Leo Schwinn
12 papers · 2021–2025 · 7 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 ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (30) 🌍 Conference Polyglot · Silver 🏆 Grand Slam 💎 Century Club · Bronze
🗃️
Keyword Collector
(61)
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Machine Learning
(11)
Artificial Intelligence
(7)
Core AI
(6)
Learning Types
(6)
Deep Learning
(4)
Natural Language Processing
(3)
Application Areas
(3)
Core Methods
(3)
Architectures
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Data Science & Analytics
(1)
Mathematics & Optimization
(1)
Reinforcement Learning
(1)
Applications
(1)
Keywords
adversarial attack
(3)
adversarial training
(2)
out-of-distribution detection
(2)
distribution shift
(2)
question answering
(1)
information retrieval
(1)
adversarial robustness
(1)
output distribution
(1)
optimal transport
(1)
category discovery
(1)
flow matching
(1)
loss landscape
(1)
computational complexity
(1)
safety alignment
(1)
time series forecasting
(1)
conditional generation
(1)
gaussian process
(1)
model alignment
(1)
model unlearning
(1)
embedding space
(1)
Papers
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
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
ICLR 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
When to retrain a machine learning model
ICML 2025
Efficient Adversarial Training in LLMs with Continuous Attacks
NeurIPS 2024
On the Scalability of Certified Adversarial Robustness with Generated Data
NeurIPS 2024
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
NeurIPS 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