Tootfinder

🌱 Plant cell wall mechanics informs how to grow sustainable architectural forms
#cornell

Plant cell wall mechanics informs how to grow sustainable architectural forms
Clothing that adapts to one's needs and senses the external habitat. A lunar lava tunnel that uses bacteria, plants and fungi to create sustainable human habitats within otherwise unlivable places. Buildings grown from living things.

Temporal Network Analysis of Microservice Architectural Degradation
Alexander Bakhtin
https://arxiv.org/abs/2508.11571 https://arxiv.org/pdf/2508.11571

Temporal Network Analysis of Microservice Architectural Degradation
Microservice architecture can be modeled as a network of microservices making calls to each other, commonly known as the service dependency graph. Network Science can provide methods to study such networks. In particular, temporal network analysis is a branch of Network Science that analyzes networks evolving with time. In microservice systems, temporal networks can arise if we examine the architecture of the system across releases or monitor a deployed system using tracing. In this research …

This is a lovely review of my latest Buildings&Cities paper on clinic layouts at Moorfields Eye Hospital NHS Trust
https://sustainableconstructionreview.com/2025/06/12/moorfields-eye-hospital-redesigns-pa…

Moorfields Eye Hospital Redesigns Patient Flow with Architectural Innovation
In the bustling corridors of Moorfields Eye Hospital, a silent revolution is underway, one that could reshape how we think about patient flow and clinic design. At the heart of this transformation is…

North Korean Scammers Are Doing Architectural Design Now
https://www.wired.com/story/north-korean-scammers-are-doing-architectural-design-now/

North Korean Scammers Are Doing Architectural Design Now
New research shows that North Koreans appear to be trying to trick US companies into hiring them to develop architectural designs using fake profiles, résumés, and Social Security numbers.

Sentinel Agents for Secure and Trustworthy Agentic AI in Multi-Agent Systems
Diego Gosmar, Deborah A. Dahl
https://arxiv.org/abs/2509.14956 https://arxiv.o…

Sentinel Agents for Secure and Trustworthy Agentic AI in Multi-Agent Systems
This paper proposes a novel architectural framework aimed at enhancing security and reliability in multi-agent systems (MAS). A central component of this framework is a network of Sentinel Agents, functioning as a distributed security layer that integrates techniques such as semantic analysis via large language models (LLMs), behavioral analytics, retrieval-augmented verification, and cross-agent anomaly detection. Such agents can potentially oversee inter-agent communications, identify potenti…

Masked Feature Modeling Enhances Adaptive Segmentation
Wenlve Zhou, Zhiheng Zhou, Tiantao Xian, Yikui Zhai, Weibin Wu, Biyun Ma
https://arxiv.org/abs/2509.13801 https://

Masked Feature Modeling Enhances Adaptive Segmentation
Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer models from a labeled source domain to an unlabeled target domain. While auxiliary self-supervised tasks-particularly contrastive learning-have improved feature discriminability, masked modeling approaches remain underexplored in this setting, largely due to architectural incompatibility and misaligned optimization objectives. We propose Masked Feature Modeling (MFM), a novel auxiliary task that performs feature mas…

ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting
Hyotaek Jeon, Hyunwook Lee, Juwon Kim, Sungahn Ko
https://arxiv.org/abs/2509.13753 https://…

ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting
Traffic forecasting represents a crucial problem within intelligent transportation systems. In recent research, Large Language Models (LLMs) have emerged as a promising method, but their intrinsic design, tailored primarily for sequential token processing, introduces notable challenges in effectively capturing spatial dependencies. Specifically, the inherent limitations of LLMs in modeling spatial relationships and their architectural incompatibility with graph-structured spatial data remain la…

On The Road - To Xi’An/ Geometry 📐
在路上 - 去西安/ 几何 📐
📷 Pentax MX
🎞️Fujifilm Neopan F, expired 1993
#filmphotography #Photography #blackandwhite

3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation
Nikolaos Gkanatsios, Jiahe Xu, Matthew Bronars, Arsalan Mousavian, Tsung-Wei Ke, Katerina Fragkiadaki
https://arxiv.org/abs/2508.11002

3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation
We present 3D FlowMatch Actor (3DFA), a 3D policy architecture for robot manipulation that combines flow matching for trajectory prediction with 3D pretrained visual scene representations for learning from demonstration. 3DFA leverages 3D relative attention between action and visual tokens during action denoising, building on prior work in 3D diffusion-based single-arm policy learning. Through a combination of flow matching and targeted system-level and architectural optimizations, 3DFA achieve…

🇺🇦 #NowPlaying on #BBC6Music's #The6MixWithMaryAnneHobbs
Architectural:
🎵 Bad-Tempered Drumming
#Architectural
https://architecturalrecs.bandcamp.com/track/bad-tempered-drumming
https://open.spotify.com/track/6zXkqif1ScOePM1DUxuKVh

Shift-Left Techniques in Electronic Design Automation: A Survey
Xinyue Wu, Zixuan Li, Fan Hu, Ting Lin, Xiaotian Zhao, Runxi Wang, Xinfei Guo
https://arxiv.org/abs/2509.14551 ht…

Shift-Left Techniques in Electronic Design Automation: A Survey
The chip design process involves numerous steps, beginning with defining product requirements and progressing through architectural planning, system-level design, and the physical layout of individual circuit blocks. As the enablers of large-scale chip development, Electronic Design Automation (EDA) tools play a vital role in helping designers achieve high-quality results. The Shift-Left methodology introduces a pathway toward creating digital twins and fusing multiple design steps, thereby tra…

🧺 Prehistoric basketweaving inspires new materials for stiff, resilient robots
https://techxplore.com/news/2025-08-prehistoric-basketweaving-materials-stiff-resilient.html

Prehistoric basketweaving inspires new materials for stiff, resilient robots
Able to undergo repeated compressions without losing their shape, woven materials could form robots, exoskeletons, car parts, architectural components and more.

Towards Nomadic 6G Communication Networks: Implications on Architecture, Standardization, and Regulatory Aspects
Daniel Lindenschmitt, Marcos Rates Crippa, Hans D. Schotten
https://arxiv.org/abs/2508.12710

Towards Nomadic 6G Communication Networks: Implications on Architecture, Standardization, and Regulatory Aspects
The emergence of nomadic mobile communication networks for sixth-generation (6G) introduces a paradigm shift in how network infrastructure is conceptualized, deployed, and operated. Unlike traditional fixed systems, Nomadic Networks (NNs) consist of mobile and self-organizing nodes that provide radio infrastructure capabilities in motion. This paper explores the architectural implications of such systems, with a particular focus on the design and evolution of network interfaces. We analyze the …

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
Hanshuai Cui, Zhiqing Tang, Zhifei Xu, Zhi Yao, Wenyi Zeng, Weijia Jia
https://arxiv.org/abs/2509.13789

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiting real-world applicability. Existing acceleration methods either compromise visual quality due to architectural modifications or fail to reuse intermediate features at proper granularity. Our analysis reveals that DiT blocks are the primary contributors to inference latency. Ac…

On The Road - To Xi’An/ Mordern Relics
在路上 - 去西安/ 现代遗风
📷 Pentax MX
🎞️Fujifilm Neopan F, expired 1993
#filmphotography #Photography #blackandwhite

As usual we watched the "Stoertebekker" stage play at Ralswiek on Rügen Island. The stage setups and wardrobes were as awesome as always. They really try to improve on that every year and come up with clever mechanisms to transform the building for the various acts of the play. The script this year left room for desire ;) Nevertheless a happing worth attending
htt…

Trump Unveils Plan for Tacky Giant Golden Addition to D.C.
https://www.yahoo.com/news/articles/trump-plotting-even-bigger-architectural-234958283.html

DeepAssert: An LLM-Aided Verification Framework with Fine-Grained Assertion Generation for Modules with Extracted Module Specifications
Yonghao Wang, Jiaxin Zhou, Hongqin Lyu, Zhiteng Chao, Tiancheng Wang, Huawei Li
https://arxiv.org/abs/2509.14668

DeepAssert: An LLM-Aided Verification Framework with Fine-Grained Assertion Generation for Modules with Extracted Module Specifications
Assertion-Based Verification (ABV) is a crucial method for ensuring that logic designs conform to their architectural specifications. However, existing assertion generation methods primarily rely on information either from the design specification, or register-transfer level (RTL) code. The former methods are typically limited to generating assertions for the top-level design. As the top-level design is composed of different modules without module-level specifications, they are unable to genera…

A Traditional Approach to Symbolic Piano Continuation
Christian Zhou-Zheng, John Backsund, Dun Li Chan, Alex Coventry, Avid Eslami, Jyotin Goel, Xingwen Han, Danysh Soomro, Galen Wei
https://arxiv.org/abs/2509.12267

A Traditional Approach to Symbolic Piano Continuation
We present a traditional approach to symbolic piano music continuation for the MIREX 2025 Symbolic Music Generation challenge. While computational music generation has recently focused on developing large foundation models with sophisticated architectural modifications, we argue that simpler approaches remain more effective for constrained, single-instrument tasks. We thus return to a simple, unaugmented next-token-prediction objective on tokenized raw MIDI, aiming to outperform large foundatio…

Every year someone on #GBBO tries to construct some kind of fancy architectural showstopper thing using a dough that isn't gingerbread. Every year they say "this is risky, it might crack" and you know what, every year someone on GBBO sees their fancy architectural showstopper crack apart.
Now I'm no baker, but I can at least learn from history. Use gingerbread, people!

Pre/Absence: Prompting Cultural Awareness and Understanding for Lost Architectural Heritage in Virtual Reality
Yaning Li, Ke Zhao, Shucheng Zheng, Xingyu Chen, Chenyi Chen, Wenxi Dai, Weile Jiang, Qi Dong, Yiqing Zhao, Meng Li, Lin-Ping Yuan
https://arxiv.org/abs/2510.07967

Pre/Absence: Prompting Cultural Awareness and Understanding for Lost Architectural Heritage in Virtual Reality
Lost architectural heritage presents interpretive challenges due to vanished structures and fragmented historical records. Using Hanyuan Hall of the Tang dynasty's Daming Palace as a case study, we conducted a formative investigation with archaeologists, heritage administrators, and visitors to identify key issues in current interpretation practices. We found that these practices often compress complex cultural layers into factual summaries and rely on linear narratives that overlook the contin…

Series A, Episode 11 - Bounty
BLAKE: I just want you to listen.
SARKOFF: I've wasted my life listening, listening to people who are arrogant, or vacuous, or just plain vicious. I smiled and acquiesced in the face of prejudice and stupidity. I've tolerated mediocrity and accepted the tyranny of second-class minds. But now all that is over. I am ready to die, here among the things I value. I am ready to let you kill me but I am not ready to listen to you justify the act. […

Moody Urbanity - Odes III 🎵
情绪化城市 - 颂 III 🎵
📷 Zeiss Super Ikonta 533/16
🎞️ Ilford HP5 Plus, expired 1993
#filmphotography #Photography #blackandwhite

Cross-Prompt Encoder for Low-Performing Languages
Beso Mikaberidze, Teimuraz Saghinadze, Simon Ostermann, Philipp Muller
https://arxiv.org/abs/2508.10352 https://

Cross-Prompt Encoder for Low-Performing Languages
Soft prompts have emerged as a powerful alternative to adapters in parameter-efficient fine-tuning (PEFT), enabling large language models (LLMs) to adapt to downstream tasks without architectural changes or parameter updates. While prior work has focused on stabilizing training via parameter interaction in small neural prompt encoders, their broader potential for transfer across languages remains unexplored. In this paper, we demonstrate that a prompt encoder can play a central role in improvin…

Replaced article(s) found for cs.AR. https://arxiv.org/list/cs.AR/new
[1/1]:
- LaZagna: An Open-Source Framework for Flexible 3D FPGA Architectural Exploration
Ismael Youssef, Hang Yang, Cong Hao

https://www.stirworld.com/think-opinions-remaking-the-chinese-garden-a-contemporary-architectural-dilemma

Remaking the Chinese Garden: a contemporary architectural dilemma
The Chinese garden is not just a single, independent entity built for crafting landscapes or modelling nature itself, it is a lexicon of symbols, layered upon built reality.

