Tootfinder

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
Yi Liu, Yang Liu, Leqian Zheng, Jue Hong, Junjie Shi, Qingyou Yang, Ye Wu, Cong Wang
https://arxiv.org/abs/2510.12494

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
With the rapid advancement of the digital economy, data collaboration between organizations has become a well-established business model, driving the growth of various industries. However, privacy concerns make direct data sharing impractical. To address this, Two-Party Split Learning (a.k.a. Vertical Federated Learning (VFL)) has emerged as a promising solution for secure collaborative learning. Despite its advantages, this architecture still suffers from low computational resource utilization…

SDC-Based Model Predictive Control: Enhancing Computational Feasibility for Safety-Critical Quadrotor Control
Saber Omidi
https://arxiv.org/abs/2509.24208 https://

SDC-Based Model Predictive Control: Enhancing Computational Feasibility for Safety-Critical Quadrotor Control
Nonlinear Model Predictive Control (NMPC) is widely used for controlling high-speed robotic systems such as quadrotors. However, its significant computational demands often hinder real-time feasibility and reliability, particularly in environments requiring robust obstacle avoidance. This paper proposes a novel SDC-Based Model Predictive Control (MPC) framework, which preserves the high-precision performance of NMPC while substantially reducing computational complexity by over 30%. By reformula…

TAG-K: Tail-Averaged Greedy Kaczmarz for Computationally Efficient and Performant Online Inertial Parameter Estimation
Shuo Sha, Anupam Bhakta, Zhenyuan Jiang, Kevin Qiu, Ishaan Mahajan, Gabriel Bravo, Brian Plancher
https://arxiv.org/abs/2510.04839

TAG-K: Tail-Averaged Greedy Kaczmarz for Computationally Efficient and Performant Online Inertial Parameter Estimation
Accurate online inertial parameter estimation is essential for adaptive robotic control, enabling real-time adjustment to payload changes, environmental interactions, and system wear. Traditional methods such as Recursive Least Squares (RLS) and the Kalman Filter (KF) often struggle to track abrupt parameter shifts or incur high computational costs, limiting their effectiveness in dynamic environments and for computationally constrained robotic systems. As such, we introduce TAG-K, a lightweigh…

Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning
Sai Teja Reddy Adapala
https://arxiv.org/abs/2509.19517 https://arxiv.org/…

Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning
The scaling of Large Language Models (LLMs) has exposed a critical gap between their performance on static benchmarks and their fragility in dynamic, information-rich environments. While models excel at isolated tasks, the computational limits that govern their reasoning under cognitive load remain poorly understood. In this work, we introduce a formal theory of computational cognitive load, positing that extraneous, task-irrelevant information (Context Saturation) and interference from task-sw…

Microstructure sensitive recurrent neural network surrogate model of crystal plasticity
Michael D. Atkinson, Michael D. White, Adam J. Plowman, Pratheek Shanthraj
https://arxiv.org/abs/2510.06904

Microstructure sensitive recurrent neural network surrogate model of crystal plasticity
The development of next-generation structural materials for harsh environments requires rapid assessment of mechanical performance and its dependence on microstructure. While full-field crystal plasticity (CP) models provide detailed insights, the high computational cost limits their use with uncertainty quantification workflows and in component-scale simulation. Surrogate models based on recurrent neural networks (RNNs) have shown promise in reproducing history-dependent mechanical behaviour b…

Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation
Miao Rang, Zhenni Bi, Hang Zhou, Hanting Chen, An Xiao, Tianyu Guo, Kai Han, Xinghao Chen, Yunhe Wang
https://arxiv.org/abs/2509.26497

Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation
The rapid advancement of large language models (LLMs) has significantly advanced the capabilities of artificial intelligence across various domains. However, their massive scale and high computational costs render them unsuitable for direct deployment in resource-constrained edge environments. This creates a critical need for high-performance small models that can operate efficiently at the edge. Yet, after pre-training alone, these smaller models often fail to meet the performance requirements…

Securing IoT Devices in Smart Cities: A Review of Proposed Solutions
Andr\'es F. Betancur-L\'opez
https://arxiv.org/abs/2510.01445 https://arxiv.or…

Securing IoT Devices in Smart Cities: A Review of Proposed Solutions
Privacy and security in Smart Cities remain at constant risk due to the vulnerabilities introduced by Internet of Things (IoT) devices. The limited computational resources of these devices make them especially susceptible to attacks, while their widespread adoption increases the potential impact of security breaches. This article presents a review of security proposals aimed at protecting IoT devices in Smart City environments. The review was conducted by analyzing recent literature on device-l…

