Tootfinder

$\pi^3$: Scalable Permutation-Equivariant Visual Geometry Learning
Yifan Wang, Jianjun Zhou, Haoyi Zhu, Wenzheng Chang, Yang Zhou, Zizun Li, Junyi Chen, Jiangmiao Pang, Chunhua Shen, Tong He
https://arxiv.org/abs/2507.13347

$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning
We introduce $π^3$, a feed-forward neural network that offers a novel approach to visual geometry reconstruction, breaking the reliance on a conventional fixed reference view. Previous methods often anchor their reconstructions to a designated viewpoint, an inductive bias that can lead to instability and failures if the reference is suboptimal. In contrast, $π^3$ employs a fully permutation-equivariant architecture to predict affine-invariant camera poses and scale-invariant local point maps …

Patent Language Model Pretraining with ModernBERT
Amirhossein Yousefiramandi, Ciaran Cooney
https://arxiv.org/abs/2509.14926 https://arxiv.org/pdf/2509.149…

Patent Language Model Pretraining with ModernBERT
Transformer-based language models such as BERT have become foundational in NLP, yet their performance degrades in specialized domains like patents, which contain long, technical, and legally structured text. Prior approaches to patent NLP have primarily relied on fine-tuning general-purpose models or domain-adapted variants pretrained with limited data. In this work, we pretrain 3 domain-specific masked language models for patents, using the ModernBERT architecture and a curated corpus of over …

Threat Modeling for Enhancing Security of IoT Audio Classification Devices under a Secure Protocols Framework
Sergio Benlloch-Lopez, Miquel Viel-Vazquez, Javier Naranjo-Alcazar, Jordi Grau-Haro, Pedro Zuccarello
https://arxiv.org/abs/2509.14657

Threat Modeling for Enhancing Security of IoT Audio Classification Devices under a Secure Protocols Framework
The rapid proliferation of IoT nodes equipped with microphones and capable of performing on-device audio classification exposes highly sensitive data while operating under tight resource constraints. To protect against this, we present a defence-in-depth architecture comprising a security protocol that treats the edge device, cellular network and cloud backend as three separate trust domains, linked by TPM-based remote attestation and mutually authenticated TLS 1.3. A STRIDE-driven threat model…

Scaling Wideband Massive MIMO Radar via Beamspace Dimension Reduction
Oveys Delafrooz Noroozi, Jiyoon Han, Wei Tang, Zhengya Zhang, Upamanyu Madhow
https://arxiv.org/abs/2508.11790

Scaling Wideband Massive MIMO Radar via Beamspace Dimension Reduction
We present an architecture for scaling digital beamforming for wideband massive MIMO radar. Conventional spatial processing becomes computationally prohibitive as array size grows; for example, the computational complexity of MVDR beamforming scales as O(N^3) for an N-element array. In this paper, we show that energy concentration in beamspace provides the basis for drastic complexity reduction, with array scaling governed by the O(NlogN) complexity of the spatial FFT used for beamspace transfo…

Entanglement architecture of beyond-Landau quantum criticality
Menghan Song, Ting-Tung Wang, Liuke Lyu, William Witczak-Krempa, Zi Yang Meng
https://arxiv.org/abs/2509.09983 htt…

Entanglement architecture of beyond-Landau quantum criticality
Quantum critical points beyond the Landau paradigm exhibit fractionalized excitations and emergent gauge fields. Here, we use entanglement microscopy--full tomography of the reduced density matrix of small subregions and subsequent extraction of their quantum correlations--to resolve the entanglement architecture near such exotic critical points. We focus on genuine multipartite entanglement (GME). Through unbiased quantum Monte Carlo sampling of RDMs across conventional O(2)/O(3) Wilson-Fisher…

CLAIRE: A Dual Encoder Network with RIFT Loss and Phi-3 Small Language Model Based Interpretability for Cross-Modality Synthetic Aperture Radar and Optical Land Cover Segmentation
Debopom Sutradhar, Arefin Ittesafun Abian, Mohaimenul Azam Khan Raiaan, Reem E. Mohamed, Sheikh Izzal Azid, Sami Azam
https://arxiv.org/abs/2509.11952

