research
∙
03/13/2023
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
The high computational and memory requirements of large language model (...
share
research
∙
02/21/2023
Hyena Hierarchy: Towards Larger Convolutional Language Models
Recent advances in deep learning have relied heavily on the use of large...
research
∙
02/13/2023
Simple Hardware-Efficient Long Convolutions for Sequence Modeling
State space models (SSMs) have high performance on long sequence modelin...
research
∙
12/28/2022
Hungry Hungry Hippos: Towards Language Modeling with State Space Models
State space models (SSMs) have demonstrated state-of-the-art sequence mo...
research
∙
06/10/2022
Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models
We study how networking corruptions–data corruptions caused by networkin...
research
∙
05/27/2022
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Transformers are slow and memory-hungry on long sequences, since the tim...
research
∙
04/18/2022
TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
Entity retrieval–retrieving information about entity mentions in a query...
research
∙
04/15/2022
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
An ideal learned representation should display transferability and robus...
research
∙
03/24/2022
Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Foundation models offer an exciting new paradigm for constructing models...
research
∙
08/13/2020
Analyzing Who and What Appears in a Decade of US Cable TV News
Cable TV news reaches millions of U.S. households each day, meaning that...
research
∙
06/26/2020
Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
Our goal is to enable machine learning systems to be trained interactive...
research
∙
02/27/2020
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Weak supervision is a popular method for building machine learning model...
research
∙
10/21/2019
Multi-Resolution Weak Supervision for Sequential Data
Since manually labeling training data is slow and expensive, recent indu...
research
∙
10/07/2019
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Many real-world video analysis applications require the ability to ident...
research
∙
07/29/2018
Automatic Parallelization of Sequential Programs
Prior work on Automatically Scalable Computation (ASC) suggests that it ...
research
∙
04/23/2018