Tootfinder

Ancilla measurement-based Quantum Otto engine using double-pair spin architecture
S R Rathnakaran, Asoka Biswas
https://arxiv.org/abs/2506.05948 https://…

Ancilla measurement-based Quantum Otto engine using double-pair spin architecture
We present a quantum heat engine model utilizing a dual spin-pair architecture, wherein an Otto-like cycle is implemented using a single heat bath. The conventional cold bath is replaced by a measurement protocol, enabling engine operation without the need for a second thermal reservoir. Unlike standard quantum heat engines, our framework employs an ancillary spin pair in a two-dimensional configuration to regulate performance. Operating in finite time, the engine attains finite power, which is…

Interview with Craig Federighi and Greg Joswiak on Apple's struggles to ship AI features, demoed in 2024, with the "V1 Siri architecture" and work on a V2 model (Lance Ulanoff/TechRadar)
https://www.techra…

This is what really happened with Siri and Apple Intelligence, according to Apple
Is it a delay, a strategy... or something else?

MLOps with Microservices: A Case Study on the Maritime Domain
Renato Cordeiro Ferreira (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Rowanne Trapmann (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Willem-Jan van den Heuvel (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University)

MLOps with Microservices: A Case Study on the Maritime Domain
This case study describes challenges and lessons learned on building Ocean Guard: a Machine Learning-Enabled System (MLES) for anomaly detection in the maritime domain. First, the paper presents the system's specification, and architecture. Ocean Guard was designed with a microservices' architecture to enable multiple teams to work on the project in parallel. Then, the paper discusses how the developers adapted contract-based design to MLOps for achieving that goal. As a MLES, Ocean Guard emplo…

This https://arxiv.org/abs/2410.18239 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

E2E-Swin-Unet++: An Enhanced End-to-End Swin-Unet Architecture With Dual Decoders For PTMC Segmentation
Precise segmentation of papillary thyroid microcarcinoma (PTMC) during ultrasound-guided radiofrequency ablation (RFA) is critical for effective treatment but remains challenging due to acoustic artifacts, small lesion size, and anatomical variability. In this study, we propose \textbf{DualSwinUnet++}, a dual-decoder transformer-based architecture designed to enhance PTMC segmentation by incorporating thyroid gland context. DualSwinUnet++ employs independent linear projection heads for each dec…

Functional Architecture of the Human Hypothalamus: Cortical Coupling and Subregional Organization Using 7-Tesla fMRI
Kent M. Lee, Joshua Rodriguez, Ludger Hartley, Philip A. Kragel, Lorena Chanes, Tor D. Wager, Karen S. Quigley, Lawrence L. Wald, Marta Bianciardi, Lisa Feldman Barrett, Jordan E. Theriault, Ajay B. Satpute
https://

Functional Architecture of the Human Hypothalamus: Cortical Coupling and Subregional Organization Using 7-Tesla fMRI
The hypothalamus plays an important role in the regulation of the bodys metabolic state and behaviors related to survival. Despite its importance however, many questions exist regarding the intrinsic and extrinsic connections of the hypothalamus in humans, especially its relationship with the cortex. As a heterogeneous structure, it is possible that the hypothalamus is composed of different subregions, which have their own distinct relationships with the cortex. Previous work on functional conn…

Series B, Episode 05 - Pressure Point
TRAVIS: Come on, come on. Where were you to rendezvous with Blake?
KASABI: You can rot, Travis. I'll tell you nothing, nothing. [Kasabi spits on Travis. Travis crosses to Servalan.]
https://blake.torpidity.net/m/205/170 B7B5

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Residuality Theory: A Rebellious Take on Building Systems That Actually Survive
#resiliency

This https://arxiv.org/abs/2505.23868 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Noise-Robustness Through Noise: Asymmetric LoRA Adaption with Poisoning Expert
Current parameter-efficient fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data. Conventional noise-handling approaches either rely on laborious data pre-processing or employ model architecture modifications prone to error accumulation. In contrast to existing noise-process paradigms, we propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE), a novel framework that enhances model robustne…

This https://arxiv.org/abs/2505.24009 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
Transformers deliver outstanding performance across a wide range of tasks and are now a dominant backbone architecture for large language models (LLMs). Their task-solving performance is improved by increasing parameter size, as shown in the recent studies on parameter scaling laws. Although recent mechanistic-interpretability studies have deepened our understanding of the internal behavior of Transformers by analyzing their residual stream, the relationship between these internal mechanisms an…

This https://arxiv.org/abs/2505.07263 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning
We propose Skywork-VL Reward, a multimodal reward model that provides reward signals for both multimodal understanding and reasoning tasks. Our technical approach comprises two key components: First, we construct a large-scale multimodal preference dataset that covers a wide range of tasks and scenarios, with responses collected from both standard vision-language models (VLMs) and advanced VLM reasoners. Second, we design a reward model architecture based on Qwen2.5-VL-7B-Instruct, integrating …

Interested in how #architecture can be understood sociologically?
In this podcast hosted by Alon Schwartz, I'm discussing how architecture can integrate human needs and usage processes in workplaces
So much fun to rise to the deep and challenging questions Alon threw at me

space design with Kerstin sailer- Sociology and Architecture
עיצוב מרחב עם אלון שוורץ · Episode

Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
Sheng Chen, Peiyu He, Jiaxin Hu, Ziyang Liu, Yansheng Wang, Tao Xu, Chi Zhang, Chongchong Zhang, Chao An, Shiyu Cai, Duo Cao, Kangping Chen, Shuai Chu, Tianwei Chu, Mingdi Dan, Min Du, Weiwei Fang, Pengyou Fu, Junkai Hu, Xiaowei Jiang, Zhaodi Jiang, Fuxuan Li, Jun Li, Minghui Li, Mingyao Li, Yanchang Li, Zhibin Li, Guangming Liu, Kairui Liu, Lihao Liu, Weizhi Liu, Xiaoshun Liu, Yufei Liu, Yunfei Liu, Qiang…

Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
Modern robot navigation systems encounter difficulties in diverse and complex indoor environments. Traditional approaches rely on multiple modules with small models or rule-based systems and thus lack adaptability to new environments. To address this, we developed Astra, a comprehensive dual-model architecture, Astra-Global and Astra-Local, for mobile robot navigation. Astra-Global, a multimodal LLM, processes vision and language inputs to perform self and goal localization using a hybrid topol…

Sentinel: SOTA model to protect against prompt injections
Dror Ivry, Oran Nahum
https://arxiv.org/abs/2506.05446 https://arxiv.org/pd…

Sentinel: SOTA model to protect against prompt injections
Large Language Models (LLMs) are increasingly powerful but remain vulnerable to prompt injection attacks, where malicious inputs cause the model to deviate from its intended instructions. This paper introduces Sentinel, a novel detection model, qualifire/prompt-injection-sentinel, based on the \answerdotai/ModernBERT-large architecture. By leveraging ModernBERT's advanced features and fine-tuning on an extensive and diverse dataset comprising a few open-source and private collections, Sentinel …

Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components
Jumana Alsubhi, Mohammad D. Alahmadi, Ahmed Alhusayni, Ibrahim Aldailami, Israa Hamdine, Ahmad Shabana, Yazeed Iskandar, Suhayb Khayyat
https://arxiv.org/abs/2506.06339

Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components
Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for combining the precision of retrieval systems with the fluency of large language models. While several studies have investigated RAG pipelines for high-resource languages, the optimization of RAG components for Arabic remains underexplored. This study presents a comprehensive empirical evaluation of state-of-the-art RAG components-including chunking strategies, embedding models, rerankers, and language models-across …

[2025-06-09 Mon (UTC), 2 new articles found for cs.AR Hardware Architecture]
#toXiv_bot_toot #toXiv_bot_new_article_summary_toot

This https://arxiv.org/abs/2504.09030 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Authoritarian Recursions: How Fiction, History, and AI Reinforce Control in Education, Warfare, and Discourse
This article develops the concept of authoritarian recursion to theorize how artificial intelligence (AI) systems consolidate institutional control across education, military operations, and digital discourse. Rather than treating these domains in isolation, it identifies a shared recursive architecture in which algorithmic systems mediate judgment, obscure accountability, and reshape the conditions of moral and epistemic agency. Grounded in critical discourse analysis and sociotechnical ethi…

This https://arxiv.org/abs/2409.08826 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Generalized Nearest Neighbor Decoding: General Input Constellation and a Case Study of Interference Suppression
In this work, generalized nearest neighbor decoding (GNND), a recently proposed receiver architecture, is studied for channels under general input constellations, and multiuser uplink interference suppression is employed as a case study for demonstrating its potential. In essence, GNND generalizes the well-known nearest neighbor decoding, by introducing a symbol-level memoryless processing step, which can be rendered seamlessly compatible with Gaussian channel-based decoders. First, criteria of…

WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction
Jakaria Islam Emon, Kazi Tamanna Alam, Md. Abu Salek
https://arxiv.org/abs/2506.05899

WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction
Mean Opinion Score (MOS) prediction for text to music systems requires evaluating both overall musical quality and text prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge through sequence level co-attention and optimal transport regularization. WhisQ employs the Whisper Base pretrained model for temporal audio encoding and Qwen 3, a 0.6B Small Language Model (SLM), for text encoding, with both maintaining sequence structure for…

[2025-06-09 Mon (UTC), 3 new articles found for cs.NI Networking and Internet Architecture]
#toXiv_bot_toot #toXiv_bot_new_article_summary_toot

Runtime Analysis of Evolutionary NAS for Multiclass Classification
Zeqiong Lv, Chao Qian, Yun Liu, Jiahao Fan, Yanan Sun
https://arxiv.org/abs/2506.06019 h…

Runtime Analysis of Evolutionary NAS for Multiclass Classification
Evolutionary neural architecture search (ENAS) is a key part of evolutionary machine learning, which commonly utilizes evolutionary algorithms (EAs) to automatically design high-performing deep neural architectures. During past years, various ENAS methods have been proposed with exceptional performance. However, the theory research of ENAS is still in the infant. In this work, we step for the runtime analysis, which is an essential theory aspect of EAs, of ENAS upon multiclass classification pr…

Hierarchical Debate-Based Large Language Model (LLM) for Complex Task Planning of 6G Network Management
Yuyan Lin (Charlie), Hao Zhou (Charlie), Chengming Hu (Charlie), Xue Liu (Charlie), Hao Chen (Charlie), Yan Xin (Charlie), Jianzhong (Charlie), Zhang
https://arxiv.org/abs/2506.06519…

Hierarchical Debate-Based Large Language Model (LLM) for Complex Task Planning of 6G Network Management
6G networks have become increasingly complicated due to novel network architecture and newly emerging signal processing and transmission techniques, leading to significant burdens to 6G network management. Large language models (LLMs) have recently been considered a promising technique to equip 6G networks with AI-native intelligence. Different from most existing studies that only consider a single LLM, this work involves a multi-LLM debate-based scheme for 6G network management, where multiple…

This https://arxiv.org/abs/2412.10580 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

DeepWiener: Neural Networks for CMB polarization maps and power spectrum computation
To study the early Universe, it is essential to estimate cosmological parameters with high accuracy, which depends on the optimal reconstruction of Cosmic Microwave Background (CMB) maps and the measurement of their power spectrum. In this paper, we generalize the neural network developed for applying the Wiener Filter, initially presented for temperature maps in previous work, to polarization maps. Our neural network has a UNet architecture, including an extra channel for the noise variance ma…

This https://arxiv.org/abs/2505.18565 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning Fluid-Structure Interaction Dynamics with Physics-Informed Neural Networks and Immersed Boundary Methods
We introduce neural network architectures that combine physics-informed neural networks (PINNs) with the immersed boundary method (IBM) to solve fluid-structure interaction (FSI) problems. Our approach features two distinct architectures: a Single-FSI network with a unified parameter space, and an innovative Eulerian-Lagrangian network that maintains separate parameter spaces for fluid and structure domains. We study each architecture using standard Tanh and adaptive B-spline activation functio…

Optimal absorption and emission of itinerant fields into a spin ensemble memory
Linda Greggio, Tristan Lorriaux, Alexandru Petrescu, Mazyar Mirrahimi, Audrey Bienfait
https://arxiv.org/abs/2506.06107

Optimal absorption and emission of itinerant fields into a spin ensemble memory
Quantum memories integrated in a modular quantum processing architecture can rationalize the resources required for quantum computation. This work focuses on spin-based quantum memories, where itinerant electromagnetic fields are stored in large ensembles of effective two-level systems, such as atomic or solid-state spin ensembles, embedded in a cavity. Using a mean-field framework, we model the ensemble as an effective spin communication channel and develop a cascaded quantum model to describe…

Leveraging Network Methods for Hub-like Microservice Detection
Alexander Bakhtin, Matteo Esposito, Valentina Lenarduzzi, Davide Taibi
https://arxiv.org/abs/2506.07683

Leveraging Network Methods for Hub-like Microservice Detection
Context: Microservice Architecture is a popular architectural paradigm that facilitates flexibility by decomposing applications into small, independently deployable services. Catalogs of architectural anti-patterns have been proposed to highlight the negative aspects of flawed microservice design. In particular, the Hub-like anti-pattern lacks an unambiguous definition and detection method. Aim: In this work, we aim to find a robust detection approach for the Hub-like microservice anti-pattern …

Exploring Length Generalization For Transformer-based Speech Enhancement
Qiquan Zhang, Hongxu Zhu, Xinyuan Qian, Eliathamby Ambikairajah, Haizhou Li
https://arxiv.org/abs/2506.06697

Exploring Length Generalization For Transformer-based Speech Enhancement
Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios, speech enhancement models are often required to perform on noisy speech at run-time that is substantially longer than the training utterances. It remains a challenge how a Transformer-based speech enhancement model can generalize to long speech utterances. I…

