Vision-language models (VLMs) have gained widespread attention for their strong zero-shot capabilities across numerous downstream tasks. However, these models assume that each test image’s class label is drawn from a predefined label set and lack a reliable mechanism to reject samples from emerging unknown classes when only unlabeled data are available. To address this gap, open-set domain adaptation methods retrain models to push potential unknowns away from known clusters. Yet, some unknown samples remain stably anchored to specific known classes in the VLM feature space due to semantic relevance, which is termed as Semantic Affinity Anchoring (SAA). Forcibly repelling these samples unavoidably distorts the native geometry of VLMs and degrades performance. Meanwhile, existing score‑based unknown detectors use simplistic thresholds and suffer from threshold sensitivity, resulting in sub‑optimal performance. To address aforementioned issues, we propose VLM-OpenXpert, which comprises two training‑free, plug‑and‑play inference modules. SUFF performs SVD on high-confidence unknowns to extract a low-rank "unknown subspace". Each sample’s projection onto this subspace is weighted and softly removed from its feature, suppressing unknown components while preserving semantics. BGAT corrects score skewness via a Box–Cox transform, then fits a bimodal Gaussian mixture to adaptively estimate the optimal threshold balancing known-class recognition and unknown-class rejection. Experiments on 9 benchmarks and three backbones (CLIP, SigLIP, ALIGN) under Source-Free OSDA settings show that our training-free pipeline matches or outperforms retraining-heavy state-of-the-art methods, establishing a powerful lightweight inference calibration paradigm for open-set VLM deployment.

Large language models (LLMs) require continual knowledge updates to keep pace with the evolving world.While various model editing methods have been proposed, most face critical challenges in the context of lifelong learning due to two fundamental limitations: (1) Edit Overshooting -parameter updates intended for a specific fact spill over to unrelated regions, causing interference with previously retained knowledge; and (2) Knowledge Entanglement -polysemantic neurons' overlapping encoding of multiple concepts makes it difficult to isolate and edit a single fact.In this paper, we propose MicroEdit, a neuron-level editing method that performs minimal and controlled interventions within LLMs.By leveraging a sparse autoencoder (SAE), MicroEdit disentangles knowledge representations and activates only a minimal set of necessary neurons for precise parameter updates.This targeted design enables fine-grained control over the editing scope, effectively mitigating interference and preserving unrelated knowledge.Extensive experiments show that MicroEdit outperforms prior methods and robustly handles lifelong knowledge editing across QA and Hallucination settings on LLaMA 1 and Mistral 2 .

Graph anomaly detection methods based on contrastive learning have been widely proposed due to their powerful unsupervised feature learning capabilities. However, most existing methods overlook the loss and degradation of original graph information caused by the random data augmentation. In addition, the impact of anomalous nodes is usually ignored during the training phase. To address these issues, we propose a collaborative contrastive self-supervised graph anomaly detection model, namely, CCS-GAD. The core idea lies in the collaboration and mutual constraints among its submodules. Specifically, we design a view collaboration module to seamlessly integrate contrastive-based and reconstruction-based frameworks, capturing node patterns from both local and global views simultaneously to alleviate the graph information gaps caused by data augmentation in conventional self-supervised paradigms. Additionally, we introduce a filtering collaboration method to identify and filter out potential anomalies exhibiting abnormal behaviors from other nodes, thereby reducing their interference with the model’s learning of normal patterns. Finally, anomalies are detected based on local consistency and global reconstruction errors. Extensive experiments on six real-world datasets with seven state-of-the-art(SOTA) baselines demonstrate the superior adaptability of our model in graph anomaly detection. Specifically, our model achieves an average improvement of 16.43% in AUC, 5.83% in Precision, and 9.48% in F1-score.

The cooperation in mixed cooperative-competitive tasks has drawn significant attention in multi-agent deep reinforcement learning. Agents need to cooperate with their teammates while competing against their opponents. However, most existing works treat the cooperative agents and competitive agents equally as they perform the same operation on all the agents. As a result, without distinguishing between cooperative and competitive agents, they may suffer from information disorder in learning an optimally cooperative policy and struggle to decide on the next step action. To address the above issues, we decompose the final Q-value into a weighted combination of three parts: the Q-values of the cooperative agents, the competitive group, and the current agent. A theoretical proof of the correctness of the decomposition is provided. With this decomposition, we are able to consider cooperative and competitive agents separately. Accordingly, we propose a multi-agent actor-critic algorithm called actor-double-attention-critic (ADAC) under centralized training and decentralized execution according to the decomposition. In ADAC, networks with group-specific attention and an attentional weighting network are specially designed. With the designed double-attention structure, ADAC can capture the distributions from different agents and improve cooperation performance. Extensive experiments are conducted in three scenarios with nine settings against six representative methods. The results demonstrate the superiority of the proposed ADAC model against state-of-the-art methods in various mixed cooperative-competitive tasks. The code is available at https://github.com/CrazyBayes/ADAC

Transformer and its variants, built based on attention mechanisms, have recently achieved remarkable performance in many NLP tasks. Most existing works on Transformer explanation tend to reveal and utilize the attention matrix with human subjective intuitions in a qualitative manner. However, the huge size of dimensions directly challenges these methods to quantitatively analyze the attention matrix. Therefore, in this paper, we propose a novel reinforcement learning (RL) based framework for Transformer explanation via attention matrix, namely AttExplainer. The RL agent learns to perform step-by-step masking operations by observing the change in attention matrices. We have adapted our method to two scenarios, perturbation-based model explanation and text adversarial attack. Experiments on three widely used text classification benchmarks validate the effectiveness of the proposed method compared to state-of-the-art baselines. Additional studies show that our method is highly transferable and consistent with human intuition. The code of this paper is available at https://github.com/niuzaisheng/AttExplainer .