Mantas Mazeika
15 papers · 2018–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Conference Polyglot (4) π Academic Marathon (7) π§ Keyword Pioneer π Interdisciplinary Bridge π Cross-Pollinator (9)
π
Cross-Pollinator
(9)
π
Renaissance Researcher
(8)
πΊοΈ
Taxonomy Completionist
(40)
π₯
Mega-Team
(46)
π
Triple Crown
π€
Dynamic Duo
(14)
ποΈ
Keyword Collector
(50)
π
Century Club
(15)
π₯
Unstoppable
(5)
β
The Questioner
(2)
β‘
Prolific Year
(5)
Conferences
NIPS (6)
ICML (5)
ICLR (3)
CVPR (1)
Top co-authors
Keywords
adversarial robustness
(3)
uncertainty estimation
(3)
out-of-distribution detection
(3)
anomaly detection
(2)
deep neural network
(2)
label noise
(2)
model robustness
(1)
uncertainty quantification
(1)
adversarial learning
(1)
question answering
(1)
toxicity detection
(1)
confidence calibration
(1)
video understanding
(1)
ai safety
(1)
temporal reasoning
(1)
event forecasting
(1)
spectral analysis
(1)
data augmentation
(1)
affective computing
(1)
self-supervised learning
(1)
Papers
Tamper-Resistant Safeguards for Open-Weight LLMs
ICLR 2025
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
NIPS 2024
The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
ICML 2024
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
ICML 2024
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
NIPS 2023
How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
NIPS 2022
How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
ICML 2022
Forecasting Future World Events With Neural Networks
NIPS 2022
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
CVPR 2022
Scaling Out-of-Distribution Detection for Real-World Settings
ICML 2022
Measuring Massive Multitask Language Understanding
ICLR 2021
Deep Anomaly Detection with Outlier Exposure
ICLR 2019
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
NIPS 2019
Using Pre-Training Can Improve Model Robustness and Uncertainty
ICML 2019
Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
NIPS 2018