The 6G network aspires to deliver everyone-centric services with stringent and dynamic QoS demands. Compared to 4G/5G, 6G requires finer-grained, per-flow resource allocation that accounts for real-time traffic variations and highly dynamic wireless channel conditions to improve user satisfaction. However, enabling per-flow QoS introduces substantial complexity in scheduling, and existing heuristic-based approaches—lacking long-term resource planning and global channel awareness—struggle to ensure fairness and service satisfaction, especially under high load and large-scale scenarios.In this paper, we present 6GQoS, a flow-level QoS assurance framework that integrates real-time QoS target setting, long-term resource management, and global channel awareness. 6GQoS continuously monitors user channel conditions, traffic demands, and service-level objectives to dynamically adjust per-flow service targets. It models long-term resource allocation via Lyapunov control theory and incorporates a novel BestUsage algorithm to guide scheduling decisions based on queue states, bandwidth gains, and resource costs. Extensive evaluations show that 6GQoS outperforms all baselines, achieving 40%–80% higher service satisfaction, reducing radio resource usage by 20%–80%, and consistently ensuring 100% fairness.

Continual Anomaly Detection (CAD) enables anomaly detection models in learning new classes while preserving knowledge of historical classes. CAD faces two key challenges: catastrophic forgetting and segmentation of small anomalous regions. Existing CAD methods store image distributions or patch features to mitigate catastrophic forgetting, but they fail to preserve pixel-level detailed features for accurate segmentation. To overcome this limitation, we propose ReplayCAD, a novel diffusion-driven generative replay framework that replay high-quality historical data, thus effectively preserving pixel-level detailed features. Specifically, we compress historical data by searching for a class semantic embedding in the conditional space of the pre-trained diffusion model, which can guide the model to replay data with fine-grained pixel details, thus improving the segmentation performance. However, relying solely on semantic features results in limited spatial diversity. Hence, we further use spatial features to guide data compression, achieving precise control of sample space, thereby generating more diverse data. Our method achieves state-of-the-art performance in both classification and segmentation, with notable improvements in segmentation: 11.5% on VisA and 8.1% on MVTec. Our source code is available at https://github.com/HULEI7/ReplayCAD.

We are witnessing more real-time network applications that demand high transmission reliability and low delay, for meeting desired Quality of Experience (QoE). Forward Error Correction (FEC) is widely employed to combat packet loss, but its effectiveness depends on accurate packet loss rate prediction. Existing forecasting models exhibit limitations in handling multiperiodicity and complex variations, particularly in terms of trend prediction consistency and forecasting conservativeness, leading to suboptimal performance of FEC strategies. To address these challenges, we propose FitFEC, a Multi-Scale Dynamic Adjustment Transformer that enhances packet loss prediction and optimizes FEC strategies. FitFEC integrates Adaptive Frequency Analysis for capturing periodic components, Trend-Detail Decomposition Transformer for improving trend accuracy, and Dynamic Prediction Adjustment to control prediction aggressiveness. Furthermore, we implement an FEC scheme based on QUIC to further enhance transmission efficiency. Extensive empirical studies demonstrate that FitFEC improves trend prediction accuracy, reduces retransmission rates, and reduces transmission latency, ultimately enhancing network performance and user experience.

Document Large Vision Language Models excel in document-centric tasks and have become a key focus of research. Existing frameworks embed features from a lightweight, document-specific encoder into the first layer of a general-purpose Vision Language Model (VLM). However, this introduces a feature mismatch problem. VLMs typically consist of many stacked layers, with the feature hierarchy becoming increasingly abstract at higher layers. Specifically, the first-layer feature in a VLM is token-level, whereas the feature from the encoder is task-level, resulting in a mismatch. Consequently, it is crucial to identify an optimal layer within the VLM for embedding the encoder's features. Inspired by physics, we reformulate the search for the optimal embedding as a problem of finding the shortest time curve. Leveraging the properties of the shortest time curve, we theoretically derive a task-agnostic proxy score that requires only partial training and propose our searching framework, Brac4VLM. Our theoretical derivation shows that Brac4VLM reduces search time by 97.8% compared to brute-force methods. Experimental results further demonstrate that Brac4VLM identifies embedding points that closely align with the true optima. Moreover, the DocVLM with the optimal embedding position identified achieves state-of-the-art performance across various document-centric tasks. Codes: https://github.com/MaxKinny/Brac4VLM.