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations
Ron F. Del Rosario, Klaudia Krawiecka, Christian Schroeder de Witt
https://arxiv.org/abs/2509.08646

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations
As Large Language Model (LLM) agents become increasingly capable of automating complex, multi-step tasks, the need for robust, secure, and predictable architectural patterns is paramount. This paper provides a comprehensive guide to the ``Plan-then-Execute'' (P-t-E) pattern, an agentic design that separates strategic planning from tactical execution. We explore the foundational principles of P-t-E, detailing its core components - the Planner and the Executor - and its architectural advantages i…

Why does your graph neural network fail on some graphs? Insights from exact generalisation error
Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar
https://arxiv.org/abs/2509.10337

Why does your graph neural network fail on some graphs? Insights from exact generalisation error
Graph Neural Networks (GNNs) are widely used in learning on graph-structured data, yet a principled understanding of why they succeed or fail remains elusive. While prior works have examined architectural limitations such as over-smoothing and over-squashing, these do not explain what enables GNNs to extract meaningful representations or why performance varies drastically between similar architectures. These questions are related to the role of generalisation: the ability of a model to make acc…

Towards the Next Generation of Software: Insights from Grey Literature on AI-Native Applications
Lingli Cao, Shanshan Li, Ying Fan, Danyang Li, Chenxing Zhong
https://arxiv.org/abs/2509.13144

Towards the Next Generation of Software: Insights from Grey Literature on AI-Native Applications
Background: The rapid advancement of large language models (LLMs) has given rise to AI-native applications, a new paradigm in software engineering that fundamentally redefines how software is designed, developed, and evolved. Despite their growing prominence, AI-native applications still lack a unified engineering definition and architectural blueprint, leaving practitioners without systematic guidance for system design, quality assurance, and technology selection. Objective: This study seeks…

Moody Urbanity - Odes II 🎶
情绪化城市 - 颂 II🎶
📷 Pentax MX
🎞️ Kentmere Pan 400
#filmphotography #Photography #blackandwhite

Relaying for a friend and colleague
Sr. Network Engineer (Akamai) - US based Remote person. The role is on the the Akamai backbone network engineering team. If you have experience with large scale MPLS and Traffic Engineering and would like to works on some large scale networking problems... https://jobs.akamai.com/en/sit…

Architectural practice process and artificial intelligence -- an evolving practice
Mustapha El Moussaoui
https://arxiv.org/abs/2507.23653 https://arxiv.org…

Architectural practice process and artificial intelligence -- an evolving practice
In an era of exponential technological advancement, artificial intelligence (AI) has emerged as a transformative force in architecture, reshaping traditional design and construction practices. This article explores the multifaceted roles of AI in the architectural process, emphasizing its potential to enhance creativity and efficiency while addressing its limitations in capturing multisensory and experiential dimensions of space. Historically, architectural innovation has paralleled technologic…

Accelerating vRAN and O-RAN with SIMD: Architectural Perspectives and Performance Evaluation
Jaebum Park, Chan-Byoung Chae, Robert W. Heath Jr
https://arxiv.org/abs/2510.07843 h…

Accelerating vRAN and O-RAN with SIMD: Architectural Perspectives and Performance Evaluation
The evolution of radio access networks (RANs) toward virtualization and openness creates new opportunities for flexible, cost-effective, and high-performance deployments. Achieving real-time and energy-efficient baseband processing on commercial off-the-shelf platforms, however, remains a critical challenge. This article explores how single instruction multiple data (SIMD) architectures can accelerate RAN workloads. We first outline why key physical-layer functions, such as channel estimation, …

MACO: A Multi-Agent LLM-Based Hardware/Software Co-Design Framework for CGRAs
Zesong Jiang, Yuqi Sun, Qing Zhong, Mahathi Krishna, Deepak Patil, Cheng Tan, Sriram Krishnamoorthy, Jeff Zhang
https://arxiv.org/abs/2509.13557

MACO: A Multi-Agent LLM-Based Hardware/Software Co-Design Framework for CGRAs
Coarse-grained Reconfigurable Arrays (CGRAs) are a promising computing architecture that can deliver high-performance, energy-efficient acceleration across diverse domains. By supporting reconfiguration at the functional unit level, CGRAs efficiently adapt to varying computational patterns and optimize resource utilization. However, designing CGRAs is highly challenging due to the vast design space, independent architectural parameters, and the time-consuming nature of manual design. Fortunatel…

#OTD: 13 years ago, I visited the Mercedes-Benz Museum in Stuttgart.
It is one of Germany's temples to “das Auto”. Architectural gems, this one is by UN Studio.

Architectural #Patterns, The Pattern Language of #SoftwareArchitecture
https://github.com/denyspoltorak/metap…

You can now virtually explore the stunning landscapes and vibrant culture of Nepal in Street View.
Wander the lively streets of Kathmandu, discover the serene beauty of the Terai region or wind along roads that offer breathtaking views of the snow-capped Himalayas — all virtually.
You can even immerse yourself in Nepal’s rich architectural history, ancient temples and bustling markets.

Street View has now come to Nepal.
You can now virtually explore the stunning landscapes and vibrant culture of Nepal in Street View. Wander the lively streets of Kathmandu, discover the serene beauty of the Terai region or wind along roads that offer breathtaking views of the snow-capped Himalayas — all virtually. You can even immerse yourself in Nepal’s rich architectural history, ancient temples and bustling markets.To see the newest images of Nepal, open up Maps from your phone or computer, click the 360° view or the ye…

A Decentralized Microservice Scheduling Approach Using Service Mesh in Cloud-Edge Systems
Yangyang Wen, Paul Townend, Per-Olov \"Ostberg, Abel Souza, Cl\'ement Courageux-Sudan
https://arxiv.org/abs/2510.11189

A Decentralized Microservice Scheduling Approach Using Service Mesh in Cloud-Edge Systems
As microservice-based systems scale across the cloud-edge continuum, traditional centralized scheduling mechanisms increasingly struggle with latency, coordination overhead, and fault tolerance. This paper presents a new architectural direction: leveraging service mesh sidecar proxies as decentralized, in-situ schedulers to enable scalable, low-latency coordination in large-scale, cloud-native environments. We propose embedding lightweight, autonomous scheduling logic into each sidecar, allowin…

SpikePool: Event-driven Spiking Transformer with Pooling Attention
Donghyun Lee, Alex Sima, Yuhang Li, Panos Stinis, Priyadarshini Panda
https://arxiv.org/abs/2510.12102 https:/…

SpikePool: Event-driven Spiking Transformer with Pooling Attention
Building on the success of transformers, Spiking Neural Networks (SNNs) have increasingly been integrated with transformer architectures, leading to spiking transformers that demonstrate promising performance on event-based vision tasks. However, despite these empirical successes, there remains limited understanding of how spiking transformers fundamentally process event-based data. Current approaches primarily focus on architectural modifications without analyzing the underlying signal process…

