Graph neural networks (GNNs) have become a dominant modeling paradigm for graph-structured data, and the emergence of large language models (LLMs) has spurred growing interest in integrating external semantic knowledge into GNNs. Current LLM-based GNNs are devoted to extracting semantically similar information from LLMs to enhance representation learning. However, they generally overlook key signals that are semantically dissimilar but exhibit stronger inter-class discriminative ability. Especially when the original graph data contains noise or semantic ambiguity, a single similarity-based semantic augmentation strategy not only fails to provide effective enhancement, but may also amplify misleading signals generated by the LLM in response to low-quality inputs or its own hallucinations, further degrading the discriminative power and robustness of GNNs. To this end, we propose a dual positive-negative knowledge extraction strategy based on LLMs, and integrate it with a knowledge distillation mechanism to dynamically transfer multi-dimensional enhanced signals to GNNs, thereby achieving fine-grained and robust graph representation learning. Specifically, we design personalized prompts to guide LLMs in generating semantically similar positive signals and semantically dissimilar negative signals, which help the model capture intra-class consistency and inter-class distinction. Then, we further generate structural and semantic reasoning as supplementary knowledge to support the rationality and guidance of supervision signals. To identify high-confidence transferred knowledge, we introduce a language-based evaluation mechanism to filter low-confidence or hallucinated outputs. Finally, under a unified distillation framework, our method uses both positive and negative knowledge to guide GNN training, achieving adaptive and robust representation learning. Extensive experiments on benchmark datasets verify the superior performance of our approach across various tasks.

3D Gaussian splatting (3DGS) has emerged as a promising direction for SLAM due to its high-fidelity reconstruction and rapid convergence. However, 3DGS-SLAM algorithms remain impractical for mobile platforms due to their high computational cost, especially for their tracking process. This work introduces Splatonic, a sparse and efficient realtime 3DGS-SLAM algorithm-hardware co-design for resourceconstrained devices. Inspired by classical SLAMs, we propose an adaptive sparse pixel sampling algorithm that reduces the number of rendered pixels by up to$256 \times$while retaining accuracy. To unlock this performance potential on mobile GPUs, we design a novel pixel-based rendering pipeline that improves hardware utilization via Gaussian-parallel rendering and preemptive$\alpha$-checking. Together, these optimizations yield up to$121.7 \times$speedup on the bottleneck stages and$14.6 \times$end-toend speedup on off-the-shelf GPUs. To further address new bottlenecks introduced by our rendering pipeline, we propose a pipelined architecture that simplifies the overall design while addressing newly emerged bottlenecks in projection and aggregation. Evaluated across four 3DGS-SLAM algorithms, Splatonic achieves up to$274.9 \times$speedup and$4738.5 \times$energy savings over mobile GPUs and up to$25.2 \times$speedup and$241.1 \times$energy savings over state-of-the-art accelerators, all with comparable accuracy.

Heterophily in graphs is a key challenge for Graph Neural Networks (GNNs). By proposing various homophily measures, recent work has provided insights into how heterophily affects node classification. However, while both graph homophily and heterophily can be further refined into diverse connection patterns, previous work has largely overlooked the role of connection pattern inconsistency. In this paper, we delve deeper into heterophily and homophily by shifting from coarse-grained heterophily ratios to a unified, fine-grained formulation based on connection patterns, and we further reveal an uneven distribution and a train–test gap of these patterns. Empirical studies indicate that this inconsistency leads to severe performance disparity. To address this issue, we propose a novel two-stage method named IVQ-GNN. In the pre-training phase, IVQ-GNN encodes diverse connection patterns into a codebook that serves as an orthogonal basis for the representation space. In the fine-tuning phase, a self-attention module linearly combines these orthogonal bases to expand the learned token space of connection patterns, thereby improving adaptation to rare and out-of-distribution (OOD) patterns. Experimental results on multiple datasets demonstrate that IVQ-GNN significantly improves model performance and validate that the proposed method effectively addresses the connection pattern inconsistency. Our code is available at https://github.com/Duyx5149/IVQ-GNN.

