Alert button
Picture for Donglin Wang

Donglin Wang

Alert button

Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation

Nov 30, 2023
Siteng Huang, Biao Gong, Yutong Feng, Xi Chen, Yuqian Fu, Yu Liu, Donglin Wang

This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data and generalize it to unseen humans or even animals. Experimental results show that existing subject-driven customization methods fail to learn the representative characteristics of actions and struggle in decoupling actions from context features, including appearance. To overcome the preference for low-level features and the entanglement of high-level features, we propose an inversion-based method Action-Disentangled Identifier (ADI) to learn action-specific identifiers from the exemplar images. ADI first expands the semantic conditioning space by introducing layer-wise identifier tokens, thereby increasing the representational richness while distributing the inversion across different features. Then, to block the inversion of action-agnostic features, ADI extracts the gradient invariance from the constructed sample triples and masks the updates of irrelevant channels. To comprehensively evaluate the task, we present an ActionBench that includes a variety of actions, each accompanied by meticulously selected samples. Both quantitative and qualitative results show that our ADI outperforms existing baselines in action-customized T2I generation. Our project page is at

Viaarxiv icon

A Short Overview of 6G V2X Communication Standards

Nov 28, 2023
Donglin Wang, Yann Nana Nganso, Hans D. Schotten

We are on the verge of a new age of linked autonomous cars with unheard-of user experiences, dramatically improved air quality and road safety, extremely varied transportation settings, and a plethora of cutting-edge apps. A substantially improved Vehicle-to-Everything (V2X) communication network that can simultaneously support massive hyper-fast, ultra-reliable, and low-latency information exchange is necessary to achieve this ambitious goal. These needs of the upcoming V2X are expected to be satisfied by the Sixth Generation (6G) communication system. In this article, we start by introducing the history of V2X communications by giving details on the current, developing, and future developments. We compare the applications of communication technologies such as Wi-Fi, LTE, 5G, and 6G. we focus on the new technologies for 6G V2X which are brain-vehicle interface, blocked-based V2X, and Machine Learning (ML). To achieve this, we provide a summary of the most recent ML developments in 6G vehicle networks. we discuss the security challenges of 6G V2X. We address the strengths, open challenges, development, and improving areas of further study in this field.

* 7 pages, 2 figures, IEEE ICN 2023 
Viaarxiv icon

RSG: Fast Learning Adaptive Skills for Quadruped Robots by Skill Graph

Nov 10, 2023
Hongyin Zhang, Diyuan Shi, Zifeng Zhuang, Han Zhao, Zhenyu Wei, Feng Zhao, Sibo Gai, Shangke Lyu, Donglin Wang

Developing robotic intelligent systems that can adapt quickly to unseen wild situations is one of the critical challenges in pursuing autonomous robotics. Although some impressive progress has been made in walking stability and skill learning in the field of legged robots, their ability to fast adaptation is still inferior to that of animals in nature. Animals are born with massive skills needed to survive, and can quickly acquire new ones, by composing fundamental skills with limited experience. Inspired by this, we propose a novel framework, named Robot Skill Graph (RSG) for organizing massive fundamental skills of robots and dexterously reusing them for fast adaptation. Bearing a structure similar to the Knowledge Graph (KG), RSG is composed of massive dynamic behavioral skills instead of static knowledge in KG and enables discovering implicit relations that exist in be-tween of learning context and acquired skills of robots, serving as a starting point for understanding subtle patterns existing in robots' skill learning. Extensive experimental results demonstrate that RSG can provide rational skill inference upon new tasks and environments and enable quadruped robots to adapt to new scenarios and learn new skills rapidly.

