Picture for Samet Oymak

Samet Oymak

TREACLE: Thrifty Reasoning via Context-Aware LLM and Prompt Selection

Apr 17, 2024
Viaarxiv icon

Mechanics of Next Token Prediction with Self-Attention

Mar 12, 2024
Figure 1 for Mechanics of Next Token Prediction with Self-Attention
Figure 2 for Mechanics of Next Token Prediction with Self-Attention
Figure 3 for Mechanics of Next Token Prediction with Self-Attention
Figure 4 for Mechanics of Next Token Prediction with Self-Attention
Viaarxiv icon

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

Feb 21, 2024
Viaarxiv icon

FLASH: Federated Learning Across Simultaneous Heterogeneities

Feb 13, 2024
Viaarxiv icon

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

Add code
Feb 06, 2024
Viaarxiv icon

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

Jan 25, 2024
Viaarxiv icon

Plug-and-Play Transformer Modules for Test-Time Adaptation

Jan 10, 2024
Viaarxiv icon

MeTA: Multi-source Test Time Adaptation

Jan 04, 2024
Viaarxiv icon

Noise in the reverse process improves the approximation capabilities of diffusion models

Dec 14, 2023
Viaarxiv icon

Effective Restoration of Source Knowledge in Continual Test Time Adaptation

Nov 08, 2023
Viaarxiv icon