Yansong Gao
6 papers · 2019–2025 · 3 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird
❓
The Questioner
(2)
Venues
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(3)
Application Areas
(3)
Optimization & Theory
(3)
Deep Learning
(2)
Security & Privacy
(2)
Core AI
(2)
Learning Types
(2)
Models
(2)
Privacy
(2)
Bayesian & Probabilistic
(1)
Core Methods
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Paradigms · Machine Learning
(1)
Keywords
transfer learning
(3)
generative model
(2)
membership inference
(2)
privacy attack
(1)
semi-supervised learning
(1)
variational inference
(1)
bayesian inference
(1)
assignment problem
(1)
optimal transport
(1)
free energy
(1)
information geometry
(1)
diffusion model
(1)
text-to-image model
(1)
welfare maximization
(1)
generalization gap
(1)
text-to-image diffusion
(1)
privacy leakage
(1)
gradient inversion
(1)
conditional likelihood
(1)
memorization estimation
(1)
Papers
Where Does This Data Come From? Enhanced Source Inference Attacks in Federated Learning
IJCAI 2025
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
NeurIPS 2024
Deep Reference Priors: What is the best way to pretrain a model?
ICML 2022
An Information-Geometric Distance on the Space of Tasks
ICML 2021
A Free-Energy Principle for Representation Learning
ICML 2020
Average-case Analysis of the Assignment Problem with Independent Preferences
IJCAI 2019