Christopher Re

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data ICLR 2025 Towards Learning High-Precision Least Squares Algorithms with Sequence Models ICLR 2025 Scaling Laws for Precision ICLR 2025 HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation CVPR 2025 Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers JMLR 2025 KernelBench: Can LLMs Write Efficient GPU Kernels? ICML 2025 An Architecture Search Framework for Inference-Time Techniques ICML 2025 Restructuring Vector Quantization with the Rotation Trick ICLR 2025 Cost-efficient Collaboration between On-device and Cloud Language Models ICML 2025 ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels ICLR 2025 Aioli: A Unified Optimization Framework for Language Model Data Mixing ICLR 2025 LoLCATs: On Low-Rank Linearizing of Large Language Models ICLR 2025 Smoothie: Label Free Language Model Routing NIPS 2024 State-Free Inference of State-Space Models: The *Transfer Function* Approach ICML 2024 Prospector Heads: Generalized Feature Attribution for Large Models & Data ICML 2024 Simple linear attention language models balance the recall-throughput tradeoff ICML 2024 Collage Diffusion WACV 2024 Zoology: Measuring and Improving Recall in Efficient Language Models ICLR 2024 Context-Aware Meta-Learning ICLR 2024 The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry ICLR 2024 FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores ICLR 2024 Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT ICML 2024 Mechanistic Design and Scaling of Hybrid Architectures ICML 2024 WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks NIPS 2024 RedPajama: an Open Dataset for Training Large Language Models NIPS 2024 Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time ICML 2023 How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections ICLR 2023 Simple Hardware-Efficient Long Convolutions for Sequence Modeling ICML 2023 Ask Me Anything: A simple strategy for prompting language models ICLR 2023 Hungry Hungry Hippos: Towards Language Modeling with State Space Models ICLR 2023 CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks ICML 2023 HAPI Explorer: Comprehension, Discovery, and Explanation on History of ML APIs AAAI 2023 Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification NIPS 2023 Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture NIPS 2023 TART: A plug-and-play Transformer module for task-agnostic reasoning NIPS 2023 Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions NIPS 2023 H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models NIPS 2023 Hyena Hierarchy: Towards Larger Convolutional Language Models ICML 2023 Fast Algorithms for a New Relaxation of Optimal Transport COLT 2023 FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU ICML 2023 Effectively Modeling Time Series with Simple Discrete State Spaces ICLR 2023 Skill-it! A data-driven skills framework for understanding and training language models NIPS 2023 HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution NIPS 2023 LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models NIPS 2023 A case for reframing automated medical image classification as segmentation NIPS 2023 Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations ICML 2022 Machine Learning on Graphs: A Model and Comprehensive Taxonomy JMLR 2022 Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning ICML 2022 Monarch: Expressive Structured Matrices for Efficient and Accurate Training ICML 2022 Shoring up the foundations: fusing model embeddings and weak supervision UAI 2022 S4ND: Modeling Images and Videos as Multidimensional Signals with State Spaces NIPS 2022 Transform Once: Efficient Operator Learning in Frequency Domain NIPS 2022 FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness NIPS 2022 Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees NIPS 2022 Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data NIPS 2022 Contrastive Adapters for Foundation Model Group Robustness NIPS 2022 HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions NIPS 2022 Decentralized Training of Foundation Models in Heterogeneous Environments NIPS 2022 On the Parameterization and Initialization of Diagonal State Space Models NIPS 2022 Reducing Reliance on Spurious Features in Medical Image Classification with Spatial Specificity MLHC 2022 Metadata Shaping: A Simple Approach for Knowledge-Enhanced Language Models ACL 2022 TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval ACL 2022 VORTEX: Physics-Driven Data Augmentations Using Consistency Training for Robust