383 citations · 1.2k across the 28 of their papers we have counts for
28 papers
Pretrained Diffusion Models for Unified Human Motion Synthesis
Jianxin Ma, Shuai Bai, Chang Zhou
Generative modeling of human motion has broad applications in computer animation, virtual reality, and robotics. Conventional approaches develop separate models for different motio…
Prompt Tuning for Generative Multimodal Pretrained Models
Hao Yang, Junyang Lin, An Yang +3
Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining. In this work, we explore the t…
Single Stage Virtual Try-on via Deformable Attention Flows
Shuai Bai, Huiling Zhou, Zhikang Li +2
Virtual try-on aims to generate a photo-realistic fitting result given an in-shop garment and a reference person image. Existing methods usually build up multi-stage frameworks to…
Instance-wise Prompt Tuning for Pretrained Language Models
Yuezihan Jiang, Hao Yang, Junyang Lin +6
Prompt Learning has recently gained great popularity in bridging the gap between pretraining tasks and various downstream tasks. It freezes Pretrained Language Models (PLMs) and on…
M6-Fashion: High-Fidelity Multi-modal Image Generation and Editing
Zhikang Li, Huiling Zhou, Shuai Bai +3
The fashion industry has diverse applications in multi-modal image generation and editing. It aims to create a desired high-fidelity image with the multi-modal conditional signal a…
M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems
Zeyu Cui, Jianxin Ma, Chang Zhou +2
Industrial recommender systems have been growing increasingly complex, may involve \emph{diverse domains} such as e-commerce products and user-generated contents, and can comprise…
Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
Yu Huang, Junyang Lin, Chang Zhou +2
Despite the remarkable success of deep multi-modal learning in practice, it has not been well-explained in theory. Recently, it has been observed that the best uni-modal network ou…
In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
Xiao Pan, Peike Li, Zongxin Yang +5
In this paper, we focus on unsupervised learning for Video Object Segmentation (VOS) which learns visual correspondence (i.e., the similarity between pixel-level features) from unl…
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
Peng Wang, An Yang, Rui Men +7
In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Mo…
Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks
Qingsong Lv, Ming Ding, Qiang Liu +7
Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understandi…
M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Junyang Lin, An Yang, Jinze Bai +9
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 a…
Learning to Rehearse in Long Sequence Memorization
Zhu Zhang, Chang Zhou, Jianxin Ma +4
Existing reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning, requiring unlimited storage resources and suffering from…
Controllable Gradient Item Retrieval
Haonan Wang, Chang Zhou, Carl Yang +2
In this paper, we identify and study an important problem of gradient item retrieval. We define the problem as retrieving a sequence of items with a gradual change on a certain att…
Connecting Language and Vision for Natural Language-Based Vehicle Retrieval
Shuai Bai, Zhedong Zheng, Xiaohan Wang +5
Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing practices focus on the image-based vehicle matching, including vehicle…
Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation
Peng Wang, Junyang Lin, An Yang +4
Table-to-text generation refers to generating a descriptive text from a key-value table. Traditional autoregressive methods, though can generate text with high fluency, suffer from…
M6-T: Exploring Sparse Expert Models and Beyond
An Yang, Junyang Lin, Rui Men +12
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scal…
M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers
Zhu Zhang, Jianxin Ma, Chang Zhou +6
Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as…
CogView: Mastering Text-to-Image Generation via Transformers
Ming Ding, Zhuoyi Yang, Wenyi Hong +8
Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4…
CogDL: A Comprehensive Library for Graph Deep Learning
Yukuo Cen, Zhenyu Hou, Yan Wang +15
Graph neural networks (GNNs) have attracted tremendous attention from the graph learning community in recent years. It has been widely adopted in various real-world applications fr…
Understanding Negative Sampling in Graph Representation Learning
Zhen Yang, Ming Ding, Chang Zhou +3
Graph representation learning has been extensively studied in recent years. Despite its potential in generating continuous embeddings for various networks, both the effectiveness a…
Controllable Multi-Interest Framework for Recommendation
Yukuo Cen, Jianwei Zhang, Xu Zou +3
Recently, neural networks have been widely used in e-commerce recommender systems, owing to the rapid development of deep learning. We formalize the recommender system as a sequent…
Learning Disentangled Representations for Recommendation
Jianxin Ma, Chang Zhou, Peng Cui +2
User behavior data in recommender systems are driven by the complex interactions of many latent factors behind the users' decision making processes. The factors are highly entangle…
Dimensional Reweighting Graph Convolutional Networks
Xu Zou, Qiuye Jia, Jianwei Zhang +3
Graph Convolution Networks (GCNs) are becoming more and more popular for learning node representations on graphs. Though there exist various developments on sampling and aggregatio…
Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
Zhengxiao Du, Chang Zhou, Ming Ding +2
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies…