Jonathan Hayase
12 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐝 Cross-Pollinator (12) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (5) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (6)
🐣
Hot Topic Early Bird
🌍
Conference Polyglot
(5)
👥
Mega-Team
(34)
💎
Century Club
(12)
🗃️
Keyword Collector
(57)
🔥
Unstoppable
(5)
Conferences
NIPS (5)
ICLR (3)
ICML (2)
COLT (1)
CVPR (1)
Top co-authors
Research topics
Keywords
backdoor attack
(2)
zero-shot learning
(1)
lagrangian relaxation
(1)
convex optimization
(1)
knowledge transfer
(1)
adversarial machine learning
(1)
robust statistics
(1)
model merging
(1)
neural network merging
(1)
covariance estimation
(1)
formal verification
(1)
model alignment
(1)
linear programming
(1)
least squares regression
(1)
transfer learning
(1)
differential privacy
(1)
adversarial attack
(1)
multimodal dataset
(1)
language model
(1)
model compression
(1)
Papers
PLeaS - Merging Models with Permutations and Least Squares
CVPR 2025
Scalable Extraction of Training Data from Aligned, Production Language Models
ICLR 2025
Query-Based Adversarial Prompt Generation
NIPS 2024
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares Extended Abstract
COLT 2024
Stealing part of a production language model
ICML 2024
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
NIPS 2024
Label Poisoning is All You Need
NIPS 2023
Few-shot Backdoor Attacks via Neural Tangent Kernels
ICLR 2023
Git Re-Basin: Merging Models modulo Permutation Symmetries
ICLR 2023
DataComp: In search of the next generation of multimodal datasets
NIPS 2023
Zonotope Domains for Lagrangian Neural Network Verification
NIPS 2022
SPECTRE: defending against backdoor attacks using robust statistics
ICML 2021