Christopher Ré
associate professor
The advent of large language models (LLMs) and their adoption by the leg...
The quality of training data impacts the performance of pre-trained larg...
Recent work has shown that language models' (LMs) prompt-based learning
...
We introduce a new class of objectives for optimal transport computation...
Large Language Models (LLMs), despite their recent impressive
accomplish...
A major barrier to deploying healthcare AI models is their trustworthine...
Large language models (LLMs) exhibit in-context learning abilities which...
A long standing goal of the data management community is to develop gene...
Time series modeling is a well-established problem, which often requires...
The high computational and memory requirements of large language model (...
Text-conditional diffusion models generate high-quality, diverse images....
Recent advances in deep learning have relied heavily on the use of large...
State space models (SSMs) have high performance on long sequence modelin...
State space models (SSMs) have demonstrated state-of-the-art sequence
mo...
Spectral analysis provides one of the most effective paradigms for
infor...
Language models (LMs) are becoming the foundation for almost all major
l...
Visual data such as images and videos are typically modeled as
discretiz...
Large language models (LLMs) transfer well to new tasks out-of-the-box s...
Commercial ML APIs offered by providers such as Google, Amazon and Micro...
Can foundation models be guided to execute tasks involving legal reasoni...
While large pretrained foundation models (FMs) have shown remarkable
zer...
Linear time-invariant state space models (SSM) are a classical model fro...
State space models (SSM) have recently been shown to be very effective a...
Domain generalization in medical image classification is an important pr...
Communication compression is a crucial technique for modern distributed
...
Training foundation models, such as GPT-3 and PaLM, can be extremely
exp...
Deep learning (DL) methods find increasing application in mental state
d...
Transformers are slow and memory-hungry on long sequences, since the tim...
A key promise of machine learning is the ability to assist users with
pe...
Foundation Models (FMs) are models trained on large corpora of data that...
Entity retrieval–retrieving information about entity mentions in a query...
An ideal learned representation should display transferability and
robus...
Machine learning models that achieve high overall accuracy often make
sy...
Foundation models offer an exciting new paradigm for constructing models...
Users and organizations are generating ever-increasing amounts of privat...
Magnetic resonance imaging (MRI) is a cornerstone of modern medical imag...
Spurious correlations pose a major challenge for robust machine learning...
Developing architectures suitable for modeling raw audio is a challengin...
While neural networks have shown remarkable success on classification ta...
Overparameterized neural networks generalize well but are expensive to t...
A central goal of sequence modeling is designing a single principled mod...
Recent advances in efficient Transformers have exploited either the spar...
Recurrent neural networks (RNNs), temporal convolutions, and neural
diff...
Language models (LMs) have made remarkable progress, but still struggle ...
Named entity disambiguation (NED), which involves mapping textual mentio...
In cognitive decoding, researchers aim to characterize a brain region's
...
In the last years machine learning (ML) has moved from a academic endeav...
Machine learning models are often deployed in different settings than th...
This paper studies Principal Component Analysis (PCA) for data lying in
...
Structured data, or data that adheres to a pre-defined schema, can suffe...