Dimitris Papailiopoulos

Affiliations

University of Wisconsin-Madison

papers

1,476

total citations

papers (15)

An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks

NEURIPS 2021arXiv

citations

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

NEURIPS 2023arXiv

citations

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

ICML 2025arXiv

citations

From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data

ICLR 2025arXiv

citations

Task Vectors in In-Context Learning: Emergence, Formation, and Benefits

COLM 2025arXiv

citations

CHAI: Clustered Head Attention for Efficient LLM Inference

ICML 2024arXiv

citations

Extrapolation by Association: Length Generalization Transfer In Transformers

NEURIPS 2025arXiv

citations

Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient

NEURIPS 2020

citations

Dimitris Papailiopoulos

Affiliations

papers (15)

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning

LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks

Teaching Arithmetic to Small Transformers

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

Bad Global Minima Exist and SGD Can Reach Them

Looped Transformers are Better at Learning Learning Algorithms

Rare Gems: Finding Lottery Tickets at Initialization

An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks

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

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data

Task Vectors in In-Context Learning: Emergence, Formation, and Benefits

CHAI: Clustered Head Attention for Efficient LLM Inference

Extrapolation by Association: Length Generalization Transfer In Transformers

Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient

papers (15)

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning

LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks

Teaching Arithmetic to Small Transformers

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

Bad Global Minima Exist and SGD Can Reach Them

Looped Transformers are Better at Learning Learning Algorithms

Rare Gems: Finding Lottery Tickets at Initialization

An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks

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

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data

Task Vectors in In-Context Learning: Emergence, Formation, and Benefits

CHAI: Clustered Head Attention for Efficient LLM Inference

Extrapolation by Association: Length Generalization Transfer In Transformers

Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient