Graph Anomaly Detection (GAD) is crucial for identifying abnormal entities within networks, garnering significant attention across various fields. Traditional unsupervised methods, which decode encoded latent representations of unlabeled data with a reconstruction focus, often fail to capture critical discriminative content, leading to suboptimal anomaly detection. To address these challenges, we present a Diffusion-based Graph Anomaly Detector (DiffGAD). At the heart of DiffGAD is a novel latent space learning paradigm, meticulously designed to enhance the model's proficiency by guiding it with discriminative content. This innovative approach leverages diffusion sampling to infuse the latent space with discriminative content and introduces a content-preservation mechanism that retains valuable information across different scales, significantly improving the model’s adeptness at identifying anomalies with limited time and space complexity. Our comprehensive evaluation of DiffGAD, conducted on six real-world and large-scale datasets with various metrics, demonstrated its exceptional performance. Our code is available at https://github.com/fortunato-all/DiffGAD

In the endeavor to make autonomous robots take actions, task planning is a major challenge that requires translating high-level task descriptions to long-horizon action sequences. Despite recent advances in language model agents, they remain prone to planning errors and limited in their ability to plan ahead. To address these limitations in robotic planning, we advocate a self-refining scheme that iteratively refines a draft plan until an equilibrium is reached. Remarkably, this process can be optimized end-to-end from an analytical perspective without the need to curate additional verifiers or reward models, allowing us to train self-refining planners in a simple supervised learning fashion. Meanwhile, a nested equilibrium sequence modeling procedure is devised for efficient closed-loop planning that incorporates useful feedback from the environment (or an internal world model). Our method is evaluated on the VirtualHome-Env benchmark, showing advanced performance with improved scaling w.r.t. inference-time computation. Code is available at https://github.com/anonymous-icml-2025/equilibrium-planner.

Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences. However, existing methods exhibit an imbalanced responsiveness to the data of varying hardness, tending to overfit on the easy-to-distinguish data while underfitting on the hard-to-distinguish data. In this paper, we propose Data- and Model-aware DPO (DAMA) to dynamically adjust the optimization process from two key aspects: (1) a data-aware strategy that incorporates data hardness, and (2) a model-aware strategy that integrates real-time model responses. By combining the two strategies, DAMA enables the model to effectively adapt to data with varying levels of hardness. Extensive experiments on five benchmarks demonstrate that DAMA not only significantly enhances the trustworthiness, but also improves the effectiveness over general tasks. For instance, on the Object HalBench, our DAMA-7B reduces response-level and mentioned-level hallucination by 90.0% and 95.3%, respectively, surpassing the performance of GPT-4V.

Open world object detection aims to identify objects of unseen categories and incrementally recognize them once their annotations are provided. In distinction to the traditional paradigm that is limited to predefined categories, this setting promises a continual and generalizable way of estimating objectness using class-agnostic information. However, achieving such decorrelation between objectness and class information proves challenging. Without explicit consideration, existing methods usually exhibit low recall on unknown objects and can misclassify them into known classes. To address this problem, we exploit three levels of orthogonality in the detection process: First, the objectness and classification heads are disentangled by operating on separate sets of features that are orthogonal to each other in a devised polar coordinate system. Secondly, a prediction decorrelation loss is introduced to guide the detector towards more general and class-independent prediction. Furthermore, we propose a calibration scheme that helps maintain orthogonality throughout the training process to mitigate catastrophic interference and facilitate incremental learning of previously unseen objects. Our method is comprehensively evaluated on open world and incremental object detection benchmarks, demonstrating its effectiveness in detecting both known and unknown objects. Code and models are available at this link.

Abstract With the advent of the digital era, millions of facial images are shared online daily, posing severe privacy threats. Generative face anonymization (GFA) methods generate virtual faces to conceal original identities, protecting sensitive information while preserving utility. However, deep learning based user identity linkage (UIL) methods can link similar faces to the same identity and leverage the linked profiles for malicious purposes, including localization and behaviour prediction. These UIL methods pose a significant challenge to the diversity of virtual faces, a challenge that existing GFA methods have not adequately addressed. To address this research gap, we propose Style Diversification‐based Generative Face Anonymization (SD‐GFA), a framework that generates virtual faces with diverse identities and high visual quality. SD‐GFA features an equalized control module to balance input faces and user‐specified keys, a face generation module with a re‐connection strategy for high‐quality synthesis, and a maximum probability simulation module to enhance diversity. Our experiments demonstrate that SD‐GFA effectively mitigates linkage risk by improving the diversity of virtual faces, while also enhancing their utility and visual quality. This study provides a robust solution to enhance the security of anonymized faces shared on the internet.