Viaarxiv icon

Learning How to Propagate Messages in Graph Neural Networks

Oct 01, 2023
Teng Xiao, Zhengyu Chen, Donglin Wang, Suhang Wang

Figure 1 for Learning How to Propagate Messages in Graph Neural Networks
Figure 2 for Learning How to Propagate Messages in Graph Neural Networks
Figure 3 for Learning How to Propagate Messages in Graph Neural Networks
Figure 4 for Learning How to Propagate Messages in Graph Neural Networks

This paper studies the problem of learning message propagation strategies for graph neural networks (GNNs). One of the challenges for graph neural networks is that of defining the propagation strategy. For instance, the choices of propagation steps are often specialized to a single graph and are not personalized to different nodes. To compensate for this, in this paper, we present learning to propagate, a general learning framework that not only learns the GNN parameters for prediction but more importantly, can explicitly learn the interpretable and personalized propagate strategies for different nodes and various types of graphs. We introduce the optimal propagation steps as latent variables to help find the maximum-likelihood estimation of the GNN parameters in a variational Expectation-Maximization (VEM) framework. Extensive experiments on various types of graph benchmarks demonstrate that our proposed framework can significantly achieve better performance compared with the state-of-the-art methods, and can effectively learn personalized and interpretable propagate strategies of messages in GNNs.

* KDD2021 
Viaarxiv icon

A General Offline Reinforcement Learning Framework for Interactive Recommendation

Oct 01, 2023
Teng Xiao, Donglin Wang

Figure 1 for A General Offline Reinforcement Learning Framework for Interactive Recommendation
Figure 2 for A General Offline Reinforcement Learning Framework for Interactive Recommendation
Figure 3 for A General Offline Reinforcement Learning Framework for Interactive Recommendation
Figure 4 for A General Offline Reinforcement Learning Framework for Interactive Recommendation

This paper studies the problem of learning interactive recommender systems from logged feedbacks without any exploration in online environments. We address the problem by proposing a general offline reinforcement learning framework for recommendation, which enables maximizing cumulative user rewards without online exploration. Specifically, we first introduce a probabilistic generative model for interactive recommendation, and then propose an effective inference algorithm for discrete and stochastic policy learning based on logged feedbacks. In order to perform offline learning more effectively, we propose five approaches to minimize the distribution mismatch between the logging policy and recommendation policy: support constraints, supervised regularization, policy constraints, dual constraints and reward extrapolation. We conduct extensive experiments on two public real-world datasets, demonstrating that the proposed methods can achieve superior performance over existing supervised learning and reinforcement learning methods for recommendation.

* AAAI2021 
Viaarxiv icon

A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning

Sep 13, 2023
Hongyin Zhang, Shuyu Yang, Donglin Wang

Online reinforcement learning (RL) methods are often data-inefficient or unreliable, making them difficult to train on real robotic hardware, especially quadruped robots. Learning robotic tasks from pre-collected data is a promising direction. Meanwhile, agile and stable legged robotic locomotion remains an open question in their general form. Offline reinforcement learning (ORL) has the potential to make breakthroughs in this challenging field, but its current bottleneck lies in the lack of diverse datasets for challenging realistic tasks. To facilitate the development of ORL, we benchmarked 11 ORL algorithms in the realistic quadrupedal locomotion dataset. Such dataset is collected by the classic model predictive control (MPC) method, rather than the model-free online RL method commonly used by previous benchmarks. Extensive experimental results show that the best-performing ORL algorithms can achieve competitive performance compared with the model-free RL, and even surpass it in some tasks. However, there is still a gap between the learning-based methods and MPC, especially in terms of stability and rapid adaptation. Our proposed benchmark will serve as a development platform for testing and evaluating the performance of ORL algorithms in real-world legged locomotion tasks.

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 
Viaarxiv icon

VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders

Sep 03, 2023
Xuyang Liu, Siteng Huang, Yachen Kang, Honggang Chen, Donglin Wang

Large-scale text-to-image diffusion models have shown impressive capabilities across various generative tasks, enabled by strong vision-language alignment obtained through pre-training. However, most vision-language discriminative tasks require extensive fine-tuning on carefully-labeled datasets to acquire such alignment, with great cost in time and computing resources. In this work, we explore directly applying a pre-trained generative diffusion model to the challenging discriminative task of visual grounding without any fine-tuning and additional training dataset. Specifically, we propose VGDiffZero, a simple yet effective zero-shot visual grounding framework based on text-to-image diffusion models. We also design a comprehensive region-scoring method considering both global and local contexts of each isolated proposal. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg show that VGDiffZero achieves strong performance on zero-shot visual grounding.