This https://arxiv.org/abs/2311.16593 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Empowering COVID-19 Detection: Optimizing Performance Through Fine-Tuned EfficientNet Deep Learning Architecture
The worldwide COVID-19 pandemic has profoundly influenced the health and everyday experiences of individuals across the planet. It is a highly contagious respiratory disease requiring early and accurate detection to curb its rapid transmission. Initial testing methods primarily revolved around identifying the genetic composition of the coronavirus, exhibiting a relatively low detection rate and requiring a time-intensive procedure. To address this challenge, experts have suggested using radiolo…

Leveraging Historical and Current Interests for Continual Sequential Recommendation
Gyuseok Lee, Hyunsik Yoo, Junyoung Hwang, SeongKu Kang, Hwanjo Yu
https://arxiv.org/abs/2506.07466

Leveraging Historical and Current Interests for Continual Sequential Recommendation
Sequential recommendation models based on the Transformer architecture show superior performance in harnessing long-range dependencies within user behavior via self-attention. However, naively updating them on continuously arriving non-stationary data streams incurs prohibitive computation costs or leads to catastrophic forgetting. To address this, we propose Continual Sequential Transformer for Recommendation (CSTRec) that effectively leverages well-preserved historical user interests while ca…

Adaptive recycled plastic architecture: Vacuum-Sealed Chainmail Structures Through Computational Design
Yi Xu, Farzin Lotfi-Jam, Mustafa Faruki
https://arxiv.org/abs/2506.04660

Adaptive recycled plastic architecture: Vacuum-Sealed Chainmail Structures Through Computational Design
The construction industry is a major consumer of raw materials, accounting for nearly half of global material usage annually, while generating significant waste that poses sustainability challenges. This paper explores the untapped potential of recycled plastics as a primary construction material, leveraging their lightweight, flexible, and customizable properties for advanced applications in modular chainmail systems. Through a computational workflow, the study optimizes the design, testing, a…

[2025-06-10 Tue (UTC), 11 new articles found for cs.AR Hardware Architecture]
toXiv_bot_toot

Polarized Element-pair Code Based FFMA over a Gaussian Multiple-access Channel
Zhang-li-han Liu, Qi-yue Yu
https://arxiv.org/abs/2506.06796 https://…

Polarized Element-pair Code Based FFMA over a Gaussian Multiple-access Channel
This paper presents polarized element-pair (EP) codes for polarization-adjusted finite-field multiple-access (PA-FFMA) systems. The core innovation of FFMA systems lies in their unique processing order that exchanges the conventional sequence of channel coding and multiplexing operations, effectively solving the multiuser finite-blocklength (FBL) problem while enhancing error performance. In this architecture, EPs serve as virtual resources for user separation, where different EP codes provide …

Was Residual Penalty and Neural Operators All We Needed for Solving Optimal Control Problems?
Oliver G. S. Lundqvist, Fabricio Oliveira
https://arxiv.org/abs/2506.04742

Was Residual Penalty and Neural Operators All We Needed for Solving Optimal Control Problems?
Neural networks have been used to solve optimal control problems, typically by training neural networks using a combined loss function that considers data, differential equation residuals, and objective costs. We show that including cost functions in the training process is unnecessary, advocating for a simpler architecture and streamlined approach by decoupling the optimal control problem from the training process. Thus, our work shows that a simple neural operator architecture, such as DeepON…

[2025-06-10 Tue (UTC), 5 new articles found for cs.NI Networking and Internet Architecture]
toXiv_bot_toot

Neural networks with image recognition by pairs
Polad Geidarov
https://arxiv.org/abs/2506.06322 https://arxiv.org/pdf/2506.06322

Neural networks with image recognition by pairs
Neural networks based on metric recognition methods have a strictly determined architecture. Number of neurons, connections, as well as weights and thresholds values are calculated analytically, based on the initial conditions of tasks: number of recognizable classes, number of samples, metric expressions used. This paper discusses the possibility of transforming these networks in order to apply classical learning algorithms to them without using analytical expressions that calculate weight val…

Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
Weixun Wang, Shaopan Xiong, Gengru Chen, Wei Gao, Sheng Guo, Yancheng He, Ju Huang, Jiaheng Liu, Zhendong Li, Xiaoyang Li, Zichen Liu, Haizhou Zhao, Dakai An, Lunxi Cao, Qiyang Cao, Wanxi Deng, Feilei Du, Yiliang Gu, Jiahe Li, Xiang Li, Mingjie Liu, Yijia Luo, Zihe Liu, Yadao Wang, Pei Wang, Tianyuan Wu, Yanan Wu, Yuheng Zhao, Shuaibing Zhao, Jin Yang, Siran Yang, Yingshui Tan, …

Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
We introduce ROLL, an efficient, scalable, and user-friendly library designed for Reinforcement Learning Optimization for Large-scale Learning. ROLL caters to three primary user groups: tech pioneers aiming for cost-effective, fault-tolerant large-scale training, developers requiring flexible control over training workflows, and researchers seeking agile experimentation. ROLL is built upon several key modules to serve these user groups effectively. First, a single-controller architecture combin…

A "Wenlu" Brain System for Multimodal Cognition and Embodied Decision-Making: A Secure New Architecture for Deep Integration of Foundation Models and Domain Knowledge
Liang Geng
https://arxiv.org/abs/2506.00570

A "Wenlu" Brain System for Multimodal Cognition and Embodied Decision-Making: A Secure New Architecture for Deep Integration of Foundation Models and Domain Knowledge
With the rapid penetration of artificial intelligence across industries and scenarios, a key challenge in building the next-generation intelligent core lies in effectively integrating the language understanding capabilities of foundation models with domain-specific knowledge bases in complex real-world applications. This paper proposes a multimodal cognition and embodied decision-making brain system, ``Wenlu", designed to enable secure fusion of private knowledge and public models, unified proc…

Centrality Change Proneness: an Early Indicator of Microservice Architectural Degradation
Alexander Bakhtin, Matteo Esposito, Valentina Lenarduzzi, Davide Taibi
https://arxiv.org/abs/2506.07690

Centrality Change Proneness: an Early Indicator of Microservice Architectural Degradation
Over the past decade, the wide adoption of Microservice Architecture has required the identification of various patterns and anti-patterns to prevent Microservice Architectural Degradation. Frequently, the systems are modelled as a network of connected services. Recently, the study of temporal networks has emerged as a way to describe and analyze evolving networks. Previous research has explored how software metrics such as size, complexity, and quality are related to microservice centrality in…

High-Speed Ultra-Energy-Efficient Memristor-Based Massive MIMO SIC Detector Circuit with Hybrid Analog-Digital Computing Architecture
Jia-Hui Bi, Shaoshi Yang, Sheng Chen, Ping Zhang
https://arxiv.org/abs/2506.03495

High-Speed Ultra-Energy-Efficient Memristor-Based Massive MIMO SIC Detector Circuit with Hybrid Analog-Digital Computing Architecture
The emerging memristor crossbar array based computing circuits exhibit computing speeds and energy efficiency far surpassing those of traditional digital processors. This type of circuits can complete high-dimensional matrix operations in an extremely short time through analog computing, making it naturally applicable to linear detection and maximum likelihood detection in massive multiple-input multiple-output (MIMO) systems. However, the challenge of employing memristor crossbar arrays to eff…

