Simon Schrodi
6 papers · 2022–2025 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(21)
❓
The Questioner
(2)
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(3)
Learning Types · Machine Learning
(3)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Analysis
(1)
Application Areas
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Keywords
transformer
(2)
contrastive learning
(1)
adversarial robustness
(1)
domain generalization
(1)
embedding space
(1)
natural language processing
(1)
in-context learning
(1)
neural architecture search
(1)
compositional generalization
(1)
softmax
(1)
optical flow
(1)
bayesian optimization
(1)
generalization
(1)
adversarial attack
(1)
state space model
(1)
modality gap
(1)
vision-language model
(1)
training loss
(1)
self attention
(1)
white-box attack
(1)
Papers
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
ICLR 2025
When and How Does CLIP Enable Domain and Compositional Generalization?
ICML 2025
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
ICML 2024
Is Mamba Capable of In-Context Learning?
AutoML 2024
Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars
NeurIPS 2023
Towards Understanding Adversarial Robustness of Optical Flow Networks
CVPR 2022