Leo Schwinn
12 papers · 2021–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🐝 Cross-Pollinator (15) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (20) 🧭 Keyword Pioneer
🌍
Conference Polyglot
(7)
🏆
Grand Slam
💎
Century Club
(12)
⚡
Prolific Year
(6)
🔥
Unstoppable
(5)
Conferences
ICML (3)
NIPS (3)
ICLR (2)
AAAI (1)
ACL (1)
CVPR (1)
UAI (1)
Top co-authors
Keywords
adversarial attack
(3)
out-of-distribution detection
(2)
adversarial training
(2)
embedding space
(1)
question answering
(1)
information retrieval
(1)
model unlearning
(1)
category discovery
(1)
loss landscape
(1)
safety alignment
(1)
model alignment
(1)
distribution shift
(1)
saliency map
(1)
diffusion model
(1)
language model
(1)
data efficiency
(1)
jailbreak attack
(1)
retrieval-augmented generation
(1)
robustness evaluation
(1)
monte carlo method
(1)
Papers
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
ICLR 2025
A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
ICLR 2025
Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
ICML 2025
When to retrain a machine learning model
ICML 2025
Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
ACL 2025
Joint Out-of-Distribution Filtering and Data Discovery Active Learning
CVPR 2025
Efficient Adversarial Training in LLMs with Continuous Attacks
NIPS 2024
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
NIPS 2024
On the Scalability of Certified Adversarial Robustness with Generated Data
NIPS 2024
FastAMI – a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics
AAAI 2023
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification
ICML 2022
Identifying untrustworthy predictions in neural networks by geometric gradient analysis
UAI 2021