Tootfinder

EU considering proposals to speed Russian gas phaseout by 1 year, Reuters reports: https://benborges.xyz/2025/07/25/eu-considering-proposals-to-speed.html

The new =COPILOT() function in #Microsoft #Excel enables users to easily leverage AI directly within their spreadsheets to quickly populate cells with data or analyze columns with #AI. For a 5min tutorial, v…

@… Like others have said: Generally at work you’re not the one who decides how the company communicates.
I use Slack because my clients use Slack. And I'm not in a position of leverage to dictate whether they should.

Text-Driven 3D Hand Motion Generation from Sign Language Data
L\'eore Bensabath, Mathis Petrovich, G\"ul Varol
https://arxiv.org/abs/2508.15902 https://

Text-Driven 3D Hand Motion Generation from Sign Language Data
Our goal is to train a generative model of 3D hand motions, conditioned on natural language descriptions specifying motion characteristics such as handshapes, locations, finger/hand/arm movements. To this end, we automatically build pairs of 3D hand motions and their associated textual labels with unprecedented scale. Specifically, we leverage a large-scale sign language video dataset, along with noisy pseudo-annotated sign categories, which we translate into hand motion descriptions via an LLM…

User Understanding of Privacy Permissions in Mobile Augmented Reality: Perceptions and Misconceptions
Viktorija Paneva, Verena Winterhalter, Franziska Augustinowski, Florian Alt
https://arxiv.org/abs/2506.20207

User Understanding of Privacy Permissions in Mobile Augmented Reality: Perceptions and Misconceptions
Mobile Augmented Reality (AR) applications leverage various sensors to provide immersive user experiences. However, their reliance on diverse data sources introduces significant privacy challenges. This paper investigates user perceptions and understanding of privacy permissions in mobile AR apps through an analysis of existing applications and an online survey of 120 participants. Findings reveal common misconceptions, including confusion about how permissions relate to specific AR functionali…

DriftMoE: A Mixture of Experts Approach to Handle Concept Drifts
Miguel Aspis, Sebasti\'an A. Cajas Ord\'onez, Andr\'es L. Su\'arez-Cetrulo, Ricardo Sim\'on Carbajo
https://arxiv.org/abs/2507.18464

DriftMoE: A Mixture of Experts Approach to Handle Concept Drifts
Learning from non-stationary data streams subject to concept drift requires models that can adapt on-the-fly while remaining resource-efficient. Existing adaptive ensemble methods often rely on coarse-grained adaptation mechanisms or simple voting schemes that fail to optimally leverage specialized knowledge. This paper introduces DriftMoE, an online Mixture-of-Experts (MoE) architecture that addresses these limitations through a novel co-training framework. DriftMoE features a compact neural r…

Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
Wanli Peng, Xin Chen, Hang Fu, XinYu He, Xue Yiming, Juan Wen
https://arxiv.org/abs/2506.19889

Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
Recent advances in large language models (LLMs) have made a profound impact on our society and also raised new security concerns. Particularly, due to the remarkable inference ability of LLMs, the privacy violation attack (PVA), revealed by Staab et al., introduces serious personal privacy issues. Existing defense methods mainly leverage LLMs to anonymize the input query, which requires costly inference time and cannot gain satisfactory defense performance. Moreover, directly rejecting the PVA …

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
Ran Wang, Xiaoxuan Liu, Hao Ren, Gang Chen, Fanchao Qi, Maosong Sun
https://arxiv.org/abs/2507.16768

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
Structured decoding enables large language models (LLMs) to generate outputs in formats required by downstream systems, such as HTML or JSON. However, existing methods suffer from efficiency bottlenecks due to grammar compilation, state tracking, and mask creation. We observe that many real-world tasks embed strong prior knowledge about output structure. Leveraging this, we propose a decomposition of constraints into static and dynamic components -- precompiling static structures offline and in…

Punchup Live, a ticketing and analytics platform for stand-up comedians, raised a $2.3M seed led by Social Leverage, and plans to expand into more live events (Matt Grobar/Deadline)
https://deadline.com/2025/06/punchup-live-raises-new-seed-round-1236439…

Stand-Up Ticketing Platform Punchup Live Raises $2.3 Million Seed Round
Punchup Live has raised a new $2.3 Million seed round that will allow the company to continue expanding its influence in comedy and beyond.