In maritime navigation, vessels require internet access for communication and entertainment, typically provided by terrestrial-based stations via relay. For routes that are difficult to cover from the shore, long-endurance Unmanned Aerial Vehicles (UAVs) can be deployed to accompany ships and offer Internet connection. However, existing systems consider Internet Service Provider (ISP) competition only, and do not incorporate it into the users' resource selection process. Furthermore, user competition is limited due to the time slot allocation method. To address these limitations, we propose an effective Online Maritime Double Auction Mechanism (OMDAM) aimed at maximizing social welfare of the maritime network. We introduce an online algorithm,$A_{online}$, to solve the online social welfare maximization problem, with an inner algorithm,$A_{core}$, handling the selection of Internet accessing devices and task allocation between users and ISPs. Theoretical analysis demonstrates that our mechanism ensures budget balance, individual rationality, and economic efficiency. Simulation results show a performance improvement of up to 17% in social welfare compared to prior art.

Out-of-distribution (OOD) detection is vital for the safe application of intelligent systems in real-world scenarios. This paper proposes an enhancement to OOD detection by leveraging the consistency in cognition between two models, both pretrained on in-distribution (ID) data. Specifically, for a given test sample, we first apply Principal Component Analysis (PCA)-based projection on the feature vectors from each model. These obtained feature vectors (with correlation between dimensions decoupled by PCA projection) are then aligned using a multiple linear mapping, which is fitted using the least squares method on the training data. We hypothesize that the regression error for OOD data will be larger than that for ID data, making it a useful metric for OOD detection. Our experimental results demonstrate the effectiveness of this method. When combined with existing robust baselines, our approach achieves state-of-the-art performance in OOD detection.

Out-of-Distribution (OOD) detection is crucial when deploying machine learning models in open-world applications. The core challenge in OOD detection is mitigating the model's overconfidence on OOD data. While recent methods using auxiliary outlier datasets or synthesizing outlier features have shown promising OOD detection performance, they are limited due to costly data collection or simplified assumptions. In this paper, we propose a novel OOD detection framework FodFoM that innovatively combines multiple foundation models to generate two types of challenging fake outlier images for classifier training. The first type is based on BLIP-2's image captioning capability, CLIP's vision-language knowledge, and Stable Diffusion's image generation ability. Jointly utilizing these foundation models constructs fake outlier images which are semantically similar to but different from in-distribution (ID) images. For the second type, GroundingDINO's object detection ability is utilized to help construct pure background images by blurring foreground ID objects in ID images. The proposed framework can be flexibly combined with multiple existing OOD detection methods. Extensive empirical evaluations show that image classifiers with the help of constructed fake images can more accurately differentiate real OOD image from ID ones. New state-of-the-art OOD detection performance is achieved on multiple benchmarks. The code is available at https://github.com/Cverchen/ACMMM2024-FodFoM.

Heart rate provides aln important reference for human physical conditions and psychological changes. MmWave-based heart rate estimation has increasingly attracted attention in recent years due to its non-intrusiveness and cost-effectiveness. However, when the subject locates far away from the mmWave radar and also deviates from it, the low accuracy of heart rate estimation becomes a major concern. This paper presents MMHeart, a new heart rate estimation and heartbeat waveform reconstruction system based on MIMO mmWave radar. In order to effectively improve the accuracy of heart rate estimation, MMHeart first calculates appropriate range bins based on positioning results, then estimates candidate heart rates in all channels, removes abnormal candidates based on spectrum kurtosis, and finally estimates the heart rate by clustering the remaining candidates. Then in order to reconstruct more accurate heartbeat waveform, MMHeart first segments the signal by trough detection, then resamples heartbeat waveform template, and finally fine-tunes the start and end points of each segment. Our extensive experiments show that in long-range and large-deviation scenarios, MMHeart can improve the accuracy of heart rate estimation by at least 54.1% compared to mmEGC and PiVimo, while it can improve the accuracy of cardiac cycle duration by 52.2% compared to mmEGC.