Muhammed Emrullah Ildiz
5 papers · 2023–2025 · 3 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
(15)
Top co-authors
Research topics
Keywords
in-context learning
(2)
distribution shift
(2)
bayesian inference
(1)
knowledge distillation
(1)
sample complexity
(1)
transformer
(1)
stability analysis
(1)
markov model
(1)
multivariate time series
(1)
generalization bound
(1)
algorithm learning
(1)
surrogate model
(1)
synthetic data
(1)
scaling law
(1)
weak-to-strong generalization
(1)
ridgeless regression
(1)
prior-data fitted network
(1)
self attention
(1)
gradient step
(1)
generative process
(1)
Papers
High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
ICLR 2025
Test-Time Training Provably Improves Transformers as In-context Learners
ICML 2025
TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data
AAAI 2025
From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
ICML 2024
Transformers as Algorithms: Generalization and Stability in In-context Learning
ICML 2023