Optimizing Edge Gaming Slices through an Enhanced User Plane Function and Analytics in Beyond-5G Networks
Bruno Marques da Silva, Larissa Ferreira Rodrigues Moreira, Fl\'avio de Oliveira Silva, Rodrigo Moreira
https://arxiv.org/abs/2507.17843

Optimizing Edge Gaming Slices through an Enhanced User Plane Function and Analytics in Beyond-5G Networks
The latest generation of games and pervasive communication technologies poses challenges in service management and Service-Level Agreement compliance for mobile users. State-of-the-art edge-gaming techniques enhance throughput, reduce latency, and leverage cloud computing. However, further development of core functions such as the User Plane Function (UPF) is needed for non-intrusive user latency measurement. This paper proposes a closed-loop architecture integrating the Network Data Analytics …

Reconsidering Explicit Longitudinal Mammography Alignment for Enhanced Breast Cancer Risk Prediction
Solveig Thrun, Stine Hansen, Zijun Sun, Nele Blum, Suaiba A. Salahuddin, Kristoffer Wickstr{\o}m, Elisabeth Wetzer, Robert Jenssen, Maik Stille, Michael Kampffmeyer
https://arxiv.org/abs/2506.19363

Reconsidering Explicit Longitudinal Mammography Alignment for Enhanced Breast Cancer Risk Prediction
Regular mammography screening is essential for early breast cancer detection. Deep learning-based risk prediction methods have sparked interest to adjust screening intervals for high-risk groups. While early methods focused only on current mammograms, recent approaches leverage the temporal aspect of screenings to track breast tissue changes over time, requiring spatial alignment across different time points. Two main strategies for this have emerged: explicit feature alignment through deformab…

On the Role of Age and Semantics of Information in Remote Estimation of Markov Sources
Jiping Luo, Nikolaos Pappas
https://arxiv.org/abs/2507.18514 https://

On the Role of Age and Semantics of Information in Remote Estimation of Markov Sources
This paper investigates the semantics-aware remote estimation of a finite-state Markov chain. We employ the maximum a posteriori (MAP) estimator and aim to devise a transmission policy to optimize estimation performance subject to a transmission frequency constraint. We leverage two metrics, namely the Age of Consecutive Error (AoCE) and the Age of Information (AoI), to quantify, respectively, the significance of estimation error at the transmitter and the predictability of outdated information…

CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems
Haochen Zhang, Tianyi Zhang, Junze Yin, Oren Gal, Anshumali Shrivastava, Vladimir Braverman
https://arxiv.org/abs/2506.19993

CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems
Recommender systems play a pivotal role in providing relevant content to users. With the rapid development of large language models (LLMs), researchers have begun utilizing LLMs to build more powerful recommender systems. However, existing approaches that focus on aligning LLMs with recommendation tasks do not fully leverage their sequential information processing capabilities, leading to suboptimal performance. In this paper, we propose a novel system called compressed vocabulary expansion (…

SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer
Hanwen Liu, Qihan Zhang, Ryan Marcus, Ibrahim Sabek
https://arxiv.org/abs/2508.17556 https://a…

SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer
Query optimization is a crucial problem in database systems that has been studied for decades. Learned query optimizers (LQOs) can improve performance over time by incorporating feedback; however, they suffer from cold-start issues and often require retraining when workloads shift or schemas change. Recent LLM-based query optimizers leverage pre-trained and fine-tuned LLMs to mitigate these challenges. Nevertheless, they neglect LLMs' in-context learning and execution records as feedback for co…

Explicit Sign-Magnitude Encoders Enable Power-Efficient Multipliers
Felix Arnold, Maxence Bouvier, Ryan Amaudruz, Renzo Andri, Lukas Cavigelli
https://arxiv.org/abs/2507.18179 h…

Explicit Sign-Magnitude Encoders Enable Power-Efficient Multipliers
This work presents a method to maximize power-efficiency of fixed point multiplier units by decomposing them into sub-components. First, an encoder block converts the operands from a two's complement to a sign magnitude representation, followed by a multiplier module which performs the compute operation and outputs the resulting value in the original format. This allows to leverage the power-efficiency of the Sign Magnitude encoding for the multiplication. To ensure the computing format is not …

Two-Timescale Dynamic Service Deployment and Task Scheduling with Spatiotemporal Collaboration in Mobile Edge Networks
Yang Li, Xing Zhang, Yunji Zhao, Wenbo Wang
https://arxiv.org/abs/2508.16293