Third-party libraries (TPLs) are widely utilized by Android developers to implement new apps. Unfortunately, TPLs are often suffering from various vulnerabilities, which could be exploited by attackers to cause catastrophic consequences for app users. Therefore, testing whether a vulnerability has been patched in target apps is crucial. However, existing techniques are unable to effectively test patch presence for obfuscated apps while obfuscation is pervasive in practice. To address the new challenges introduced by code obfuscation, this study presents PHunter, which is a system that captures obfuscation-resilient semantic features of patch-related methods to identify the presence of the patch in target apps. Specifically, PHunter utilizes coarse-grained features to locate patch-related methods, and compares the fine-grained semantic similarity to determine whether the code has been patched. Extensive evaluations on 94 CVEs and 200 apps show that PHunter can outperform state-of-the-art tools, achieving an average accuracy of 97.1% with high efficiency and low false positive rates. Besides, PHunter is able to be resilient to different obfuscation strategies. More importantly, PHunter is useful in eliminating the false alarms generated by existing TPL detection tools. In particular, it can help reduce up to 25.2% of the false alarms with an accuracy of 95.3%.

BACKGROUND: G protein-coupled receptors (GPCRs) mediate a variety of important physiological functions, are closely related to many diseases, and constitute the most important target family of modern drugs. Therefore, the research of GPCR analysis and GPCR ligand screening is the hotspot of new drug development. Accurately identifying the GPCR-drug interaction is one of the key steps for designing GPCR-targeted drugs. However, it is prohibitively expensive to experimentally ascertain the interaction of GPCR-drug pairs on a large scale. Therefore, it is of great significance to predict the interaction of GPCR-drug pairs directly from the molecular sequences. With the accumulation of known GPCR-drug interaction data, it is feasible to develop sequence-based machine learning models for query GPCR-drug pairs. RESULTS: In this paper, a new sequence-based method is proposed to identify GPCR-drug interactions. For GPCRs, we use a novel bag-of-words (BoW) model to extract sequence features, which can extract more pattern information from low-order to high-order and limit the feature space dimension. For drug molecules, we use discrete Fourier transform (DFT) to extract higher-order pattern information from the original molecular fingerprints. The feature vectors of two kinds of molecules are concatenated and input into a simple prediction engine distance-weighted K-nearest-neighbor (DWKNN). This basic method is easy to be enhanced through ensemble learning. Through testing on recently constructed GPCR-drug interaction datasets, it is found that the proposed methods are better than the existing sequence-based machine learning methods in generalization ability, even an unconventional method in which the prediction performance was further improved by post-processing procedure (PPP). CONCLUSIONS: The proposed methods are effective for GPCR-drug interaction prediction, and may also be potential methods for other target-drug interaction prediction, or protein-protein interaction prediction. In addition, the new proposed feature extraction method for GPCR sequences is the modified version of the traditional BoW model and may be useful to solve problems of protein classification or attribute prediction. The source code of the proposed methods is freely available for academic research at https://github.com/wp3751/GPCR-Drug-Interaction.

Blind noisy assessment aims to evaluate the quality of the degraded noisy image/video without the need for the ground-truth image. To tackle this challenge, this paper proposes a new blind noise assessment approach based on the path information of the ants' movement. The proposed modified ant shortest path (MASP) algorithm uses the path information of the ant colony optimization (ACO). The contribution of the proposed approach is two-fold. First, the proposed approach utilizes a number of artificial ants to move on a 2-D graph for constructing the path information, and calculates the ants' movement path driven by the shortest path strategy. Second, several path statistics metrics are proposed to evaluate the image quality. Experimental results are provided to demonstrate that the proposed image quality assessment approach is effective for both benchmark image database and real-world noisy video.

Blind noisy image quality assessment aims to evaluate the quality of the degraded noisy image without the need for the ground truth image. To tackle this challenge, this paper proposes an image quality assessment approach using block homogeneity. The contribution of the proposed approach is two-fold. First, a block-based homogeneity measure is proposed to estimate the statistics (e.g., variance) of the noise incurred in the image, based on adaptively selected homogeneous image regions. Second, an image quality assessment approach is proposed by exploiting the above-mentioned estimated noise variance, along with the visual masking effect of the human visual system. Experimental results are provided to demonstrate that the proposed image noise estimation approach yields superior accuracy and stability performance to that of conventional approaches, and the proposed image quality assessment approach achieves consistent performance to that of human subjective evaluation.