Search Results for author:
Found 10 papers, 4 papers with code
A Fast Transformer-based General-Purpose Lossless Compressor
To ease this problem, this paper targets on cutting down the execution time of deep-learning-based compressors.
NFL: Robust Learned Index via Distribution Transformation
Based on the characteristics of the transformed keys, we propose a robust After-Flow Learned Index (AFLI).
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over Simplex
In this work, assuming that the exact posterior or a decent approximation is obtained, we propose a generic framework to approximate the output probability distribution induced by model posterior with a parameterized model and in an amortized fashion.
Variational Nested Dropout
Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training.
EasyConvPooling: Random Pooling with Easy Convolution for Accelerating Training and Testing
Convolution operations dominate the overall execution time of Convolutional Neural Networks (CNNs).
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over the Simplex
In this work, assuming that the exact posterior or a decent approximation is obtained, we propose a generic framework to approximate the output probability distribution induced by model posterior with a parameterized model and in an amortized fashion.
Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edge
3D object detection plays a pivotal role in many applications, most notably autonomous driving and robotics.
Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion
Retrieval-based augmentations that aim to incorporate knowledge from an external database into language models have achieved great success in various knowledge-intensive (KI) tasks, such as question-answering and text generation.
Natural Language Understanding
Neural Architecture Search
+5
On the Compressibility of Quantized Large Language Models
Deploying Large Language Models (LLMs) on edge or mobile devices offers significant benefits, such as enhanced data privacy and real-time processing capabilities.
Pre-processing matters: A segment search method for WSI classification
Our study analyzes the impact of pre-processing parameters on inference and training across single- and multiple-domain datasets.
