b'Yang You'

research

∙ 09/10/2023

Boosting Unsupervised Contrastive Learning Using Diffusion-Based Data Augmentation From Scratch

Unsupervised contrastive learning methods have recently seen significant...

0 Zelin Zang, et al. ∙

research

∙ 08/30/2023

Hanayo: Harnessing Wave-like Pipeline Parallelism for Enhanced Large Model Training Efficiency

Large-scale language models have become increasingly challenging and exp...

0 Ziming Liu, et al. ∙

research

∙ 08/21/2023

Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification

Unsupervised domain adaptive person re-identification (Re-ID) methods al...

0 Jianyang Gu, et al. ∙

research

∙ 08/21/2023

Dataset Quantization

State-of-the-art deep neural networks are trained with large amounts (mi...

0 Daquan Zhou, et al. ∙

research

∙ 07/05/2023

CAME: Confidence-guided Adaptive Memory Efficient Optimization

Adaptive gradient methods, such as Adam and LAMB, have demonstrated exce...

0 Yang Luo, et al. ∙

research

∙ 05/26/2023

Summarizing Stream Data for Memory-Restricted Online Continual Learning

Replay-based methods have proved their effectiveness on online continual...

0 Jianyang Gu, et al. ∙

research

∙ 05/22/2023

Are Large Language Models Good Evaluators for Abstractive Summarization?

Human evaluations are often required for abstractive summary evaluations...

0 Chenhui Shen, et al. ∙

research

∙ 05/19/2023

Monte-Carlo Search for an Equilibrium in Dec-POMDPs

Decentralized partially observable Markov decision processes (Dec-POMDPs...

0 Yang You, et al. ∙

research

∙ 05/15/2023

A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization

Pre-trained language models (PLMs) have accomplished impressive achievem...

0 Chenhui Shen, et al. ∙

research

∙ 03/22/2023

BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency

As one of the most fundamental techniques in multimodal learning, cross-...

0 Shuo Yang, et al. ∙

research

∙ 03/12/2023

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

Continual learning (CL) can help pre-trained vision-language models effi...

0 Zangwei Zheng, et al. ∙

research

∙ 03/08/2023

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Data pruning aims to obtain lossless performances as training on the ori...

0 Ziheng Qin, et al. ∙

research

∙ 03/08/2023

DiM: Distilling Dataset into Generative Model

Dataset distillation reduces the network training cost by synthesizing s...

0 Kai Wang, et al. ∙

research

∙ 03/06/2023

CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame

Various recent methods attempt to implement rotation-invariant 3D deep l...

0 Yujing Lou, et al. ∙

research

∙ 02/28/2023

DREAM: Efficient Dataset Distillation by Representative Matching

Dataset distillation aims to generate small datasets with little informa...

0 Yanqing Liu, et al. ∙

research

∙ 02/27/2023

Robust Robot Planning for Human-Robot Collaboration

In human-robot collaboration, the objectives of the human are often unkn...

0 Yang You, et al. ∙

research

∙ 02/06/2023

Colossal-Auto: Unified Automation of Parallelization and Activation Checkpoint for Large-scale Models

In recent years, large-scale models have demonstrated state-of-the-art p...

0 Yuliang Liu, et al. ∙

research

∙ 01/20/2023

ATP: Adaptive Tensor Parallelism for Foundation Models

Foundation models have impressive performance and generalization capabil...

0 Shenggan Cheng, et al. ∙

research

∙ 01/01/2023

MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs

New architecture GPUs like A100 are now equipped with multi-instance GPU...

0 Huaizheng Zhang, et al. ∙

research

∙ 12/30/2022

On the Inconsistencies of Conditionals Learned by Masked Language Models

Learning to predict masked tokens in a sequence has been shown to be a p...

0 Tom Young, et al. ∙

research

∙ 12/29/2022

GPTR: Gestalt-Perception Transformer for Diagram Object Detection

Diagram object detection is the key basis of practical applications such...

0 Xin Hu, et al. ∙

research

∙ 12/10/2022

Elixir: Train a Large Language Model on a Small GPU Cluster

In recent years, the number of parameters of one deep learning (DL) mode...

0 Haichen Huang, et al. ∙

research

∙ 11/24/2022

Go Beyond Point Pairs: A General and Accurate Sim2Real Object Pose Voting Method with Efficient Online Synthetic Training

Object pose estimation is an important topic in 3D vision. Though most c...

0 Yang You, et al. ∙

research

∙ 11/24/2022

One-Shot General Object Localization

This paper presents a general one-shot object localization algorithm cal...

0 Yang You, et al. ∙

research

∙ 10/26/2022

SentBS: Sentence-level Beam Search for Controllable Summarization

A wide range of control perspectives have been explored in controllable ...

