Christopher Ré

papers

7,817

total citations

papers (27)

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

NEURIPS 2022arXiv

3,551

citations

Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers

NEURIPS 2021arXiv

977

citations

LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

NEURIPS 2023arXiv

319

citations

No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems

NEURIPS 2020arXiv

281

citations

Scatterbrain: Unifying Sparse and Low-rank Attention

NEURIPS 2021arXiv

154

citations

Decentralized Training of Foundation Models in Heterogeneous Environments

NEURIPS 2022arXiv

126

citations

From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

NEURIPS 2020arXiv

110

citations

Skill-it! A data-driven skills framework for understanding and training language models

NEURIPS 2023arXiv

citations

Contrastive Adapters for Foundation Model Group Robustness

NEURIPS 2022arXiv

citations

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

NEURIPS 2023arXiv

citations

Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data

NEURIPS 2022arXiv

citations

S4ND: Modeling Images and Videos as Multidimensional Signals with State Spaces

NEURIPS 2022arXiv

citations

An Architecture Search Framework for Inference-Time Techniques

ICML 2025arXiv

citations

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions

NEURIPS 2023arXiv

citations

Rethinking Neural Operations for Diverse Tasks

NEURIPS 2021arXiv

citations

Transform Once: Efficient Operator Learning in Frequency Domain

NEURIPS 2022arXiv

citations

TART: A plug-and-play Transformer module for task-agnostic reasoning

NEURIPS 2023arXiv

citations

Cost-efficient Collaboration between On-device and Cloud Language Models

ICML 2025arXiv

citations

HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions

NEURIPS 2022arXiv

citations

Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification

NEURIPS 2023arXiv

citations

ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels

ICLR 2025

citations

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

NEURIPS 2023

citations

Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees

NEURIPS 2022

citations

A case for reframing automated medical image classification as segmentation

NEURIPS 2023

citations

Christopher Ré

papers (27)

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers

HiPPO: Recurrent Memory with Optimal Polynomial Projections

On the Parameterization and Initialization of Diagonal State Space Models

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems

Scatterbrain: Unifying Sparse and Low-rank Attention

Decentralized Training of Foundation Models in Heterogeneous Environments

From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

Skill-it! A data-driven skills framework for understanding and training language models

Contrastive Adapters for Foundation Model Group Robustness

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data

S4ND: Modeling Images and Videos as Multidimensional Signals with State Spaces

An Architecture Search Framework for Inference-Time Techniques

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions

Rethinking Neural Operations for Diverse Tasks

Transform Once: Efficient Operator Learning in Frequency Domain

TART: A plug-and-play Transformer module for task-agnostic reasoning

Cost-efficient Collaboration between On-device and Cloud Language Models

HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions

Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification

ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees

A case for reframing automated medical image classification as segmentation

papers (27)

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers

HiPPO: Recurrent Memory with Optimal Polynomial Projections

On the Parameterization and Initialization of Diagonal State Space Models

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems

Scatterbrain: Unifying Sparse and Low-rank Attention

Decentralized Training of Foundation Models in Heterogeneous Environments

From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

Skill-it! A data-driven skills framework for understanding and training language models

Contrastive Adapters for Foundation Model Group Robustness

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data

S4ND: Modeling Images and Videos as Multidimensional Signals with State Spaces

An Architecture Search Framework for Inference-Time Techniques

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions

Rethinking Neural Operations for Diverse Tasks

Transform Once: Efficient Operator Learning in Frequency Domain

TART: A plug-and-play Transformer module for task-agnostic reasoning

Cost-efficient Collaboration between On-device and Cloud Language Models

HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions

Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification

ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees

A case for reframing automated medical image classification as segmentation