Two-Timescale Dynamic Service Deployment and Task Scheduling with Spatiotemporal Collaboration in Mobile Edge Networks
Collaborative edge computing addresses the resource constraints of individual edge nodes by enabling resource sharing and task co-processing across multiple nodes. To fully leverage the advantages of collaborative edge computing, joint optimization of service deployment and task scheduling is necessary. Existing optimization methods insufficiently address the collaboration across spatial and temporal dimensions, which hinders their adaptability to the spatiotemporally varying nature of user dem…

A causality inspired acceleration method for the fast temporal superposition of the finite line source solutions
Marc Basquens, Alberto Lazzarotto
https://arxiv.org/abs/2507.18200

A causality inspired acceleration method for the fast temporal superposition of the finite line source solutions
We present a novel, fast method to compute thermal interactions in solids, useful for time-dependent problems involving several sources and several time and space scales such as the ones encountered in the physics of fields of closed loop borehole heat exchangers. The new method is based on the non-history temporal superposition acceleration algorithm, but presents better performance compared to the originally proposed scheme. The main idea behind it is to leverage the propagation properties of…

ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Ahmad Mustafa, Reza Rastegar, Ghassan AlRegib
https://arxiv.org/abs/2506.19687 …

ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Prostate gland segmentation from T2-weighted MRI is a critical yet challenging task in clinical prostate cancer assessment. While deep learning-based methods have significantly advanced automated segmentation, most conventional approaches-particularly 2D convolutional neural networks (CNNs)-fail to leverage inter-slice anatomical continuity, limiting their accuracy and robustness. Fully 3D models offer improved spatial coherence but require large amounts of annotated data, which is often imprac…

Speaker Embeddings to Improve Tracking of Intermittent and Moving Speakers
Taous Iatariene (MULTISPEECH), Can Cui (MULTISPEECH), Alexandre Gu\'erin (MULTISPEECH), Romain Serizel (MULTISPEECH)
https://arxiv.org/abs/2506.19875

Speaker Embeddings to Improve Tracking of Intermittent and Moving Speakers
Speaker tracking methods often rely on spatial observations to assign coherent track identities over time. This raises limits in scenarios with intermittent and moving speakers, i.e., speakers that may change position when they are inactive, thus leading to discontinuous spatial trajectories. This paper proposes to investigate the use of speaker embeddings, in a simple solution to this issue. We propose to perform identity reassignment post-tracking, using speaker embeddings. We leverage trajec…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/8]:
- How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online C...
Giuseppe Serra, Ben Werner, Florian Buettner

Symbolic Reduction for Formal Synthesis of Global Lyapunov Functions
Jun Liu, Maxwell Fitzsimmons
https://arxiv.org/abs/2506.18171 https://

Symbolic Reduction for Formal Synthesis of Global Lyapunov Functions
We investigate the formal synthesis of global polynomial Lyapunov functions for polynomial vector fields. We establish that a sign-definite polynomial must satisfy specific algebraic constraints, which we leverage to develop a set of straightforward symbolic reduction rules. These rules can be recursively applied to symbolically simplify the Lyapunov candidate, enabling more efficient and robust discovery of Lyapunov functions via optimization or satisfiability modulo theories (SMT) solving. In…

Maximum-likelihood reprojections for reliable Koopman-based predictions and bifurcation analysis of parametric dynamical systems
Pieter van Goor, Robert Mahony, Manuel Schaller, Karl Worthmann
https://arxiv.org/abs/2506.17817

Maximum-likelihood reprojections for reliable Koopman-based predictions and bifurcation analysis of parametric dynamical systems
Koopman-based methods leverage a nonlinear lifting to enable linear regression techniques. Consequently, data generation, learning and prediction is performed through the lens of this lifting, giving rise to a nonlinear manifold that is invariant under the Koopman operator. In data-driven approximation such as Extended Dynamic Mode Decomposition, this invariance is typically lost due to the presence of (finite-data) approximation errors. In this work, we show that reprojections are crucial for …

Room temperature spin injection into commercial VCSELs at non-resonant wavelengths
Timur Almabetov, Petros Androvitsaneas, Zhongze Ren, Andrew Young, Ruth Oulton, Edmund Harbord
https://arxiv.org/abs/2506.18376