Accelerated Convolutive Transfer Function-Based Multichannel NMF Using Iterative Source Steering
Xuemai Xie, Xianrui Wang, Liyuan Zhang, Yichen Yang, Shoji Makino
https://arxiv.org/abs/2510.02382

Accelerated Convolutive Transfer Function-Based Multichannel NMF Using Iterative Source Steering
Among numerous blind source separation (BSS) methods, convolutive transfer function-based multichannel non-negative matrix factorization (CTF-MNMF) has demonstrated strong performance in highly reverberant environments by modeling multi-frame correlations of delayed source signals. However, its practical deployment is hindered by the high computational cost associated with the iterative projection (IP) update rule, which requires matrix inversion for each source. To address this issue, we propo…

Interactive High-Performance Visualization for Astronomy and Cosmology
Eva Sciacca, Nicola Tuccari, Umer Arshad, Fabio Pitari, Giuseppa Muscianisi, Emiliano Tramontana
https://arxiv.org/abs/2510.04665 …

Interactive High-Performance Visualization for Astronomy and Cosmology
The exponential growth of data in Astrophysics and Cosmology demands scalable computational tools and intuitive interfaces for analysis and visualization. In this work, we present an innovative integration of the VisIVO scientific visualization framework with the InterActive Computing (IAC) service at Cineca, enabling interactive, high-performance visual workflows directly within HPC environments. Through seamless integration into Jupyter-based science gateways, users can now access GPU-enabled…

Human vs. AI Safety Perception? Decoding Human Safety Perception with Eye-Tracking Systems, Street View Images, and Explainable AI
Yuhao Kang, Junda Chen, Liu Liu, Kshitij Sharmad, Martina Mazzarello, Simone Mora, Fabio Duarte, Carlo Ratti
https://arxiv.org/abs/2509.25457

Human vs. AI Safety Perception? Decoding Human Safety Perception with Eye-Tracking Systems, Street View Images, and Explainable AI
The way residents perceive safety plays an important role in how they use public spaces. Studies have combined large-scale street view images and advanced computer vision techniques to measure the perception of safety of urban environments. Despite their success, such studies have often overlooked the specific environmental visual factors that draw human attention and trigger people's feelings of safety perceptions. In this study, we introduce a computational framework that enriches the existin…

Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning
Sai Teja Reddy Adapala
https://arxiv.org/abs/2509.19517 https://arxiv.org/…

Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning
The scaling of Large Language Models (LLMs) has exposed a critical gap between their performance on static benchmarks and their fragility in dynamic, information-rich environments. While models excel at isolated tasks, the computational limits that govern their reasoning under cognitive load remain poorly understood. In this work, we introduce a formal theory of computational cognitive load, positing that extraneous, task-irrelevant information (Context Saturation) and interference from task-sw…

Accurate Machine-Learning Description for SiC in Extreme Environments
Jintong Wu, Zhuang Shao, Junlei Zhao, Flyura Djurabekova, Kai Nordlund, Fredric Granberg, Qingmin Zhang, and Jesper Byggm\"astar
https://arxiv.org/abs/2510.01827

Accurate Machine-Learning Description for SiC in Extreme Environments
Silicon carbide (SiC) polymorphs are widely employed as nuclear materials, mechanical components, and wide-bandgap semiconductors. The rapid advancement of SiC-based applications has been complemented by computational modeling studies, including both ab initio and classical atomistic approaches. In this work, we develop a computationally efficient and general-purpose machine-learned interatomic potential (ML-IAP) capable of multimillion-atom molecular dynamics (MD) simulations over microsecond …

MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
Zheming Yang, Qi Guo, Yunqing Hu, Chang Zhao, Chang Zhang, Jian Zhao, Wen Ji
https://arxiv.org/abs/2509.16995

MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
Multimodal large language models (MLLMs) enable powerful cross-modal inference but impose significant computational and latency burdens, posing severe challenges for deployment in resource-constrained environments. In this paper, we propose MoA-Off, an adaptive heterogeneous modality-aware offloading framework with edge-cloud collaboration for efficient MLLM inference. MoA-Off introduces a lightweight heterogeneous modality-aware module that estimates the complexity of heterogeneous inputs thro…

