The Transformer model has demonstrated success across a wide range of domains, including in Multi-Agent Reinforcement Learning (MARL) where the Multi-Agent Transformer (MAT) has emerged as a leading algorithm in the field. The Transformer model has demonstrated success across a wide range of domains, including in Multi-Agent Reinforcement Learning (MARL) where the Multi-Agent Transformer (MAT) has emerged as a leading algorithm in the field. However, a significant drawback of Transformer models is their quadratic computational complexity relative to input size, making them computationally expensive when scaling to larger inputs. This limitation restricts MAT's scalability in environments with many agents. Recently, State-Space Models (SSMs) have gained attention due to their computational efficiency, but their application in MARL remains unexplored. In this work, we investigate the use of Mamba, a recent SSM, in MARL and assess whether it can match the performance of MAT while providing significant improvements in efficiency. We introduce a modified version of MAT that incorporates standard and bi-directional Mamba blocks, as well as a novel "cross-attention" Mamba block. Extensive testing shows that our Multi-Agent Mamba (MAM) matches the performance of MAT across multiple standard multi-agent environments, while offering superior scalability to larger agent scenarios. This is significant for the MARL community, because it indicates that SSMs could replace Transformers without compromising performance, whilst also supporting more effective scaling to higher numbers of agents. Our project page is available at //sites.google.com/view/multi-agent-mamba .
相關內容
When a network slice spans multiple technology domains, it is crucial for each domain to uphold the End-to-End (E2E) Service Level Agreement (SLA) associated with the slice. Consequently, the E2E SLA must be properly decomposed into partial SLAs that are assigned to each domain involved. In a network slice management system with a two-level architecture, comprising an E2E service orchestrator and local domain controllers, we consider that the orchestrator has access solely to historical data regarding the responses of local controllers to previous requests, and this information is used to construct a risk model for each domain. In this study, we extend our previous work by investigating the dynamic nature of real-world systems and introducing an online learning-decomposition framework to tackle the dynamicity. We propose a framework that periodically updates the risk models based on the most recent feedback. This approach leverages key components such as online gradient descent and FIFO memory buffers, which enhance the stability and robustness of the overall process. Our empirical study on an analytic model-based simulator demonstrates that the proposed framework outperforms the state-of-the-art static approach, providing more accurate and resilient SLA decomposition even under varying conditions and limited data scenarios.
Protocol Reverse Engineering (PRE) is used to analyze protocols by inferring their structure and behavior. However, current PRE methods mainly focus on field identification within a single protocol and neglect Protocol State Machine (PSM) analysis in mixed protocol environments. This results in insufficient analysis of protocols' abnormal behavior and potential vulnerabilities, which are crucial for detecting and defending against new attack patterns. To address these challenges, we propose an automatic PSM inference framework for unknown protocols, including a fuzzy membership-based auto-converging DBSCAN algorithm for protocol format clustering, followed by a session clustering algorithm based on Needleman-Wunsch and K-Medoids algorithms to classify sessions by protocol type. Finally, we refine a probabilistic PSM algorithm to infer protocol states and the transition conditions between these states. Experimental results show that, compared with existing PRE techniques, our method can infer PSMs while enabling more precise classification of protocols.
Current Semi-Supervised Object Detection (SSOD) methods enhance detector performance by leveraging large amounts of unlabeled data, assuming that both labeled and unlabeled data share the same label space. However, in open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. To alleviate this issue, we propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector). Specifically, we introduce a feature-level clustering method using contrastive loss to clarify vector boundaries in the feature space and highlight class differences. Additionally, by optimizing the logits-level uncertainty classification loss, the model enhances its ability to effectively distinguish between ID and OOD classes. Extensive experiments demonstrate that our method achieves state-of-the-art performance compared to existing methods.
As sample sizes grow, scalability has become a central concern in the development of Markov chain Monte Carlo (MCMC) methods. One general approach to this problem, exemplified by the popular stochastic gradient Langevin dynamics (SGLD) algorithm, is to use a small random subsample of the data at every time step. This paper, building on recent work such as \cite{nagapetyan2017true,JohndrowJamesE2020NFLf}, shows that this approach often fails: while decreasing the sample size increases the speed of each MCMC step, for typical datasets this is balanced by a matching decrease in accuracy. This result complements recent work such as \cite{nagapetyan2017true} (which came to the same conclusion, but analyzed only specific upper bounds on errors rather than actual errors) and \cite{JohndrowJamesE2020NFLf} (which did not analyze nonreversible algorithms and allowed for logarithmic improvements).
Despite the success of the O-RAN Alliance in developing a set of interoperable interfaces, development of unique Radio Access Network (RAN) deployments remains challenging. This is especially true for military communications, where deployments are highly specialized with limited volume. The construction and maintenance of the RAN, which is a real time embedded system, is an ill-defined NP problem requiring teams of specialized system engineers, with specialized knowledge of the hardware platform. In this paper, we introduce a RAN Domain Specific Language (RDSL(TM)) to formally describe use cases, constraints, and multi-vendor hardware/software abstraction to allow automation of RAN construction. In this DSL, system requirements are declarative, and performance constraints are guaranteed by construction using an automated system solver. Using our RAN system solver platform, Gabriel(TM) we show how a system engineer can confidently modify RAN functionality without knowledge of the underlying hardware. We show benefits for specific system requirements when compared to the manually optimized, default configuration of the Intel FlexRAN(TM), and conclude that DSL/automation driven construction of the RAN can lead to significant power and latency benefits when the deployment constraints are tuned for a specific case. We give examples of how constraints and requirements can be formatted in a "Kubernetes style" YAML format which allows the use of other tools, such as Ansible, to integrate the generation of these requirements into higher level automation flows such as Service Management and Orchestration (SMO).
Artificial Intelligence (AI) has achieved transformative success across a wide range of domains, revolutionizing fields such as healthcare, education, and human-computer interaction. However, the mechanisms driving AI's performance often remain opaque, particularly in the context of large language models (LLMs), which have advanced at an unprecedented pace in recent years. Multi-modal large language models (MLLMs) like GPT-4o exemplify this evolution, integrating text, audio, and visual inputs to enable interaction across diverse domains. Despite their remarkable capabilities, these models remain largely "black boxes," offering limited insight into how they process multi-modal information internally. This lack of transparency poses significant challenges, including systematic biases, flawed associations, and unintended behaviors, which require careful investigation. Understanding the decision-making processes of MLLMs is both beneficial and essential for mitigating these challenges and ensuring their reliable deployment in critical applications. GPT-4o was chosen as the focus of this study for its advanced multi-modal capabilities, which allow simultaneous processing of textual and visual information. These capabilities make it an ideal model for investigating the parallels and distinctions between machine-driven and human-driven visual perception. While GPT-4o performs effectively in tasks involving structured and complete data, its reliance on bottom-up processing, which involves a feature-by-feature analysis of sensory inputs, presents challenges when interpreting complex or ambiguous stimuli. This limitation contrasts with human vision, which is remarkably adept at resolving ambiguity and reconstructing incomplete information through high-level cognitive processes.
Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks and applications. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a systematic literature review on the intersection of LLMs and SE, with a particular focus on understanding how LLMs can be exploited in SE to optimize processes and outcomes. We collect and analyze a total of 229 research papers from 2017 to 2023 to answer four key research questions (RQs). In RQ1, we categorize and provide a comparative analysis of different LLMs that have been employed in SE tasks, characterising their distinctive features and uses. In RQ2, we analyse the methods used in data collection, preprocessing, and application highlighting the role of robust, well-curated datasets for successful LLM for SE implementation. RQ3 investigates the strategies employed to optimize and evaluate the performance of LLMs in SE, as well as the common techniques related to prompt optimization. Finally, RQ4 examines the specific SE tasks where LLMs have shown success to date, illustrating their practical contributions to the field. From the answers to these RQs, we discuss the current state-of-the-art and trends, identifying gaps in existing research, and flagging promising areas for future study.
Recent artificial intelligence (AI) systems have reached milestones in "grand challenges" ranging from Go to protein-folding. The capability to retrieve medical knowledge, reason over it, and answer medical questions comparably to physicians has long been viewed as one such grand challenge. Large language models (LLMs) have catalyzed significant progress in medical question answering; Med-PaLM was the first model to exceed a "passing" score in US Medical Licensing Examination (USMLE) style questions with a score of 67.2% on the MedQA dataset. However, this and other prior work suggested significant room for improvement, especially when models' answers were compared to clinicians' answers. Here we present Med-PaLM 2, which bridges these gaps by leveraging a combination of base LLM improvements (PaLM 2), medical domain finetuning, and prompting strategies including a novel ensemble refinement approach. Med-PaLM 2 scored up to 86.5% on the MedQA dataset, improving upon Med-PaLM by over 19% and setting a new state-of-the-art. We also observed performance approaching or exceeding state-of-the-art across MedMCQA, PubMedQA, and MMLU clinical topics datasets. We performed detailed human evaluations on long-form questions along multiple axes relevant to clinical applications. In pairwise comparative ranking of 1066 consumer medical questions, physicians preferred Med-PaLM 2 answers to those produced by physicians on eight of nine axes pertaining to clinical utility (p < 0.001). We also observed significant improvements compared to Med-PaLM on every evaluation axis (p < 0.001) on newly introduced datasets of 240 long-form "adversarial" questions to probe LLM limitations. While further studies are necessary to validate the efficacy of these models in real-world settings, these results highlight rapid progress towards physician-level performance in medical question answering.
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image.
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the component gives a substantial improvement in counting over a strong baseline by 6.6%.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191