Samet Oymak

Venues

Frequent coauthors

Papers

1. AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments
   CVPR 2025 ·

   Xiangyu Chang

   DBLP profile ↗ORCID search ↗
2. Attention with Trained Embeddings Provably Selects Important Tokens
   NeurIPS 2025 ·

   Diyuan Wu

   DBLP profile ↗ORCID search ↗
3. BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
   NeurIPS 2025 ·

   Xuechen Zhang

   DBLP profile ↗ORCID search ↗
4. Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
   ICML 2025 ·

   Zheyang Xiong

   DBLP profile ↗ORCID search ↗
5. Extrapolation by Association: Length Generalization Transfer In Transformers
   NeurIPS 2025 ·

   Ziyang Cai

   DBLP profile ↗ORCID search ↗
6. High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
   ICLR 2025 ·

   Muhammed Emrullah Ildiz

   DBLP profile ↗ORCID search ↗
7. On the Power of Convolution-Augmented Transformer
   AAAI 2025 ·

   Mingchen Li

   DBLP profile ↗ORCID search ↗
8. Provable Benefits of Task-Specific Prompts for In-context Learning
   AISTATS 2025 ·

   Xiangyu Chang

   DBLP profile ↗ORCID search ↗
9. Test-Time Training Provably Improves Transformers as In-context Learners
   ICML 2025 ·

   Halil Alperen Gozeten

   DBLP profile ↗ORCID search ↗
10. TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data
    AAAI 2025 ·

    Ege Onur Taga

    DBLP profile ↗ORCID search ↗
11. When and How Unlabeled Data Provably Improve In-Context Learning
    NeurIPS 2025 ·

    Yingcong Li

    DBLP profile ↗ORCID search ↗
12. A Score-Based Deterministic Diffusion Algorithm with Smooth Scores for General Distributions
    AAAI 2024 ·

    Karthik Elamvazhuthi

    DBLP profile ↗ORCID search ↗
13. CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
    NeurIPS 2024 ·

    Sk Miraj Ahmed

    DBLP profile ↗ORCID search ↗
14. Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks
    ICML 2024 ·

    Jongho Park

    DBLP profile ↗ORCID search ↗
15. Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective
    AAAI 2024 ·

    Xuechen Zhang

    DBLP profile ↗ORCID search ↗
16. Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
    NeurIPS 2024 ·

    Xuechen Zhang

    DBLP profile ↗ORCID search ↗
17. Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
    NeurIPS 2024 ·

    Yingcong Li

    DBLP profile ↗ORCID search ↗
18. From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
    ICML 2024 ·

    Muhammed Emrullah Ildiz

    DBLP profile ↗ORCID search ↗
19. Mechanics of Next Token Prediction with Self-Attention
    AISTATS 2024 ·

    Yingcong Li

    DBLP profile ↗ORCID search ↗
20. Selective Attention: Enhancing Transformer through Principled Context Control
    NeurIPS 2024 ·

    Xuechen Zhang

    DBLP profile ↗ORCID search ↗
21. Understanding Inverse Scaling and Emergence in Multitask Representation Learning
    AISTATS 2024 ·

    Muhammed Emrullah Ildiz

    DBLP profile ↗ORCID search ↗