Investigating solid-state CH3OH formation with chemical modelling
K. -Y. Huang, E. M\'endez-Robayo, S. Viti, Mario -A. Higuera -G
https://arxiv.org/abs/2509.22203 https://…

Investigating solid-state CH3OH formation with chemical modelling
Context. Recent Monte Carlo simulations and laboratory studies of interstellar ices have proposed an alternative pathway involving the radical-molecule H-atom abstraction reaction in the overall mechanism of methanol (CH3OH) formation in dark molecular clouds. Aims. A computational study was conducted to investigate the contribution of the radical-molecule H-atom abstraction route in CH3OH formation in interstellar ices, both in non-shocked and shocked environments, and to examine how the physi…

Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning
Siyi Zhao, Wei Wang, Yanmin Qian
https://arxiv.org/abs/2509.21833 https://

Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning
Recent advancements in automatic speech recognition (ASR) have achieved notable progress, whereas robustness in noisy environments remains challenging. While speech enhancement (SE) front-ends are widely used to mitigate noise as a preprocessing step for ASR, they often introduce computational non-negligible overhead. This paper proposes optimizations to reduce SE computational costs without compromising ASR performance. Our approach integrates layer-wise frame resampling and progressive sub-ba…

MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning
Maisha Maliha, Dean Hougen
https://arxiv.org/abs/2510.00274 ht…

MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning
Understanding the decision-making process of Deep Reinforcement Learning agents remains a key challenge for deploying these systems in safety-critical and multi-agent environments. While prior explainability methods like StateMask, have advanced the identification of critical states, they remain limited by computational cost, exploration coverage, and lack of adaptation to multi-agent settings. To overcome these limitations, we propose a mathematically grounded framework, MAGIC-MASK (Multi-Agen…

Deep Hierarchical Learning with Nested Subspace Networks
Paulius Rauba, Mihaela van der Schaar
https://arxiv.org/abs/2509.17874 https://arxiv.org/pdf/2509.…

Deep Hierarchical Learning with Nested Subspace Networks
Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing approaches to this problem present a difficult choice: training a discrete collection of specialist models is computationally prohibitive, while dynamic methods like slimmable networks often lack the flexibility to be applied to large, pre-trained foundation models. …

AERO-MPPI: Anchor-Guided Ensemble Trajectory Optimization for Agile Mapless Drone Navigation
Xin Chen, Rui Huang, Longbin Tang, Lin Zhao
https://arxiv.org/abs/2509.17340 https:/…

AERO-MPPI: Anchor-Guided Ensemble Trajectory Optimization for Agile Mapless Drone Navigation
Agile mapless navigation in cluttered 3D environments poses significant challenges for autonomous drones. Conventional mapping-planning-control pipelines incur high computational cost and propagate estimation errors. We present AERO-MPPI, a fully GPU-accelerated framework that unifies perception and planning through an anchor-guided ensemble of Model Predictive Path Integral (MPPI) optimizers. Specifically, we design a multi-resolution LiDAR point-cloud representation that rapidly extracts spat…

Low Resource Audio Codec Challenge Baseline Systems
Yusuf Ziya Isik, Rafa{\l} {\L}aganowski
https://arxiv.org/abs/2510.00264 https://arxiv.org/pdf/2510.002…

Low Resource Audio Codec Challenge Baseline Systems
The Low-Resource Audio Codec (LRAC) Challenge aims to advance neural audio coding for deployment in resource-constrained environments. The first edition focuses on low-resource neural speech codecs that must operate reliably under everyday noise and reverberation, while satisfying strict constraints on computational complexity, latency, and bitrate. Track 1 targets transparency codecs, which aim to preserve the perceptual transparency of input speech under mild noise and reverberation. Track 2 …

Fast Trajectory Planner with a Reinforcement Learning-based Controller for Robotic Manipulators
Yongliang Wang, Hamidreza Kasaei
https://arxiv.org/abs/2509.17381 https://…

Fast Trajectory Planner with a Reinforcement Learning-based Controller for Robotic Manipulators
Generating obstacle-free trajectories for robotic manipulators in unstructured and cluttered environments remains a significant challenge. Existing motion planning methods often require additional computational effort to generate the final trajectory by solving kinematic or dynamic equations. This paper highlights the strong potential of model-free reinforcement learning methods over model-based approaches for obstacle-free trajectory planning in joint space. We propose a fast trajectory planni…