Eitan Borgnia
5 papers · 2021–2023 · 2 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 ↓+2 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (16) 🧭 Keyword Pioneer
📈
Trend Setter
❓
The Questioner
(2)
Venues
Top co-authors
Research topics
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI
(4)
Machine Learning
(3)
Architectures
(3)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Security & Privacy
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Privacy
(1)
Keywords
privacy attack
(1)
image restoration
(1)
logical reasoning
(1)
in-context learning
(1)
saliency map
(1)
false positive rate
(1)
generative model
(1)
diffusion model
(1)
recurrent neural network
(1)
algorithmic reasoning
(1)
length generalization
(1)
membership inference
(1)
parameter space
(1)
progressive training
(1)
reasoning capability
(1)
algorithm synthesis
(1)
easy-to-hard generalization
(1)
recurrent network
(1)
neural network
(1)
adversarial query
(1)
Papers
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
ICLR 2023
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
NeurIPS 2023
End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking
NeurIPS 2022
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
NeurIPS 2022
Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks
NeurIPS 2021