

Overcoming Lookback Window Limitations: Exploring Longer Windows in Long-Term Time Series Forecasting

ICLR 2025Withdrawn

通讯

-1

Neural ODE with Differentiable Hidden State for Irregular Time Series

ICLR 2025Desk Rejected

合作者 (20)

Yang Wang

PepBenchmark: A Standardized Benchmark for Peptide Machine Learning

One for Two: A Unified Framework for Imbalanced Graph Classification via Dynamic Balanced Prototype

FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning

PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting

Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspective

STORM: Synergistic Cross-Scale Spatio-Temporal Modeling for Weather Forecasting

Long-tailed Test-Time Adaptation for Vision-Language Models

DATR: DDI-Aware Therapeutic Structure Reconstruction for Safer Medication Recommendation

I2Mole: Interaction-aware Invariant Molecular Learning For Generalizable Property Prediction

IBGraphRAG: Enhancing Medical Knowledge Graph Retrieval Based on Semantic Consistency and Information Bottleneck

SymSpectra: Symmetric Information Bottleneck Framework for Molecular Structure Recognition under Imbalanced Settings

ReTaMTSF: Retrieval-Based Multimodal Framework for Multivariate Time Series Forecasting

MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning

GeoCMON: Operator Learning on Deformable Domains via Disentangled Geometric Conditioning

Fusing LLMs with Scientific Literature for Heuristic Discovery

MSpecTmol: A Multi-Modal Spectroscopic Learning Framework for Molecular Structure Identification

Graph-Guided Reconstruction Diffusion for Multivariate Time Series Anomaly Detection

CBFlownet: Generating Higher-Quality Candidates via Combinatorial Bandits

LAMP: Long-tailed Multimodal Prompt Learning for Vision-Language Models

MG2FlowNet: Accelerating High-Reward Sample Generation via Enhanced MCTS and Greediness Control

Cross-Domain Adaptive Multi-Scale Representation Learning for Unified Time Series Anomaly Detection

UniErase: Towards Balanced and Precise Unlearning in Language Models

Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation

Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery

MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling

TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition

Robust Spatio-Temporal Centralized Interaction for OOD Learning

SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation

Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data

Enhancing Graph Invariant Learning from a Negative Inference Perspective

Dynamic and Chemical Constraints to Enhance the Molecular Masked Graph Autoencoders

Integrating Drug Substructures and Longitudinal Electronic Health Records for Personalized Drug Recommendation

TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting

Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck

Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting

Bridging the Gap Between Cross-Domain Theory and Practical Application: A Case Study on Molecular Dissolution

Less but More: Linear Adaptive Graph Learning Empowering Spatiotemporal Forecasting

Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics

STOP! A Out-of-Distribution Processor with Robust Spatiotemporal Interaction

Capturing substructure interactions by invariant Information Bottle Theory for Generalizable Property Prediction

COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation

Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data

TimeBase: The Power of Minimalism in Long-term Time Series Forecasting

ZeroTS: Zero-shot time series prediction via multi-party data-model interaction

Enhancing Graph Invariant Learning from a Negative Inference Perspective

Spatiotemporal Backward Inconsistency Learning Gives STGNNs Icing on the Cake

Exploring Complex Trade-offs in Information Bottleneck through Multi-Objective Optimization

Overcoming Lookback Window Limitations: Exploring Longer Windows in Long-Term Time Series Forecasting

Neural ODE with Differentiable Hidden State for Irregular Time Series