Pengkun Wang
19 papers · 2023–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (39) π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π Triple Crown π€ Dynamic Duo (17)
π
Grand Slam
ποΈ
Keyword Collector
(96)
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
π
Trend Setter
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(17)
Deep Learning
(13)
Application Areas
(10)
Core Methods
(9)
Optimization & Theory
(7)
Architectures
(6)
Learning Types Β· Machine Learning
(6)
Artificial Intelligence
(5)
Core AI
(5)
Learning Types Β· Deep Learning
(5)
Models
(3)
Computer Vision
(2)
Data Science & Analytics
(2)
Analysis
(2)
Methods
(2)
Keywords
graph neural network
(5)
long-tailed learning
(3)
large language model
(3)
representation learning
(3)
class imbalance
(3)
knowledge distillation
(2)
data augmentation
(2)
long-tailed distribution
(2)
causal learning
(2)
traffic prediction
(2)
multi-objective optimization
(2)
information theory
(2)
distribution shift
(2)
vision-language model
(2)
optimal transport
(1)
graph classification
(1)
lottery ticket hypothesis
(1)
multi-label learning
(1)
domain generalization
(1)
federated learning
(1)
Papers
FedMPT: Federated Multi-Label Prompt Tuning of Vision-Language Models
CVPR 2026
Learning Dynamics as Feedback: An Adaptive Entropy Flow Dynamics Framework for Long-tailed Human Action Recognition
AAAI 2026
LOREAL: Mitigating Low-Resolution Challenges in Vision-Language Models with Attribute-driven Prompt Self-Distillation
CVPR 2026
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
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
COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation
ICLR 2025
Multi-label Self Knowledge Distillation
AAAI 2025
Robust Spatio-Temporal Centralized Interaction for OOD Learning
ICML 2025
STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis
AAAI 2025
A Twist for Graph Classification: Optimizing Causal Information Flow in Graph Neural Networks
AAAI 2024
Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
NeurIPS 2024
Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning
ICLR 2024
LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
NeurIPS 2024
Make Bricks with a Little Straw: Large-Scale Spatio-Temporal Graph Learning with Restricted GPU-Memory Capacity
IJCAI 2024
Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective
AAAI 2024
Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning
ICML 2024
Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective
ICLR 2023