Pengkun Wang
17 papers · 2023–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Cross-Pollinator (14) π Renaissance Researcher (8) π Interdisciplinary Bridge π Conference Polyglot (5) πΊοΈ Taxonomy Completionist (32)
π§
Keyword Pioneer
π€
Dynamic Duo
(14)
π
Triple Crown
π
Grand Slam
π
Century Club
(14)
β‘
Prolific Year
(6)
ποΈ
Keyword Collector
(61)
Conferences
AAAI (7)
ICLR (3)
ICML (3)
IJCAI (2)
NIPS (2)
Top co-authors
Keywords
graph neural network
(4)
representation learning
(3)
knowledge distillation
(2)
traffic prediction
(2)
long-tailed distribution
(2)
causal learning
(2)
class imbalance
(2)
large language model
(2)
information theory
(2)
distribution shift
(2)
multi-task learning
(1)
graph representation learning
(1)
data augmentation
(1)
deep learning
(1)
continual learning
(1)
transformer architecture
(1)
knowledge transfer
(1)
graph classification
(1)
time series forecasting
(1)
mutual information
(1)
Papers
Rethinking Crystal Symmetry Prediction: A Decoupled Perspective
AAAI 2026
U2B: Scale-unbiased Representation Converter for Graph Classification with Imbalanced and Balanced Scale Distributions
AAAI 2026
Learning Dynamics as Feedback: An Adaptive Entropy Flow Dynamics Framework for Long-tailed Human Action Recognition
AAAI 2026
COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation
ICLR 2025
Multi-label Self Knowledge Distillation
AAAI 2025
STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis
AAAI 2025
Robust Spatio-Temporal Centralized Interaction for OOD Learning
ICML 2025
Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data
ICML 2025
Causal Learning Meet Covariates: Empowering Lightweight and Effective Nationwide Air Quality Forecasting
IJCAI 2025
Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
NIPS 2024
A Twist for Graph Classification: Optimizing Causal Information Flow in Graph Neural Networks
AAAI 2024
Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective
AAAI 2024
Make Bricks with a Little Straw: Large-Scale Spatio-Temporal Graph Learning with Restricted GPU-Memory Capacity
IJCAI 2024
LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
NIPS 2024
Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning
ICML 2024
Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning
ICLR 2024
Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective
ICLR 2023