Pengkun Wang

GUIDE: Gated Uncertainty-Informed Disentangled Experts for Long-tailed Recognition

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

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

PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting

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

Fusing LLMs with Scientific Literature for Heuristic Discovery

GeoCMON: Operator Learning on Deformable Domains via Disentangled Geometric Conditioning

CBFlownet: Generating Higher-Quality Candidates via Combinatorial Bandits

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

Interpretable Preference Elicitation: Aligning User Intent with Controllable Long-tailed Learning

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

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

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

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

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

Robust Spatio-Temporal Centralized Interaction for OOD Learning

Less but More: Linear Adaptive Graph Learning Empowering Spatiotemporal Forecasting

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

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

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

Spatiotemporal Backward Inconsistency Learning Gives STGNNs Icing on the Cake

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

Neural ODE with Differentiable Hidden State for Irregular Time Series