With the rapid development of 5G and Internet of Vehicles (IoV) technologies, vehicles have evolved from mere transportation devices to mobile living spaces for humans. Thus, the complexity of data processing is growing along with the increasing of vehicle applications, which makes relying solely on on-board processing capabilities insufficient. Traditional Roadside Units (RSUs)-based edge computing has limitations such as high deployment cost and finite coverage. To address those issues, we construct an Air-Ground Vehicular Cooperative Computing Network (AVC$^{\textbf{2}}$N) that introduces Cooperative Vehicles (CVs) to reduce deployment cost while incorporating Unmanned Aerial Vehicles (UAVs) to expand communication coverage. We aim to balance offloading efficiency and environmental sustainability by proposing a system cost minimization problem with weighted sum of delay and energy consumption. However, it faces new challenges such as the lack of Global State Information (GSI), and the Ultra-Reliable Low-Latency Communications (URLLC) queue delay constraints, rendering traditional methods inadequate. To address the coupling between immediate decision and long-term queuing constraints, we employ Lyapunov optimization to partition the initial problem into two distinct sub-problems. The first focuses on optimizing the system transmission cost, which is tackled using a collaborative Deep Reinforcement Learning (DRL) framework. Specifically, we design an algorithm based on Multi Agent Deep Deterministic Policy Gradient (MADDPG), which effectively addresses GSI uncertainty and ensures URLLC awareness. The second sub-problem addresses server-side computing resource optimization, and we propose a greedy algorithm to tackle it. Experimental results showcase the effectiveness of our approach, demonstrating notable achievement in terms of learning convergence speed, overall system cost, queue delay, and queue backlog.

Graph anomaly detection (GAD) under semi-supervised setting poses a significant challenge due to the distinct structural distribution between anomalous and normal nodes. Specifically, anomalous nodes constitute a minority and exhibit high heterophily and low homophily compared to normal nodes, which makes the distribution of neighbors of the two types of nodes close, that is, most of them are composed of normal nodes, which causes the two types of nodes to be difficult to distinguish during the aggregation process. Furthermore, we discover that apart from various time factors and annotation preferences, graph adversarial attacks can lead to and amplify the heterophily difference across training and testing data, which is called structural distribution shift (SDS) in this paper. Current mainstream methods for GAD tend to overlook the SDS problem, resulting in poor generalization performance and limited effectiveness in detecting anomalies. This work solves the problem from a feature view. We observe that the degree of SDS varies between anomalies and normal nodes. Hence to address the issue, the key lies in resisting high heterophily for anomalies meanwhile benefiting the learning of normals from homophily. Since different labels correspond to the difference of critical anomaly features which make great contributions to the GAD, we tease out the anomaly features on which we constrain to mitigate the effect of heterophilous neighbors and make them invariant. However, the prior distribution of anomaly features is dynamic and hard to estimate, we thus devise a prototype vector to infer and update this distribution during training. For normal nodes, we constrain the remaining features to preserve the connectivity of nodes and reinforce the influence of the homophilous neighborhood. We term our proposed framework asGraphDecompositionNetwork(GDN). To demonstrate the effectiveness of the network, we explain the process of feature decomposition in the spectral domain. Extensive experiments are conducted on four benchmark datasets, including two additional datasets and two used in the preliminary work. To further validate our performance under SDS, we conduct an adversarial attack to incur different heterophily degrees for the training set and the test set. The proposed framework achieves remarkable accuracy and robustness boost in GAD, especially in an SDS environment where anomalies have largely different structural distribution across training and testing environments. Our code is open-sourced inhttps://github.com/fortunato-all/skl-GDN.

This paper studies bumpless transfer control for a class of switched linear systems. We propose a hierarchical switching strategy to solve the bumpless transfer control problem. The key point is to design two controllers for each subsystem. This is based on the consideration that in many cases the conventional design of each subsystem equipped with only one controller cannot achieve stability and satisfactory bumpless transfer performance simultaneously. The upper level switching determines which subsystem to be active while the lower level switching chooses which controller from the two controllers of the active subsystem to be switched on. The dual design of the switching and controllers makes the closed-loop switched system asymptotically stable with a satisfactory bumpless transfer performance. Numerical examples are provided to illustrate the validity of the proposed methods.