#Algiers

Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
Anis Hamadouche, Haifeng Luo, Mathini Sellathurai, Tharm Ratnarajah
https://arxiv.org/abs/2508.08468

Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
This paper introduces a new AI-based Audio-Visual Speech Enhancement (AVSE) system and presents a comparative performance analysis of different deployment architectures. The proposed AVSE system employs convolutional neural networks (CNNs) for spectral feature extraction and long short-term memory (LSTM) networks for temporal modeling, enabling robust speech enhancement through multimodal fusion of audio and visual cues. Multiple deployment scenarios are investigated, including cloud-based, edg…

KoALA: KL-L0 Adversarial Detector via Label Agreement
Siqi Li, Yasser Shoukry
https://arxiv.org/abs/2510.12752 https://arxiv.org/pdf/2510.12752

KoALA: KL-L0 Adversarial Detector via Label Agreement
Deep neural networks are highly susceptible to adversarial attacks, which pose significant risks to security- and safety-critical applications. We present KoALA (KL-L0 Adversarial detection via Label Agreement), a novel, semantics-free adversarial detector that requires no architectural changes or adversarial retraining. KoALA operates on a simple principle: it detects an adversarial attack when class predictions from two complementary similarity metrics disagree. These metrics-KL divergence an…

Which Way You Goin’ Billy?
#VAG #Art

Dr.LLM: Dynamic Layer Routing in LLMs
Ahmed Heakl, Martin Gubri, Salman Khan, Sangdoo Yun, Seong Joon Oh
https://arxiv.org/abs/2510.12773 https://arxiv.org…

Dr.LLM: Dynamic Layer Routing in LLMs
Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and insufficient flexibility for harder ones that need deeper reasoning. Adaptive-depth methods can improve efficiency, but prior approaches rely on costly inference-time search, architectural changes, or large-scale retraining, and in practice often degrade accuracy despite efficiency gains. We introduce Dr.LLM, Dynamic routing of Layers for LLMs, a retrofitt…

Agentic AI Frameworks: Architectures, Protocols, and Design Challenges
Hana Derouiche, Zaki Brahmi, Haithem Mazeni
https://arxiv.org/abs/2508.10146 https://

Agentic AI Frameworks: Architectures, Protocols, and Design Challenges
The emergence of Large Language Models (LLMs) has ushered in a transformative paradigm in artificial intelligence, Agentic AI, where intelligent agents exhibit goal-directed autonomy, contextual reasoning, and dynamic multi-agent coordination. This paper provides a systematic review and comparative analysis of leading Agentic AI frameworks, including CrewAI, LangGraph, AutoGen, Semantic Kernel, Agno, Google ADK, and MetaGPT, evaluating their architectural principles, communication mechanisms, m…

DiffTex: Differentiable Texturing for Architectural Proxy Models
Weidan Xiong, Yongli Wu, Bochuan Zeng, Jianwei Guo, Dani Lischinski, Daniel Cohen-Or, Hui Huang
https://arxiv.org/abs/2509.23336

DiffTex: Differentiable Texturing for Architectural Proxy Models
Simplified proxy models are commonly used to represent architectural structures, reducing storage requirements and enabling real-time rendering. However, the geometric simplifications inherent in proxies result in a loss of fine color and geometric details, making it essential for textures to compensate for the loss. Preserving the rich texture information from the original dense architectural reconstructions remains a daunting task, particularly when working with unordered RGB photographs. We …

Ultra Ethernet's Design Principles and Architectural Innovations
Torsten Hoefler, Karen Schramm, Eric Spada, Keith Underwood, Cedell Alexander, Bob Alverson, Paul Bottorff, Adrian Caulfield, Mark Handley, Cathy Huang, Costin Raiciu, Abdul Kabbani, Eugene Opsasnick, Rong Pan, Adee Ran, Rip Sohan
https://arxiv.org/abs/2508.08906

Ultra Ethernet's Design Principles and Architectural Innovations
The recently released Ultra Ethernet (UE) 1.0 specification defines a transformative High-Performance Ethernet standard for future Artificial Intelligence (AI) and High-Performance Computing (HPC) systems. This paper, written by the specification's authors, provides a high-level overview of UE's design, offering crucial motivations and scientific context to understand its innovations. While UE introduces advancements across the entire Ethernet stack, its standout contribution is the novel Ultra…

Series A, Episode 11 - Bounty
SARKOFF: Yes, we may have need of thirteen million credits-
TYCE: Over my dead body.
SARKOFF: I hope you're not going to make a habit of that particular threat. Ready!
JENNA: Would you move back, please.
https://blake.torpidity.net/m/111/543

HECATE: An ECS-based Framework for Teaching and Developing Multi-Agent Systems
Arthur Casals, Anarosa A. F. Brand\~ao
https://arxiv.org/abs/2509.06431 https://

HECATE: An ECS-based Framework for Teaching and Developing Multi-Agent Systems
This paper introduces HECATE, a novel framework based on the Entity-Component-System (ECS) architectural pattern that bridges the gap between distributed systems engineering and MAS development. HECATE is built using the Entity-Component-System architectural pattern, leveraging data-oriented design to implement multiagent systems. This approach involves engineering multiagent systems (MAS) from a distributed systems (DS) perspective, integrating agent concepts directly into the DS domain. This …

CNN-ViT Hybrid for Pneumonia Detection: Theory and Empiric on Limited Data without Pretraining
Prashant Singh Basnet, Roshan Chitrakar
https://arxiv.org/abs/2509.08586 https://

CNN-ViT Hybrid for Pneumonia Detection: Theory and Empiric on Limited Data without Pretraining
This research explored the hybridization of CNN and ViT within a training dataset of limited size, and introduced a distinct class imbalance. The training was made from scratch with a mere focus on theoretically and experimentally exploring the architectural strengths of the proposed hybrid model. Experiments were conducted across varied data fractions with balanced and imbalanced training datasets. Comparatively, the hybrid model, complementing the strengths of CNN and ViT, achieved the highes…

Sub-Diffraction Chromatin Domains: Architecture, Regulation, and Functional Roles in Nuclear Organization
Vinayak Vinayak, Melike Lakadamyali, Vivek B Shenoy
https://arxiv.org/abs/2510.09375