AI Agent Behavioral Science
Lin Chen, Yunke Zhang, Jie Feng, Haoye Chai, Honglin Zhang, Bingbing Fan, Yibo Ma, Shiyuan Zhang, Nian Li, Tianhui Liu, Nicholas Sukiennik, Keyu Zhao, Yu Li, Ziyi Liu, Fengli Xu, Yong Li
https://arxiv.org/abs/2506.06366

AI Agent Behavioral Science
Recent advances in large language models (LLMs) have enabled AI systems to behave in increasingly human-like ways, exhibiting planning, adaptation, and social dynamics across increasingly diverse, interactive, and open-ended scenarios. These behaviors are not solely the product of the models' internal architecture, but emerge from their integration into agentic systems that operate within situated contexts, where goals, feedback, and interactions shape behavior over time. This shift calls for a…

Looking forward to joining the panel for the book launch of @… book 'Selected papers by Bill Hillier' this evening, 7 May at 6pm BST at the Bartlett School of Architecture, London
Join the launch event online:

Welcome! You are invited to join a webinar: Book Launch – Space Syntax: Selected Papers by Bill Hillier. After registering, you will receive a confirmation email about joining the webinar.
Join us online for the launch of Space Syntax: Selected Papers by Bill Hillier, a landmark volume celebrating 50 years of space syntax research. This long-awaited collection reflects Bill Hillier’s transformational way of thinking about buildings and cities that influenced generations of scholars, researchers and practitioners within the built environment disciplines and way beyond – in fields ranging from archaeology and biology to physics and zoology. Edited by Laura Vaughan, John Pepon…

Design and Implementation of a RISC-V SoC with Custom DSP Accelerators for Edge Computing
Priyanshu Yadav
https://arxiv.org/abs/2506.06693 https://

Design and Implementation of a RISC-V SoC with Custom DSP Accelerators for Edge Computing
This paper presents a comprehensive analysis of the RISC-V instruction set architecture, focusing on its modular design, implementation challenges, and performance characteristics. We examine the RV32I base instruction set with extensions for multiplication (M) and atomic operations (A). Through cycle-accurate simulation of a pipelined implementation, we evaluate performance metrics including CPI (cycles per instruction) and power efficiency. Our results demonstrate RISC-V's advantages in embed…

HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel Retrieval
Arian Askari, Emmanouil Stergiadis, Ilya Gusev, Moran Beladev
https://arxiv.org/abs/2506.07296

HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel Retrieval
We present HotelMatch-LLM, a multimodal dense retrieval model for the travel domain that enables natural language property search, addressing the limitations of traditional travel search engines which require users to start with a destination and editing search parameters. HotelMatch-LLM features three key innovations: (1) Domain-specific multi-task optimization with three novel retrieval, visual, and language modeling objectives; (2) Asymmetrical dense retrieval architecture combining a small …

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Rishona Daniels, Duna Wattad, Ronny Ronen, David Saad, Shahar Kvatinsky
https://arxiv.org/abs/2506.05588

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC systems benefit from their dynamic properties, which make them ideal for reservoir construction. However, achieving high performance in memristor-based RC remains challenging, as it critically depends on the input preprocessing method and reservoir size. Despite …

DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling
Hangyu Ji
https://arxiv.org/abs/2506.05297 https://

DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling
Accurate 3D medical image segmentation demands architectures capable of reconciling global context modeling with spatial topology preservation. While State Space Models (SSMs) like Mamba show potential for sequence modeling, existing medical SSMs suffer from encoder-decoder incompatibility: the encoder's 1D sequence flattening compromises spatial structures, while conventional decoders fail to leverage Mamba's state propagation. We present DM-SegNet, a Dual-Mamba architecture integrating direct…

Enhancing Software Supply Chain Security Through STRIDE-Based Threat Modelling of CI/CD Pipelines
Sowmiya Dhandapani
https://arxiv.org/abs/2506.06478 https…

Enhancing Software Supply Chain Security Through STRIDE-Based Threat Modelling of CI/CD Pipelines
With the increasing adoption of Continuous Integration and Continuous Deployment pipelines, securing software supply chains has become a critical challenge for modern DevOps teams. This study addresses these challenges by applying a structured threat modeling approach to identify and mitigate risks throughout the CI/CD lifecycle. By modeling a representative pipeline architecture incorporating tools such as GitHub, Jenkins, Docker, and Kubernetes and applying the STRIDE framework, we systematic…

This https://arxiv.org/abs/2408.08968 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNI_…

Online SLA Decomposition: Enabling Real-Time Adaptation to Evolving Network Systems
When a network slice spans multiple technology domains, it is crucial for each domain to uphold the End-to-End (E2E) Service Level Agreement (SLA) associated with the slice. Consequently, the E2E SLA must be properly decomposed into partial SLAs that are assigned to each domain involved. In a network slice management system with a two-level architecture, comprising an E2E service orchestrator and local domain controllers, we consider that the orchestrator has access only to historical data rega…

Galileo Project Observatory Class System Architecture
Phillip Bridgham, Alex Delacroix, Laura Domine, Andriy Fedorenko, Ezra Kelderman, Sarah Little, Abraham Loeb, Robert Lundstrom, Eric Masson, Andrew Mead, Michael W Prior, Matthew Szenher, Foteini Vervelidou, Wesley Andres Watters
https://arxiv.org/abs/2506.00125

Galileo Project Observatory Class System Architecture
Scientific investigation of Unidentified Anomalous Phenomena (UAP) is limited by poor data quality and a lack of transparency. Existing data are often fragmented, uncalibrated, and missing critical metadata. To address these limitations, the authors present the Observatory Class Integrated Computing Platform (OCICP), a system designed for the systematic and scientific study of UAPs. OCICP employs multiple sensors to collect and analyze data on aerial phenomena. The OCICP system consists of two …

got a shipment of some dev boards to port #klutshnik to microcontrollers over usb/ble, these things are small, powerful and cheap!
Waveshare RP2350-Plus https://www.waveshare.com/rp2350-plus.htm

CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition
Yun-Shao Tsai, Yi-Cheng Lin, Huang-Cheng Chou, Hung-yi Lee
https://arxiv.org/abs/2506.06071

CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition
Bias in speech emotion recognition (SER) systems often stems from spurious correlations between speaker characteristics and emotional labels, leading to unfair predictions across demographic groups. Many existing debiasing methods require model-specific changes or demographic annotations, limiting their practical use. We present CO-VADA, a Confidence-Oriented Voice Augmentation Debiasing Approach that mitigates bias without modifying model architecture or relying on demographic information. CO-…

FREESS: An Educational Simulator of a RISC-V-Inspired Superscalar Processor Based on Tomasulo's Algorithm
Roberto Giorgi
https://arxiv.org/abs/2506.07665