Room temperature spin injection into commercial VCSELs at non-resonant wavelengths
Spin lasers leverage electron spin-polarisation to control photon polarisation, offering the potential for lower thresholds, rapid modulation, and all-optical data processing. We report successful spin injection into a commercial Vertical Cavity Surface Emitting Laser (VCSEL) using optical pumping at wavelengths of 794 nm and 810 nm. Maximum circular polarisation achieved was about 20% at 794 nm, whereas this falls to 5% with exciting at 810 nm. We attribute this to reduced spin injection due t…

Surrogate-Assisted Evolution for Efficient Multi-branch Connection Design in Deep Neural Networks
Fergal Stapleton, Daniel Garc\'ia N\'u\~nez, Yanan Sun, Edgar Galv\'an
https://arxiv.org/abs/2506.20469

Surrogate-Assisted Evolution for Efficient Multi-branch Connection Design in Deep Neural Networks
State-of-the-art Deep Neural Networks (DNNs) often incorporate multi-branch connections, enabling multi-scale feature extraction and enhancing the capture of diverse features. This design improves network capacity and generalisation to unseen data. However, training such DNNs can be computationally expensive. The challenge is further exacerbated by the complexity of identifying optimal network architectures. To address this, we leverage Evolutionary Algorithms (EAs) to automatically discover hi…

Rethinking LLM-Based RTL Code Optimization Via Timing Logic Metamorphosis
Zhihao Xu, Bixin Li, Lulu Wang
https://arxiv.org/abs/2507.16808 https://

Rethinking LLM-Based RTL Code Optimization Via Timing Logic Metamorphosis
Register Transfer Level(RTL) code optimization is crucial for achieving high performance and low power consumption in digital circuit design. However, traditional optimization methods often rely on manual tuning and heuristics, which can be time-consuming and error-prone. Recent studies proposed to leverage Large Language Models(LLMs) to assist in RTL code optimization. LLMs can generate optimized code snippets based on natural language descriptions, potentially speeding up the optimization pro…

How Walmart plans to leverage its $2.3B Vizio acquisition to push shoppable TV experiences; Walmart's ad business had just $4.4B of sales in FY 2025 (Jaewon Kang/Bloomberg)
https://www.bloomberg.com/news/articles/20

HAWC Performance Enhanced by Machine Learning in Gamma-Hadron Separation
R. Alfaro, C. Alvarez, A. Andr\'es, E. Anita-Rangel, M. Araya, J. C. Arteaga-Vel\'azquez, D. Avila Rojas, H. A. Ayala Solares, R. Babu, P. Bangale, E. Belmont-Moreno, A. Bernal, T. Capistr\'an, A. Carrami\~nana, F. Carre\'on, S. Casanova, U. Cotti, E. De la Fuente, D. Depaoli, P. Desiati, N. Di Lalla, R. Diaz Hernandez, M. A. DuVernois, J. C. D\'iaz-V\'elez, K. Engel, T. Ergin, C. Espinoza,…

HAWC Performance Enhanced by Machine Learning in Gamma-Hadron Separation
Improving gamma-hadron separation is one of the most effective ways to enhance the performance of ground-based gamma-ray observatories. With over a decade of continuous operation, the High-Altitude Water Cherenkov (HAWC) Observatory has contributed significantly to high-energy astrophysics. To further leverage its rich dataset, we introduce a machine learning approach for gamma-hadron separation. A Multilayer Perceptron shows the best performance, surpassing traditional and other Machine Learni…

HuggingGraph: Understanding the Supply Chain of LLM Ecosystem
Mohammad Shahedur Rahman, Peng Gao, Yuede Ji
https://arxiv.org/abs/2507.14240 https://…

HuggingGraph: Understanding the Supply Chain of LLM Ecosystem
Large language models (LLMs) leverage deep learning to process and predict sequences of words from context, enabling them to perform various NLP tasks, such as translation, summarization, question answering, and content generation. However, the growing size and complexity of developing, training, and deploying advanced LLMs require extensive computational resources and large datasets. This creates a barrier for users. As a result, platforms that host models and datasets are widely used. For exa…

Structure-Preserving Medical Image Generation from a Latent Graph Representation
Kevin Arias, Edwin Vargas, Kumar Vijay Mishra, Antonio Ortega, Henry Arguello
https://arxiv.org/abs/2508.15920