Accelerated MRI Reconstruction MIDL 2022 Domino: Discovering Systematic Errors with Cross-Modal Embeddings ICLR 2022 Efficiently Modeling Long Sequences with Structured State Spaces ICLR 2022 Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models ICLR 2022 It’s Raw! Audio Generation with State-Space Models ICML 2022 Cut out the annotator, keep the cutout: better segmentation with weak supervision ICLR 2021 MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training ICLR 2021 HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections ICML 2021 Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation AISTATS 2021 Scatterbrain: Unifying Sparse and Low-rank Attention NIPS 2021 Rethinking Neural Operations for Diverse Tasks NIPS 2021 Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers NIPS 2021 Robustness Gym: Unifying the NLP Evaluation Landscape NAACL 2021 Goodwill Hunting: Analyzing and Repurposing Off-the-Shelf Named Entity Linking Systems NAACL 2021 Catformer: Designing Stable Transformers via Sensitivity Analysis ICML 2021 Mandoline: Model Evaluation under Distribution Shift ICML 2021 Cross-Domain Data Integration for Named Entity Disambiguation in Biomedical Text EMNLP 2021 Model Patching: Closing the Subgroup Performance Gap with Data Augmentation ICLR 2021 On the Generalization Effects of Linear Transformations in Data Augmentation ICML 2020 Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods ICML 2020 From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering NIPS 2020 Ivy: Instrumental Variable Synthesis for Causal Inference AISTATS 2020 Low-Dimensional Hyperbolic Knowledge Graph Embeddings ACL 2020 Contextual Embeddings: When Are They Worth It? ACL 2020 HiPPO: Recurrent Memory with Optimal Polynomial Projections NIPS 2020 Understanding and Improving Information Transfer in Multi-Task Learning ICLR 2020 Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps ICLR 2020 No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems NIPS 2020 Learning Mixed-Curvature Representations in Product Spaces ICLR 2019 Hyperbolic Graph Convolutional Neural Networks NIPS 2019 Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices NIPS 2019 Multi-Resolution Weak Supervision for Sequential Data NIPS 2019 On the Downstream Performance of Compressed Word Embeddings NIPS 2019 Training Complex Models with Multi-Task Weak Supervision AAAI 2019 Low-Precision Random Fourier Features for Memory-constrained Kernel Approximation AISTATS 2019 Scene Graph Prediction With Limited Labels ICCV 2019 Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations ICML 2019 A Kernel Theory of Modern Data Augmentation ICML 2019 Learning Dependency Structures for Weak Supervision Models ICML 2019 Learning Compressed Transforms with Low Displacement Rank NIPS 2018 Weighted SGD for $\ell_p$ Regression with Randomized Preconditioning JMLR 2018 Representation Tradeoffs for Hyperbolic Embeddings ICML 2018 Training Classifiers with Natural Language Explanations ACL 2018 Inferring Generative Model Structure with Static Analysis NIPS 2017 Gaussian Quadrature for Kernel Features NIPS 2017 Learning the Structure of Generative Models without Labeled Data ICML 2017 Learning to Compose Domain-Specific Transformations for Data Augmentation NIPS 2017 Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling IJCAI 2017 Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much NIPS 2016 Data Programming: Creating Large Training Sets, Quickly NIPS 2016 Sub-sampled Newton Methods with Non-uniform Sampling NIPS 2016 Cyclades: Conflict-free Asynchronous Machine Learning NIPS 2016 Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width NIPS 2015 An Asynchronous Parallel Stochastic Coordinate Descent Algorithm JMLR 2015 Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems ICML 2015 Asynchronous stochastic convex optimization: the noise is in the noise and SGD don't care NIPS 2015 Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms NIPS 2015 An Asynchronous Parallel Stochastic Coordinate Descent Algorithm ICML 2014 Parallel Feature Selection Inspired by Group Testing NIPS 2014 Understanding Tables in Context Using Standard NLP Toolkits ACL 2013 An Approximate, Efficient LP Solver for LP Rounding NIPS 2013 Toward a Noncommutative Arithmetic-geometric Mean Inequality: Conjectures, Case-studies, and Consequences COLT 2012 Factoring nonnegative matrices with linear programs NIPS 2012 Big Data versus the Crowd: Looking for Relationships in All the Right Places ACL 2012 Hogwild!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent NIPS 2011