Multi-agent systems (MAS) powered by large language models (LLMs) hold significant promise for solving complex decision-making tasks. However, the core process of collaborative decision-making (CDM) within these systems remains underexplored. Existing approaches often rely on either "dictatorial" strategies that are vulnerable to the cognitive biases of a single agent, or "voting-based" methods that fail to fully harness collective intelligence. To address these limitations, we propose AgentCDM, a structured framework for enhancing collaborative decision-making in LLM-based multi-agent systems. Drawing inspiration from the Analysis of Competing Hypotheses (ACH) in cognitive science, AgentCDM introduces a structured reasoning paradigm that systematically mitigates cognitive biases and shifts decision-making from passive answer selection to active hypothesis evaluation and construction. To internalize this reasoning process, we develop a two-stage training paradigm: the first stage uses explicit ACH-inspired scaffolding to guide the model through structured reasoning, while the second stage progressively removes this scaffolding to encourage autonomous generalization. Experiments on multiple benchmark datasets demonstrate that AgentCDM achieves state-of-the-art performance and exhibits strong generalization, validating its effectiveness in improving the quality and robustness of collaborative decisions in MAS.

In real-world graph data, in addition to the class imbalance problem, there also exists topological imbalance. However, existing methods mainly focus on addressing class imbalance or only utilize shallow topological information. To address this issue, we first analyze the impact of graph robustness on label propagation and find that local topological robustness, measured by graph efficiency, plays a crucial role in label propagation. Based on this finding, we propose the GLoFT framework, which redefines topological weights by integrating global influence and local topological robustness, effectively addressing the topological imbalance problem. However, the implementation of GLoFT's core idea relies on high-quality labelled data generated by clustering. In partially labelled scenarios, a decline in pseudo-label quality can significantly weaken its effectiveness and even intensify the class imbalance problem. To cope with this challenge, we propose the fusion-based progressive matching for self-training module (FPMist), which is specifically designed for GLoFT, aiming to enhance the quality of pseudo-labels generated by clustering and improve GLoFT's robustness in partially labelled data settings. Experimental results demonstrate that GLoFT + FPMist outperforms existing methods constructed on multiple GNN backbones and in scenarios with severe class imbalance, showing its superior generalization ability and stability.

ABSTRACT City‐scale 3D urban generation requires planning‐level semantic grounding from user intent and scalable geometric synthesis with structural validity and editability. Procedural content generation (PCG) offers controllability and scalability, but is hard to author due to high‐dimensional parameters and nonintuitive workflows. Meanwhile, directly generating city geometry or scripts from text with LLMs can suffer from weak large‐scale consistency and limited geometric validity, hindering downstream editing and engine deployment. We present Text‐to‐3D City, a plan‐then‐execute framework that couples an LLM‐based City Planner with a PCG‐based Implementer. Given a natural language description, the Planner grounds textual intent into a structured city plan by composing PCG parameters via a schema and in‐context exemplars. The Implementer deterministically executes road generation, block extraction, lot subdivision, and asset placement with validity checks and reproducible seeding to synthesize an engine‐ready 3D city. Experiments on multi‐view renderings evaluate text‐scene alignment, diversity, realism, and runtime, demonstrating rapid generation and scalability to large urban scenes.

The goal of this paper is to raise awareness of challenges and opportunities in the Collaborative Intelligence (CI) field and promote research on related standards. We begin by identifying a key challenge in CI applications, i.e., is it still possible for feature streams received in the cloud to be reused in the future by more advanced multitasking networks to achieve effective task accuracy? We then propose a framework to explore the generalization ability of cloud-received feature streams on more advanced networks from a coarse-grained to a fine-grained manner. We design a series of adapters of varying complexity to further explore the potential of feature streams for task network adaptation. Experiments show that sharing feature streams across multiple task networks could achieve an average of nearly 80% bitrate saving compared to Versatile Video Coding (VVC), which demonstrates the reuse potential of cloud-received feature streams. In addition, we make theoretical inferences about the adaptation range of shared feature streams, especially for those networks with high precision.

