Tootfinder

Distributed AI Agents for Cognitive Underwater Robot Autonomy
Markus Buchholz, Ignacio Carlucho, Michele Grimaldi, Yvan R. Petillot
https://arxiv.org/abs/2507.23735 https://

Distributed AI Agents for Cognitive Underwater Robot Autonomy
Achieving robust cognitive autonomy in robots navigating complex, unpredictable environments remains a fundamental challenge in robotics. This paper presents Underwater Robot Self-Organizing Autonomy (UROSA), a groundbreaking architecture leveraging distributed Large Language Model AI agents integrated within the Robot Operating System 2 (ROS 2) framework to enable advanced cognitive capabilities in Autonomous Underwater Vehicles. UROSA decentralises cognition into specialised AI agents respons…

DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation
Bla\v{z} \v{S}krlj, Yonatan Karni, Grega Ga\v{s}per\v{s}i\v{c}, Bla\v{z} Mramor, Yulia Stolin, Martin Jakomin, Jasna Urban\v{c}i\v{c}, Yuval Dishi, Natalia Silberstein, Ophir Friedler, Assaf Klein
https://arxiv.org/abs/2506.21…

DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation
The Deep and Cross architecture (DCNv2) is a robust production baseline and is integral to numerous real-life recommender systems. Its inherent efficiency and ability to model interactions often result in models that are both simpler and highly competitive compared to more computationally demanding alternatives, such as Deep FFMs. In this work, we introduce three significant algorithmic improvements to the DCNv2 architecture, detailing their formulation and behavior at scale. The enhanced archi…

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 …

Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN
Abdelaziz Salama, Zeinab Nezami, Mohammed M. H. Qazzaz, Maryam Hafeez, Syed Ali Raza Zaidi
https://arxiv.org/abs/2507.21696

Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN
The deployment of AI agents within legacy Radio Access Network (RAN) infrastructure poses significant safety and reliability challenges for future 6G networks. This paper presents a novel Edge AI framework for autonomous network optimisation in Open RAN environments, addressing these challenges through three core innovations: (1) a persona-based multi-tools architecture enabling distributed, context-aware decision-making; (2) proactive anomaly detection agent powered by traffic predictive tool;…

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

Mix-of-Language-Experts Architecture for Multilingual Programming
Yifan Zong, Yuntian Deng, Pengyu Nie
https://arxiv.org/abs/2506.18923 https://

Mix-of-Language-Experts Architecture for Multilingual Programming
Large language models (LLMs) have demonstrated impressive capabilities in aiding developers with tasks like code comprehension, generation, and translation. Supporting multilingual programming -- i.e., coding tasks across multiple programming languages -- typically requires either (1) finetuning a single LLM across all programming languages, which is cost-efficient but sacrifices language-specific specialization and performance, or (2) finetuning separate LLMs for each programming language, whi…

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…

PyG 2.0: Scalable Learning on Real World Graphs
Matthias Fey, Jinu Sunil, Akihiro Nitta, Rishi Puri, Manan Shah, Bla\v{z} Stojanovi\v{c}, Ramona Bendias, Alexandria Barghi, Vid Kocijan, Zecheng Zhang, Xinwei He, Jan Eric Lenssen, Jure Leskovec
https://arxiv.org/abs/2507.16991

PyG 2.0: Scalable Learning on Real World Graphs
PyG (PyTorch Geometric) has evolved significantly since its initial release, establishing itself as a leading framework for Graph Neural Networks. In this paper, we present Pyg 2.0 (and its subsequent minor versions), a comprehensive update that introduces substantial improvements in scalability and real-world application capabilities. We detail the framework's enhanced architecture, including support for heterogeneous and temporal graphs, scalable feature/graph stores, and various optimization…

Replaced article(s) found for cs.NI. https://arxiv.org/list/cs.NI/new
[1/1]:
- Towards Constraint-aware Learning for Resource Allocation in NFV Networks
Tianfu Wang, Long Yang, Chao Wang, Chuan Qin, Liwei Deng, Wei Wu, Junyang Wang, Li Shen, Hui Xiong

A Compact 16-bit S-box over Tower Field $\F_{(((2^2)^2)^2)^2}$ with High Security
Bahram Rashidi, Behrooz Khadem
https://arxiv.org/abs/2507.01423 https://