Viaarxiv icon

Learning on Graphs with Out-of-Distribution Nodes

Aug 13, 2023
Yu Song, Donglin Wang

Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs. While existing GNNs have shown great performance on various tasks related to graphs, little attention has been paid to the scenario where out-of-distribution (OOD) nodes exist in the graph during training and inference. Borrowing the concept from CV and NLP, we define OOD nodes as nodes with labels unseen from the training set. Since a lot of networks are automatically constructed by programs, real-world graphs are often noisy and may contain nodes from unknown distributions. In this work, we define the problem of graph learning with out-of-distribution nodes. Specifically, we aim to accomplish two tasks: 1) detect nodes which do not belong to the known distribution and 2) classify the remaining nodes to be one of the known classes. We demonstrate that the connection patterns in graphs are informative for outlier detection, and propose Out-of-Distribution Graph Attention Network (OODGAT), a novel GNN model which explicitly models the interaction between different kinds of nodes and separate inliers from outliers during feature propagation. Extensive experiments show that OODGAT outperforms existing outlier detection methods by a large margin, while being better or comparable in terms of in-distribution classification.

* Accepted by KDD'22 
Viaarxiv icon

STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization

Jul 19, 2023
Yachen Kang, Li He, Jinxin Liu, Zifeng Zhuang, Donglin Wang

Figure 1 for STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization
Figure 2 for STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization
Figure 3 for STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization
Figure 4 for STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization

Preference-based reinforcement learning (PbRL) promises to learn a complex reward function with binary human preference. However, such human-in-the-loop formulation requires considerable human effort to assign preference labels to segment pairs, hindering its large-scale applications. Recent approache has tried to reuse unlabeled segments, which implicitly elucidates the distribution of segments and thereby alleviates the human effort. And consistency regularization is further considered to improve the performance of semi-supervised learning. However, we notice that, unlike general classification tasks, in PbRL there exits a unique phenomenon that we defined as similarity trap in this paper. Intuitively, human can have diametrically opposite preferredness for similar segment pairs, but such similarity may trap consistency regularization fail in PbRL. Due to the existence of similarity trap, such consistency regularization improperly enhances the consistency possiblity of the model's predictions between segment pairs, and thus reduces the confidence in reward learning, since the augmented distribution does not match with the original one in PbRL. To overcome such issue, we present a self-training method along with our proposed peer regularization, which penalizes the reward model memorizing uninformative labels and acquires confident predictions. Empirically, we demonstrate that our approach is capable of learning well a variety of locomotion and robotic manipulation behaviors using different semi-supervised alternatives and peer regularization.

Viaarxiv icon

CEIL: Generalized Contextual Imitation Learning

Jun 26, 2023
Jinxin Liu, Li He, Yachen Kang, Zifeng Zhuang, Donglin Wang, Huazhe Xu

Figure 1 for CEIL: Generalized Contextual Imitation Learning
Figure 2 for CEIL: Generalized Contextual Imitation Learning
Figure 3 for CEIL: Generalized Contextual Imitation Learning
Figure 4 for CEIL: Generalized Contextual Imitation Learning

In this paper, we present \textbf{C}ont\textbf{E}xtual \textbf{I}mitation \textbf{L}earning~(CEIL), a general and broadly applicable algorithm for imitation learning (IL). Inspired by the formulation of hindsight information matching, we derive CEIL by explicitly learning a hindsight embedding function together with a contextual policy using the hindsight embeddings. To achieve the expert matching objective for IL, we advocate for optimizing a contextual variable such that it biases the contextual policy towards mimicking expert behaviors. Beyond the typical learning from demonstrations (LfD) setting, CEIL is a generalist that can be effectively applied to multiple settings including: 1)~learning from observations (LfO), 2)~offline IL, 3)~cross-domain IL (mismatched experts), and 4) one-shot IL settings. Empirically, we evaluate CEIL on the popular MuJoCo tasks (online) and the D4RL dataset (offline). Compared to prior state-of-the-art baselines, we show that CEIL is more sample-efficient in most online IL tasks and achieves better or competitive performances in offline tasks.

Viaarxiv icon