FREESS: An Educational Simulator of a RISC-V-Inspired Superscalar Processor Based on Tomasulo's Algorithm
FREESS is a free, interactive simulator that illustrates instruction-level parallelism in a RISC-V-inspired superscalar processor. Based on an extended version of Tomasulo's algorithm, FREESS is intended as a hands-on educational tool for Advanced Computer Architecture courses. It enables students to explore dynamic, out-of-order instruction execution, emphasizing how instructions are issued as soon as their operands become available. The simulator models key microarchitectural components, in…

This https://arxiv.org/abs/2506.05588 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC systems benefit from their dynamic properties, which make them ideal for reservoir construction. However, achieving high performance in memristor-based RC remains challenging, as it critically depends on the input preprocessing method and reservoir size. Despite …

Improving compiler support for SIMD offload using Arm Streaming SVE
Mohamed Husain Noor Mohamed, Adarsh Patil, Latchesar Ionkov, Eric Van Hensbergen
https://arxiv.org/abs/2506.02233

Improving compiler support for SIMD offload using Arm Streaming SVE
The wider adoption of tightly coupled core-adjacent accelerators, such as Arm Scalable Matrix Extension (SME), hinges on lowering software programming complexity. In this paper, we focus on enabling the use of SME architecture in Streaming Scalable Vector Extension (SSVE) mode for workloads written in C/C++. While current compilers optimize loops for all types of SIMD instructions, these techniques primarily target vector units within the core and falter when applied to disaggregated, core-adja…

Good Morning ESWC 2025! If you want to join me for a morning run during the conference week, don’t hesitate to address me when you see me around 🏃
#eswc2025 #academiclife #semweb

(1/3) Please join me today on Zoom at 12pm ET / 11am CT / 10am MT / 9am PT for "Beyond the Algorithmic Feed," a free MediaEd Club webinar for the Media Education Lab:
https://mediaeducationlab.com/index.php/events/beyond-algorithmic-feed
While som…

CrossNAS: A Cross-Layer Neural Architecture Search Framework for PIM Systems
Md Hasibul Amin, Mohammadreza Mohammadi, Jason D. Bakos, Ramtin Zand
https://arxiv.org/abs/2505.22868 …

CrossNAS: A Cross-Layer Neural Architecture Search Framework for PIM Systems
In this paper, we propose the CrossNAS framework, an automated approach for exploring a vast, multidimensional search space that spans various design abstraction layers-circuits, architecture, and systems-to optimize the deployment of machine learning workloads on analog processing-in-memory (PIM) systems. CrossNAS leverages the single-path one-shot weight-sharing strategy combined with the evolutionary search for the first time in the context of PIM system mapping and optimization. CrossNAS se…

This https://arxiv.org/abs/2505.02580 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Temperature and pressure reconstruction in turbulent Rayleigh-Bénard convection by Lagrangian velocities using PINN
Velocity, pressure, and temperature are the key variables for understanding thermal convection, and measuring them all is a complex task. In this paper, we demonstrate a method to reconstruct temperature and pressure fields based on given Lagrangian velocity data. A physics-informed neural network (PINN) based on a multilayer perceptron architecture and a periodic sine activation function is used to reconstruct both the temperature and the pressure for two cases of turbulent Rayleigh-Bénard co…

Supporting architecture evaluation for ATAM scenarios with LLMs
Rafael Capilla, J. Andr\'es D\'iaz-Pace, Yamid Ram\'irez, Jennifer P\'erez, Vanessa Rodr\'iguez-Horcajo
https://arxiv.org/abs/2506.00150

Supporting architecture evaluation for ATAM scenarios with LLMs
Architecture evaluation methods have long been used to evaluate software designs. Several evaluation methods have been proposed and used to analyze tradeoffs between different quality attributes. Having competing qualities leads to conflicts for selecting which quality-attribute scenarios are the most suitable ones that an architecture should tackle and for prioritizing the scenarios required by the stakeholders. In this context, architecture evaluation is carried out manually, often involving …

QForce-RL: Quantized FPGA-Optimized Reinforcement Learning Compute Engine
Anushka Jha, Tanushree Dewangan, Mukul Lokhande, Santosh Kumar Vishvakarma
https://arxiv.org/abs/2506.07046

QForce-RL: Quantized FPGA-Optimized Reinforcement Learning Compute Engine
Reinforcement Learning (RL) has outperformed other counterparts in sequential decision-making and dynamic environment control. However, FPGA deployment is significantly resource-expensive, as associated with large number of computations in training agents with high-quality images and possess new challenges. In this work, we propose QForce-RL takes benefits of quantization to enhance throughput and reduce energy footprint with light-weight RL architecture, without significant performance degrada…

Federated Learning Assisted Edge Caching Scheme Based on Lightweight Architecture DDPM
Xun Li, Qiong Wu
https://arxiv.org/abs/2506.04593 https://

Federated Learning Assisted Edge Caching Scheme Based on Lightweight Architecture DDPM
Edge caching is an emerging technology that empowers caching units at edge nodes, allowing users to fetch contents of interest that have been pre-cached at the edge nodes. The key to pre-caching is to maximize the cache hit percentage for cached content without compromising users' privacy. In this letter, we propose a federated learning (FL) assisted edge caching scheme based on lightweight architecture denoising diffusion probabilistic model (LDPM). Our simulation results verify that our propo…

Introduction to Predictive Coding Networks for Machine Learning
Mikko Stenlund
https://arxiv.org/abs/2506.06332 https://arxiv.org/pdf…

Introduction to Predictive Coding Networks for Machine Learning
Predictive coding networks (PCNs) constitute a biologically inspired framework for understanding hierarchical computation in the brain, and offer an alternative to traditional feedforward neural networks in ML. This note serves as a quick, onboarding introduction to PCNs for machine learning practitioners. We cover the foundational network architecture, inference and learning update rules, and algorithmic implementation. A concrete image-classification task (CIFAR-10) is provided as a benchmark…

This https://arxiv.org/abs/2503.22733 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection
Neural Architecture Search (NAS) is an automated technique to design optimal neural network architectures for a specific workload. Conventionally, evaluating candidate networks in NAS involves extensive training, which requires significant time and computational resources. To address this, training-free NAS has been proposed to expedite network evaluation with minimal search time. However, state-of-the-art training-free NAS algorithms struggle to precisely distinguish well-performing networks f…

This https://arxiv.org/abs/2506.02040 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem
The Model Context Protocol (MCP) is an emerging standard designed to enable seamless interaction between Large Language Model (LLM) applications and external tools or resources. Within a short period, thousands of MCP services have already been developed and deployed. However, the client-server integration architecture inherent in MCP may expand the attack surface against LLM Agent systems, introducing new vulnerabilities that allow attackers to exploit by designing malicious MCP servers. In th…

It's publication day for 'Space Syntax - Selected papers by Bill Hillier', edited by my wonderful Bartlett School of Architecture colleague Laura Vaughan with John Peponis and Ruth Conroy Dalton.
The book brings together Hillier's groundbreaking work spanning half a century with current commentaries by international researchers
It is available #openAccess by
…