Image Coding for Machines (ICM) has yielded significant developments recently. Variable-rate support is necessary for image coding, while performance gap still exists, in learning-based image coding, between the single-model and multiple-fixed-models methods. This paper proposes a Machine Intelligence Variable-Rate Codec (MIVRCodec) with single-model method. We introduce a method to generate, compress, and utilize image semantic feature information, enabling the codec to adaptively process different semantic content of the image. Additionally, current studies employ fixed methods to remove redundant information between luminance and chrominance components, neglecting the dynamic characteristics of this redundancy and leading to its inappropriate utilization. We further propose a Color Dynamic Fusion Module (CDFM), which adaptively fuses image color component features based on various conditions (e.g., bitrate and image content) to utilize the redundancy among image color components as appropriately as possible. Lastly, we propose a Progressive Training Strategy (PTS) for training MIVRCodec. These proposed methods not only reduce performance loss in variable-rate ICM but also improve baseline performance. Experimental results demonstrate that our proposed MIVRCodec works well in the bitrate range corresponding to meaningful accuracy intervals in machine intelligence tasks using a single model, achieving coding efficiency on par with multiple fixed-rate models and surpassing existing state-of-the-art codecs.

Time series forecasting (TSF) is an essential branch of machine learning with various applications. Most methods for TSF focus on constructing different networks to extract better information and improve performance. However, practical application data contain different internal mechanisms, resulting in a mixture of multiple patterns. That is, the model's ability to fit different patterns is different and generates different errors. In order to solve this problem, we propose an end-to-end framework, namely probability pattern-guided time series forecasting (PPGF). PPGF reformulates the TSF problem as a forecasting task guided by probabilistic pattern classification. First, we propose the grouping strategy to approach forecasting problems as classification and alleviate the impact of data imbalance on classification. Second, we predict the corresponding class interval to guarantee the consistency of classification and forecasting. In addition, true class probability (TCP) is introduced to pay more attention to the difficult samples to improve the classification accuracy. Detailedly, PPGF classifies the different patterns to determine which one the target value may belong to and estimates it accurately in the corresponding interval. To demonstrate the effectiveness of the proposed framework, we conduct extensive experiments on real-world datasets, and PPGF achieves significant performance improvements over several baseline methods. Furthermore, the effectiveness of TCP and the necessity of consistency between classification and forecasting are proved in the experiments. All data and codes are available online: https://github.com/syrGitHub/PPGF.

Recent advances in deep neural networks (DNNs) for computer vision tasks have made intelligent analysis on edge devices more prevalent and practical. To better distribute computational load between edge devices and the cloud, a novel deep learning deployment strategy called Collaborative Intelligence (CI) has been proposed. In this strategy, features extracted from edge devices are first compressed and then transmitted to the cloud. However, it is unclear whether these compressed features have enough information to perform diverse downstream tasks. This paper focuses on the generalization of compressed features from one neural network among other object detection and instance segmentation task networks. We first propose a scheme to evaluate the generalization of features and further perform experiments on feature compression. Our experiments show that the extracted features contain enough information for other task networks and feature compression scheme for multi-task networks offers a 82.04% average bitrate saving compared to VVC.

Streaming high-quality 360-degree video over constrained networks with low latency is very challenging due to high bandwidth requirement. Tile-based viewport adaptive streaming that proactively delivers predicted visible fields with higher quality is bandwidth-friendly, but limited prediction accuracy of head movement results in degraded viewport quality. In this letter, we propose a perception-based pseudo-motion response strategy to mitigate the damage to viewport quality, benefiting from human perception thresholds for head rotation losses and gains in virtual environment. It employs imperceptible virtual rotation losses when the imminent physical viewports may exceed the high-quality region, and immediate losses compensation once the prediction performs well. Experiments results show that our proposed strategy achieves an additional average 1.43% coding gain compared to traditional tile-based video streaming. Most notably, the proposed method is compatible with any tile-based video streaming.

In video coding, Random Access Points (RAPs) are inserted in a bitstream to support flexible tune-in but divide it into multiple independent Random Access Segments (RASs) that may have similar contents. To reduce redundancy between RASs, this letter proposes a novel Cross Random-access-point Referencing (CRR) structure to provide inter prediction for RAP pictures by using multiple External Reference Pictures (ERPs) across RAPs that are selected from preceding or following RASs other than the current RAS. With ERPs shared by multiple RASs, a crowdsourcing method is proposed to optimize the joint rate distortion costs of RASs and ERPs to generate an optimal set of ERPs. Content preparation and bitstream splicing processes supported by system environments are also designed to ensure random access functionality of CRR coded RASs. Simulation results show that CRR achieves significant coding gain compared to Versatile Video Coding (VVC), i.e., 12.00% on sequences in common test condition and 25.48% on long drama sequences.