0 Chenhui Shen, et al. ∙

research

∙ 09/06/2022

EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models

Large transformer models display promising performance on a wide range o...

0 Jiangsu Du, et al. ∙

research

∙ 08/18/2022

Prompt Vision Transformer for Domain Generalization

Though vision transformers (ViTs) have exhibited impressive ability for ...

0 Zangwei Zheng, et al. ∙

research

∙ 08/08/2022

A Frequency-aware Software Cache for Large Recommendation System Embeddings

Deep learning recommendation models (DLRMs) have been widely applied in ...

0 Jiarui Fang, et al. ∙

research

∙ 07/19/2022

Active-Learning-as-a-Service: An Efficient MLOps System for Data-Centric AI

The success of today's AI applications requires not only model training ...

0 Yizheng Huang, et al. ∙

research

∙ 05/28/2022

Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

Domain Adaptation of Black-box Predictors (DABP) aims to learn a model o...

0 Jianfei Yang, et al. ∙

research

∙ 05/23/2022

FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders

Face recognition, as one of the most successful applications in artifici...

16 Kai Wang, et al. ∙

research

∙ 04/30/2022

Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Learning with noisy labels has aroused much research interest since data...

0 Kai Wang, et al. ∙

research

∙ 03/07/2022

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

In this paper, we tackle the problem of category-level 9D pose estimatio...

0 Yang You, et al. ∙

research

∙ 03/05/2022

Towards Efficient and Scalable Sharpness-Aware Minimization

Recently, Sharpness-Aware Minimization (SAM), which connects the geometr...

5 Yong Liu, et al. ∙

research

∙ 03/03/2022

CAFE: Learning to Condense Dataset by Aligning Features

Dataset condensation aims at reducing the network training effort throug...

23 Kai Wang, et al. ∙

research

∙ 03/02/2022

FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours

Protein structure prediction is an important method for understanding ge...

0 Shenggan Cheng, et al. ∙

research

∙ 02/07/2022

Crafting Better Contrastive Views for Siamese Representation Learning

Recent self-supervised contrastive learning methods greatly benefit from...

0 Xiangyu Peng, et al. ∙

research

∙ 11/21/2021

Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine

Pixel-level 2D object semantic understanding is an important topic in co...

1 Yang You, et al. ∙

research

∙ 10/28/2021

Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training

The Transformer architecture has improved the performance of deep learni...

0 Zhengda Bian, et al. ∙

research

∙ 10/14/2021

MReD: A Meta-Review Dataset for Controllable Text Generation

When directly using existing text generation datasets for controllable g...

0 Chenhui Shen, et al. ∙

research

∙ 09/17/2021

Solving infinite-horizon Dec-POMDPs using Finite State Controllers within JESP

This paper looks at solving collaborative planning problems formalized a...

0 Yang You, et al. ∙

research

∙ 08/12/2021

PatrickStar: Parallel Training of Pre-trained Models via a Chunk-based Memory Management

The pre-trained model (PTM) is revolutionizing Artificial intelligence (...

0 Jiarui Fang, et al. ∙

research

∙ 08/08/2021

Online Evolutionary Batch Size Orchestration for Scheduling Deep Learning Workloads in GPU Clusters

Efficient GPU resource scheduling is essential to maximize resource util...

0 Zhengda Bian, et al. ∙

research

∙ 06/01/2021

Concurrent Adversarial Learning for Large-Batch Training

Large-batch training has become a commonly used technique when training ...

0 Yong Liu, et al. ∙

research

∙ 05/30/2021

2.5-dimensional distributed model training

Data parallelism does a good job in speeding up the training. However, w...

0 Boxiang Wang, et al. ∙

research

∙ 05/30/2021

Maximizing Parallelism in Distributed Training for Huge Neural Networks

The recent Natural Language Processing techniques have been refreshing t...

0 Zhengda Bian, et al. ∙

research

∙ 05/21/2021

An Efficient Training Approach for Very Large Scale Face Recognition

Face recognition has achieved significant progress in deep-learning era ...

10 Kai Wang, et al. ∙

research

∙ 04/12/2021

An Efficient 2D Method for Training Super-Large Deep Learning Models

Huge neural network models have shown unprecedented performance in real-...

0 Qifan Xu, et al. ∙

research

∙ 03/19/2021

Skeleton Merger: an Unsupervised Aligned Keypoint Detector

Detecting aligned 3D keypoints is essential under many scenarios such as...

0 Ruoxi Shi, et al. ∙

research

∙ 02/24/2021

PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

Point cloud analysis without pose priors is very challenging in real app...

7 Yang You, et al. ∙

Yang You

Featured Co-authors