A Reference Architecture for Gamified Cultural Heritage Applications Leveraging Generative AI and Augmented Reality
Federico Martusciello, Henry Muccini, Antonio Bucchiarone
https://arxiv.org/abs/2506.04090

A Reference Architecture for Gamified Cultural Heritage Applications Leveraging Generative AI and Augmented Reality
The rapid advancement of Information and Communication Technologies is transforming Cultural Heritage access, experience, and preservation. However, many digital heritage applications lack interactivity, personalization, and adaptability, limiting user engagement and educational impact. This short paper presents a reference architecture for gamified cultural heritage applications leveraging generative AI and augmented reality. Gamification enhances motivation, artificial intelligence enables ad…

This https://arxiv.org/abs/2506.01297 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MobCLIP: Learning General-purpose Geospatial Representation at Scale
Representation learning of geospatial locations remains a core challenge in achieving general geospatial intelligence. Current embedding methods often lack versatility, limiting their utility across diverse tasks in both human and natural domains. We present MobCLIP, the first nationwide general-purpose location encoder, integrating an unprecedented diversity of data modalities through effective and scalable multimodal fusion. Adopting a novel CLIP-based architecture, our framework aligns 100M+…

This https://arxiv.org/abs/2505.22813 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

X-Factor: Quality Is a Dataset-Intrinsic Property
In the universal quest to optimize machine-learning classifiers, three factors -- model architecture, dataset size, and class balance -- have been shown to influence test-time performance but do not fully account for it. Previously, evidence was presented for an additional factor that can be referred to as dataset quality, but it was unclear whether this was actually a joint property of the dataset and the model architecture, or an intrinsic property of the dataset itself. If quality is truly d…

This https://arxiv.org/abs/2501.18564 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
Robotic manipulation systems operating in diverse, dynamic environments must exhibit three critical abilities: multitask interaction, generalization to unseen scenarios, and spatial memory. While significant progress has been made in robotic manipulation, existing approaches often fall short in generalization to complex environmental variations and addressing memory-dependent tasks. To bridge this gap, we introduce SAM2Act, a multi-view robotic transformer-based policy that leverages multi-reso…

Cloud-Based Interoperability in Residential Energy Systems
Darren Leniston, David Ryan, Ammar Malik, Jack Jackman, Terence O'Donnell
https://arxiv.org/abs/2506.05076

Cloud-Based Interoperability in Residential Energy Systems
As distributed energy resources (DERs) such as solar PV, batteries and electric vehicles become increasingly prevalent at the edge, maintaining grid stability requires advanced monitoring and control mechanisms. This paper presents a scalable smart grid gateway architecture that enables interoperability between Modbus-based inverters and IEEE 2030.5 cloud-based control systems. The proposed solution leverages Azure cloud services and edge-computing gateway devices to support dynamic configurati…

For all the German speakers in my network: my research on spatial layouts and communication has been featured in a lovely and detailed article in the weekly German newspaper Die Zeit discussing the manifold relations between architecture and social outcomes, ranging from political coalition negotiations to the mutiny on the Bounty, from team meetings in offices to places for living

Architektur: Wie Architekten Gespräche lenken – und Macht verteilen
Gute Architektur verbindet Menschen, schlechte trennt sie. Wer die Gesetze des Bauens kennt, kann Politiker zusammenbringen – und sogar den Lauf der Geschichte verändern.

VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration
Shereef Helal, Alberto Garcia-Ortiz, Lennart Bamberg
https://arxiv.org/abs/2506.01166

VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration
Leveraging high degrees of unstructured sparsity is a promising approach to enhance the efficiency of deep neural network DNN accelerators - particularly important for emerging Edge-AI applications. We introduce VUSA, a systolic-array architecture that virtually grows based on the present sparsity to perform larger matrix multiplications with the same number of physical multiply-accumulate MAC units. The proposed architecture achieves saving by 37% and 68% in area and power efficiency, respecti…

A Tree-guided CNN for image super-resolution
Chunwei Tian, Mingjian Song, Xiaopeng Fan, Xiangtao Zheng, Bob Zhang, David Zhang
https://arxiv.org/abs/2506.02585

A Tree-guided CNN for image super-resolution
Deep convolutional neural networks can extract more accurate structural information via deep architectures to obtain good performance in image super-resolution. However, it is not easy to find effect of important layers in a single network architecture to decrease performance of super-resolution. In this paper, we design a tree-guided CNN for image super-resolution (TSRNet). It uses a tree architecture to guide a deep network to enhance effect of key nodes to amplify the relation of hierarchica…

A Systematic Mapping Study on Software Architecture for AI-based Mobility Systems
Amra Ramic, Stefan Kugele
https://arxiv.org/abs/2506.01595 https://

A Systematic Mapping Study on Software Architecture for AI-based Mobility Systems
Background: Due to their diversity, complexity, and above all importance, safety-critical and dependable systems must be developed with special diligence. Criticality increases as these systems likely contain artificial intelligence (AI) components known for their uncertainty. As software and reference architectures form the backbone of any successful system, including safety-critical dependable systems with learning-enabled components, choosing the suitable architecture that guarantees safety …

This https://arxiv.org/abs/2412.12106 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

The Syncytial Mesh Model: A Biophysical Framework for Scale-Dependent Coherence in the Brain
The brain-mesh model introduces a novel three-layered architecture that integrates local and macro-regional connectivity with an underlying, mesh-inspired network layer. This foundational mesh layer, based on metallic mesh structures, spans the entire brain and generates interference patterns, noise, and resonance effects that modulate both local and global neural dynamics. The fused model goes beyond traditional connectivity frameworks by providing a unified explanation for phenomena such as b…

Laterally Excited Bulk Acoustic Wave (LBAW) X-Cut Lithium Niobate Resonators
Walter Gubinelli, Ryan Tetro, Pietro Simeoni, Luca Colombo, Matteo Rinaldi
https://arxiv.org/abs/2506.04433

Laterally Excited Bulk Acoustic Wave (LBAW) X-Cut Lithium Niobate Resonators
In this work, Laterally excited Bulk Acoustic Wave (LBAW) resonators on X-cut Lithium Niobate (LiNbO3) and, for the first time their higher-order overtones (LOBAW) are demonstrated by embedding interdigitated electrodes recessed into the piezoelectric thin film, allowing to exploit both S0 and SH0 vibrational modes. This recessed electrode architecture decouples the dispersion relation from film thickness, enabling lithographic tuning of resonance frequency and on-chip multi-frequency scaling o…

“We need to go beyond legislation to a cultural change, where disability is treated as an identity to be celebrated.”
Brilliant article in the FT on housing design for disability and the aesthetics of accessibility
https://www.ft.com/content/05309cf9-96d9-460…

The aesthetics of accessibility: design for disability that’s dynamic not dreary
Architecture is at a fertile inflection point. But while housebuilding goals, sustainability and retrofitting are dominating the agenda, why does accessibility too often remain an afterthought?

