Samet Oymak

20

Papers

28

Total Citations

Papers (20)

Retrieval Augmented Time Series Forecasting

Extrapolation by Association: Length Generalization Transfer In Transformers

NeurIPS 2025arXiv

Test-Time Training Provably Improves Transformers as In-context Learners

A Score-Based Deterministic Diffusion Algorithm with Smooth Scores for General Distributions

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks

Unsupervised Multi-Source Domain Adaptation Without Access to Source Data

Parallel Correlation Clustering on Big Graphs

AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments

On the Power of Convolution-Augmented Transformer

TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data

Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective

Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View

AutoBalance: Optimized Loss Functions for Imbalanced Data

Label-Imbalanced and Group-Sensitive Classification under Overparameterization

Towards Sample-efficient Overparameterized Meta-learning

Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning

Max-Margin Token Selection in Attention Mechanism

Learning Compact Neural Networks with Regularization

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?