Search Results for author:
Found 12 papers, 6 papers with code
Restructuring Vector Quantization with the Rotation Trick
However, as vector quantization is non-differentiable, the gradient to the encoder flows around the vector quantization layer rather than through it in a straight-through approximation.
Context-Aware Meta-Learning
Large Language Models like ChatGPT demonstrate a remarkable capacity to learn new concepts during inference without any fine-tuning.
Ranked #1 on
Few-Shot Image Classification
on Tiered ImageNet 5-way (5-shot)
(using extra training data)
In-Context Learning for Few-Shot Molecular Property Prediction
In this paper, we adapt the concepts underpinning in-context learning to develop a new algorithm for few-shot molecular property prediction.
Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction
However, many important molecular properties depend on complex molecular characteristics -- such as the various 3D geometries a molecule may adopt or the types of chemical interactions it can form -- that are not explicitly encoded in the feature space and must be approximated from low amounts of data.
Layerwise Bregman Representation Learning with Applications to Knowledge Distillation
In this work, we propose a novel approach for layerwise representation learning of a trained neural network.
N-Grammer: Augmenting Transformers with latent n-grams
Transformer models have recently emerged as one of the foundational models in natural language processing, and as a byproduct, there is significant recent interest and investment in scaling these models.
Ranked #7 on
Language Modelling
on C4
Step-size Adaptation Using Exponentiated Gradient Updates
In this paper, we update the step-size scale and the gain variables with exponentiated gradient updates instead.
Co-training Transformer with Videos and Images Improves Action Recognition
We term this approach as Co-training Videos and Images for Action Recognition (CoVeR).
Ranked #6 on
Action Classification
on MiT
(using extra training data)
Efficiently Identifying Task Groupings for Multi-Task Learning
Multi-task learning can leverage information learned by one task to benefit the training of other tasks.
Measuring and Harnessing Transference in Multi-Task Learning
Multi-task learning can leverage information learned by one task to benefit the training of other tasks.
Small Towers Make Big Differences
A delicate balance between multi-task generalization and multi-objective optimization is therefore needed for finding a better trade-off between efficiency and generalization.
Simplifying Graph Convolutional Networks
Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.
Ranked #3 on
Text Classification
on Ohsumed
