research
∙
09/20/2023
DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
We propose DISC-LawLLM, an intelligent legal system utilizing large lang...
share
research
∙
09/19/2023
Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
With the fast growth of parameter size, it becomes increasingly challeng...
research
∙
09/13/2023
CARE: Large Precision Matrix Estimation for Compositional Data
High-dimensional compositional data are prevalent in many applications. ...
research
∙
09/13/2023
TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
Vision and Language Models (VLMs), such as CLIP, have enabled visual rec...
research
∙
06/23/2023
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
Multimodal Large Language Model (MLLM) relies on the powerful LLM to per...
research
∙
06/07/2023
Multivariate two-sample test statistics based on data depth
Data depth has been applied as a nonparametric measurement for ranking m...
research
∙
05/29/2023
LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
Recently, large-scale pre-trained Vision and Language (VL) models have s...
research
∙
05/11/2023
HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level
Link Prediction on Hyper-relational Knowledge Graphs (HKG) is a worthwhi...
research
∙
04/11/2023
Neural Delay Differential Equations: System Reconstruction and Image Classification
Neural Ordinary Differential Equations (NODEs), a framework of continuou...
research
∙
03/27/2023
AIR-DA: Adversarial Image Reconstruction for Unsupervised Domain Adaptive Object Detection
Unsupervised domain adaptive object detection is a challenging vision ta...
research
∙
03/16/2023
Embedding Theory of Reservoir Computing and Reducing Reservoir Network Using Time Delays
Reservoir computing (RC), a particular form of recurrent neural network,...
research
∙
03/15/2023
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
Large scale Vision-Language (VL) models have shown tremendous success in...
research
∙
03/09/2023
TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering
Temporal action segmentation in untrimmed videos has gained increased at...
research
∙
03/03/2023
Ada-Grouper: Accelerating Pipeline Parallelism in Preempted Network by Adaptive Group-Scheduling for Micro-Batches
Pipeline parallelism has been demonstrated to be a remarkable approach t...
research
∙
02/16/2023
Auto-Parallelizing Large Models with Rhino: A Systematic Approach on Production AI Platform
We present Rhino, a system for accelerating tensor programs with automat...
research
∙
02/13/2023
Expediting Distributed DNN Training with Device Topology-Aware Graph Deployment
This paper presents TAG, an automatic system to derive optimized DNN tra...
research
∙
02/01/2023
TAP: Accelerating Large-Scale DNN Training Through Tensor Automatic Parallelisation
Model parallelism has become necessary to train large neural networks. H...
research
∙
11/26/2022
SKDBERT: Compressing BERT via Stochastic Knowledge Distillation
In this paper, we propose Stochastic Knowledge Distillation (SKD) to obt...
research
∙
11/24/2022
Video Test-Time Adaptation for Action Recognition
Although action recognition systems can achieve top performance when eva...
research
∙
11/23/2022
ActMAD: Activation Matching to Align Distributions for Test-Time-Training
Test-Time-Training (TTT) is an approach to cope with out-of-distribution...
research
∙
11/21/2022
MATE: Masked Autoencoders are Online 3D Test-Time Learners
We propose MATE, the first Test-Time-Training (TTT) method designed for ...
research
∙
10/07/2022
Multi-Frequency-Aware Patch Adversarial Learning for Neural Point Cloud Rendering
We present a neural point cloud rendering pipeline through a novel multi...
research
∙
09/26/2022
Optimizing DNN Compilation for Distributed Training with Joint OP and Tensor Fusion
This paper proposes DisCo, an automatic deep learning compilation module...
research
∙
09/19/2022
Heterogeneous Federated Learning on a Graph
Federated learning, where algorithms are trained across multiple decentr...
research
∙
08/30/2022
EasyScale: Accuracy-consistent Elastic Training for Deep Learning
Distributed synchronized GPU training is commonly used for deep learning...
research
∙
06/17/2022
GDsmith: Detecting Bugs in Graph Database Engines
Graph database engines stand out in the era of big data for their effici...
research
∙
05/03/2022
Cross-View Cross-Scene Multi-View Crowd Counting
Multi-view crowd counting has been previously proposed to utilize multi-...
research
∙
04/30/2022
EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing
The success of Pre-Trained Models (PTMs) has reshaped the development of...
research
∙
04/22/2022
Efficient Pipeline Planning for Expedited Distributed DNN Training
To train modern large DNN models, pipeline parallelism has recently emer...
research
∙
04/11/2022
PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems
The development of personalized recommendation has significantly improve...
research
∙
03/30/2022
CycDA: Unsupervised Cycle Domain Adaptation from Image to Video
Although action recognition has achieved impressive results over recent ...
research
∙
01/04/2022
Neural Piecewise-Constant Delay Differential Equations
Continuous-depth neural networks, such as the Neural Ordinary Differenti...
research
∙
10/22/2021
Temporal Point Process Graphical Models
Many real-world objects can be modeled as a stream of events on the node...
research
∙
10/08/2021
M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Recent expeditious developments in deep learning algorithms, distributed...
research
∙
09/10/2021
Principal component analysis for high-dimensional compositional data
Dimension reduction for high-dimensional compositional data plays an imp...
research
∙
08/24/2021
Binary Code based Hash Embedding for Web-scale Applications
Nowadays, deep learning models are widely adopted in web-scale applicati...
research
∙
08/24/2021
Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
Embedding learning for categorical features is crucial for the deep lear...
research
∙
07/16/2021
Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data
Recently, neural network compression schemes like channel pruning have b...
research
∙
06/09/2021
Harmless Overparametrization in Two-layer Neural Networks
Overparametrized neural networks, where the number of active parameters ...
research
∙
05/31/2021
Exploring Sparse Expert Models and Beyond
Mixture-of-Experts (MoE) models can achieve promising results with outra...
research
∙
05/17/2021
Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach
In real-world search, recommendation, and advertising systems, the multi...
research
∙
03/09/2021
DISC: A Dynamic Shape Compiler for Machine Learning Workloads
Many recent machine learning models show dynamic shape characteristics. ...
research
∙
03/01/2021
M6: A Chinese Multimodal Pretrainer
In this work, we construct the largest dataset for multimodal pretrainin...
research
∙
02/22/2021
Neural Delay Differential Equations
Neural Ordinary Differential Equations (NODEs), a framework of continuou...
research
∙
12/16/2020
Focusing More on Conflicts with Mis-Predictions Helps Language Pre-Training
In this work, we propose to improve the effectiveness of language pre-tr...
research
∙
11/18/2020
EasyTransfer – A Simple and Scalable Deep Transfer Learning Platform for NLP Applications
The literature has witnessed the success of applying deep Transfer Learn...
research
∙
11/18/2020
Whale: A Unified Distributed Training Framework
Data parallelism (DP) has been a common practice to speed up the trainin...
research
∙
10/28/2020
INT8 Winograd Acceleration for Conv1D Equipped ASR Models Deployed on Mobile Devices
The intensive computation of Automatic Speech Recognition (ASR) models o...
research
∙
09/23/2020
FusionStitching: Boosting Memory Intensive Computations for Deep Learning Workloads
We show in this work that memory intensive computations can result in se...
research
∙
09/09/2020