CLAIRE: A Dual Encoder Network with RIFT Loss and Phi-3 Small Language Model Based Interpretability for Cross-Modality Synthetic Aperture Radar and Optical Land Cover Segmentation
Accurate land cover classification from satellite imagery is crucial in environmental monitoring and sustainable resource management. However, it remains challenging due to the complexity of natural landscapes, the visual similarity between classes, and the significant class imbalance in the available datasets. To address these issues, we propose a dual encoder architecture that independently extracts modality-specific features from optical and Synthetic Aperture Radar (SAR) imagery, which are …

Programmable Optical Filters Based on Feed-Forward Photonic Meshes
Carson G. Valdez, Anne R. Kroo, Marek Vlk, Charles Roques-Carmes, Shanhui Fan, David A. B. Miller, Olav Solgaard
https://arxiv.org/abs/2509.12059

Programmable Optical Filters Based on Feed-Forward Photonic Meshes
We demonstrate an integrated photonic circuit based on feed forward photonic meshes that can be programmed and reconfigured to perform arbitrary spectral filter functions. We investigate a subset of the available filter functions, demonstrating that a N = 4 input triangular mesh with M = 3 layers may be operated via self-configuration algorithms to filter M arbitrary wavelengths from a given input spectrum. The tunable nature of the architecture enables preconfigured filter functions to be swep…

Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents
Rajesh Tembarai Krishnamachari, Srividya Rajesh
https://arxiv.org/abs/2509.04979 https:…

Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents
AI agents -- powered by reasoning-capable large language models (LLMs) and integrated with tools, data, and web search -- are poised to transform the internet into a \emph{Web of Agents}: a machine-native ecosystem where autonomous agents interact, collaborate, and execute tasks at scale. Realizing this vision requires \emph{Agent Ranking} -- selecting agents not only by declared capabilities but by proven, recent performance. Unlike Web~1.0's PageRank, a global, transparent network of agent in…

Salesforce launches Agentforce 3 with an observability tool called Command Center and MCP support, and says 8,000 customers have signed up to deploy Agentforce (Larry Dignan/Constellation Research)
https://www.constellationr.com/blog-news/i

Salesforce launches Agentforce 3, Command Center for visibility
Salesforce launched Agentforce 3, which features Agentforce Command Center, support for Model Context Protocol (MCP), and updated Atlas architecture to speed up reasoning and performance. The rollout maintains Salesforce's Agentforce cadence, which includes updates every few months as the company learns from enterprise use cases. In addition, Salesforce has added more than 30 partners to AgentExchange including AWS, Box, Cisco, Google Cloud, IBM and payments players such as PayPal and Stripe.

CI/CD #Pipeline #Architecture: Complete Guide to Building Robust CI and CD Pipelines
https://

Series B, Episode 03 - Weapon
AVON: Auron may be different, Cally, but on Earth it is considered ill-mannered to kill your friends while committing suicide.
GAN: Why that base, Cally?
https://blake.torpidity.net/m/203/31 B7B3

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/4]:
- MedicalPatchNet: A Patch-Based Self-Explainable AI Architecture for Chest X-ray Classification
Patrick Wienholt, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn

The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data
Petteri Teikari, Mike Jarrell, Maryam Azh, Harri Pesola
https://arxiv.org/abs/2508.02765

The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data
The Uniform Appraisal Dataset (UAD) 3.6's mandatory 2026 implementation transforms residential property valuation from narrative reporting to structured, machine-readable formats. This paper provides the first comprehensive analysis of this regulatory shift alongside concurrent AI advances in computer vision, natural language processing, and autonomous systems. We develop a three-layer framework for AI-augmented valuation addressing technical implementation and institutional trust requirements.…

A small and interesting architecture for early fault-tolerant quantum computers
Jacob S. Nelson, Andrew J. Landahl, Andrew D. Baczewski
https://arxiv.org/abs/2507.20387 https://…

A small and interesting architecture for early fault-tolerant quantum computers
We present an architecture for early fault-tolerant quantum computers based on the smallest interesting colour code (Earl Campbell, 2016). It realizes a universal logical gate set consisting of single-qubit measurements and preparations in the X and Z bases, single- qubit Hadamard (H) gates, and three-qubit controlled-controlled-Z (CCZ) gates. State teleportations between [[4, 2, 2]] (2D) and [[8, 3, 2]] (3D) error-detecting color codes allow one to make use of the respective transversal H and …

Replaced article(s) found for cs.NI. https://arxiv.org/list/cs.NI/new
[1/1]:
- Performance Comparison of HTTP/3 and HTTP/2 with Proxy Integration
Fan Liu, Behrooz Farkiani, John Dehart, Jyoti Parwatikar, Patrick Crowley