Structure-Preserving Medical Image Generation from a Latent Graph Representation
Supervised learning techniques have proven their efficacy in many applications with abundant data. However, applying these methods to medical imaging is challenging due to the scarcity of data, given the high acquisition costs and intricate data characteristics of those images, thereby limiting the full potential of deep neural networks. To address the lack of data, augmentation techniques leverage geometry, color, and the synthesis ability of generative models (GMs). Despite previous efforts, …

As Trump Fails to Deliver, Russia Looks to Musk's America Party for Leverage (Dave Troy/America 2.0)
https://america2.news/as-trump-fails-to-deliver-russia-looks-to-musks-america-party-for-leverage/
http://www.memeorandum.com/250707/p135#a250707p135

From Cracks to Crooks: YouTube as a Vector for Malware Distribution
Iman Vakilinia
https://arxiv.org/abs/2507.16996 https://arxiv.org/pdf/2507.16996…

From Cracks to Crooks: YouTube as a Vector for Malware Distribution
With billions of users and an immense volume of daily uploads, YouTube has become an attractive target for cybercriminals aiming to leverage its vast audience. The platform's openness and trustworthiness provide an ideal environment for deceptive campaigns that can operate under the radar of conventional security tools. This paper explores how cybercriminals exploit YouTube to disseminate malware, focusing on campaigns that promote free software or game cheats. It discusses deceptive video demo…

Nonlinear Framework for Speech Bandwidth Extension
Tarikul Islam Tamiti, Nursad Mamun, Anomadarshi Barua
https://arxiv.org/abs/2507.15970 https://

Nonlinear Framework for Speech Bandwidth Extension
Recovering high-frequency components lost to bandwidth constraints is crucial for applications ranging from telecommunications to high-fidelity audio on limited resources. We introduce NDSI-BWE, a new adversarial Band Width Extension (BWE) framework that leverage four new discriminators inspired by nonlinear dynamical system to capture diverse temporal behaviors: a Multi-Resolution Lyapunov Discriminator (MRLD) for determining sensitivity to initial conditions by capturing deterministic chaos, …

Anthropic CEO Dario Amodei saying the quiet part out loud in a CNN interview about impending job losses due to AI:
"There's an inherent social contract in democracy where ultimately the ordinary person has a certain amount of leverage because they're contributing to the economy.
"If that leverage goes away, then it's harder to make democracies work, and it's harder to prevent concentration of power."

@… My, admittedly super naive, not carefully considered, take is: If anyone has them, it’s unreasonable to expect others not to attempt to get on par.
Why should some powers hold permanent leverage over the rest? Why should anyone trust them not to abuse the position?
I would prefer a world where they simply don’t exist, but given that they do, here we are.

Stochastic Modeling of a Memory-Assisted Measurement-Device-Independent Quantum Key Distribution System in Free-Space Metropolitan Environments
Fares Nada, Amber Hussain, Tasmi R. Ahmed, Connor Kupchak
https://arxiv.org/abs/2508.14983

Stochastic Modeling of a Memory-Assisted Measurement-Device-Independent Quantum Key Distribution System in Free-Space Metropolitan Environments
On the pathway to quantum key distribution on a global scale, will be the realization of metropolitan-sized Memory Assisted Measurement-Device-Independent Quantum Key Distribution (MA-MDI-QKD) systems. Here, we present a simplistic and intuitive stochastic model to predict key distribution rates in a MA-MDI-QKD scheme that addresses the real-world parameters inherent to free-space quantum communication channels. Specific to our algorithm, the memory-assisted based system allows us to leverage t…

Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users
Weixin Chen, Yuhan Zhao, Li Chen, Weike Pan
https://arxiv.org/abs/2507.17749 https…

Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users
Cross-domain recommendation (CDR) methods predominantly leverage overlapping users to transfer knowledge from a source domain to a target domain. However, through empirical studies, we uncover a critical bias inherent in these approaches: while overlapping users experience significant enhancements in recommendation quality, non-overlapping users benefit minimally and even face performance degradation. This unfairness may erode user trust, and, consequently, negatively impact business engagement…

"Hackers exploit a blind spot by hiding malware inside DNS records"
Hah! I predicted years ago that attackers would leverage DNS like this!
My insistence to include DNS requests in anomaly detection and threat detection was on point 😤 so vindicated!
https://

Hackers exploit a blind spot by hiding malware inside DNS records
Technique transforms the Internet DNS into an unconventional file storage system.