Adaptive Privacy-Preserving SSD
Na Young Ahn, Dong Hoon Lee
https://arxiv.org/abs/2506.02030 https://arxiv.org/pdf/2506.02030

Adaptive Privacy-Preserving SSD
Data remanence in NAND flash complicates complete deletion on IoT SSDs. We design an adaptive architecture offering four privacy levels (PL0-PL3) that select among address, data, and parity deletion techniques. Quantitative analysis balances efficacy, latency, endurance, and cost. Machine-learning adjusts levels contextually, boosting privacy with negligible performance overhead and complexity.

Trustworthy Provenance for Big Data Science: a Modular Architecture Leveraging Blockchain in Federated Settings
Nicola Giuseppe Marchioro, Yannis Velegrakis, Valentine Anantharaj, Ian Foster, Sandro Luigi Fiore
https://arxiv.org/abs/2505.24675

Trustworthy Provenance for Big Data Science: a Modular Architecture Leveraging Blockchain in Federated Settings
Ensuring the trustworthiness and long-term verifiability of scientific data is a foundational challenge in the era of data-intensive, collaborative research. Provenance metadata plays a key role in this context, capturing the origin, transformation, and usage of research artifacts. However, existing solutions often fall short when applied to distributed, multi-institutional settings. This paper introduces a modular, domain-agnostic architecture for provenance tracking in federated environments,…

MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs
Nicole Hsing
https://arxiv.org/abs/2506.00430

MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs
Human intelligence relies on inner monologue to process complex information through simultaneous reflection, memory retrieval, and response formulation. We introduce MIRROR (Modular Internal Reasoning, Reflection, Orchestration, and Response), a cognitive architecture that systematically implements these parallel reasoning capabilities in large language models. MIRROR operates as a unified system with two distinct functional layers: the Thinker and the Talker. The Thinker encompasses: (1) the I…

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
Ishika Singh, Ankit Goyal, Stan Birchfield, Dieter Fox, Animesh Garg, Valts Blukis
https://arxiv.org/abs/2506.01196

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of mapping natural language instructions and multi-view RGBD observations to quasi-static robot actions. 3D-aware robot policies achieve state-of-the-art performance on precise robot manipulation tasks, but struggle with generalization to unseen instructions, scenes, and objects. On …

This https://arxiv.org/abs/2503.09492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Learning Cascade Ranking as One Network
Cascade Ranking is a prevalent architecture in large-scale top-k selection systems like recommendation and advertising platforms. Traditional training methods focus on single-stage optimization, neglecting interactions between stages. Recent advances have introduced interaction-aware training paradigms, but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i.e., end-to-end recall of ground-truth items) and 2) learn effective collaboration patterns for d…

Bi-SamplerZ: A Hardware-Efficient Gaussian Sampler Architecture for Quantum-Resistant Falcon Signatures
Binke Zhao, Ghada Alsuhi, Hani Saleh, Baker Mohammad
https://arxiv.org/abs/2505.24509

Bi-SamplerZ: A Hardware-Efficient Gaussian Sampler Architecture for Quantum-Resistant Falcon Signatures
FALCON is a standardized quantum-resistant digital signature scheme that offers advantages over other schemes, but features more complex signature generation process. This paper presents Bi-Samplerz, a fully hardware-implemented, high-efficiency dual-path discrete Gaussian sampler designed to accelerate Falcon signature generation. Observing that the SamplerZ subroutine is consistently invoked in pairs during each signature generation, we propose a dual-datapath architecture capable of generati…

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem
Hao Song, Yiming Shen, Wenxuan Luo, Leixin Guo, Ting Chen, Jiashui Wang, Beibei Li, Xiaosong Zhang, Jiachi Chen
https://arxiv.org/abs/2506.02040

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem
The Model Context Protocol (MCP) is an emerging standard designed to enable seamless interaction between Large Language Model (LLM) applications and external tools or resources. Within a short period, thousands of MCP services have already been developed and deployed. However, the client-server integration architecture inherent in MCP may expand the attack surface against LLM Agent systems, introducing new vulnerabilities that allow attackers to exploit by designing malicious MCP servers. In th…

This https://arxiv.org/abs/2503.07792 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Efficient Neural Clause-Selection Reinforcement
Clause selection is arguably the most important choice point in saturation-based theorem proving. Framing it as a reinforcement learning (RL) task is a way to challenge the human-designed heuristics of state-of-the-art provers and to instead automatically evolve -- just from prover experiences -- their potentially optimal replacement. In this work, we present a neural network architecture for scoring clauses for clause selection that is powerful yet efficient to evaluate. Following RL principle…

This https://arxiv.org/abs/2506.02965 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs
Mixture-of-Experts (MoE) has been gaining popularity due to its successful adaptation to large language models (LLMs). In this work, we introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE), which leverages the sparsity of the MoE architecture for memory-efficient decentralized collaborative LLM training, enabling multiple parties with limited GPU-memory and data resources to collectively train more capable LLMs than they could achieve individually. At the same time, this appro…

This https://arxiv.org/abs/2505.23516 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

The CASE Framework -- A New Architecture for Participatory Research and Digital Health Surveillance
We present the CASE framework, an open-source platform for adaptive, context-aware participatory research, and pandemic preparedness. CASE implements an event-driven architecture that enables dynamic survey workflows, allowing real-time adaptation based on participant responses, external data, temporal conditions, and evolving user states. The framework supports a broad range of research needs, from simple one-time questionnaires to complex longitudinal studies with advanced conditional logic. …

Large Processor Chip Model
Kaiyan Chang, Mingzhi Chen, Yunji Chen, Zhirong Chen, Dongrui Fan, Junfeng Gong, Nan Guo, Yinhe Han, Qinfen Hao, Shuo Hou, Xuan Huang, Pengwei Jin, Changxin Ke, Cangyuan Li, Guangli Li, Huawei Li, Kuan Li, Naipeng Li, Shengwen Liang, Cheng Liu, Hongwei Liu, Jiahua Liu, Junliang Lv, Jianan Mu, Jin Qin, Bin Sun, Chenxi Wang, Duo Wang, Mingjun Wang, Ying Wang, Chenggang Wu, Peiyang Wu, Teng Wu, Xiao Xiao, Mengyao Xie, Chenwei Xiong, Ruiyuan Xu, Mingyu Yan, Xiaoc…

Large Processor Chip Model
Computer System Architecture serves as a crucial bridge between software applications and the underlying hardware, encompassing components like compilers, CPUs, coprocessors, and RTL designs. Its development, from early mainframes to modern domain-specific architectures, has been driven by rising computational demands and advancements in semiconductor technology. However, traditional paradigms in computer system architecture design are confronting significant challenges, including a reliance on…

[2025-06-06 Fri (UTC), 7 new articles found for cs.NI Networking and Internet Architecture]
#toXiv_bot_toot

The CASE Framework -- A New Architecture for Participatory Research and Digital Health Surveillance
Marco Hirsch, Peter Hevesi, Paul Lukowicz
https://arxiv.org/abs/2505.23516