Scaling Fabric-Based Piezoresistive Sensor Arrays for Whole-Body Tactile Sensing
Curtis C. Johnson, Daniel Webb, David Hill, Marc D. Killpack
https://arxiv.org/abs/2508.20959 ht…

Scaling Fabric-Based Piezoresistive Sensor Arrays for Whole-Body Tactile Sensing
Scaling tactile sensing for robust whole-body manipulation is a significant challenge, often limited by wiring complexity, data throughput, and system reliability. This paper presents a complete architecture designed to overcome these barriers. Our approach pairs open-source, fabric-based sensors with custom readout electronics that reduce signal crosstalk to less than 3.3% through hardware-based mitigation. Critically, we introduce a novel, daisy-chained SPI bus topology that avoids the practi…

E2ATST: A Temporal-Spatial Optimized Energy-Efficient Architecture for Training Spiking Transformer
Yunhao Ma, Yanyu Lin, Mingjing Li, Puli Quan, Chenlin Zhou, Wenyue Zhang, Zhiwei Zhong, Wanyi Jia, Xueke Zhu, Qingyan Meng, Huihui Zhou, Fengwei An
https://arxiv.org/abs/2508.00475

E2ATST: A Temporal-Spatial Optimized Energy-Efficient Architecture for Training Spiking Transformer
(1) Pengcheng Laboratory, (2) Southern University of Science and Technology, (3) Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, (4) University of Chinese Academy of Sciences

Suggest, Complement, Inspire: Story of Two Tower Recommendations at Allegro.com
Aleksandra Osowska-Kurczab, Klaudia Nazarko, Mateusz Marzec, Lidia Wojciechowska, Eli\v{s}ka Kreme\v{n}ov\'a
https://arxiv.org/abs/2508.03702

Suggest, Complement, Inspire: Story of Two Tower Recommendations at Allegro.com
Building large-scale e-commerce recommendation systems requires addressing three key technical challenges: (1) designing a universal recommendation architecture across dozens of placements, (2) decreasing excessive maintenance costs, and (3) managing a highly dynamic product catalogue. This paper presents a unified content-based recommendation system deployed at Allegro.com, the largest e-commerce platform of European origin. The system is built on a prevalent Two Tower retrieval framework, rep…

Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture
Bochen Han, Songmao Zhang
https://arxiv.org/abs/2507.01701 https://

Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture
In this paper, we propose to incorporate the blackboard architecture into LLM multi-agent systems (MASs) so that (1) agents with various roles can share all the information and others' messages during the whole problem-solving process, (2) agents that will take actions are selected based on the current content of the blackboard, and (3) the selection and execution round is repeated until a consensus is reached on the blackboard. We develop the first implementation of this proposal and conduct e…

Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture
Anderson de Lima Luiz, Shubham Vijay Kurlekar, Munir Georges
https://arxiv.org/abs/2508.17814

Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture
This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic resource scheduling and seamless integration of containerized microservices have been leveraged herein to manage CPU, GPU, and memory allocations efficiently in multi-node clusters. Extensive experiments, using Llama 3.2 (1B and 3B parameters) [2] and Llama 3.1 …

Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
Junghwan Lim, Gangwon Jo, Sungmin Lee, Jiyoung Park, Dongseok Kim, Jihwan Kim, Junhyeok Lee, Wai Ting Cheung, Dahye Choi, Kibong Choi, Jaeyeon Huh, Beomgyu Kim, Jangwoong Kim, Taehyun Kim, Haesol Lee, Jeesoo Lee, Dongpin Oh, Changseok Song, Daewon Suh
https://

Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
We introduce Llama-3-Motif, a language model consisting of 102 billion parameters, specifically designed to enhance Korean capabilities while retaining strong performance in English. Developed on the Llama 3 architecture, Llama-3-Motif employs advanced training techniques, including LlamaPro and Masked Structure Growth, to effectively scale the model without altering its core Transformer architecture. Using the MoAI platform for efficient training across hyperscale GPU clusters, we optimized Ll…

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms
Tarek Gasmi, Ramzi Guesmi, Ines Belhadj, Jihene Bennaceur
https://arxiv.org/abs/2507.06323