Sub-Diffraction Chromatin Domains: Architecture, Regulation, and Functional Roles in Nuclear Organization
Nanoscale chromatin domains, variously termed nucleosome clutches, nanodomains, or packing domains, have emerged as fundamental architectural units of the mammalian genome during interphase and mitosis. Unlike cohesin-dependent loops or TADs, these 50-200 nm structures persist in the absence of loop extrusion, pointing to a distinct organizing principle shaped by histone post-translational modifications and constrained by interactions with the nuclear lamina. Super-resolution microscopy and ele…

Moody Urbanity - Odes 🎶
情绪化城市 - 颂 🎶
📷 Zeiss Super Ikonta 533/16
🎞️ Ilford HP5 Plus, expired 1993
#filmphotography #Photography #blackandwhite

Interfacing Quantum Computing Systems with High-Performance Computing Systems: An Overview
Konstantinos Rallis, Ioannis Liliopoulos, Georgios D. Varsamis, Evangelos Tsipas, Ioannis G. Karafyllidis, Georgios Ch. Sirakoulis, Panagiotis Dimitrakis
https://arxiv.org/abs/2509.06205

Interfacing Quantum Computing Systems with High-Performance Computing Systems: An Overview
The connection and eventual integration of High-Performance Computing (HPC) with Quantum Computing (QC) represents a transformative advancement in computational technology, promising significant enhancements in solving complex, previously intractable problems. This manuscript provides a comprehensive overview of the current state of HPC-QC interfacing, detailing architectural methodologies, software stack developments, middleware functionalities, and hardware integration strategies. It critical…

Rethinking Knowledge Distillation: A Data Dependent Regulariser With a Negative Asymmetric Payoff
Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis
https://arxiv.org/abs/2510.12615

Rethinking Knowledge Distillation: A Data Dependent Regulariser With a Negative Asymmetric Payoff
Knowledge distillation is often considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. In this work, we quantify the compression capacity of knowledge distillation and the resulting knowledge transfer from a functional perspective, decoupling compression from architectural reduction, which provides an improved understanding of knowledge distillation. We employ hypothesis testing, controls, and random control d…

Compressed Video Quality Enhancement: Classifying and Benchmarking over Standards
Xiem HoangVan, Dang BuiDinh, Sang NguyenQuang, Wen-Hsiao Peng
https://arxiv.org/abs/2509.10407 …

Compressed Video Quality Enhancement: Classifying and Benchmarking over Standards
Compressed video quality enhancement (CVQE) is crucial for improving user experience with lossy video codecs like H.264/AVC, H.265/HEVC, and H.266/VVC. While deep learning based CVQE has driven significant progress, existing surveys still suffer from limitations: lack of systematic classification linking methods to specific standards and artifacts, insufficient comparative analysis of architectural paradigms across coding types, and underdeveloped benchmarking practices. To address these gaps, …

An AUTOSAR-Aligned Architectural Study of Vulnerabilities in Automotive SoC Software
Srijita Basu, Haraldsson Bengt, Miroslaw Staron, Christian Berger, Jennifer Horkoff, Magnus Almgren
https://arxiv.org/abs/2510.07941

An AUTOSAR-Aligned Architectural Study of Vulnerabilities in Automotive SoC Software
Cooperative, Connected and Automated Mobility (CCAM) are complex cyber-physical systems (CPS) that integrate computation, communication, and control in safety-critical environments. At their core, System-on-Chip (SoC) platforms consolidate processing units, communication interfaces, AI accelerators, and security modules into a single chip. AUTOSAR (AUTomotive Open System ARchitecture) standard was developed in the automotive domain to better manage this complexity, defining layered software str…

Future Illiteracies -- Architectural Epistemology and Artificial Intelligence
Mustapha El Moussaoui
https://arxiv.org/abs/2507.23434 https://arxiv.org/pdf/…

Future Illiteracies -- Architectural Epistemology and Artificial Intelligence
In the age of artificial intelligence, architectural practice faces a paradox of immense potential and creeping standardization. As humans are increasingly relying on AI-generated outputs, architecture risks becoming a spectacle of repetition- a shuffling of data that neither truly innovates nor progresses vertically in creative depth. This paper explores the critical role of data in AI systems, scrutinizing the training datasets that form the basis of AI's generative capabilities and the impli…

Empirical Investigation into Configuring Echo State Networks for Representative Benchmark Problem Domains
Brooke R. Weborg, Gursel Serpen
https://arxiv.org/abs/2508.10887 https:…

Empirical Investigation into Configuring Echo State Networks for Representative Benchmark Problem Domains
This paper examines Echo State Network, a reservoir computer, performance using four different benchmark problems, then proposes heuristics or rules of thumb for configuring the architecture, as well as the selection of parameters and their values, which are applicable to problems within the same domain, to help serve to fill the experience gap needed by those entering this field of study. The influence of various parameter selections and their value adjustments, as well as architectural change…

🏰 ‘It’s back to the future’: the 13th-century castle built by hand in France
https://www.theguardian.com/world/2025/aug/23/13th-century-castle-built-by-hand-in-france-guedelon

Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
Jayakrishna Duggempudi, Lu Gao, Ahmed Senouci, Zhe Han, Yunpeng Zhang
https://arxiv.org/abs/2509.00543

Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
This paper presents the development of an AI-powered workflow that uses Large Language Models (LLMs) to assist in drafting schematic architectural floor plans from natural language prompts. The proposed system interprets textual input to automatically generate layout options including walls, doors, windows, and furniture arrangements. It combines prompt engineering, a furniture placement refinement algorithm, and Python scripting to produce spatially coherent draft plans compatible with design …

Towards Dynamic Urban Scene Synthesis: The Digital Twin Descriptor Service
Ioannis Tsampras, Georgios Stergiopoulos, Tanya Politi, Spyros Denazis
https://arxiv.org/abs/2509.11810

Towards Dynamic Urban Scene Synthesis: The Digital Twin Descriptor Service
Digital twins have been introduced as supporters to city operations, yet existing scene-descriptor formats and digital twin platforms often lack the integration, federation, and adaptable connectivity that urban environments demand. Modern digital twin platforms decouple data streams and representations into separate architectural planes, fusing them only at the visualization layer and limiting potential for simulation or further processing of the combined assets. At the same time, geometry-cen…

ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
Shu Zhao, Tan Yu, Anbang Xu, Japinder Singh, Aaditya Shukla, Rama Akkiraju
https://arxiv.org/abs/2508.09303

ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
Reasoning-augmented search agents such as Search-R1, trained via reinforcement learning with verifiable rewards (RLVR), demonstrate remarkable capabilities in multi-step information retrieval from external knowledge sources. These agents address the limitations of their parametric memory by dynamically gathering relevant facts to address complex reasoning tasks. However, existing approaches suffer from a fundamental architectural limitation: they process search queries strictly sequentially, ev…

Towards an Architectural Perspective for Sustainability: Bundle the Needs from Industry
Markus Funke, Patricia Lago
https://arxiv.org/abs/2508.20774 https://

Towards an Architectural Perspective for Sustainability: Bundle the Needs from Industry
Sustainability is increasingly recognized as an emerging quality property in software-intensive systems, yet architects lack structured guidance to address it effectively throughout the software design phase. Architectural perspectives-an architectural knowledge artifact composed of concerns, activities, tactics, pitfalls, and checklists-offer a promising approach to tackle such emerging quality properties across architectural views and are also independent of architecture frameworks and indust…

Blockchain-Enabled Federated Learning
Murtaza Rangwala, Venugopal K R, Rajkumar Buyya
https://arxiv.org/abs/2508.06406 https://arxiv.org/pdf/2508.06406

Blockchain-Enabled Federated Learning
Blockchain-enabled federated learning (BCFL) addresses fundamental challenges of trust, privacy, and coordination in collaborative AI systems. This chapter provides comprehensive architectural analysis of BCFL systems through a systematic four-dimensional taxonomy examining coordination structures, consensus mechanisms, storage architectures, and trust models. We analyze design patterns from blockchain-verified centralized coordination to fully decentralized peer-to-peer networks, evaluating tr…

Diffusion Transformers with Representation Autoencoders
Boyang Zheng, Nanye Ma, Shengbang Tong, Saining Xie
https://arxiv.org/abs/2510.11690 https://arxiv.…

Diffusion Transformers with Representation Autoencoders
Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (DiT); however, the autoencoder component has barely evolved. Most DiTs continue to rely on the original VAE encoder, which introduces several limitations: outdated backbones that compromise architectural simplicity, low-dimensional latent spaces that restrict information capacity, and weak representations that result f…

Moody Urbanity - Up Up ⏏️
情绪化城市 - 上面上面 ⏏️
📷 Pentax MX
🎞️ Kentmere Pan 400
#filmphotography #Photography #blackandwhite

A10 - Breakdown
BLAKE: Jenna? [Gan throws Jenna to the floor] Jenna. Jenna! [Gan drags Jenna to front of flight deck]
BLAKE: Gan! Gan, it's me, Blake. Gan, listen to me. [Gan attacks Blake. Avon, Cally, and Vila run in. Avon and Vila pull Gan off Blake]
https://blake.torpidity.net/m/110/9

The Monte Carlo Method and New Device and Architectural Techniques for Accelerating It
Janith Petangoda, Chatura Samarakoon, James Meech, Divya Thekke Kanapram, Hamid Toshani, Nathaniel Tye, Vasileios Tsoutsouras, Phillip Stanley-Marbell
https://arxiv.org/abs/2508.07457

The Monte Carlo Method and New Device and Architectural Techniques for Accelerating It
Computing systems interacting with real-world processes must safely and reliably process uncertain data. The Monte Carlo method is a popular approach for computing with such uncertain values. This article introduces a framework for describing the Monte Carlo method and highlights two advances in the domain of physics-based non-uniform random variate generators (PPRVGs) to overcome common limitations of traditional Monte Carlo sampling. This article also highlights recent advances in architectur…

Bio-Generative Design Morphology with Radiolaria: An application of a Nature-Based Generative Shape Grammar for Geometrical Design of Space Frames
Michael Kleiss, Seyedehaysan Mokhtarimousavi, Sida Dai, Mostafa Alani
https://arxiv.org/abs/2508.08572

Bio-Generative Design Morphology with Radiolaria: An application of a Nature-Based Generative Shape Grammar for Geometrical Design of Space Frames
This paper presents a study on using Radiolaria as a basis for generation of space-based geometry for structural design with shape grammars. Radiolaria has been a source of inspiration for architectural design with its intricate structural features and geometric patterns (Lim, 2012). We use the basis of the Radiolaria geometry to create a generative shape grammar as a computational system; then use the shape grammar to create spatial configurations for potential applications in design of 3D spa…

Replaced article(s) found for cs.SE. https://arxiv.org/list/cs.SE/new
[1/1]:
- A MAPE-K-Based Method for Architectural Conformance Checking in Self-Adaptive Systems
Daniel San Mart\'in, Guisella Angulo, Valter Vieira de Camargo

Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive Review
Mahdi Golizadeh, Nassibeh Golizadeh, Mohammad Ali Keyvanrad, Hossein Shirazi
https://arxiv.org/abs/2508.03317

Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive Review
Object detection has achieved remarkable accuracy through deep learning, yet these improvements often come with increased computational cost, limiting deployment on resource-constrained devices. Knowledge Distillation (KD) provides an effective solution by enabling compact student models to learn from larger teacher models. However, adapting KD to object detection poses unique challenges due to its dual objectives-classification and localization-as well as foreground-background imbalance and mu…

Half-organic, half-architectural for #AbstractAug
#photo #photography #tree

City Features III 🌆
城市特征 III 🌆
📷 Nikon FE
🎞️Ilford FP4 Plus, expired 1994
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Sustaining Research Software: A Fitness Function Approach
Philipp Zech, Irdin Pekaric
https://arxiv.org/abs/2509.10085 https://arxiv.org/pdf/2509.10085

Sustaining Research Software: A Fitness Function Approach
The long-term sustainability of research software is a critical challenge, as it usually suffers from poor maintainability, lack of adaptability, and eventual obsolescence. This paper proposes a novel approach to addressing this issue by leveraging the concept of fitness functions from evolutionary architecture. Fitness functions are automated, continuously evaluated metrics designed to ensure that software systems meet desired non-functional, architectural qualities over time. We define a set …

Aurora: Architecting Argonne's First Exascale Supercomputer for Accelerated Scientific Discovery
Benjamin S. Allen, James Anchell, Victor Anisimov, Thomas Applencourt, Abhishek Bagusetty, Ramesh Balakrishnan, Riccardo Balin, Solomon Bekele, Colleen Bertoni, Cyrus Blackworth, Renzo Bustamante, Kevin Canada, John Carrier, Christopher Chan-nui, Lance C. Cheney, Taylor Childers, Paul Coffman, Susan Coghlan, Michael D'Mello, Murali Emani, Kyle G. Felker, Sam Foreman, Olivier Franza,…