A Compact 16-bit S-box over Tower Field $\F_{(((2^2)^2)^2)^2}$ with High Security
This paper introduces a compact and secure 16-bit substitution box (S-box) designed over the composite field $\F_{(((2^2)^2)^2)^2}$, optimized for both hardware efficiency and cryptographic robustness. The proposed S-box decomposes operations into subfields, leveraging a tower field architecture. This enables significant hardware reduction through optimized field inversion and a low-cost affine transformation. Security evaluations confirm resilience against linear, differential, algebraic and D…

Replaced article(s) found for cs.AR. https://arxiv.org/list/cs.AR/new
[1/1]:
- LLM-Aided Testbench Generation and Bug Detection for Finite-State Machines
Jitendra Bhandari, Johann Knechtel, Ramesh Narayanaswamy, Siddharth Garg, Ramesh Karri

How cool is this? #music #art
https://www.instagram.com/reel/DL3CAxCPgxy/?igsh=MTJ…

Interior Design & Architecture on Instagram: "Step into a world where sound floats, time slows down, and art breathes on its own. In the heart of the Bourse de Commerce, artist Céleste Boursier-Mougenot invites us to experience clinamen—an immersive aquatic installation where porcelain bowls drift gently in an 18-meter pool, creating an ever-changing, accidental symphony without human touch. Inspired by the Epicurean theory of atoms veering off course, this piece blurs the boundaries between matter and meaning, silence and sound, presence and perception. It’s not just art—it’s a living poem in motion. Let yourself be still. Listen deeply. 📍Bourse de Commerce - Pinault Collection 📷 @elisabarg @boursedecommerce @celesteboursiermougenot"
126K likes, 377 comments - d.signers on July 8, 2025: "Step into a world where sound floats, time slows down, and art breathes on its own. In the heart of the Bourse de Commerce, artist Céleste Boursier-Mougenot invites us to experience clinamen—an immersive aquatic installation where porcelain bowls drift gently in an 18-meter pool, creating an ever-changing, accidental symphony without human touch. Inspired by the Epicurean theory of atoms veering off course, this piece blurs the bounda…

Upcoming GÉANT infoshare - Part 2 🚀
🔐 Quantum KMS Architectures and Services
This session will explore the key aspects of Key Management Systems (KMS) in enabling secure, scalable Quantum Key Distribution. Gain insights on architecture, standardisation, and integration—from both research and industry voices.
🔗 Sign up here: https://

Infoshare: Quantum KMS Architectures and Services
The infoshare will focus on the aspects of Key Management Systems (KMS) for Quantum Key Distribution systems. KMS is a crucial component that allows to build, manage, scale QKD networks, define the interfaces for key delivery. The presentations will show KMS architectures, standardization, integration examples and strategies. KMS technologies are integral part of EuroQCI infrastructure and interconnectivity. The presentations will be provided by research institutions and also companies.The...

If you are a vendor or developer for #macOS who has not yet moved to Universal 2 or ship a product only for the x86_64 architecture, there is extremely straight forward guidance for you here to update your product ASAP
#Apple #WWDC25
https://developer.apple.com/documentation/apple-silicon/about-the-rosetta-translation-environment

Replaced article(s) found for quant-ph. https://arxiv.org/list/quant-ph/new
[2/2]:
- Information-acquiring von Neumann architecture of a computer: Functionality and subjectivity
Eiji Konishi

Causal Graph Fuzzy LLMs: A First Introduction and Applications in Time Series Forecasting
Omid Orang, Patricia O. Lucas, Gabriel I. F. Paiva, Petronio C. L. Silva, Felipe Augusto Rocha da Silva, Adriano Alonso Veloso, Frederico Gadelha Guimaraes
https://arxiv.org/abs/2507.17016

Causal Graph Fuzzy LLMs: A First Introduction and Applications in Time Series Forecasting
In recent years, the application of Large Language Models (LLMs) to time series forecasting (TSF) has garnered significant attention among researchers. This study presents a new frame of LLMs named CGF-LLM using GPT-2 combined with fuzzy time series (FTS) and causal graph to predict multivariate time series, marking the first such architecture in the literature. The key objective is to convert numerical time series into interpretable forms through the parallel application of fuzzification and c…

