Thaddäus Wiedemer
6 papers · 2023–2025 · 4 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
❓
The Questioner
Venues
Top co-authors
Research topics
Keywords
foundation model
(3)
compositional generalization
(2)
out-of-distribution generalization
(2)
transfer learning
(1)
style transfer
(1)
multimodal learning
(1)
audio-visual learning
(1)
benchmark dataset
(1)
evaluation benchmark
(1)
object-centric representation
(1)
downstream performance
(1)
multimodal understanding
(1)
data contamination
(1)
clip model
(1)
identifiability theory
(1)
model assessment
(1)
training distribution
(1)
neural network
(1)
pretraining data
(1)
scaling trend
(1)
Papers
In Search of Forgotten Domain Generalization
ICLR 2025
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
ICML 2025
VGGSounder: Audio-Visual Evaluations for Foundation Models
ICCV 2025
Does CLIP’s generalization performance mainly stem from high train-test similarity?
ICLR 2024
Provable Compositional Generalization for Object-Centric Learning
ICLR 2024
Compositional Generalization from First Principles
NeurIPS 2023