Samet Oymak

papers

704

total citations

papers (19)

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

NEURIPS 2020arXiv

citations

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

ICML 2024arXiv

citations

Towards Sample-efficient Overparameterized Meta-learning

NEURIPS 2021arXiv

citations

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

NEURIPS 2023arXiv

citations

TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data

AAAI 2025arXiv

citations

Retrieval Augmented Time Series Forecasting

ICML 2025arXiv

citations

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws

ICLR 2025arXiv

citations

Extrapolation by Association: Length Generalization Transfer In Transformers

NEURIPS 2025arXiv

citations

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning

COLM 2025

citations

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

ICML 2025arXiv

citations

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

AAAI 2024arXiv

citations

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

AAAI 2024

citations

On the Power of Convolution-Augmented Transformer

AAAI 2025

citations

AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments

CVPR 2025

citations

Samet Oymak

papers (19)

Unsupervised Multi-Source Domain Adaptation Without Access to Source Data

Label-Imbalanced and Group-Sensitive Classification under Overparameterization

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

AutoBalance: Optimized Loss Functions for Imbalanced Data

Max-Margin Token Selection in Attention Mechanism

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

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

Towards Sample-efficient Overparameterized Meta-learning

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

TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data

Retrieval Augmented Time Series Forecasting

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws

Extrapolation by Association: Length Generalization Transfer In Transformers

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning

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

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

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

On the Power of Convolution-Augmented Transformer

AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments

papers (19)

Unsupervised Multi-Source Domain Adaptation Without Access to Source Data

Label-Imbalanced and Group-Sensitive Classification under Overparameterization

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

AutoBalance: Optimized Loss Functions for Imbalanced Data

Max-Margin Token Selection in Attention Mechanism

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

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

Towards Sample-efficient Overparameterized Meta-learning

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

TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data

Retrieval Augmented Time Series Forecasting

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws

Extrapolation by Association: Length Generalization Transfer In Transformers

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning

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

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

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

On the Power of Convolution-Augmented Transformer

AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments