Tootfinder

MGPRL: Distributed Multi-Gaussian Processes for Wi-Fi-based Multi-Robot Relative Localization in Large Indoor Environments
Sai Krishna Ghanta, Ramviyas Parasuraman
https://arxiv.org/abs/2506.23514

MGPRL: Distributed Multi-Gaussian Processes for Wi-Fi-based Multi-Robot Relative Localization in Large Indoor Environments
Relative localization is a crucial capability for multi-robot systems operating in GPS-denied environments. Existing approaches for multi-robot relative localization often depend on costly or short-range sensors like cameras and LiDARs. Consequently, these approaches face challenges such as high computational overhead (e.g., map merging) and difficulties in disjoint environments. To address this limitation, this paper introduces MGPRL, a novel distributed framework for multi-robot relative loca…

Logarithmic Depth Decomposition of Approximate Multi-Controlled Single-Qubit Gates Without Ancilla Qubits
Jefferson D. S. Silva, Adenilton J. da Silva
https://arxiv.org/abs/2507.00400

Logarithmic Depth Decomposition of Approximate Multi-Controlled Single-Qubit Gates Without Ancilla Qubits
The synthesis of quantum operators involves decomposing general quantum gates into the gate set supported by a given quantum device. Multi-controlled gates are essential components in this process. In this work, we present improved decompositions of multi-controlled NOT gates with logarithmic depth using a single ancilla qubit, while also reducing the constant factors in the circuit depth compared to previous work. We optimize a previously proposed decomposition of multi-target, multi-controlle…

MRGSEM-Sum: An Unsupervised Multi-document Summarization Framework based on Multi-Relational Graphs and Structural Entropy Minimization
Yongbing Zhang, Fang Nan, Shengxiang Gao, Yuxin Huang, Kaiwen Tan, Zhengtao Yu
https://arxiv.org/abs/2507.23400

MRGSEM-Sum: An Unsupervised Multi-document Summarization Framework based on Multi-Relational Graphs and Structural Entropy Minimization
The core challenge faced by multi-document summarization is the complexity of relationships among documents and the presence of information redundancy. Graph clustering is an effective paradigm for addressing this issue, as it models the complex relationships among documents using graph structures and reduces information redundancy through clustering, achieving significant research progress. However, existing methods often only consider single-relational graphs and require a predefined number o…

Evaluating Recabilities of Foundation Models: A Multi-Domain, Multi-Dataset Benchmark
Qijiong Liu, Jieming Zhu, Yingxin Lai, Xiaoyu Dong, Lu Fan, Zhipeng Bian, Zhenhua Dong, Xiao-Ming Wu
https://arxiv.org/abs/2508.21354

Evaluating Recabilities of Foundation Models: A Multi-Domain, Multi-Dataset Benchmark
Comprehensive evaluation of the recommendation capabilities of existing foundation models across diverse datasets and domains is essential for advancing the development of recommendation foundation models. In this study, we introduce RecBench-MD, a novel and comprehensive benchmark designed to assess the recommendation abilities of foundation models from a zero-resource, multi-dataset, and multi-domain perspective. Through extensive evaluations of 19 foundation models across 15 datasets spannin…

MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI
Huanjin Yao, Jiaxing Huang, Yawen Qiu, Michael K. Chen, Wenzheng Liu, Wei Zhang, Wenjie Zeng, Xikun Zhang, Jingyi Zhang, Yuxin Song, Wenhao Wu, Dacheng Tao
https://arxiv.org/abs/2506.23563

MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI
Reasoning plays a crucial role in advancing Multimodal Large Language Models (MLLMs) toward Artificial General Intelligence. However, existing MLLM benchmarks often fall short in precisely and comprehensively evaluating long-chain reasoning abilities from three key aspects: (1) lack of difficulty and diversity, (2) susceptibility to guessability and memorization, (3) inadequate assessment of intermediate reasoning steps. To fill this gap, we introduce MMReason, a new benchmark designed to preci…

Vision Transformers for Multi-Variable Climate Downscaling: Emulating Regional Climate Models with a Shared Encoder and Multi-Decoder Architecture
Fabio Merizzi, Harilaos Loukos
https://arxiv.org/abs/2506.22447

Vision Transformers for Multi-Variable Climate Downscaling: Emulating Regional Climate Models with a Shared Encoder and Multi-Decoder Architecture
Global Climate Models (GCMs) are critical for simulating large-scale climate dynamics, but their coarse spatial resolution limits their applicability in regional studies. Regional Climate Models (RCMs) refine this through dynamic downscaling, albeit at considerable computational cost and with limited flexibility. While deep learning has emerged as an efficient data-driven alternative, most existing studies have focused on single-variable models that downscale one variable at a time. This approa…

Moduli of Multi-Uniformized Stacks and Seifert $\mathbb{G}_m^d$-Bundles
Zhengkai Pan
https://arxiv.org/abs/2506.22573 https://arxiv.o…

Moduli of Multi-Uniformized Stacks and Seifert $\mathbb{G}_m^d$-Bundles
We introduce multi-uniformized stacks as a generalization of the Abramovich--Hassett construction of uniformized twisted varieties. We prove an equivalence between the category of multi $\mathbb{Q}$-line bundles satisfying an analogue of Kollár's condition and the category of multi-uniformized twisted varieties, and we construct the corresponding moduli space. We then broaden the framework to encompass Kollár's Seifert $\mathbb{G}_m^d$-bundles, showing that their moduli likewise coincide with…

OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
Jiazheng Xing, Hai Ci, Hongbin Xu, Hangjie Yuan, Yong Liu, Mike Zheng Shou
https://arxiv.org/abs/2508.21727

OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bit watermarking systems lack the capacity for large-scale user tracking, while multi-bit methods are highly sensitive to certain image transformations or generative attacks, resulting in a lack of comprehensive robustness. In this paper, we propose OptMark, an optimization-based approach that embeds a robust multi-bit …

A Multi-Stage Fine-Tuning and Ensembling Strategy for Pancreatic Tumor Segmentation in Diagnostic and Therapeutic MRI
Omer Faruk Durugol, Maximilian Rokuss, Yannick Kirchhoff, Klaus H. Maier-Hein
https://arxiv.org/abs/2508.21775

A Multi-Stage Fine-Tuning and Ensembling Strategy for Pancreatic Tumor Segmentation in Diagnostic and Therapeutic MRI
Automated segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) from MRI is critical for clinical workflows but is hindered by poor tumor-tissue contrast and a scarcity of annotated data. This paper details our submission to the PANTHER challenge, addressing both diagnostic T1-weighted (Task 1) and therapeutic T2-weighted (Task 2) segmentation. Our approach is built upon the nnU-Net framework and leverages a deep, multi-stage cascaded pre-training strategy, starting from a general anatomical …

Multimodal, Multi-Disease Medical Imaging Foundation Model (MerMED-FM)
Yang Zhou, Chrystie Wan Ning Quek, Jun Zhou, Yan Wang, Yang Bai, Yuhe Ke, Jie Yao, Laura Gutierrez, Zhen Ling Teo, Darren Shu Jeng Ting, Brian T. Soetikno, Christopher S. Nielsen, Tobias Elze, Zengxiang Li, Linh Le Dinh, Lionel Tim-Ee Cheng, Tran Nguyen Tuan Anh, Chee Leong Cheng, Tien Yin Wong, Nan Liu, Iain Beehuat Tan, Tony Kiat Hon Lim, Rick Siow Mong Goh, Yong Liu, Daniel Shu Wei Ting

Multimodal, Multi-Disease Medical Imaging Foundation Model (MerMED-FM)
Current artificial intelligence models for medical imaging are predominantly single modality and single disease. Attempts to create multimodal and multi-disease models have resulted in inconsistent clinical accuracy. Furthermore, training these models typically requires large, labour-intensive, well-labelled datasets. We developed MerMED-FM, a state-of-the-art multimodal, multi-specialty foundation model trained using self-supervised learning and a memory module. MerMED-FM was trained on 3.3 mi…

Multi-IRS Aided ISAC System: Multi-Path Exploitation Versus Reduction
Guangji Chen, Qingqing Wu, Shihang Lu, Meng Hua, Wen Chen
https://arxiv.org/abs/2506.21968

Multi-IRS Aided ISAC System: Multi-Path Exploitation Versus Reduction
This paper investigates a multi-intelligent reflecting surface (IRS) aided integrated sensing and communication (ISAC) system, where multiple IRSs are strategically deployed not only to assist the communication from a multi-antenna base station (BS) to a multi-antenna communication user (CU), but also enable the sensing service for a point target in the non-line-of-sight (NLoS) region of the BS. First, we propose a hybrid multi-IRS architecture, which consists of several passive IRSs and one se…

Distributionally Robust Cascading Risk Quantification in Multi-Agent Rendezvous: Effects of Time Delay and Network Connectivity
Vivek Pandey, Nader Motee
https://arxiv.org/abs/2507.23489

Distributionally Robust Cascading Risk Quantification in Multi-Agent Rendezvous: Effects of Time Delay and Network Connectivity
Achieving safety in autonomous multi-agent systems, particularly in time-critical tasks like rendezvous, is a critical challenge. In this paper, we propose a distributionally robust risk framework for analyzing cascading failures in multi-agent rendezvous. To capture the complex interactions between network connectivity, system dynamics, and communication delays, we use a time-delayed network model as a benchmark. We introduce a conditional distributionally robust functional to quantify cascadi…

Studying the multi-phase interstellar medium in the Large Magellanic Cloud with SRG/eROSITA -- I. Analysis of diffuse X-ray emission
Martin G. F. Mayer, Manami Sasaki, Frank Haberl, Kisetsu Tsuge, Yasuo Fukui, Chandreyee Maitra, Miroslav D. Filipovic, Zachary J. Smeaton, Lister Staveley-Smith, Baerbel Koribalski, Sean Points, Patrick Kavanagh
https:/…

Studying the multi-phase interstellar medium in the Large Magellanic Cloud with SRG/eROSITA -- I. Analysis of diffuse X-ray emission
The Large Magellanic Cloud (LMC), being a nearby and actively star-forming satellite galaxy of the Milky Way, is an ideal site to observe the multi-phase interstellar medium (ISM) of a galaxy across the electromagnetic spectrum. We aim to exploit the available SRG/eROSITA all-sky survey data to study the distribution, composition and properties of the diffuse X-ray emitting hot gas in the LMC. We construct multi-band X-ray images of the LMC, reflecting the morphology and temperatures of the dif…

Multi-goal-oriented anisotropic error control and mesh adaptivity for time-dependent convection-dominated problems
Markus Bause, Marius Paul Bruchh\"auser, Bernhard Endtmayer, Nils Margenberg, Ioannis Toulopoulos, Thomas Wick
https://arxiv.org/abs/2507.00723

Multi-goal-oriented anisotropic error control and mesh adaptivity for time-dependent convection-dominated problems
In this work, we present an anisotropic multi-goal error control based on the Dual Weighted Residual (DWR) method for time-dependent convection-diffusion-reaction (CDR) equations. This multi-goal oriented approach allows for an accurate and efficient error control with regard to several quantities of interest simultaneously. Using anisotropic interpolation and restriction operators, we obtain elementwise error indicators in space and time, where the spatial indicators are additionally separated…

iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement
Kohou Wang, ZhaoXiang Liu, Lin Bai, Kun Fan, Xiang Liu, Huan Hu, Kai Wang, Shiguo Lian
https://arxiv.org/abs/2507.22896

iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement
It is crucial that robots' performance can be improved after deployment, as they are inherently likely to encounter novel scenarios never seen before. This paper presents an innovative solution: an interactive learning-based robot system powered by a Multi-modal Large Language Model(MLLM). A key feature of our system is its ability to learn from natural dialogues with non-expert users. We also propose chain of question to clarify the exact intent of the question before providing an answer and d…

Leveraging a Multi-Agent LLM-Based System to Educate Teachers in Hate Incidents Management
Ewelina Gajewska, Michal Wawer, Katarzyna Budzynska, Jaros{\l}aw A. Chudziak
https://arxiv.org/abs/2506.23774

Leveraging a Multi-Agent LLM-Based System to Educate Teachers in Hate Incidents Management
Computer-aided teacher training is a state-of-the-art method designed to enhance teachers' professional skills effectively while minimising concerns related to costs, time constraints, and geographical limitations. We investigate the potential of large language models (LLMs) in teacher education, using a case of teaching hate incidents management in schools. To this end, we create a multi-agent LLM-based system that mimics realistic situations of hate, using a combination of retrieval-augmented…

Towards an Optimized Multi-Cyclic Queuing and Forwarding in Time Sensitive Networking with Time Injection
Rubi Debnath, Mohammadreza Barzegaran, Sebastian Steinhorst
https://arxiv.org/abs/2506.22671

Towards an Optimized Multi-Cyclic Queuing and Forwarding in Time Sensitive Networking with Time Injection
Cyclic Queuing and Forwarding (CQF) is a Time-Sensitive Networking (TSN) shaping mechanism that provides bounded latency and deterministic Quality of Service (QoS). However, CQF's use of a single cycle restricts its ability to support TSN traffic with diverse timing requirements. Multi-Cyclic Queuing and Forwarding (Multi-CQF) is a new and emerging TSN shaping mechanism that uses multiple cycles on the same egress port, allowing it to accommodate TSN flows with varied timing requirements more e…

Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scaling
Bruce Fang, Danyi Gao
https://arxiv.org/abs/2507.00550 https:/…

Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scaling
This paper addresses the challenges of rapid resource variation and highly uncertain task loads in cloud computing environments. It proposes an optimization method for elastic cloud resource scaling based on a multi-agent system. The method deploys multiple autonomous agents to perceive resource states in parallel and make local decisions. While maintaining the distributed nature of the system, it introduces a collaborative value function to achieve global coordination. This improves the respon…

Cooperative Sensing in Cell-free Massive MIMO ISAC Systems: Performance Optimization and Signal Processing
Haotian Liu, Zhiqing Wei, Luyang Sun, Ruizhong Xu, Yixin Zhang, Zhiyong Feng
https://arxiv.org/abs/2506.23473

Cooperative Sensing in Cell-free Massive MIMO ISAC Systems: Performance Optimization and Signal Processing
Integrated sensing and communication (ISAC), as a technology enabled seamless connection between communication and sensing, is regarded a core enabling technology for these applications. However, the accuracy of single-node sensing in ISAC system is limited, prompting the emergence of multi-node cooperative sensing. In multi-node cooperative sensing, the synchronization error limits the sensing accuracy, which can be mitigated by the architecture of cell-free massive multi-input multi-output (C…

Origami of Multi-Layered Spaced Sheets
Guowei Wayne Tu, Evgueni T. Filipov
https://arxiv.org/abs/2507.00341 https://arxiv.org/pdf/250…

Origami of Multi-Layered Spaced Sheets
Two-dimensional (2D) origami tessellations such as the Miura-ori are often generalized to build three-dimensional (3D) architected materials with sandwich or cellular structures. However, such 3D blocks are densely packed with continuity of the internal material, while for many engineering structures with multi-physical functionality, it is necessary to have thin sheets that are separately spaced and sparsely connected. This work presents a framework for the design and analysis of multi-layered…

Assisted Fibre Inflation in Perturbative LVS
George K. Leontaris, Pramod Shukla
https://arxiv.org/abs/2506.22630 https://arxiv.org/pd…

Assisted Fibre Inflation in Perturbative LVS
We propose a multi-field fiber inflation scenario in type IIB perturbative large volume compactifications, showing that the multi-field dynamics suppresses trans-Planckian displacements of the canonical inflaton. Considering a concrete K3-fibred Calabi-Yau (CY) threefold with $h^{1,1}({\rm CY})=3$ and having certain underlying symmetries, we show that the presence of multi-fibre moduli creates an assisted inflation scenario where multiple moduli collectively help in producing the cosmological o…

Novel Pigeon-inspired 3D Obstacle Detection and Avoidance Maneuver for Multi-UAV Systems
Reza Ahmadvand, Sarah Safura Sharif, Yaser Mike Banad
https://arxiv.org/abs/2507.00443

Novel Pigeon-inspired 3D Obstacle Detection and Avoidance Maneuver for Multi-UAV Systems
Recent advances in multi-agent systems manipulation have demonstrated a rising demand for the implementation of multi-UAV systems in urban areas, which are always subjected to the presence of static and dynamic obstacles. Inspired by the collective behavior of tilapia fish and pigeons, the focus of the presented research is on the introduction of a nature-inspired collision-free formation control for a multi-UAV system, considering the obstacle avoidance maneuvers. The developed framework in th…

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
Wenyong Zhou, Zhengwu Liu, Yuan Ren, Ngai Wong
https://arxiv.org/abs/2508.21524 https://…

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
Compute-in-memory (CIM) accelerators have emerged as a promising way for enhancing the energy efficiency of convolutional neural networks (CNNs). Deploying CNNs on CIM platforms generally requires quantization of network weights and activations to meet hardware constraints. However, existing approaches either prioritize hardware efficiency with binary weight and activation quantization at the cost of accuracy, or utilize multi-bit weights and activations for greater accuracy but limited efficie…

Deep Learning for Optical Misalignment Diagnostics in Multi-Lens Imaging Systems
Tomer Slor, Dean Oren, Shira Baneth, Tom Coen, Haim Suchowski
https://arxiv.org/abs/2506.23173

Deep Learning for Optical Misalignment Diagnostics in Multi-Lens Imaging Systems
In the rapidly evolving field of optical engineering, precise alignment of multi-lens imaging systems is critical yet challenging, as even minor misalignments can significantly degrade performance. Traditional alignment methods rely on specialized equipment and are time-consuming processes, highlighting the need for automated and scalable solutions. We present two complementary deep learning-based inverse-design methods for diagnosing misalignments in multi-element lens systems using only optic…

Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning
Anton Andreychuk, Konstantin Yakovlev, Aleksandr Panov, Alexey Skrynnik
https://arxiv.org/abs/2506.23793

Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning
Multi-agent pathfinding (MAPF) is a common abstraction of multi-robot trajectory planning problems, where multiple homogeneous robots simultaneously move in the shared environment. While solving MAPF optimally has been proven to be NP-hard, scalable, and efficient, solvers are vital for real-world applications like logistics, search-and-rescue, etc. To this end, decentralized suboptimal MAPF solvers that leverage machine learning have come on stage. Building on the success of the recently intro…

Multi-interaction TTS toward professional recording reproduction
Hiroki Kanagawa, Kenichi Fujita, Aya Watanabe, Yusuke Ijima
https://arxiv.org/abs/2507.00808

Multi-interaction TTS toward professional recording reproduction
Voice directors often iteratively refine voice actors' performances by providing feedback to achieve the desired outcome. While this iterative feedback-based refinement process is important in actual recordings, it has been overlooked in text-to-speech synthesis (TTS). As a result, fine-grained style refinement after the initial synthesis is not possible, even though the synthesized speech often deviates from the user's intended style. To address this issue, we propose a TTS method with multi-s…

Decentralised Multi-Manager Fund Framework
Arman Abgaryan, Utkarsh Sharma, Joshua Tobkin
https://arxiv.org/abs/2507.00978 https://arx…

Decentralised Multi-Manager Fund Framework
We introduce a decentralised, algorithmic framework for permissionless, multi-strategy capital allocation via tokenised, automated vaults. The system is designed to function analogously to a multi-strategy asset management company, but implemented entirely on-chain through a modular architecture comprising four interacting layers. The first, the capitalisation layer, composed of vaults that facilitate multi-asset deposits, tokenises investor participation, and specifies high level risk limits a…

Improved design of an active landing gear for a passenger aircraft using multi-objective optimization technique
Milad Zarchi, Behrooz Attaran
https://arxiv.org/abs/2506.22870

Improved design of an active landing gear for a passenger aircraft using multi-objective optimization technique
The landing gear system is a major aircraft subsystem that must withstand extreme forces during ground maneuvers and absorb vibrations. While traditional systems perform well under normal conditions, their efficiency drops under varying landing and runway scenarios. This study addresses this issue by simultaneously optimizing controller coefficients, parameters of a nonlinear hydraulic actuator integrated into the traditional shock absorber, and a vibration absorber using a bee-inspired multi-o…

Minimally dissipative multi-bit logical operations
J\'er\'emie Klinger, Grant M. Rotskoff
https://arxiv.org/abs/2506.24021 https://

Minimally dissipative multi-bit logical operations
Modern computing architectures are vastly more energy-dissipative than fundamental thermodynamic limits suggest, motivating the search for principled approaches to low-dissipation logical operations. We formulate multi-bit logical gates (bit erasure, NAND) as optimal transport problems, extending beyond classical one-dimensional bit erasure to scenarios where existing methods fail. Using entropically regularized unbalanced optimal transport, we derive tractable solutions and establish general e…

Simulation-Efficient Cosmological Inference with Multi-Fidelity SBI
Leander Thiele, Adrian E. Bayer, Naoya Takeishi
https://arxiv.org/abs/2507.00514 https:…

Simulation-Efficient Cosmological Inference with Multi-Fidelity SBI
The simulation cost for cosmological simulation-based inference can be decreased by combining simulation sets of varying fidelity. We propose an approach to such multi-fidelity inference based on feature matching and knowledge distillation. Our method results in improved posterior quality, particularly for small simulation budgets and difficult inference problems.

CFDagent: A Language-Guided, Zero-Shot Multi-Agent System for Complex Flow Simulation
Zhaoyue Xu, Long Wang, Chunyu Wang, Yixin Chen, Qingyong Luo, Hua-Dong Yao, Shizhao Wang, Guowei He
https://arxiv.org/abs/2507.23693

CFDagent: A Language-Guided, Zero-Shot Multi-Agent System for Complex Flow Simulation
We introduce CFDagent, a zero-shot, multi-agent system that enables fully autonomous computational fluid dynamics (CFD) simulations from natural language prompts. CFDagent integrates three specialized LLM-driven agents: (i) the Preprocessing Agent that generates 3D geometries from textual or visual inputs using a hybrid text-to-3D diffusion model (Point-E) and automatically meshes the geometries; (ii) the Solver Agent that configures and executes an immersed boundary flow solver; and (iii) the …

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
Han Li, Yuling Shi, Shaoxin Lin, Xiaodong Gu, Heng Lian, Xin Wang, Yantao Jia, Tao Huang, Qianxiang Wang
https://arxiv.org/abs/2507.23348

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
Issue resolution has made remarkable progress thanks to the advanced reasoning capabilities of large language models (LLMs). Recently, agent-based frameworks such as SWE-agent have further advanced this progress by enabling autonomous, tool-using agents to tackle complex software engineering tasks. While existing agent-based issue resolution approaches are primarily based on agents' independent explorations, they often get stuck in local solutions and fail to identify issue patterns that span a…

Optimization Method of Multi-factor Investment Model Driven by Deep Learning for Risk Control
Ruisi Li, Xinhui Gu
https://arxiv.org/abs/2507.00332 https://…

Optimization Method of Multi-factor Investment Model Driven by Deep Learning for Risk Control
Propose a deep learning driven multi factor investment model optimization method for risk control. By constructing a deep learning model based on Long Short Term Memory (LSTM) and combining it with a multi factor investment model, we optimize factor selection and weight determination to enhance the model's adaptability and robustness to market changes. Empirical analysis shows that the LSTM model is significantly superior to the benchmark model in risk control indicators such as maximum retrace…

A Practical Guide to Interpretable Role-Based Clustering in Multi-Layer Financial Networks
Christian Franssen, Iman van Lelyveld, Bernd Heidergott
https://arxiv.org/abs/2507.00600

A Practical Guide to Interpretable Role-Based Clustering in Multi-Layer Financial Networks
Understanding the functional roles of financial institutions within interconnected markets is critical for effective supervision, systemic risk assessment, and resolution planning. We propose an interpretable role-based clustering approach for multi-layer financial networks, designed to identify the functional positions of institutions across different market segments. Our method follows a general clustering framework defined by proximity measures, cluster evaluation criteria, and algorithm sel…

Multi-peak solutions for the fractional Schr\"odinger equation with Dirichlet datum
Maria Medina, Jing Wu
https://arxiv.org/abs/2507.00806 https://

Multi-peak solutions for the fractional Schrödinger equation with Dirichlet datum
Let $s\in (0,1)$, $\varepsilon>0$ and let $Ω$ be a bounded smooth domain. Given the problem $$\varepsilon^{2s}(-Δ)^{s} u + V(x)u = |u|^{p-1}u \quad \mbox{in }\; Ω,$$ with Dirichlet boundary conditions and $1

Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction
Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
https://arxiv.org/abs/2508.21460 ht…

Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction
In click-through rate prediction, click-through rate prediction is used to model users' interests. However, most of the existing CTR prediction methods are mainly based on the ID modality. As a result, they are unable to comprehensively model users' multi-modal preferences. Therefore, it is necessary to introduce multi-modal CTR prediction. Although it seems appealing to directly apply the existing multi-modal fusion methods to click-through rate prediction models, these methods (1) fail to eff…

Multi-point local time penalizations with various clocks for one-dimensional L\'{e}vy processes
Kohki Iba
https://arxiv.org/abs/2507.00457 https://

Multi-point local time penalizations with various clocks for one-dimensional Lévy processes
We study the penalization problem with various clocks where the weight is given as the exponential functional of multi-point local times for one-dimensional Lévy processes. The limit processes may vary according to the choice of random clock, and are singular to the original process.

MVGBench: Comprehensive Benchmark for Multi-view Generation Models
Xianghui Xie, Chuhang Zou, Meher Gitika Karumuri, Jan Eric Lenssen, Gerard Pons-Moll
https://arxiv.org/abs/2507.00006

MVGBench: Comprehensive Benchmark for Multi-view Generation Models
We propose MVGBench, a comprehensive benchmark for multi-view image generation models (MVGs) that evaluates 3D consistency in geometry and texture, image quality, and semantics (using vision language models). Recently, MVGs have been the main driving force in 3D object creation. However, existing metrics compare generated images against ground truth target views, which is not suitable for generative tasks where multiple solutions exist while differing from ground truth. Furthermore, different M…

A survey of multi-agent geosimulation methodologies: from ABM to LLM
Virginia Padilla, Jacinto D\'avila
https://arxiv.org/abs/2507.23694 https://arxiv.…

A survey of multi-agent geosimulation methodologies: from ABM to LLM
We provide a comprehensive examination of agent-based approaches that codify the principles and linkages underlying multi-agent systems, simulations, and information systems. Based on two decades of study, this paper confirms a framework intended as a formal specification for geosimulation platforms. Our findings show that large language models (LLMs) can be effectively incorporated as agent components if they follow a structured architecture specific to fundamental agent activities such as per…

Consistency of Feature Attribution in Deep Learning Architectures for Multi-Omics
Daniel Claborne, Javier Flores, Samantha Erwin, Luke Durell, Rachel Richardson, Ruby Fore, Lisa Bramer
https://arxiv.org/abs/2507.22877

Consistency of Feature Attribution in Deep Learning Architectures for Multi-Omics
Machine and deep learning have grown in popularity and use in biological research over the last decade but still present challenges in interpretability of the fitted model. The development and use of metrics to determine features driving predictions and increase model interpretability continues to be an open area of research. We investigate the use of Shapley Additive Explanations (SHAP) on a multi-view deep learning model applied to multi-omics data for the purposes of identifying biomolecules…

Multi-Hazard Early Warning Systems for Agriculture with Featural-Temporal Explanations
Boyuan Zheng, Victor W. Chu
https://arxiv.org/abs/2507.22962 https://

Multi-Hazard Early Warning Systems for Agriculture with Featural-Temporal Explanations
Climate extremes present escalating risks to agriculture intensifying the need for reliable multi-hazard early warning systems (EWS). The situation is evolving due to climate change and hence such systems should have the intelligent to continue to learn from recent climate behaviours. However, traditional single-hazard forecasting methods fall short in capturing complex interactions among concurrent climatic events. To address this deficiency, in this paper, we combine sequential deep learning …

CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation
Xinlei Yu, Chanmiao Wang, Hui Jin, Ahmed Elazab, Gangyong Jia, Xiang Wan, Changqing Zou, Ruiquan Ge
https://arxiv.org/abs/2506.23121

CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation
Multi-organ medical segmentation is a crucial component of medical image processing, essential for doctors to make accurate diagnoses and develop effective treatment plans. Despite significant progress in this field, current multi-organ segmentation models often suffer from inaccurate details, dependence on geometric prompts and loss of spatial information. Addressing these challenges, we introduce a novel model named CRISP-SAM2 with CRoss-modal Interaction and Semantic Prompting based on SAM2.…

Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks
Sarfaroz Yunusov, Kaige Chen, Kazi Nishat Anwar, Ali Emami
https://arxiv.org/abs/2508.21628

Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks
As Large Language Models (LLMs) increasingly integrate into everyday workflows, where users shape outcomes through multi-turn collaboration, a critical question emerges: do users with different personality traits systematically prefer certain LLMs over others? We conducted a study with 32 participants evenly distributed across four Keirsey personality types, evaluating their interactions with GPT-4 and Claude 3.5 across four collaborative tasks: data analysis, creative writing, information retr…

Evolution of multi-qubit correlations driven by mutual interactions
Aleksandra Kwiatkowska, Waldemar K{\l}obus
https://arxiv.org/abs/2507.00692 https://

Evolution of multi-qubit correlations driven by mutual interactions
A particularly useful tool for characterizing multi-qubit systems is the correlation tensor, providing an experimentally friendly and theoretically concise representation of quantum states. In this work, we analyze the evolution of the correlation tensor elements of quantum systems composed of $\frac12$-spins, generated by mutual interactions and the influence of the external field. We focus on two-body interactions in the form of anisotropic Heisenberg as well as antisymmetric exchange interac…

Multi-Modal Model Predictive Path Integral Control for Collision Avoidance
Alberto Bertipaglia, Dariu M. Gavrila, Barys Shyrokau
https://arxiv.org/abs/2508.21364 https://…

Multi-Modal Model Predictive Path Integral Control for Collision Avoidance
This paper proposes a novel approach to motion planning and decision-making for automated vehicles, using a multi-modal Model Predictive Path Integral control algorithm. The method samples with Sobol sequences around the prior input and incorporates analytical solutions for collision avoidance. By leveraging multiple modes, the multi-modal control algorithm explores diverse trajectories, such as manoeuvring around obstacles or stopping safely before them, mitigating the risk of sub-optimal solu…

An optimal preconditioner for high-order scheme arising from multi-dimensional Riesz space fractional diffusion equations with variable coefficients
Yuan-Yuan Huang, Wei Qu, Sean Y. Hon, Siu-Long Lei
https://arxiv.org/abs/2507.23408

An optimal preconditioner for high-order scheme arising from multi-dimensional Riesz space fractional diffusion equations with variable coefficients
In this paper, we propose an efficient method for solving multi-dimensional Riesz space fractional diffusion equations with variable coefficients. The Crank-Nicolson (CN) method is used for temporal discretization, while the fourth-order fractional centered difference (4FCD) method is employed for spatial discretization. Using a novel technique, we show that the CN-4FCD scheme for the multi-dimensional case is unconditionally stable and convergent, achieving second-order accuracy in time and fo…

Multi-Method Ensemble for Out-of-Distribution Detection
Lucas Rakotoarivony
https://arxiv.org/abs/2508.21463 https://arxiv.org/pdf/2508.21463

Multi-Method Ensemble for Out-of-Distribution Detection
Detecting out-of-distribution (OOD) samples is essential for neural networks operating in open-world settings, particularly in safety-critical applications. Existing methods have improved OOD detection by leveraging two main techniques: feature truncation, which increases the separation between in-distribution (ID) and OOD samples, and scoring functions, which assign scores to distinguish between ID and OOD data. However, most approaches either focus on a single family of techniques or evaluate…

UniMLR: Modeling Implicit Class Significance for Multi-Label Ranking
V. Bugra Yesilkaynak, Emine Dari, Alican Mertan, Gozde Unal
https://arxiv.org/abs/2508.21772 https://…

UniMLR: Modeling Implicit Class Significance for Multi-Label Ranking
Existing multi-label ranking (MLR) frameworks only exploit information deduced from the bipartition of labels into positive and negative sets. Therefore, they do not benefit from ranking among positive labels, which is the novel MLR approach we introduce in this paper. We propose UniMLR, a new MLR paradigm that models implicit class relevance/significance values as probability distributions using the ranking among positive labels, rather than treating them as equally important. This approach un…

Liftings of ideals in positive characteristic to those in characteristic zero: Higher dimension
Shihoko Ishii
https://arxiv.org/abs/2506.23533 https://

Liftings of ideals in positive characteristic to those in characteristic zero: Higher dimension
We study a pair consisting of a smooth variety of arbitrary dimension over a field of positive characteristic and a multi-ideal with a real exponent. We prove that the set of log discrepancies for a fixed exponent is discrete. Additionally, we show that the set of log canonical thresholds (lcts) of multi-ideals on a smooth variety in positive characteristic is contained within the set of lcts of multi-ideals on a smooth variety over the complex number field. As a result, we find that the accumu…

Evaluating Multi-Agent Defences Against Jailbreaking Attacks on Large Language Models
Maria Carolina Cornelia Wit, Jun Pang
https://arxiv.org/abs/2506.23576

Evaluating Multi-Agent Defences Against Jailbreaking Attacks on Large Language Models
Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We evaluate three jailbreaking strategies, including the original AutoDefense attack and two from Deepleaps: BetterDan and JB. Reproducing the AutoDefense framework, we compare single-agent setups with two- and three-agent configurations. Our results show that mu…

Multi-wavelength Study of HESS J0632 057: New Insights into Pulsar-Disk Interaction
Jaegeun Park (Chungbuk National University), Hongjun An (Chungbuk National University), Chanho Kim (Chungbuk National University), Natalie Matchett (University of the Free State), Kaya Mori (Columbia University), Brian van Soelen (University of the Free State), VERITAS Collaboration, :, A. Archer, P. Bangale, J. T. Bartkoske, W. Benbow, J. H. Buckley, Y. Chen, A. J. Chromey, A. Duerr, M. Errando, M. Es…

Multi-wavelength Study of HESS J0632+057: New Insights into Pulsar-Disk Interaction
We present an analysis of new multi-wavelength observations of the TeV gamma-ray binary HESS J0632+057, conducted using SALT, Swift, NuSTAR, and VERITAS in 2023--2024. By combining these new data with archival observations, we confirm previous suggestions of orbital variability in the source's X-ray spectrum, including increased X-ray absorption at the orbital phase interval of $ϕ\approx0.3\textrm{--}0.4$. The source's X-ray flux within this phase interval seems to have exhibited a significant…

Fair Rate Maximization for Fluid Antenna Relay (FAR)-assisted Multi-user MISO Communications
Ruopeng Xu, Zhaohui Yang, Ting Zhang, Mingzhe Chen, Chen Zhu, Zhaoyang Zhang
https://arxiv.org/abs/2507.00529

Fair Rate Maximization for Fluid Antenna Relay (FAR)-assisted Multi-user MISO Communications
In this paper, we investigate the problem of max-min rate maximization in fluid antenna relay (FAR)-assisted multi-user uplink multiple-input single-output (MISO) wireless systems, where each user is equipped with a single fluid antenna (FA) and the base station (BS) is equipped with multiple FAs. Unlike most existing relevant work focusing on maximizing sum rate of the fluid antenna system (FAS), which may cause unbearable rate loss to weak users, we propose to maximize the minimal rate of the…

A Multi-Criteria Evaluation Framework for Siting Fusion Energy Facilities: Application and Evaluation of U.S. Coal Power Plants
Muhammad R. Abdussami, Kevin Daley, Gabrielle Hoelzle, Aditi Verma
https://arxiv.org/abs/2506.22489

A Multi-Criteria Evaluation Framework for Siting Fusion Energy Facilities: Application and Evaluation of U.S. Coal Power Plants
This paper proposes a comprehensive methodology for siting fusion energy facilities, integrating expert judgment, geospatial data, and multi-criteria decision making tools to evaluate site suitability systematically. As a case study, we apply this framework to all currently operational coal power plant sites in the United States to examine their potential for hosting future fusion facilities at a time when these coal plants are shut down on reaching their end of life - timelines which are expec…

Enhancing Live Broadcast Engagement: A Multi-modal Approach to Short Video Recommendations Using MMGCN and User Preferences
Saeid Aghasoleymani Najafabadi
https://arxiv.org/abs/2506.23085

Enhancing Live Broadcast Engagement: A Multi-modal Approach to Short Video Recommendations Using MMGCN and User Preferences
The purpose of this paper is to explore a multi-modal approach to enhancing live broadcast engagement by developing a short video recommendation system that incorporates Multi-modal Graph Convolutional Networks (MMGCN) with user preferences. In order to provide personalized recommendations tailored to individual interests, the proposed system takes into account user interaction data, video content features, and contextual information. With the aid of a hybrid approach combining collaborative fi…

PRIME: Pseudo-Random Integrated Multi-Part Entropy for Adaptive Packet Spraying in AI/ML Data centers
Ashkan Sobhani, Sogand Sadrhaghighi, Xingjun Chu
https://arxiv.org/abs/2507.23012

PRIME: Pseudo-Random Integrated Multi-Part Entropy for Adaptive Packet Spraying in AI/ML Data centers
Large-scale distributed training in production data centers place significant demands on network infrastructure. In particular, significant load balancing challenges arise when processing AI/ML workloads, consisting of low-entropy, bursty and long-lived flows. Existing solutions designed for Ethernet, such as Equal-Cost Multi-Path (ECMP) struggle to maintain high network utilization. While major industry players (e.g., Ultra Ethernet Consortium) and parts of academia have proposed packet sprayi…

SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches
Ehsan Latif, Zirak Khan, Xiaoming Zhai
https://arxiv.org/abs/2507.22904 https://

SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches
Scientific sketches (e.g., models) offer a powerful lens into students' conceptual understanding, yet AI-powered automated assessment of such free-form, visually diverse artifacts remains a critical challenge. Existing solutions often treat sketch evaluation as either an image classification task or monolithic vision-language models, which lack interpretability, pedagogical alignment, and adaptability across cognitive levels. To address these limitations, we present SketchMind, a cognitively gr…

A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback
Guoliang Duan, Mingwei Liu, Yanlin Wang, Chong Wang, Xin Peng, Zibin Zheng
https://arxiv.org/abs/2507.00699

A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback
Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize functional correctness, overlooking the nuanced requirements found in real-world development. We introduce MultiCodeIF, a comprehensive benchmark designed to evaluate instruction-following in code generation across multiple dimensions: constraint type, hierarchica…

Simulation-based planning of Motion Sequences for Automated Procedure Optimization in Multi-Robot Assembly Cells
Loris Schneider, Marc Ungen, Elias Huber, Jan-Felix Klein
https://arxiv.org/abs/2507.23270

Simulation-based planning of Motion Sequences for Automated Procedure Optimization in Multi-Robot Assembly Cells
Reconfigurable multi-robot cells offer a promising approach to meet fluctuating assembly demands. However, the recurrent planning of their configurations introduces new challenges, particularly in generating optimized, coordinated multi-robot motion sequences that minimize the assembly duration. This work presents a simulation-based method for generating such optimized sequences. The approach separates assembly steps into task-related core operations and connecting traverse operations. While co…

Short proof of the conditioning property for multi-dimensional Poisson point processes
Nicolas Lanchier
https://arxiv.org/abs/2508.21303 https://arxiv.org/…

Short proof of the conditioning property for multi-dimensional Poisson point processes
Poisson processes and one-dimensional Poisson point processes satisfy three main properties: superposition, thinning, and conditioning. The proof of the first two relies on basic estimates involving the Poisson distribution that are also true for multi-dimensional Poisson point processes. In contrast, the proof of conditioning uses that the distances between consecutive occurrences in time or entities in space are independent and exponentially distributed, which is nonsensical in higher dimensi…

Glyph-Based Multiscale Visualization of Turbulent Multi-Physics Statistics
Arisa Cowe, Tyson Neuroth, Qi Wu, Martin Rieth, Jacqueline Chen, Myoungkyu Lee, Kwan-Liu Ma
https://arxiv.org/abs/2506.23092

Glyph-Based Multiscale Visualization of Turbulent Multi-Physics Statistics
Many scientific and engineering problems involving multi-physics span a wide range of scales. Understanding the interactions across these scales is essential for fully comprehending such complex problems. However, visualizing multivariate, multiscale data within an integrated view where correlations across space, scales, and fields are easily perceived remains challenging. To address this, we introduce a novel local spatial statistical visualization of flow fields across multiple fields and tur…

Towards Building Private LLMs: Exploring Multi-Node Expert Parallelism on Apple Silicon for Mixture-of-Experts Large Language Model
Mu-Chi Chen, Po-Hsuan Huang, Xiangrui Ke, Chia-Heng Tu, Chun Jason Xue, Shih-Hao Hung
https://arxiv.org/abs/2506.23635

Towards Building Private LLMs: Exploring Multi-Node Expert Parallelism on Apple Silicon for Mixture-of-Experts Large Language Model
Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) with significant advancements such as OpenAI's ChatGPT, Meta's Llama, and Databricks' DBRX. This paper addresses the cost and scalability challenges encountered when constructing private LLM systems for personal or small group services, as aimed by Apple Intelligence. A Mac Studio cluster with Apple's M2 Ultra chips is established as a cost-efficient solution to host and accelerate the pretrained DBRX model with the M…

Multi-Source COVID-19 Detection via Variance Risk Extrapolation
Runtian Yuan, Qingqiu Li, Junlin Hou, Jilan Xu, Yuejie Zhang, Rui Feng, Hao Chen
https://arxiv.org/abs/2506.23208

Multi-Source COVID-19 Detection via Variance Risk Extrapolation
We present our solution for the Multi-Source COVID-19 Detection Challenge, which aims to classify chest CT scans into COVID and Non-COVID categories across data collected from four distinct hospitals and medical centers. A major challenge in this task lies in the domain shift caused by variations in imaging protocols, scanners, and patient populations across institutions. To enhance the cross-domain generalization of our model, we incorporate Variance Risk Extrapolation (VREx) into the training…