Aurora: Architecting Argonne's First Exascale Supercomputer for Accelerated Scientific Discovery
Aurora is Argonne National Laboratory's pioneering Exascale supercomputer, designed to accelerate scientific discovery with cutting-edge architectural innovations. Key new technologies include the Intel(TM) Xeon(TM) Data Center GPU Max Series (code-named Sapphire Rapids) with support for High Bandwidth Memory (HBM), alongside the Intel(TM) Data Center GPU Max Series (code-named Ponte Vecchio) on each compute node. Aurora also integrates the Distributed Asynchronous Object Storage (DAOS), a nove…

YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
Ranjan Sapkota, Rahul Harsha Cheppally, Ajay Sharda, Manoj Karkee
https://arxiv.org/abs/2509.25164

YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
This study presents Key Architectural Enhancements and Performance Benchmarking of Ultralytics YOLO26 for real-time edge object detection, providing a comprehensive overview of the design principles of YOLO26, technological advances, and deployment readiness. YOLO26, released in September 2025 by Ultralytics, represents the newest and most cutting-edge member of the You Only Look Once (YOLO) family, engineered to push the boundaries of efficiency and accuracy on edge and low-power devices. This…

An Interpretable Deep Learning Model for General Insurance Pricing
Patrick J. Laub, Tu Pho, Bernard Wong
https://arxiv.org/abs/2509.08467 https://arxiv.org…

An Interpretable Deep Learning Model for General Insurance Pricing
This paper introduces the Actuarial Neural Additive Model, an inherently interpretable deep learning model for general insurance pricing that offers fully transparent and interpretable results while retaining the strong predictive power of neural networks. This model assigns a dedicated neural network (or subnetwork) to each individual covariate and pairwise interaction term to independently learn its impact on the modeled output while implementing various architectural constraints to allow for…

Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies
Binghan Wu, Shoufeng Wang, Yunxin Liu, Ya-Qin Zhang, Joseph Sifakis, Ye Ouyang
https://arxiv.org/abs/2509.08312

Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies
The evolution toward Level 4 (L4) Autonomous Networks (AN) represents a strategic inflection point in telecommunications, where networks must transcend reactive automation to achieve genuine cognitive capabilities--fulfilling TM Forum's vision of self-configuring, self-healing, and self-optimizing systems that deliver zero-wait, zero-touch, and zero-fault services. This work bridges the gap between architectural theory and operational reality by implementing Joseph Sifakis's AN Agent reference …

A Systematic Review: Affective Perception on Urban Facades
Chenxi Wang, Haining Ding, Michal Gath-Morad
https://arxiv.org/abs/2509.22599 https://arxiv.org/…

A Systematic Review: Affective Perception on Urban Facades
Architectural facades critically shape affective perception in urban environments. Here, affect is understood as a multidimensional psychological construct encompassing valence (pleasure-displeasure) and arousal (activation-deactivation). Despite growing interest in affective responses to the built environment, the affective impact of urban architectural facades remains under-theorized. This study conducts a systematic review of 61 works, guided by the PRISMA framework, to identify which facade…

On The Road - To Xi’An/ Angles ↕️
在路上 - 去西安/ 角度 ↕️
📷 Pentax MX
🎞️Fujifilm Neopan F, expired 1993
#filmphotography #Photography #blackandwhite

Functional vs. Object-Oriented: Comparing How Programming Paradigms Affect the Architectural Characteristics of Systems
Briza Mel Dias de Sousa (University of S\~ao Paulo), Renato Cordeiro Ferreira (University of S\~ao Paulo, Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Alfredo Goldman (University of S\~ao Paulo)
h…

Functional vs. Object-Oriented: Comparing How Programming Paradigms Affect the Architectural Characteristics of Systems
After decades of dominance by object-oriented programming (OOP), functional programming (FP) is gaining increasing attention in the software industry. This study compares the impact of OOP and FP on the architectural characteristics of software systems. For that, it examines the design and implementation of a Digital Wallet system, developed in Kotlin (representing OOP) and Scala (representing FP). The comparison is made through both qualitative and quantitative analyses to explore how each par…

Moody Urbanity - UP 🆙
情绪化城市 - 上面 🆙
📷 Nikon FE
🎞️ Ilford HP5 Plus 400, expired 1993
#filmphotography #Photography #blackandwhite

ISAAC: Intelligent, Scalable, Agile, and Accelerated CPU Verification via LLM-aided FPGA Parallelism
Jialin Sun, Yuchen Hu, Dean You, Yushu Du, Hui Wang, Xinwei Fang, Weiwei Shan, Nan Guan, Zhe Jiang
https://arxiv.org/abs/2510.10225

ISAAC: Intelligent, Scalable, Agile, and Accelerated CPU Verification via LLM-aided FPGA Parallelism
Functional verification is a critical bottleneck in integrated circuit development, with CPU verification being especially time-intensive and labour-consuming. Industrial practice relies on differential testing for CPU verification, yet faces bottlenecks at nearly each stage of the framework pipeline: front-end stimulus generation lacks micro-architectural awareness, yielding low-quality and redundant tests that impede coverage closure and miss corner cases. Meanwhile, back-end simulation infra…

Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders
Dohun Lee, Hyeonho Jeong, Jiwook Kim, Duygu Ceylan, Jong Chul Ye
https://arxiv.org/abs/2509.09547

Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders
Video diffusion models have advanced rapidly in the recent years as a result of series of architectural innovations (e.g., diffusion transformers) and use of novel training objectives (e.g., flow matching). In contrast, less attention has been paid to improving the feature representation power of such models. In this work, we show that training video diffusion models can benefit from aligning the intermediate features of the video generator with feature representations of pre-trained vision enc…

Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
Abdul Waheed, Chancharik Mitra, Laurie Z. Wang, Deva Ramanan, Bhiksha Raj
https://arxiv.org/abs/2509.05226

Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
Chain-of-thought reasoning, while powerful, can produce unnecessarily verbose output for simpler problems. We present a framework for difficulty-aware reasoning that teaches models to dynamically adjust reasoning depth based on problem complexity. Remarkably, we show that models can be endowed with such dynamic inference pathways without any architectural modifications; we simply post-train on data that is carefully curated to include chain-of-thought traces that are proportional in length to p…

