Dongyue Li
7 papers · 2021–2025 · 5 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 ↓
🌍
Conference Polyglot · Silver
🗺️
Taxonomy Completionist
(21)
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(7)
Deep Learning
(5)
Learning Types · Machine Learning
(4)
Optimization & Theory · Machine Learning
(4)
Artificial Intelligence
(3)
Learning Paradigms
(3)
Learning Types · Deep Learning
(3)
Application Areas
(2)
Architectures
(2)
Core Methods
(2)
Optimization & Theory · Deep Learning
(2)
Models
(1)
Techniques
(1)
Keywords
transfer learning
(4)
generalization bound
(2)
multi-task learning
(2)
graph neural network
(2)
label noise
(1)
pac-bayesian analysis
(1)
subset selection
(1)
graph diffusion
(1)
ensemble method
(1)
generalization guarantee
(1)
language model
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
model ensemble
(1)
noisy label
(1)
multi-dataset training
(1)
pac-bayesian theory
(1)
hessian analysis
(1)
graph-level classification
(1)
weighted ensemble
(1)
Papers
Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets
ACL 2025
Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation
EMNLP 2025
Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach
EMNLP 2024
Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
AISTATS 2023
Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
NeurIPS 2023
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
ICML 2022
Improved Regularization and Robustness for Fine-tuning in Neural Networks
NeurIPS 2021