Pok\'eAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
Zihao Liu, Xinhang Sui, Yueran Song, Siwen Wang
https://arxiv.org/abs/2506.23689

PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
We introduce PokéAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pokémon Red. Our system consists of three specialized agents-Planning, Execution, and Critique-each with its own memory bank, role, and skill set. The Planning Agent functions as the central brain, generating tasks to progress through the game. These tasks are then delegated to the Execution Agent, which carries them out within the game environment. Up…

Standardized Multi-Layer Tissue Maps for Enhanced Artificial Intelligence Integration and Search in Large-Scale Whole Slide Image Archives
Gernot Fiala, Markus Plass, Robert Harb, Peter Regitnig, Kristijan Skok, Wael Al Zoughbi, Carmen Zerner, Paul Torke, Michaela Kargl, Heimo M\"uller, Tomas Brazdil, Matej Gallo, Jaroslav Kub\'in, Roman Stoklasa, Rudolf Nenutil, Norman Zerbe, Andreas Holzinger, Petr Holub

Standardized Multi-Layer Tissue Maps for Enhanced Artificial Intelligence Integration and Search in Large-Scale Whole Slide Image Archives
A Whole Slide Image (WSI) is a high-resolution digital image created by scanning an entire glass slide containing a biological specimen, such as tissue sections or cell samples, at multiple magnifications. These images can be viewed, analyzed, shared digitally, and are used today for Artificial Intelligence (AI) algorithm development. WSIs are used in a variety of fields, including pathology for diagnosing diseases and oncology for cancer research. They are also utilized in neurology, veterinar…

Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
Xiaolong Wei, Bo Lu, Xingyu Zhang, Zhejun Zhao, Dongdong Shen, Long Xia, Dawei Yin
https://arxiv.org/abs/2508.21476

Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
Large Language Models (LLMs) have demonstrated remarkable creative writing capabilities, yet their substantial computational demands hinder widespread use. Enhancing Small Language Models (SLMs) offers a promising alternative, but current methods like Supervised Fine-Tuning (SFT) struggle with novelty, and Reinforcement Learning from Human Feedback (RLHF) is costly. This paper explores two distinct AI-driven reward strategies within a Reinforcement Learning from AI Feedback (RLAIF) framework to…

Multi-Target Density Matrix Renormalization Group X algorithm and its application to circuit quantum electrodynamics
Sof\'ia Gonz\'alez-Garc\'ia, Aaron Szasz, Alice Pagano, Dvir Kafri, Guifr\'e Vidal, Agustin Di Paolo
https://arxiv.org/abs/2506.24109

Multi-Target Density Matrix Renormalization Group X algorithm and its application to circuit quantum electrodynamics
Obtaining accurate representations of the eigenstates of an array of coupled superconducting qubits is a crucial step in the design of circuit quantum electrodynamics (QED)-based quantum processors. However, exact diagonalization of the device Hamiltonian is challenging for system sizes beyond tens of qubits. Here, we employ a variant of the density matrix renormalization group (DMRG) algorithm, DMRG-X, to efficiently obtain localized eigenstates of a 2D transmon array without the need to first…

A Multi-Frequency Helmholtz Solver Based on the WaveHoltz Algorithm
Daniel Appel\"o, Francis Appiah, Jeffrey W. Banks, Cassandra Carrick, William D. Henshaw, Donald W. Schwendeman
https://arxiv.org/abs/2507.23613

A Multi-Frequency Helmholtz Solver Based on the WaveHoltz Algorithm
We develop and analyze a new approach for simultaneously computing multiple solutions to the Helmholtz equation for different frequencies and different forcing functions. The new Multi-Frequency WaveHoltz (MFWH) algorithm is an extension of the original WaveHoltz method and both are based on time-filtering solutions to an associated wave equation. With MFWH, the different Helmholtz solutions are computed simultaneously by solving a single wave equation combined with multiple time filters. The M…

A-MHA*: Anytime Multi-Heuristic A*
Ramkumar Natarajan, Muhammad Suhail Saleem, William Xiao, Sandip Aine, Howie Choset, Maxim Likhachev
https://arxiv.org/abs/2508.21637 https://…

A-MHA*: Anytime Multi-Heuristic A*
Designing good heuristic functions for graph search requires adequate domain knowledge. It is often easy to design heuristics that perform well and correlate with the underlying true cost-to-go values in certain parts of the search space but these may not be admissible throughout the domain thereby affecting the optimality guarantees of the search. Bounded suboptimal search using several such partially good but inadmissible heuristics was developed in Multi-Heuristic A* (MHA*). Although MHA* le…

QoS-Aware Proportional Fairness Scheduling for Multi-Flow 5G UEs: A Smart Factory Perspective
Mohamed Seliem, Utz Roedig, Cormac Sreenan, Dirk Pesch
https://arxiv.org/abs/2508.21783

QoS-Aware Proportional Fairness Scheduling for Multi-Flow 5G UEs: A Smart Factory Perspective
Private 5G networks are emerging as key enablers for smart factories, where a single device often handles multiple concurrent traffic flows with distinct Quality of Service (QoS) requirements. Existing simulation frameworks, however, lack the fidelity to model such multi-flow behavior at the QoS Flow Identifier (QFI) level. This paper addresses this gap by extending Simu5G to support per-QFI modeling and by introducing a novel QoS-aware Proportional Fairness (QoS-PF) scheduler. The scheduler dy…

Multi-Domain FeFET-Based Pixel for In-Sensor Multiply-and-Accumulate Operations
Md Rahatul Islam Udoy, Wantong Li, Kai Ni, Ahmedullah Aziz
https://arxiv.org/abs/2506.22596

Multi-Domain FeFET-Based Pixel for In-Sensor Multiply-and-Accumulate Operations
This paper presents an FeFET-based active pixel sensor that performs in-sensor multiply-and-accumulate (MAC) operations by leveraging the multi-domain polarization states of ferroelectric layers. The proposed design integrates a programmable FeFET into a 3-transistor pixel circuit, where the FeFET's non-volatile conductance encodes the weight, and the photodiode voltage drop encodes the input. Their interaction generates an output current proportional to the product, enabling in-pixel analog mu…

Improving vulnerability type prediction and line-level detection via adversarial training-based data augmentation and multi-task learning
Siyu Chen, Jiongyi Yang, Xiang Chen, Menglin Zheng, Minnan Wei, Xiaolin Ju
https://arxiv.org/abs/2506.23534

Improving vulnerability type prediction and line-level detection via adversarial training-based data augmentation and multi-task learning
Context: Software vulnerabilities pose a significant threat to modern software systems, as evidenced by the growing number of reported vulnerabilities and cyberattacks. These escalating trends underscore the urgent need for effective approaches that can automatically detect and understand software vulnerabilities. Objective: However, the scarcity of labeled samples and the class imbalance issue in vulnerability datasets present significant challenges for both Vulnerability Type Prediction (VTP)…

GamerAstra: Enhancing Video Game Accessibility for Blind and Low-Vision Players through a Multi-Agent AI Framework
Tianrun Qiu, Changxin Chen, Sizhe Cheng, Yiming Yang, Yixiao Guo, Zhicong Lu, Yuxin Ma
https://arxiv.org/abs/2506.22937

GamerAstra: Enhancing Video Game Accessibility for Blind and Low-Vision Players through a Multi-Agent AI Framework
Blind and low-vision (BLV) players encounter critical challenges in engaging with video games due to the inaccessibility of visual elements, difficulties in navigating interfaces, and limitations in sending interaction input. Moreover, the development of specialized accessibility features typically requires substantial programming effort and is often implemented on a game-by-game basis. To address these challenges, we introduce \textit{GamerAstra}, a generalized accessibility framework that lev…

Multi-robot Path Planning and Scheduling via Model Predictive Optimal Transport (MPC-OT)
Usman A. Khan, Mouhacine Benosman, Wenliang Liu, Federico Pecora, Joseph W. Durham
https://arxiv.org/abs/2508.21205

Multi-robot Path Planning and Scheduling via Model Predictive Optimal Transport (MPC-OT)
In this paper, we propose a novel methodology for path planning and scheduling for multi-robot navigation that is based on optimal transport theory and model predictive control. We consider a setup where $N$ robots are tasked to navigate to $M$ targets in a common space with obstacles. Mapping robots to targets first and then planning paths can result in overlapping paths that lead to deadlocks. We derive a strategy based on optimal transport that not only provides minimum cost paths from robot…

Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
Langming Liu, Wanyu Wang, Chi Zhang, Bo Li, Hongzhi Yin, Xuetao Wei, Wenbo Su, Bo Zheng, Xiangyu Zhao
https://arxiv.org/abs/2506.23090

Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
Online advertising in recommendation platforms has gained significant attention, with a predominant focus on channel recommendation and budget allocation strategies. However, current offline reinforcement learning (RL) methods face substantial challenges when applied to sparse advertising scenarios, primarily due to severe overestimation, distributional shifts, and overlooking budget constraints. To address these issues, we propose MTORL, a novel multi-task offline RL model that targets two key…

Hierarchical Adversarially-Resilient Multi-Agent Reinforcement Learning for Cyber-Physical Systems Security
Saad Alqithami
https://arxiv.org/abs/2506.22445

Hierarchical Adversarially-Resilient Multi-Agent Reinforcement Learning for Cyber-Physical Systems Security
Cyber-Physical Systems play a critical role in the infrastructure of various sectors, including manufacturing, energy distribution, and autonomous transportation systems. However, their increasing connectivity renders them highly vulnerable to sophisticated cyber threats, such as adaptive and zero-day attacks, against which traditional security methods like rule-based intrusion detection and single-agent reinforcement learning prove insufficient. To overcome these challenges, this paper introdu…

The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning
Yiming Lin, Yuchen Niu, Shang Wang, Kaizhu Huang, Qiufeng Wang, Xiao-Bo Jin
https://arxiv.org/abs/2508.21816

The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning
Context recognition (SR) is a fundamental task in computer vision that aims to extract structured semantic summaries from images by identifying key events and their associated entities. Specifically, given an input image, the model must first classify the main visual events (verb classification), then identify the participating entities and their semantic roles (semantic role labeling), and finally localize these entities in the image (semantic role localization). Existing methods treat verb cl…

Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture
Yeawon Lee, Xiaoyang Wang, Christopher C. Yang
https://arxiv.org/abs/2508.21803

Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture
Accurate interpretation of clinical narratives is critical for patient care, but the complexity of these notes makes automation challenging. While Large Language Models (LLMs) show promise, single-model approaches can lack the robustness required for high-stakes clinical tasks. We introduce a collaborative multi-agent system (MAS) that models a clinical consultation team to address this gap. The system is tasked with identifying clinical problems by analyzing only the Subjective (S) and Objecti…

Multi-dimensional frequency-bin entanglement-based quantum key distribution network
George Claudiu Crisan, Antoine Henry, Dario Alessandro Fioretto, Juan Rafael Alvarez, St\'ephan Monfray, Fr\'ed\'eric Boeuf, Laurent Vivien, Eric Cassan, Carlos Alonso-Ramos, Nadia Belabas
https://arxiv.org/abs/2507.00972

Multi-dimensional frequency-bin entanglement-based quantum key distribution network
Quantum networks enhance quantum communication schemes and link multiple users over large areas. Harnessing high dimensional quantum states - i.e. qu-d-its - allows for a denser transfer of information with increased robustness to noise compared to qubits. Frequency encoding enables access to such qu-d-its at telecom wavelengths, while manipulating quantum information with off-the-shelf fibered devices. We use a low free spectral range silicon microresonator to generate Bell states of dimensi…

MDPG: Multi-domain Diffusion Prior Guidance for MRI Reconstruction
Lingtong Zhang, Mengdie Song, Xiaohan Hao, Huayu Mai, Bensheng Qiu
https://arxiv.org/abs/2506.23701

MDPG: Multi-domain Diffusion Prior Guidance for MRI Reconstruction
Magnetic Resonance Imaging (MRI) reconstruction is essential in medical diagnostics. As the latest generative models, diffusion models (DMs) have struggled to produce high-fidelity images due to their stochastic nature in image domains. Latent diffusion models (LDMs) yield both compact and detailed prior knowledge in latent domains, which could effectively guide the model towards more effective learning of the original data distribution. Inspired by this, we propose Multi-domain Diffusion Prior…

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
Vira Joshi, Zifan Xu, Bo Liu, Peter Stone, Amy Zhang
https://arxiv.org/abs/2507.23172 ht…

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which demands a generalizable and robust policy. At the same time, \emph{massively parallelized training} has gained popularity, not only for significantly accelerating data collection through GPU-accelerated simulation but also for enabling diverse data collection across multiple tasks by simulating heterogeneous scenes in p…

Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration
Haoxiang Luo, Yinqiu Liu, Ruichen Zhang, Jiacheng Wang, Gang Sun, Dusit Niyato, Hongfang Yu, Zehui Xiong, Xianbin Wang, Xuemin Shen
https://arxiv.org/abs/2507.00672

Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration
Edge computing enables real-time data processing closer to its source, thus improving the latency and performance of edge-enabled AI applications. However, traditional AI models often fall short when dealing with complex, dynamic tasks that require advanced reasoning and multimodal data processing. This survey explores the integration of multi-LLMs (Large Language Models) to address this in edge computing, where multiple specialized LLMs collaborate to enhance task performance and adaptability …

Many LLMs Are More Utilitarian Than One
Anita Keshmirian, Razan Baltaji, Babak Hemmatian, Hadi Asghari, Lav R. Varshney
https://arxiv.org/abs/2507.00814 ht…

Many LLMs Are More Utilitarian Than One
Moral judgment is integral to large language model (LLM) alignment and social reasoning. As multi-agent systems gain prominence, it becomes crucial to understand how LLMs function collectively during collaboration, compared to individual agents. In human moral judgment, group deliberation leads to a utilitarian boost: a tendency to endorse norm violations that maximize benefits for the greatest number of people despite harms. We study whether a similar dynamic emerges in multi-agent LLM systems…

MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models
Jianghao Lin, Xinyuan Wang, Xinyi Dai, Menghui Zhu, Bo Chen, Ruiming Tang, Yong Yu, Weinan Zhang
https://arxiv.org/abs/2507.00487

MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models
Tool retrieval is a critical component in enabling large language models (LLMs) to interact effectively with external tools. It aims to precisely filter the massive tools into a small set of candidates for the downstream tool-augmented LLMs. However, most existing approaches primarily focus on optimizing tool representations, often neglecting the importance of precise query comprehension. To address this gap, we introduce MassTool, a multi-task search-based framework designed to enhance both qu…

Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
Guizhe Jin, Zhuoren Li, Bo Leng, Ran Yu, Lu Xiong
https://arxiv.org/abs/2506.23771

Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
Reinforcement Learning (RL) is increasingly used in autonomous driving (AD) and shows clear advantages. However, most RL-based AD methods overlook policy structure design. An RL policy that only outputs short-timescale vehicle control commands results in fluctuating driving behavior due to fluctuations in network outputs, while one that only outputs long-timescale driving goals cannot achieve unified optimality of driving behavior and control. Therefore, we propose a multi-timescale hierarchica…

MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion
Zihan Wang, Jeff Tan, Tarasha Khurana, Neehar Peri, Deva Ramanan
https://arxiv.org/abs/2507.23782 https://

MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion
We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panoptic Studio). Such multi-view setups are prohibitively expensive to build and cannot capture diverse scenes in-the-wild. In contrast, we aim to reconstruct dynamic human behaviors, such as repairing a bike or dancing, from a small set of sparse-view cameras with complete scene coverage (e.g. four equidistant inward-faci…

Quantum-Enhanced Natural Language Generation: A Multi-Model Framework with Hybrid Quantum-Classical Architectures
Chi-Sheng Chen, En-Jui Kuo
https://arxiv.org/abs/2508.21332 htt…

Quantum-Enhanced Natural Language Generation: A Multi-Model Framework with Hybrid Quantum-Classical Architectures
This paper presents a comprehensive evaluation of quantum text generation models against traditional Transformer/MLP architectures, addressing the growing interest in quantum computing applications for natural language processing. We conduct systematic experiments comparing five distinct models: Transformer (baseline), Quantum Kernel Self-Attention Network (QKSAN), Quantum RWKV (QRWKV), and Quantum Attention Sequence Architecture (QASA) across five diverse datasets including simple sentences, s…

In-between Motion Generation Based Multi-Style Quadruped Robot Locomotion
Yuanhao Chen, Liu Zhao, Ji Ma, Peng Lu
https://arxiv.org/abs/2507.23053 https://a…

In-between Motion Generation Based Multi-Style Quadruped Robot Locomotion
Quadruped robots face persistent challenges in achieving versatile locomotion due to limitations in reference motion data diversity. To address these challenges, this approach introduces an in-between motion generation based multi-style quadruped robot locomotion framework, integrating synergistic advances in motion generation and imitation learning. Our approach establishes a unified pipeline addressing two fundamental aspects: First, we propose a CVAE based motion generator, synthesizing mult…

Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation
Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Dongjie Wang, Zijun Yao
https://arxiv.org/abs/2508.21320

Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation
Medical ontology graphs map external knowledge to medical codes in electronic health records via structured relationships. By leveraging domain-approved connections (e.g., parent-child), predictive models can generate richer medical concept representations by incorporating contextual information from related concepts. However, existing literature primarily focuses on incorporating domain knowledge from a single ontology system, or from multiple ontology systems (e.g., diseases, drugs, and proce…

Transfer entropy and O-information to detect grokking in tensor network multi-class classification problems
Domenico Pomarico, Roberto Cilli, Alfonso Monaco, Loredana Bellantuono, Marianna La Rocca, Tommaso Maggipinto, Giuseppe Magnifico, Marlis Ontivero Ortega, Ester Pantaleo, Sabina Tangaro, Sebastiano Stramaglia, Roberto Bellotti, Nicola Amoroso
https://

Transfer entropy and O-information to detect grokking in tensor network multi-class classification problems
Quantum-enhanced machine learning, encompassing both quantum algorithms and quantum-inspired classical methods such as tensor networks, offers promising tools for extracting structure from complex, high-dimensional data. In this work, we study the training dynamics of Matrix Product State (MPS) classifiers applied to three-class problems, using both fashion MNIST and hyper-spectral satellite imagery as representative datasets. We investigate the phenomenon of grokking, where generalization emer…

Observability-driven Assignment of Heterogeneous Sensors for Multi-Target Tracking
Seyed Ali Rakhshan, Mehdi Golestani, He Kong
https://arxiv.org/abs/2508.21309 https://

Observability-driven Assignment of Heterogeneous Sensors for Multi-Target Tracking
This paper addresses the challenge of assigning heterogeneous sensors (i.e., robots with varying sensing capabilities) for multi-target tracking. We classify robots into two categories: (1) sufficient sensing robots, equipped with range and bearing sensors, capable of independently tracking targets, and (2) limited sensing robots, which are equipped with only range or bearing sensors and need to at least form a pair to collaboratively track a target. Our objective is to optimize tracking qualit…

PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation
Jiho Choi, Seojeong Park, Seongjong Song, Hyunjung Shim
https://arxiv.org/abs/2508.21720 ht…

PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation
We present a novel training-free framework, \textit{PosterForest}, for automated scientific poster generation. Unlike prior approaches, which largely neglect the hierarchical structure of scientific documents and the semantic integration of textual and visual elements, our method addresses both challenges directly. We introduce the \textit{Poster Tree}, a hierarchical intermediate representation that jointly encodes document structure and visual-textual relationships at multiple levels. Our fra…

User Experience Estimation in Human-Robot Interaction Via Multi-Instance Learning of Multimodal Social Signals
Ryo Miyoshi, Yuki Okafuji, Takuya Iwamoto, Junya Nakanishi, Jun Baba
https://arxiv.org/abs/2507.23544

User Experience Estimation in Human-Robot Interaction Via Multi-Instance Learning of Multimodal Social Signals
In recent years, the demand for social robots has grown, requiring them to adapt their behaviors based on users' states. Accurately assessing user experience (UX) in human-robot interaction (HRI) is crucial for achieving this adaptability. UX is a multi-faceted measure encompassing aspects such as sentiment and engagement, yet existing methods often focus on these individually. This study proposes a UX estimation method for HRI by leveraging multimodal social signals. We construct a UX dataset …

Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AI
Farhad Abtahi, Mehdi Astaraki, Fernando Seoane
https://arxiv.org/abs/2508.21648 https://…

Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AI
Bias in medical artificial intelligence is conventionally viewed as a defect requiring elimination. However, human reasoning inherently incorporates biases shaped by education, culture, and experience, suggesting their presence may be inevitable and potentially valuable. We propose MEDLEY (Medical Ensemble Diagnostic system with Leveraged diversitY), a conceptual framework that orchestrates multiple AI models while preserving their diverse outputs rather than collapsing them into a consensus. U…

Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies
Hugo Garrido-Lestache, Jeremy Kedziora
https://arxiv.org/abs/2507.22782 https://

Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies
This paper introduces Team-Attention-Actor-Critic (TAAC), a reinforcement learning algorithm designed to enhance multi-agent collaboration in cooperative environments. TAAC employs a Centralized Training/Centralized Execution scheme incorporating multi-headed attention mechanisms in both the actor and critic. This design facilitates dynamic, inter-agent communication, allowing agents to explicitly query teammates, thereby efficiently managing the exponential growth of joint-action spaces while …

Scalable Solution Methods for Dec-POMDPs with Deterministic Dynamics
Yang You, Alex Schutz, Zhikun Li, Bruno Lacerda, Robert Skilton, Nick Hawes
https://arxiv.org/abs/2508.21595

Scalable Solution Methods for Dec-POMDPs with Deterministic Dynamics
Many high-level multi-agent planning problems, including multi-robot navigation and path planning, can be effectively modeled using deterministic actions and observations. In this work, we focus on such domains and introduce the class of Deterministic Decentralized POMDPs (Det-Dec-POMDPs). This is a subclass of Dec-POMDPs characterized by deterministic transitions and observations conditioned on the state and joint actions. We then propose a practical solver called Iterative Deterministic P…

Multi-Waypoint Path Planning and Motion Control for Non-holonomic Mobile Robots in Agricultural Applications
Mahmoud Ghorab, Matthias Lorenzen
https://arxiv.org/abs/2507.23350 h…

Multi-Waypoint Path Planning and Motion Control for Non-holonomic Mobile Robots in Agricultural Applications
There is a growing demand for autonomous mobile robots capable of navigating unstructured agricultural environments. Tasks such as weed control in meadows require efficient path planning through an unordered set of coordinates while minimizing travel distance and adhering to curvature constraints to prevent soil damage and protect vegetation. This paper presents an integrated navigation framework combining a global path planner based on the Dubins Traveling Salesman Problem (DTSP) with a Nonlin…

MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
Yaolun Zhang, Xiaogeng Liu, Chaowei Xiao
https://arxiv.org/abs/2507.22606 https://

MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
Large Language Models (LLMs) have demonstrated the ability to solve a wide range of practical tasks within multi-agent systems. However, existing human-designed multi-agent frameworks are typically limited to a small set of pre-defined scenarios, while current automated design methods suffer from several limitations, such as the lack of tool integration, dependence on external training data, and rigid communication structures. In this paper, we propose MetaAgent, a finite state machine based fr…

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
Shaofei Cai, Zhancun Mu, Haiwen Xia, Bowei Zhang, Anji Liu, Yitao Liang
https://arxiv.org/abs/2507.23698

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
While Reinforcement Learning (RL) has achieved remarkable success in language modeling, its triumph hasn't yet fully translated to visuomotor agents. A primary challenge in RL models is their tendency to overfit specific tasks or environments, thereby hindering the acquisition of generalizable behaviors across diverse settings. This paper provides a preliminary answer to this challenge by demonstrating that RL-finetuned visuomotor agents in Minecraft can achieve zero-shot generalization to unse…

Multi-Robot Assembly of Deformable Linear Objects Using Multi-Modal Perception
Kejia Chen, Celina Dettmering, Florian Pachler, Zhuo Liu, Yue Zhang, Tailai Cheng, Jonas Dirr, Zhenshan Bing, Alois Knoll, R\"udiger Daub
https://arxiv.org/abs/2506.22034

Multi-Robot Assembly of Deformable Linear Objects Using Multi-Modal Perception
Industrial assembly of deformable linear objects (DLOs) such as cables offers great potential for many industries. However, DLOs pose several challenges for robot-based automation due to the inherent complexity of deformation and, consequentially, the difficulties in anticipating the behavior of DLOs in dynamic situations. Although existing studies have addressed isolated subproblems like shape tracking, grasping, and shape control, there has been limited exploration of integrated workflows tha…

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
Leander Melroy Maben, Gayathri Ganesh Lakshmy, Srijith Radhakrishnan, Siddhant Arora, Shinji Watanabe
https://arxiv.org/abs/2506.23049

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
Despite advances in language and speech technologies, no open-source system enables full speech-to-speech, multi-turn dialogue with integrated tool use and agentic reasoning. We introduce AURA (Agent for Understanding, Reasoning, and Automated Tool Use), the first open-source, speech-native assistant capable of completing complex, goal-driven tasks through dynamic tool invocation and multi-turn conversation. AURA combines open-weight ASR, TTS, and LLMs in a cascaded pipeline and supports tools …