The CASE Framework -- A New Architecture for Participatory Research and Digital Health Surveillance
We present the CASE framework, an open-source platform for adaptive, context-aware participatory research, and pandemic preparedness. CASE implements an event-driven architecture that enables dynamic survey workflows, allowing real-time adaptation based on participant responses, external data, temporal conditions, and evolving user states. The framework supports a broad range of research needs, from simple one-time questionnaires to complex longitudinal studies with advanced conditional logic. …

This https://arxiv.org/abs/2506.00691 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Optimizing Sensory Neurons: Nonlinear Attention Mechanisms for Accelerated Convergence in Permutation-Invariant Neural Networks for Reinforcement Learning
Training reinforcement learning (RL) agents often requires significant computational resources and extended training times. To address this, we build upon the foundation laid by Google Brain's Sensory Neuron, which introduced a novel neural architecture for reinforcement learning tasks that maintained permutation in-variance in the sensory neuron system. While the baseline model demonstrated significant performance improvements over traditional approaches, we identified opportunities to enhance…

AI Accelerators for Large Language Model In-ference: Architecture Analysis and Scaling Strategies
Amit Sharma
https://arxiv.org/abs/2506.00008 https://

AI Accelerators for Large Language Model In-ference: Architecture Analysis and Scaling Strategies
The rapid growth of large-language models (LLMs) is driving a new wave of specialized hardware for inference. This paper presents the first workload-centric, cross-architectural performance study of commercial AI accelerators, spanning GPU-based chips, hybrid packages, and wafer-scale engines. We compare memory hierarchies, compute fabrics, and on-chip interconnects, and observe up to 3.7x performance variation across architectures as batch size and sequence length change. Four scaling techniqu…

Design and Analysis of Power Consumption Models for Open-RAN Architectures
Urooj Tariq, Rishu Raj, Dan Kilper
https://arxiv.org/abs/2505.24552 https://

Design and Analysis of Power Consumption Models for Open-RAN Architectures
The open radio access network (O-RAN) Alliance developed an architecture and specifications for open and disaggregated cellular networks including many elements that are being widely adopted and implemented in both commercial and research networks. In this paper, we develop transaction-based power consumption models of a centralized O-RAN architecture based on commercial hardware and considering the full end-to-end data path from the radio unit to the data center. We focus on recent fanout limi…

Hybrid SLC-MLC RRAM Mixed-Signal Processing-in-Memory Architecture for Transformer Acceleration via Gradient Redistribution
Chang Eun Song, Priyansh Bhatnagar, Zihan Xia, Nam Sung Kim, Tajana Rosing, Mingu Kang
https://arxiv.org/abs/2506.00020

Hybrid SLC-MLC RRAM Mixed-Signal Processing-in-Memory Architecture for Transformer Acceleration via Gradient Redistribution
Transformers, while revolutionary, face challenges due to their demanding computational cost and large data movement. To address this, we propose HyFlexPIM, a novel mixed-signal processing-in-memory (PIM) accelerator for inference that flexibly utilizes both single-level cell (SLC) and multi-level cell (MLC) RRAM technologies to trade-off accuracy and efficiency. HyFlexPIM achieves efficient dual-mode operation by utilizing digital PIM for high-precision and write-intensive operations while ana…

A Novel Cost-Effective MIMO Architecture with Ray Antenna Array for Enhanced Wireless Communication Performance
Zhenjun Dong, Zhiwen Zhou, Yong Zeng
https://arxiv.org/abs/2505.23394

A Novel Cost-Effective MIMO Architecture with Ray Antenna Array for Enhanced Wireless Communication Performance
This paper proposes a novel multi-antenna architecture, termed ray antenna array (RAA), which practically enables flexible beamforming and also enhances wireless communication performance for high frequency systems in a cost-effective manner. RAA consists of a large number of inexpensive antenna elements and a few radio frequency (RF) chains. These antenna elements are arranged in a novel ray like structure, where each ray corresponds to one simple uniform linear array (sULA) with a carefully d…

CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detection
David Ortiz-Perez, Manuel Benavent-Lledo, Javier Rodriguez-Juan, Jose Garcia-Rodriguez, David Tom\'as
https://arxiv.org/abs/2506.01890

CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detection
Early detection of cognitive disorders such as Alzheimer's disease is critical for enabling timely clinical intervention and improving patient outcomes. In this work, we introduce CogniAlign, a multimodal architecture for Alzheimer's detection that integrates audio and textual modalities, two non-intrusive sources of information that offer complementary insights into cognitive health. Unlike prior approaches that fuse modalities at a coarse level, CogniAlign leverages a word-level temporal alig…

[2025-06-05 Thu (UTC), 9 new articles found for cs.NI Networking and Internet Architecture]
#toXiv_bot_toot

Energy-Oriented Computing Architecture Simulator for SNN Training
Yunhao Ma (Pengcheng Laboratory, Southern University of Science and Technology), Wanyi Jia (Pengcheng Laboratory, Southern University of Science and Technology), Yanyu Lin (Pengcheng Laboratory), Wenjie Lin (Pengcheng Laboratory), Xueke Zhu (Pengcheng Laboratory), Huihui Zhou (Pengcheng Laboratory), Fengwei An (Southern University of Science and Technology)

Energy-Oriented Computing Architecture Simulator for SNN Training
With the growing demand for intelligent computing, neuromorphic computing, a paradigm that mimics the structure and functionality of the human brain, offers a promising approach to developing new high-efficiency intelligent computing systems. Spiking Neural Networks (SNNs), the foundation of neuromorphic computing, have garnered significant attention due to their unique potential in energy efficiency and biomimetic neural processing. However, current hardware development for efficient SNN train…

This https://arxiv.org/abs/2505.24137 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAR_…

Energy-Oriented Computing Architecture Simulator for SNN Training
With the growing demand for intelligent computing, neuromorphic computing, a paradigm that mimics the structure and functionality of the human brain, offers a promising approach to developing new high-efficiency intelligent computing systems. Spiking Neural Networks (SNNs), the foundation of neuromorphic computing, have garnered significant attention due to their unique potential in energy efficiency and biomimetic neural processing. However, current hardware development for efficient SNN train…

[2025-06-06 Fri (UTC), 3 new articles found for cs.AR Hardware Architecture]
#toXiv_bot_toot

[2025-06-05 Thu (UTC), no new articles found for cs.AR Hardware Architecture]
#toXiv_bot_toot

This https://arxiv.org/abs/2411.18065 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAR_…

FlexiBit: Fully Flexible Precision Bit-parallel Accelerator Architecture for Arbitrary Mixed Precision AI
Recent research has shown that large language models (LLMs) can utilize low-precision floating point (FP) quantization to deliver high efficiency while maintaining original model accuracy. In particular, recent works have shown the effectiveness of non-power-of-two precisions, such as FP6 and FP5, and diverse sensitivity to low-precision arithmetic of LLM layers, which motivates mixed precision arithmetic including non-power-of-two precisions in LLMs. Although low-precision algorithmically lead…