Diversity-oriented models have been developed to recommend top-K items, which utilize some static parameters to make a trade-off or construct an objective function, derived from item relevance and item diversity. However, such a process directly narrows the interest points of the item list, and would not satisfy users' preferences very much. Besides, the static parameters mentioned above make recommendation algorithms a lack of adaptability and limit their application scenarios. Aiming at improving the adaptability and efficiency of diversity-aware recommendations, we propose a coverage-based approach according to the concepts of user-coverage and users' interest domain we have defined in this paper. Our method is parameter-free and suitable for either implicit data or explicit data. From a technique perspective, we design an improved greedy algorithm, which is used to achieve user interest domain coverage maximization, and provide solid theoretical proof about performance guarantee on efficiency and recommendation quality. During the experiments, we compare our model against two novel methods on two real-world data sets. Experimental results demonstrate the superiority of our method over the state-of-the-art techniques in terms of item relevance and diversity.

Existing video rain streaks removal methods utilize various manual models to represent the appearance of rain streaks, and only use convolutional neural network (CNN) as a post-processing part to compensate the artifacts like misalignment caused by traditional de-raining operations. However, these manual models only work for some particular scenes because the distribution of rain streaks is complex and random. Moreover, since CNN network and previous traditional de-raining operations cannot be trained jointly, the output of CNN network may still contain artifacts. To address these problems, we propose an end-to-end video rain streaks removal CNN network called EEVRSR net. Experimental results of both synthetic and real data demonstrate that the proposed EEVRSR net achieves better performance in both speed and effectiveness over state-of-the-art methods.

In video coding, slice-level and block-level weighted bi-prediction are used for scenes with temporal brightness variation. However, there are still structured residuals when applying weighted bi-prediction in slice and block level. Recently, CNN-based bi-prediction has achieved remarkable success on reducing significant structured residuals, in which bi-predictor is generated by CNN model using two reference blocks as inputs. Inspired by high spatial correlation of pixels, this paper uses spatial neighboring pixels of both current block and two reference blocks as the additional information of the proposed CNN model to further reduce residual and generate a more accurate bi-predictor. Moreover, by comparing AMVP and merge/skip mode, this paper illustrates that CNN-based bi-prediction is more efficient for merge/skip mode than for AMVP mode. Experimental results show that proposed method reaches 3.46% BD-rate saving for random access configuration on average compared to HM 16.15.

In videos like movies and TV shows, similar scenes usually appear alternately. The period between these similar scenes is so long that it even exceeds the length of a random access (RA) segment. This means that the temporal correlation among these similar scenes crosses random access point (RAP). Besides, in videos like surveillance videos, a similar scene usually lasts for a long time which is longer than a RA segment. In other words, the temporal correlation among this scene also crosses RAP. To exploit the cross-RAP temporal correlation for further improving coding performance and keep the random access functionality at the same time, library picture based cross random access point reference is proposed and adopted in AVS3, which is going to be introduced in this paper. Firstly, a library picture is used as a reference picture for similar RA segments to exploit the temporal correlation among these RA segments. Secondly, to support random access, decoder and system layer are both designed to ensure that the decoder can get the corresponding library picture when random access occurs to correctly decode RA segments. Experimental results show that this method can save 6.4% and 31.5% BD-rate on the AVS3 general sequences and special sequences.

In HEVC, there are two types of motion vector (MV) when long-term reference is enabled: short-term MV (SMV) pointing to short-term reference frame and long-term MV (LMV) pointing to long-term reference frame. And cross-class prediction between SMV and LMV is not allowed because of their low correlation. Therefore, MV predictor candidates of current block would be inadequate when neighboring MVs are in different types. This paper proposes a complementary MV to enrich MV predictor candidates for current block. There would be two types of MV for each neighboring inter block. In addition to MV used in motion compensation, a complementary MV of the other type is derived by reconstructed pixels. This paper also proposed a reliability-based MV predictor candidate list construction method to improve the prediction efficiency of complementary MVs. Experimental results show that the proposed method can achieve 1.18% coding performance improvement on average.