Feasibility Study of CNNs and MLPs for Radiation Heat Transfer in 2-D Furnaces with Spectrally Participative Gases
Axel TahmasebiMoradi, Vincent Ren, Benjamin Le-Creurer, Chetra Mang
https://arxiv.org/abs/2506.08033

Feasibility Study of CNNs and MLPs for Radiation Heat Transfer in 2-D Furnaces with Spectrally Participative Gases
Aiming to reduce the computational cost of numerical simulations, a convolutional neural network (CNN) and a multi-layer perceptron (MLP) are introduced to build a surrogate model to approximate radiative heat transfer solutions in a 2-D walled domain with participative gases. The originality of this work lays in the adaptation of the inputs of the problem (gas and wall properties) in order to fit with the CNN architecture, more commonly used for image processing. Two precision datasets have be…

TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
Sizhen Bian, Mengxi Liu, Vitor Fortes Rey, Daniel Geissler, Paul Lukowicz
https://arxiv.org/abs/2507.07949

TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
Human Activity Recognition (HAR) on resource-constrained wearable devices demands inference models that harmonize accuracy with computational efficiency. This paper introduces TinierHAR, an ultra-lightweight deep learning architecture that synergizes residual depthwise separable convolutions, gated recurrent units (GRUs), and temporal aggregation to achieve SOTA efficiency without compromising performance. Evaluated across 14 public HAR datasets, TinierHAR reduces Parameters by 2.7x (vs. TinyHA…

GCC: A 3DGS Inference Architecture with Gaussian-Wise and Cross-Stage Conditional Processing
Minnan Pei, Gang Li, Junwen Si, Zeyu Zhu, Zitao Mo, Peisong Wang, Zhuoran Song, Xiaoyao Liang, Jian Cheng
https://arxiv.org/abs/2507.15300

GCC: A 3DGS Inference Architecture with Gaussian-Wise and Cross-Stage Conditional Processing
3D Gaussian Splatting (3DGS) has emerged as a leading neural rendering technique for high-fidelity view synthesis, prompting the development of dedicated 3DGS accelerators for mobile applications. Through in-depth analysis, we identify two major limitations in the conventional decoupled preprocessing-rendering dataflow adopted by existing accelerators: 1) a significant portion of preprocessed Gaussians are not used in rendering, and 2) the same Gaussian gets repeatedly loaded across different t…

Towards Scalable AASIST: Refining Graph Attention for Speech Deepfake Detection
Ivan Viakhirev, Daniil Sirota, Aleksandr Smirnov, Kirill Borodin
https://arxiv.org/abs/2507.11777

Towards Scalable AASIST: Refining Graph Attention for Speech Deepfake Detection
Advances in voice conversion and text-to-speech synthesis have made automatic speaker verification (ASV) systems more susceptible to spoofing attacks. This work explores modest refinements to the AASIST anti-spoofing architecture. It incorporates a frozen Wav2Vec 2.0 encoder to retain self-supervised speech representations in limited-data settings, substitutes the original graph attention block with a standardized multi-head attention module using heterogeneous query projections, and replaces h…

Replaced article(s) found for cs.NI. https://arxiv.org/list/cs.NI/new
[1/1]:
- Semantic-Aware Resource Allocation Based on Deep Reinforcement Learning for 5G-V2X HetNets
Zhiyu Shao, Qiong Wu, Pingyi Fan, Nan Cheng, Qiang Fan, Jiangzhou Wang

Fast and Interactive Byzantine Fault-tolerant Web Services via Session-Based Consensus Decoupling
Ahmad Zaki Akmal, Azkario Rizky Pratama, Guntur Dharma Putra
https://arxiv.org/abs/2507.08281

Fast and Interactive Byzantine Fault-tolerant Web Services via Session-Based Consensus Decoupling
Byzantine fault-tolerant (BFT) web services provide critical integrity guarantees for distributed applications but face significant latency challenges that hinder interactive user experiences. We propose a novel two-layer architecture that addresses this fundamental tension between security and responsiveness in BFT systems. Our approach introduces a session-aware transaction buffer layer (Layer 2) that delivers immediate feedback to users through consensus simulation, while periodically commit…

This https://arxiv.org/abs/2505.24799 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images
Super-resolution aims to increase the resolution of satellite images by reconstructing high-frequency details, which go beyond naïve upsampling. This has particular relevance for Earth observation missions like Sentinel-2, which offer frequent, regular coverage at no cost; but at coarse resolution. Its pixel footprint is too large to capture small features like houses, streets, or hedge rows. To address this, we present SEN4X, a hybrid super-resolution architecture that combines the advantages…