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms
Large Language Model (LLM) agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function Calling architecture and Model Context Protocol (MCP) deployment paradigms using a unified threat classification framework. We tested 3,250 attack scenarios across seven language models, evaluating simple, composed, and chained attacks targeting both AI-specif…

MRI-Based Brain Tumor Detection through an Explainable EfficientNetV2 and MLP-Mixer-Attention Architecture
Mustafa Yurdakul, \c{S}akir Ta\c{s}demir
https://arxiv.org/abs/2509.06713

MRI-Based Brain Tumor Detection through an Explainable EfficientNetV2 and MLP-Mixer-Attention Architecture
Brain tumors are serious health problems that require early diagnosis due to their high mortality rates. Diagnosing tumors by examining Magnetic Resonance Imaging (MRI) images is a process that requires expertise and is prone to error. Therefore, the need for automated diagnosis systems is increasing day by day. In this context, a robust and explainable Deep Learning (DL) model for the classification of brain tumors is proposed. In this study, a publicly available Figshare dataset containing 3,…

DeepQuark: deep-neural-network approach to multiquark bound states
Wei-Lin Wu, Lu Meng, Shi-Lin Zhu
https://arxiv.org/abs/2506.20555 https://

DeepQuark: deep-neural-network approach to multiquark bound states
For the first time, we implement the deep-neural-network-based variational Monte Carlo approach for the multiquark bound states, whose complexity surpasses that of electron or nucleon systems due to strong SU(3) color interactions. We design a novel and high-efficiency architecture, DeepQuark, to address the unique challenges in multiquark systems such as stronger correlations, extra discrete quantum numbers, and intractable confinement interaction. Our method demonstrates competitive performan…

Cortex-Synth: Differentiable Topology-Aware 3D Skeleton Synthesis with Hierarchical Graph Attention
Mohamed Zayaan S
https://arxiv.org/abs/2509.06705 https://

Cortex-Synth: Differentiable Topology-Aware 3D Skeleton Synthesis with Hierarchical Graph Attention
We present Cortex Synth, a novel end-to-end differentiable framework for joint 3D skeleton geometry and topology synthesis from single 2D images. Our architecture introduces three key innovations: (1) A hierarchical graph attention mechanism with multi-scale skeletal refinement, (2) Differentiable spectral topology optimization via Laplacian eigen decomposition, and (3) Adversarial geometric consistency training for pose structure alignment. The framework integrates four synergistic modules: a …

A while ago, I've followed the example given by #Fedora and unbundled ensurepip wheels from #Python in #Gentoo (just checked — "a while ago" was 3 years ago). This had the important advantage that it enabled us to update these wheels along with the actual pip and setuptools packages, meaning new virtual environments would get fresh versions rather than whatever CPython happened to bundle at the time of release.
I had considered using our system packages to prepare these wheels, but since we were already unbundling dependencies back then, that couldn't work. So I just went with fetching upstream wheels from PyPI. Why not build them from source instead? Well, besides feeling unnecessary (it's not like the PyPI wheels are actually binary packages), we probably didn't have the right kind of eclass support for that at the time.
Inspired by @…, today I've tried preparing new revisions of ensurepip packages that actually do build everything from source. So what changed, and why should building from source matter now? Firstly, as part of the wheel reuse patches, we do have a reasonably clean architecture to grab the wheels created as part of the PEP517 build. Secondly, since we're unbundling dependencies from pip and setuptools, we're effectively testing different packages than these installed as ensurepip wheels — and so it would be meaningful to test both variants. Thirdly, building from source is going to make patching easier, and at the very least enable user patching.
While at it, I've refreshed the test suite runs in all three regular packages (pip, setuptools and wheel — we need an "ensurepip" wheel for the last because of test suites). And of course, I hit some test failures in testing the versions with bundled dependencies, and I've discovered a random bug in #PyPy.
https://github.com/gentoo/gentoo/pull/42882 (yes, we haven't moved yet)
https://github.com/pypy/pypy/issues/5306

Continuous operation of a coherent 3,000-qubit system
Neng-Chun Chiu, Elias C. Trapp, Jinen Guo, Mohamed H. Abobeih, Luke M. Stewart, Simon Hollerith, Pavel Stroganov, Marcin Kalinowski, Alexandra A. Geim, Simon J. Evered, Sophie H. Li, Lisa M. Peters, Dolev Bluvstein, Tout T. Wang, Markus Greiner, Vladan Vuleti\'c, Mikhail D. Lukin
https://

