Search Results for author:
Found 33 papers, 13 papers with code
DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines
This paper proposes a dynamic micro-batching approach to tackle sequence length variation and enable efficient multi-task model training.
Serving Deep Learning Model in Relational Databases
Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains, sparking growing interest recently.
Target-independent XLA optimization using Reinforcement Learning
We also propose enhancements to the deep RL algorithms to further improve optimal search performance and open the research direction for domain-specific guidance for RL.
$\mathrm{SAM^{Med}}$: A medical image annotation framework based on large vision model
The $\mathrm{SAM^{assist}}$ demonstrates the generalization ability of SAM to the downstream medical segmentation task using the prompt-learning approach.
RAF: Holistic Compilation for Deep Learning Model Training
In this paper, we present RAF, a deep learning compiler for training.
Decoupled Model Schedule for Deep Learning Training
Specifically, the schedule works on a PyTorch model and uses a set of schedule primitives to convert the model for common model training optimizations such as high-performance kernels, effective 3D parallelism, and efficient activation checkpointing.
Lidar Upsampling with Sliced Wasserstein Distance
This in turn enables our method to employ a one-stage upsampling paradigm without the need for coarse and fine reconstruction.
Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs
With the proposed paradigm, we implement a deep learning compiler Hidet.
SoftPool++: An Encoder-Decoder Network for Point Cloud Completion
We propose a novel convolutional operator for the task of point cloud completion.
Towards Reliable and Explainable AI Model for Solid Pulmonary Nodule Diagnosis
However, detection and accurate diagnosis of pulmonary nodules depend heavily on the experiences of radiologists and can be a heavy workload for them.
Learning Local Displacements for Point Cloud Completion
To this aim, we introduce a second model that assembles our layers within a transformer architecture.
From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction
There have been numerous recently proposed methods for monocular depth prediction (MDP) coupled with the equally rapid evolution of benchmarking tools.
Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning
Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations.
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones.
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
Most modern deep learning-based multi-view 3D reconstruction techniques use RNNs or fusion modules to combine information from multiple images after independently encoding them.
Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues
This paper propose to combine pretrained language models with the modular dialogue paradigm for open-domain dialogue modeling.
Diversifying Dialog Generation via Adaptive Label Smoothing
Neural dialogue generation models trained with the one-hot target distribution suffer from the over-confidence issue, which leads to poor generation diversity as widely reported in the literature.
Bring Your Own Codegen to Deep Learning Compiler
Deep neural networks (DNNs) have been ubiquitously applied in many applications, and accelerators are emerged as an enabler to support the fast and efficient inference tasks of these applications.
UNIT: Unifying Tensorized Instruction Compilation
However, it is hard to leverage mixed precision without hardware support because of the overhead of data casting.
HAWQV3: Dyadic Neural Network Quantization
Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values.
FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems
FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge.
SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification
In this paper, we propose a method for 3D object completion and classification based on point clouds.
A Large-Scale Chinese Short-Text Conversation Dataset
The cleaned dataset and the pre-training models will facilitate the research of short-text conversation modeling.
Structure-SLAM: Low-Drift Monocular SLAM in Indoor Environments
In this paper a low-drift monocular SLAM method is proposed targeting indoor scenarios, where monocular SLAM often fails due to the lack of textured surfaces.
Robotics
Efficient Execution of Quantized Deep Learning Models: A Compiler Approach
A deep learning compiler such as Apache TVM can enable the efficient execution of model from various frameworks on various targets.
Is Network the Bottleneck of Distributed Training?
As such, we advocate that the real challenge of distributed training is for the network community to develop high-performance network transport to fully utilize the network capacity and achieve linear scale-out.
Ansor: Generating High-Performance Tensor Programs for Deep Learning
Ansor can find high-performance programs that are outside the search space of existing state-of-the-art approaches.
Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference
Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes.
Optimizing Memory-Access Patterns for Deep Learning Accelerators
Deep learning (DL) workloads are moving towards accelerators for faster processing and lower cost.
ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image
We propose a novel model for 3D semantic completion from a single depth image, based on a single encoder and three separate generators used to reconstruct different geometric and semantic representations of the original and completed scene, all sharing the same latent space.
Ranked #7 on
3D Semantic Scene Completion
on NYUv2
(using extra training data)
Adversarial Semantic Scene Completion from a Single Depth Image
We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image.
Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models
In this paper, our generative model trained with synthetic images rendered from 3D models reduces the workload of data collection and limitation of conditions.
Enabling Factor Analysis on Thousand-Subject Neuroimaging Datasets
The scale of functional magnetic resonance image data is rapidly increasing as large multi-subject datasets are becoming widely available and high-resolution scanners are adopted.