Investigating the Potential of Large Language Model-Based Router Multi-Agent Architectures for Foundation Design Automation: A Task Classification and Expert Selection Study
Sompote Youwai, David Phim, Vianne Gayl Murcia, Rianne Clair Onas
https://arxiv.org/abs/2506.13811

Investigating the Potential of Large Language Model-Based Router Multi-Agent Architectures for Foundation Design Automation: A Task Classification and Expert Selection Study
This study investigates router-based multi-agent systems for automating foundation design calculations through intelligent task classification and expert selection. Three approaches were evaluated: single-agent processing, multi-agent designer-checker architecture, and router-based expert selection. Performance assessment utilized baseline models including DeepSeek R1, ChatGPT 4 Turbo, Grok 3, and Gemini 2.5 Pro across shallow foundation and pile design scenarios. The router-based configuration…

Design and optimization of neural networks for multifidelity cosmological emulation
Yanhui Yang, Simeon Bird, Ming-Feng Ho, Mahdi Qezlou
https://arxiv.org/abs/2507.07184

Design and optimization of neural networks for multifidelity cosmological emulation
Accurate and efficient simulation-based emulators are essential for interpreting cosmological survey data down to nonlinear scales. Multifidelity emulation techniques reduce simulation costs by combining high- and low-fidelity data, but traditional regression methods such as Gaussian processes struggle with scalability in sample size and dimensionality. In this work, we present T2N-MusE, a neural network framework characterized by (i) a novel 2-step multifidelity architecture, (ii) a 2-stage Ba…

BenchRL-QAS: Benchmarking reinforcement learning algorithms for quantum architecture search
Azhar Ikhtiarudin, Aditi Das, Param Thakkar, Akash Kundu
https://arxiv.org/abs/2507.12189

BenchRL-QAS: Benchmarking reinforcement learning algorithms for quantum architecture search
We introduce BenchRL-QAS, a unified benchmarking framework for systematically evaluating reinforcement learning (RL) algorithms in quantum architecture search (QAS) across diverse variational quantum algorithm tasks and system sizes ranging from 2- to 8-qubit. Our study benchmarks nine RL agents including both value-based and policy-gradient methods on representative quantum problems such as variational quantum eigensolver, variational quantum state diagonalization, quantum classification, and …

Replaced article(s) found for cs.RO. https://arxiv.org/list/cs.RO/new
[1/2]:
- Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability throu...
Fern\'andez-Becerra, Gonz\'alez-Santamarta, Guerrero-Higueras, Rodr\'iguez-Lera, Olivera…

STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support
Chenqi Zhang, Yu Feng, Jieru Zhao, Guangda Liu, Wenchao Ding, Chentao Wu, Minyi Guo
https://arxiv.org/abs/2506.09070

STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support
3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices, achieving only 2 to 9 FPS.Existing accelerators focus on compute efficiency but overlook memory efficiency, leading to redundant DRAM traffic. We introduce STREAMINGGS, a fully streaming 3DGS algorithm-architecture co-design that achieves fine-grained pipelin…

This https://arxiv.org/abs/2503.03913 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Proton Flows, Proton Gradients and Subcellular Architecture in Biological Energy Conversion
Hydrogen cations, or protons, provide the medium by which energy is stored and converted in biological systems. Such pre-eminence relies on the interplay between interfacial and bulk chemical transformations, according to mechanisms that are shared by organisms in all phyla of life. The present work provides an introduction to the fundamental aspects of biological energy management by focusing on the relationship between vectorial proton flows and the geometry of energy producing organelles in …

A Simple and Novel Passive Double-Sensitivity Optical Gyroscope Based on Non-Reciprocal Polarization Techniques
Onder Akcaalan, Melike Gumus Akcaalan
https://arxiv.org/abs/2506.03498

A Simple and Novel Passive Double-Sensitivity Optical Gyroscope Based on Non-Reciprocal Polarization Techniques
This paper presents a novel interferometric fiber optic gyroscope (IFOG) architecture, the Double-Sensitive Non-Reciprocal Polarization Phase Shifter IFOG (DS-NRPPS-IFOG), which introduces for the first time a fully passive phase biasing scheme capable of simultaneous operation at two quadrature points $π/2$ and $3π/2$. Building upon prior passive biasing techniques, this design uses a Non-Reciprocal Polarization-Dependent Phase Shifter (NRPPS) combined with a double-pass sensing coil arrange…