Continuous operation of a coherent 3,000-qubit system
Neutral atoms are a promising platform for quantum science, enabling advances in areas ranging from quantum simulations and computation to metrology, atomic clocks and quantum networking. While atom losses typically limit these systems to a pulsed mode, continuous operation could significantly enhance cycle rates, remove bottlenecks in metrology, and enable deep-circuit quantum evolution through quantum error correction. Here we demonstrate an experimental architecture for high-rate, continuous…

jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
Michael G\"unther, Saba Sturua, Mohammad Kalim Akram, Isabelle Mohr, Andrei Ungureanu, Sedigheh Eslami, Scott Martens, Bo Wang, Nan Wang, Han Xiao
https://arxiv.org/abs/2506.18902

jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
We introduce jina-embeddings-v4, a 3.8 billion parameter multimodal embedding model that unifies text and image representations through a novel architecture supporting both single-vector and multi-vector embeddings in the late interaction style. The model incorporates task-specific Low-Rank Adaptation (LoRA) adapters to optimize performance across diverse retrieval scenarios, including query-based information retrieval, cross-modal semantic similarity, and programming code search. Comprehensive…

Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection
Ali \c{S}enol, Garima Agrawal, Huan Liu
https://arxiv.org/abs/2506.21443 https://arxiv.org/pdf/2506.21443 https://arxiv.org/html/2506.21443
arXiv:2506.21443v1 Announce Type: new
Abstract: Detecting deceptive conversations on dynamic platforms is increasingly difficult due to evolving language patterns and Concept Drift (CD)\-i.e., semantic or topical shifts that alter the context or intent of interactions over time. These shifts can obscure malicious intent or mimic normal dialogue, making accurate classification challenging. While Large Language Models (LLMs) show strong performance in natural language tasks, they often struggle with contextual ambiguity and hallucinations in risk\-sensitive scenarios. To address these challenges, we present a Domain Knowledge (DK)\-Enhanced LLM framework that integrates pretrained LLMs with structured, task\-specific insights to perform fraud and concept drift detection. The proposed architecture consists of three main components: (1) a DK\-LLM module to detect fake or deceptive conversations; (2) a drift detection unit (OCDD) to determine whether a semantic shift has occurred; and (3) a second DK\-LLM module to classify the drift as either benign or fraudulent. We first validate the value of domain knowledge using a fake review dataset and then apply our full framework to SEConvo, a multiturn dialogue dataset that includes various types of fraud and spam attacks. Results show that our system detects fake conversations with high accuracy and effectively classifies the nature of drift. Guided by structured prompts, the LLaMA\-based implementation achieves 98\% classification accuracy. Comparative studies against zero\-shot baselines demonstrate that incorporating domain knowledge and drift awareness significantly improves performance, interpretability, and robustness in high\-stakes NLP applications.
toXiv_bot_toot

RadProPoser: A Framework for Human Pose Estimation with Uncertainty Quantification from Raw Radar Data
Jonas Leo Mueller, Lukas Engel, Eva Dorschky, Daniel Krauss, Ingrid Ullmann, Martin Vossiek, Bjoern M. Eskofier
https://arxiv.org/abs/2508.03578

RadProPoser: A Framework for Human Pose Estimation with Uncertainty Quantification from Raw Radar Data
Radar-based human pose estimation (HPE) provides a privacy-preserving, illumination-invariant sensing modality but is challenged by noisy, multipath-affected measurements. We introduce RadProPoser, a probabilistic encoder-decoder architecture that processes complex-valued radar tensors from a compact 3-transmitter, 4-receiver MIMO radar. By incorporating variational inference into keypoint regression, RadProPoser jointly predicts 26 three-dimensional joint locations alongside heteroscedastic al…

Supernova: Achieving More with Less in Transformer Architectures
Andrei-Valentin Tanase, Elena Pelican
https://arxiv.org/abs/2507.15773 https://

Supernova: Achieving More with Less in Transformer Architectures
We present Supernova, a 650M-parameter decoder-only transformer that demonstrates how careful architectural design and tokenization innovation can achieve the performance of larger models while maintaining computational efficiency. Our architecture combines Rotary Positional Embeddings (RoPE), Grouped Query Attention (GQA) with a 3:1 compression ratio, RMSNorm for computational efficiency, and SwiGLU activation functions. A critical innovation is our custom 128,000-vocabulary byte-level BPE tok…