Shuang Song
19 papers · 2014–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
π Conference Polyglot (8) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Academic Marathon (11)
πΊοΈ
Taxonomy Completionist
(33)
π
Interdisciplinary Bridge
π
Conference Polyglot
(8)
π¬
Deep Specialist
(12)
π
Keyword Champion
π
Grand Slam
ποΈ
Keyword Collector
(85)
π
Conference Pioneer
π
Century Club
(19)
π₯
Unstoppable
(6)
π
Trend Setter
β‘
Prolific Year
(6)
Conferences
ICML (4)
NIPS (4)
AISTATS (3)
EMNLP (2)
ICCV (2)
ICLR (2)
AAAI (1)
COLING (1)
Top co-authors
Research topics
Keywords
differential privacy
(11)
linear regression
(3)
stochastic gradient descent
(2)
recommender system
(2)
retrieval-augmented generation
(2)
user-level privacy
(2)
anomaly detection
(1)
multi-task learning
(1)
3d reconstruction
(1)
sample complexity
(1)
point cloud
(1)
3d vision
(1)
image synthesis
(1)
posterior sampling
(1)
privacy preserving
(1)
global convergence
(1)
label noise
(1)
empirical risk minimization
(1)
logistic regression
(1)
token efficiency
(1)
Papers
ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation
EMNLP 2025
EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation
EMNLP 2025
Confront Insider Threat: Precise Anomaly Detection in Behavior Logs Based on LLM Fine-Tuning
COLING 2025
Private Learning with Public Features
AISTATS 2024
Multi-Task Differential Privacy Under Distribution Skew
ICML 2023
Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments
ICCV 2023
Measuring Forgetting of Memorized Training Examples
ICLR 2023
Public Data-Assisted Mirror Descent for Private Model Training
ICML 2022
Differentially Private Model Personalization
NIPS 2021
Tempered Sigmoid Activations for Deep Learning with Differential Privacy
AAAI 2021
Vis2Mesh: Efficient Mesh Reconstruction From Unstructured Point Clouds of Large Scenes With Learned Virtual View Visibility
ICCV 2021
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
ICML 2021
Practical and Private (Deep) Learning Without Sampling or Shuffling
ICML 2021
Evading the Curse of Dimensionality in Unconstrained Private GLMs
AISTATS 2021
The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space
NIPS 2020
Scalable Private Learning with PATE
ICLR 2018
Renyi Differential Privacy Mechanisms for Posterior Sampling
NIPS 2017
Learning from Data with Heterogeneous Noise using SGD
AISTATS 2015
The Large Margin Mechanism for Differentially Private Maximization
NIPS 2014