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Ziyue Li, Yang Li, Tianyi Zhou
https://arxiv.org/abs/2507.07996 https://arxiv.org/pdf/2507.07996 https://arxiv.org/html/2507.07996
arXiv:2507.07996v1 Announce Type: new
Abstract: Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tasks? We found that the layers of a pretrained large language model (LLM) can be manipulated as separate modules to build a better and even shallower model customized for each test sample. In particular, each layer from the pretrained model can be skipped/pruned or repeated multiple times as recurrent neural networks (RNN), and stacked with others in arbitrary orders, yielding a chain-of-layers (CoLa) per sample. This compositional space greatly expands the scope of existing works on looped/recurrent pretrained modules, layer pruning, or early-exit networks. We develop a Monte Carlo Tree Search (MCTS) protocol to explore and identify the optimal CoLa for each sample from math and commonsense reasoning benchmarks. Compared to a static model of a fixed depth, CoLa allows shortcut paths (fast thinking), recurrence of the same layer(s) (slow thinking), and combining both, offering more flexible, dynamic architectures for different inputs. We conduct an extensive analysis of the MCTS-optimized CoLa, which leads to two key findings: (1) For >75% of samples with correct predictions by the original LLM, we can find shorter CoLa, suggesting a large space for improving inference efficiency; (2) For >60% of samples with originally incorrect predictions, we can identify CoLa achieving correct predictions, suggesting a large space of performance enhancement. Our results highlight the shortcomings of using a fixed architecture of pre-trained LLMs for inference on different samples and pave the way to unlock the generalization power of test-time depth adaptation.
toXiv_bot_toot

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…

Special-Unitary Parameterization for Trainable Variational Quantum Circuits
Kuan-Cheng Chen, Huan-Hsin Tseng, Samuel Yen-Chi Chen, Chen-Yu Liu, Kin K. Leung
https://arxiv.org/abs/2507.05535

Special-Unitary Parameterization for Trainable Variational Quantum Circuits
We propose SUN-VQC, a variational-circuit architecture whose elementary layers are single exponentials of a symmetry-restricted Lie subgroup, $\mathrm{SU}(2^{k}) \subset \mathrm{SU}(2^{n})$ with $k \ll n$. Confining the evolution to this compact subspace reduces the dynamical Lie-algebra dimension from $\mathcal{O}(4^{n})$ to $\mathcal{O}(4^{k})$, ensuring only polynomial suppression of gradient variance and circumventing barren plateaus that plague hardware-efficient ansätze. Exact, hardware-…

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…

Intelligent System of Emergent Knowledge: A Coordination Fabric for Billions of Minds
Moshi Wei, Sparks Li
https://arxiv.org/abs/2506.09335 https://…

Intelligent System of Emergent Knowledge: A Coordination Fabric for Billions of Minds
The Intelligent System of Emergent Knowledge (ISEK) establishes a decentralized network where human and artificial intelligence agents collaborate as peers, forming a self-organizing cognitive ecosystem. Built on Web3 infrastructure, ISEK combines three fundamental principles: (1) a decentralized multi-agent architecture resistant to censorship, (2) symbiotic AI-human collaboration with equal participation rights, and (3) resilient self-adaptation through distributed consensus mechanisms. The…

DeepCHART: Mapping the 3D dark matter density field from Ly$\alpha$ forest surveys using deep learning
Soumak Maitra (TIFR), Matteo Viel, Girish Kulkarni
https://arxiv.org/abs/2507.00135

DeepCHART: Mapping the 3D dark matter density field from Ly$α$ forest surveys using deep learning
We present DeepCHART (Deep learning for Cosmological Heterogeneity and Astrophysical Reconstruction via Tomography), a deep learning framework designed to reconstruct the three-dimensional dark matter density field at redshift $z=2.5$ from Ly$α$ forest spectra. Leveraging a 3D variational autoencoder with a U-Net architecture, DeepCHART performs fast, likelihood-free inference, accurately capturing the non-linear gravitational dynamics and baryonic processes embedded in cosmological hydrodynam…

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 …