Moody Urbanity - UP 🔝
情绪化城市 - 上面 🔝
📷 Nikon FE
🎞️ Ilford HP5 Plus 400, expired 1993
#filmphotography #Photography #blackandwhite

On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond
Chenxiao Yang, Cai Zhou, David Wipf, Zhiyuan Li
https://arxiv.org/abs/2510.06190 https://

On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond
This paper formally studies generation processes, including auto-regressive next-token prediction and masked diffusion, that abstract beyond architectural specifics. At this level of abstraction, we quantify their benefits and limitations through measurable criteria such as computational hardness and learnability. In particular, we demonstrate that allowing generation to proceed beyond autoregression and current masked diffusion, with capabilities to rewrite and length-variable edit, can bring …

Structured Cognition for Behavioral Intelligence in Large Language Model Agents: Preliminary Study
Myung Ho Kim
https://arxiv.org/abs/2510.05107 https://ar…

Structured Cognition for Behavioral Intelligence in Large Language Model Agents: Preliminary Study
Large language models have advanced natural language understanding and generation, yet their use as autonomous agents raises architectural challenges for multi-step tasks. Existing frameworks often intertwine inference, memory, and control in a single prompt, which can reduce coherence and predictability. The Structured Cognitive Loop (SCL) is introduced as an alternative architecture that separates these functions. In SCL, the language model is dedicated to inference, memory is maintained exte…

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
Kostiantyn Bevziuk, Andrii Fatula, Svetozar Lashin Yaroslav Opanasenko, Anna Tukhtarova, Ashok Jallepalli Pradeepkumar Sharma, Hritvik Shrivastava
https://arxiv.org/abs/2510.08876

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
We present a repository decomposition system that converts large software repositories into a vectorized knowledge graph which mirrors project architectural and semantic structure, capturing semantic relationships and allowing a significant level of automatization of further repository development. The graph encodes syntactic relations such as containment, implementation, references, calls, and inheritance, and augments nodes with LLM-derived summaries and vector embeddings. A hybrid retrieval …

On The Road - To Xi’An/Before & After 🌬️
在路上 - 去西安/之前之后🌬️
📷 Pentax MX
🎞️Lucky SHD 400
#filmphotography #Photography #blackandwhite

Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization
Lee Kezar, Zed Sehyr, Jesse Thomason
https://arxiv.org/abs/2509.04745 https://

Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization
Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but it has not been evaluated whether the learned units capture spurious correlations that hinder out-of-vocabulary performance. This work investigates two phonological inductive biases: Parameter Disentanglement, an architectural bias, and Phonological Semi-Sup…

RewardDance: Reward Scaling in Visual Generation
Jie Wu, Yu Gao, Zilyu Ye, Ming Li, Liang Li, Hanzhong Guo, Jie Liu, Zeyue Xue, Xiaoxia Hou, Wei Liu, Yan Zeng, Weilin Huang
https://arxiv.org/abs/2509.08826

RewardDance: Reward Scaling in Visual Generation
Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing approaches: CLIP-based RMs suffer from architectural and input modality constraints, while prevalent Bradley-Terry losses are fundamentally misaligned with the next-token prediction mechanism of Vision-Language Models (VLMs), hindering effective scaling. More critical…

When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
Arindam Chowdhury, Massimiliano Lupo Pasini
https://arxiv.org/abs/2510.05583 https://

When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
Graph neural networks (GNNs) are widely used as surrogates for costly experiments and first-principles simulations to study the behavior of compounds at atomistic scale, and their architectural complexity is constantly increasing to enable the modeling of complex physics. While most recent GNNs combine more traditional message passing neural networks (MPNNs) layers to model short-range interactions with more advanced graph transformers (GTs) with global attention mechanisms to model long-range …

Peek 🔲
窥 🔲
📷 Pentax MX
🎞️Ilford FP4 Plus, expired 1994
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Architectural Degradation: Definition, Motivations, Measurement and Remediation Approaches
Noman Ahmad, Ruoyu Su, Matteo Esposito, Andrea Janes, Valentina Lenarduzzi, Davide Taibi
https://arxiv.org/abs/2507.14547

Architectural Degradation: Definition, Motivations, Measurement and Remediation Approaches
Architectural degradation, also known as erosion, decay, or aging, impacts system quality, maintainability, and adaptability. Although widely acknowledged, current literature shows fragmented definitions, metrics, and remediation strategies. Our study aims to unify understanding of architectural degradation by identifying its definitions, causes, metrics, tools, and remediation approaches across academic and gray literature. We conducted a multivocal literature review of 108 studies extracting …

Architectural Transformations and Emerging Verification Demands in AI-Enabled Cyber-Physical Systems
Hadiza Umar Yusuf, Khouloud Gaaloul
https://arxiv.org/abs/2510.00519 https:/…

Architectural Transformations and Emerging Verification Demands in AI-Enabled Cyber-Physical Systems
In the world of Cyber-Physical Systems (CPS), a captivating real-time fusion occurs where digital technology meets the physical world. This synergy has been significantly transformed by the integration of artificial intelligence (AI), a move that dramatically enhances system adaptability and introduces a layer of complexity that impacts CPS control optimization and reliability. Despite advancements in AI integration, a significant gap remains in understanding how this shift affects CPS architec…

A Near-Cache Architectural Framework for Cryptographic Computing
Jingyao Zhang, Elaheh Sadredini
https://arxiv.org/abs/2509.23179 https://arxiv.org/pdf/250…

A Near-Cache Architectural Framework for Cryptographic Computing
Recent advancements in post-quantum cryptographic algorithms have led to their standardization by the National Institute of Standards and Technology (NIST) to safeguard information security in the post-quantum era. These algorithms, however, employ public keys and signatures that are 3 to 9$\times$ longer than those used in pre-quantum cryptography, resulting in significant performance and energy efficiency overheads. A critical bottleneck identified in our analysis is the cache bandwidth. This…

City Features 🌆
城市特征 🌆
📷 Pentax MX
🎞️Ilford FP4 Plus, expired 1994
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Moody Urbanity - UP ⬆️
情绪化城市 - 上面 ⬆️
📷 Nikon FE
🎞️ Ilford HP5 Plus 400, expired 1993
#filmphotography #Photography #blackandwhite

On The Road - To Xi’An ⛑️
在路上 - 去西安 ⛑️
📷 Pentax MX
🎞️Lucky SHD 400
#filmphotography #Photography #blackandwhite