Fuzzy support vector machine (FSVM) has been combined with class imbalance learning (CIL) strategies to address the problem of classifying skewed data. However, the existing approaches hold several inherent drawbacks, causing the inaccurate prior data distribution estimation, further decreasing the quality of the classification model. To solve this problem, we present a more robust prior data distribution information extraction method named relative density, and two novel FSVM-CIL algorithms based on the relative density information in this paper. In our proposed algorithms, a K-nearest neighbors-based probability density estimation (KNN-PDE) alike strategy is utilized to calculate the relative density of each training instance. In particular, the relative density is irrelevant with the dimensionality of data distribution in feature space, but only reflects the significance of each instance within its class; hence, it is more robust than the absolute distance information. In addition, the relative density can better seize the prior data distribution information, no matter the data distribution is easy or complex. Even for the data with small injunctions or a large class overlap, the relative density information can reflect its details well. We evaluated the proposed algorithms on an amount of synthetic and real-world imbalanced datasets. The results show that our proposed algorithms obviously outperform to some previous work, especially on those datasets with sophisticated distributions.

It is well known that active learning can simultaneously improve the quality of the classification model and decrease the complexity of training instances. However, several previous studies have indicated that the performance of active learning is easily disrupted by an imbalanced data distribution. Some existing imbalanced active learning approaches also suffer from either low performance or high time consumption. To address these problems, this paper describes an efficient solution based on the extreme learning machine (ELM) classification model, called active online-weighted ELM (AOW-ELM). The main contributions of this paper include: 1) the reasons why active learning can be disrupted by an imbalanced instance distribution and its influencing factors are discussed in detail; 2) the hierarchical clustering technique is adopted to select initially labeled instances in order to avoid the missed cluster effect and cold start phenomenon as much as possible; 3) the weighted ELM (WELM) is selected as the base classifier to guarantee the impartiality of instance selection in the procedure of active learning, and an efficient online updated mode of WELM is deduced in theory; and 4) an early stopping criterion that is similar to but more flexible than the margin exhaustion criterion is presented. The experimental results on 32 binary-class data sets with different imbalance ratios demonstrate that the proposed AOW-ELM algorithm is more effective and efficient than several state-of-the-art active learning algorithms that are specifically designed for the class imbalance scenario.

In video coding, temporal correlations between pictures are utilized by short-term and long-term reference, which are limited inside a random access segment and cannot cross random access points (RAPs). To improve coding efficiency, correlations across RAPs are exploited by some novel video coding schemes. The cross-random-access prediction structure results in alterable dependency between pictures, which is affected by random access and different from the fixed dependency in conventional video coding standard. However, current media streaming scheme, such as Dynamic Adaptive Streaming over HTTP (DASH), cannot describe dependency across RAPs. This paper introduces the cross-random-access dependency description in DASH syntax. With dependency information, client can download segments in proper temporal order but may re-download segments. This paper further improves downloading management in client. Experiments show that improved DASH system transmitting stream with cross-random-access prediction structure can save 22.1% on maximum and 14.3% on average transmission bits in contrast to conventional DASH system.

Haarlike feature has achieved great success in detecting frontal human faces, but fewer attentions have been paid to the other objects such as pedestrian. The reason of the low detection rate for Haarlike feature is attributed to the usage in a naive way. In this paper, we have revisited Haarlike feature for object detection especially focus on pedestrians, but use it in a different way which is applied based on multiple channel maps instead of raw pixels and obtains a significant improvement. Furthermore, we have proposed an improved Haarlike feature that embeds statistical information from the training data which is based on the linear discriminative analysis criterion. The proposed feature works with the classical Gentle Boosting algorithm which is effective in training, and also running at real-time speed. Experiments based on INIRA dataset demonstrate that our proposed method is easy to implement and achieves the performance comparable to the state-of-the-arts.

In many real world applications, class imbalance problems occur frequently, causing great underestimation for the classification performance of minority classes. In recent years, much effective solutions have been proposed to address this problem. Ho

Training classifiers on skewed data can be technically challenging tasks, especially if the data is high-dimensional simultaneously, the tasks can become more difficult. In biomedicine field, skewed data type often appears. In this study, we try to deal with this problem by combining asymmetric bagging ensemble classifier (asBagging) that has been presented in previous work and an improved random subspace (RS) generation strategy that is called feature subspace (FSS). Specifically, FSS is a novel method to promote the balance level between accuracy and diversity of base classifiers in asBagging. In view of the strong generalization capability of support vector machine (SVM), we adopt it to be base classifier. Extensive experiments on four benchmark biomedicine data sets indicate that the proposed ensemble learning method outperforms many baseline approaches in terms of Accuracy, F-measure, G-mean and AUC evaluation criterions, thus it can be regarded as an effective and efficient tool to deal with high-dimensional and imbalanced biomedical data.