Jonathan Hayase
12 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 ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (29) π Keyword Champion (2)
π₯
Mega-Team Β· Squad
ποΈ
Keyword Collector
(76)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(12)
Artificial Intelligence
(8)
Core AI
(8)
Application Areas
(7)
Learning Types
(6)
Optimization & Theory Β· Machine Learning
(5)
Deep Learning
(4)
Core Methods
(3)
Mathematics & Optimization
(2)
Natural Language Processing
(2)
Security & Privacy
(2)
Optimization
(2)
Optimization & Theory Β· Deep Learning
(2)
Resources & Methods
(2)
Differential Privacy
(1)
Keywords
backdoor attack
(3)
model alignment
(2)
adversarial machine learning
(2)
model merging
(2)
language model
(2)
permutation symmetry
(2)
knowledge transfer
(1)
convex optimization
(1)
neural tangent kernel
(1)
mean estimation
(1)
sample complexity
(1)
neural network merging
(1)
covariance estimation
(1)
neural network optimization
(1)
transfer learning
(1)
least squares regression
(1)
linear programming
(1)
robust statistics
(1)
lagrangian relaxation
(1)
formal verification
(1)
Papers
PLeaS - Merging Models with Permutations and Least Squares
CVPR 2025
Scalable Extraction of Training Data from Aligned, Production Language Models
ICLR 2025
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
NeurIPS 2024
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares Extended Abstract
COLT 2024
Query-Based Adversarial Prompt Generation
NeurIPS 2024
Stealing part of a production language model
ICML 2024
DataComp: In search of the next generation of multimodal datasets
NeurIPS 2023
Few-shot Backdoor Attacks via Neural Tangent Kernels
ICLR 2023
Git Re-Basin: Merging Models modulo Permutation Symmetries
ICLR 2023
Label Poisoning is All You Need
NeurIPS 2023
Zonotope Domains for Lagrangian Neural Network Verification
NeurIPS 2022
SPECTRE: defending against backdoor attacks using robust statistics
ICML 2021