Xiangyu Chang
15 papers · 2017–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Conference Polyglot (8) π£ Hot Topic Early Bird π§ Keyword Pioneer π Interdisciplinary Bridge π Academic Marathon (8)
π
Cross-Pollinator
(13)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(36)
π
Grand Slam
π
Century Club
(13)
π
Trend Setter
ποΈ
Keyword Collector
(70)
π₯
Unstoppable
(5)
Conferences
AAAI (3)
ICML (3)
JMLR (3)
NIPS (2)
AISTATS (1)
COLT (1)
CVPR (1)
ICLR (1)
Top co-authors
Research topics
Keywords
federated learning
(1)
transformer architecture
(1)
continual learning
(1)
double descent
(1)
stochastic gradient descent
(1)
semi-supervised learning
(1)
few-shot learning
(1)
spectral clustering
(1)
domain adaptation
(1)
sparse learning
(1)
attention mechanism
(1)
language modeling
(1)
composite optimization
(1)
communication complexity
(1)
distributed learning
(1)
feature correlation
(1)
decentralized optimization
(1)
data valuation
(1)
fair classification
(1)
model compression
(1)
Papers
Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
AAAI 2026
Bayes-Optimal Fair Classification with Multiple Sensitive Features
AAAI 2026
ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
ICLR 2025
Optimal Decentralized Composite Optimization for Strongly Convex Functions
JMLR 2025
Provable Benefits of Task-Specific Prompts for In-context Learning
AISTATS 2025
AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments
CVPR 2025
Selective Attention: Enhancing Transformer through Principled Context Control
NIPS 2024
CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
NIPS 2024
Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods
ICML 2024
Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient
ICML 2024
Randomized Spectral Co-Clustering for Large-Scale Directed Networks
JMLR 2023
2D-Shapley: A Framework for Fragmented Data Valuation
ICML 2023
Statistical Estimation and Online Inference via Local SGD
COLT 2022
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
AAAI 2021
Distributed Semi-supervised Learning with Kernel Ridge Regression
JMLR 2017