Emerson-Lei and Manna-Pnueli Games for LTLf and PPLTL Synthesis
Daniel Hausmann, Shufang Zhu, Gianmarco Parretti, Christoph Weinhuber, Giuseppe De Giacomo, Nir Piterman
https://arxiv.org/abs/2508.14725

Emerson-Lei and Manna-Pnueli Games for LTLf+ and PPLTL+ Synthesis
Recently, the Manna-Pnueli Hierarchy has been used to define the temporal logics LTLfp and PPLTLp, which allow to use finite-trace LTLf/PPLTL techniques in infinite-trace settings while achieving the expressiveness of full LTL. In this paper, we present the first actual solvers for reactive synthesis in these logics. These are based on games on graphs that leverage DFA-based techniques from LTLf/PPLTL to construct the game arena. We start with a symbolic solver based on Emerson-Lei games, which…

DreamCube: 3D Panorama Generation via Multi-plane Synchronization
Yukun Huang, Yanning Zhou, Jianan Wang, Kaiyi Huang, Xihui Liu
https://arxiv.org/abs/2506.17206

DreamCube: 3D Panorama Generation via Multi-plane Synchronization
3D panorama synthesis is a promising yet challenging task that demands high-quality and diverse visual appearance and geometry of the generated omnidirectional content. Existing methods leverage rich image priors from pre-trained 2D foundation models to circumvent the scarcity of 3D panoramic data, but the incompatibility between 3D panoramas and 2D single views limits their effectiveness. In this work, we demonstrate that by applying multi-plane synchronization to the operators from 2D foundat…

Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization
Shengchao Liu, Hannan Xu, Yan Ai, Huanxin Li, Yoshua Bengio, Harry Guo
https://arxiv.org/abs/2507.16110

Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization
Large language models (LLMs) leverage chain-of-thought (CoT) techniques to tackle complex problems, representing a transformative breakthrough in artificial intelligence (AI). However, their reasoning capabilities have primarily been demonstrated in solving math and coding problems, leaving their potential for domain-specific applications-such as battery discovery-largely unexplored. Inspired by the idea that reasoning mirrors a form of guided search, we introduce ChatBattery, a novel agentic f…

Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution
Tainyi Zhang, Zheng-Peng Duan, Peng-Tao Jiang, Bo Li, Ming-Ming Cheng, Chun-Le Guo, Chongyi Li
https://arxiv.org/abs/2508.16557

Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution
Diffusion-based real-world image super-resolution (Real-ISR) methods have demonstrated impressive performance. To achieve efficient Real-ISR, many works employ Variational Score Distillation (VSD) to distill pre-trained stable-diffusion (SD) model for one-step SR with a fixed timestep. However, due to the different noise injection timesteps, the SD will perform different generative priors. Therefore, a fixed timestep is difficult for these methods to fully leverage the generative priors in SD, …

Floating-Point Data Transformation for Lossless Compression
Samirasadat Jamalidinan, Kazem Cheshmi
https://arxiv.org/abs/2506.18062 https://

Floating-Point Data Transformation for Lossless Compression
Floating-point data is widely used across various domains. Depending on the required precision, each floating-point value can occupy several bytes. Lossless storage of this information is crucial due to its critical accuracy, as seen in applications such as medical imaging and language model weights. In these cases, data size is often significant, making lossless compression essential. Previous approaches either treat this data as raw byte streams for compression or fail to leverage all pattern…

Integrating Quantized LLMs into Robotics Systems as Edge AI to Leverage their Natural Language Processing Capabilities
Miguel \'A. Gonz\'alez-Santamarta, Francisco J. Rodr\'iguez-Lera, David Sobr\'in-Hidalgo, \'Angel Manuel Guerrero-Higueras, Vicente Matell\'An-Olivera
https://arxiv.org/abs/2506.09581

Integrating Quantized LLMs into Robotics Systems as Edge AI to Leverage their Natural Language Processing Capabilities
Large Language Models (LLMs) have experienced great advancements in the last year resulting in an increase of these models in several fields to face natural language tasks. The integration of these models in robotics can also help to improve several aspects such as human-robot interaction, navigation, planning and decision-making. Therefore, this paper introduces llama\_ros, a tool designed to integrate quantized Large Language Models (LLMs) into robotic systems using ROS 2. Leveraging llama.cp…

Learning from Anatomy: Supervised Anatomical Pretraining (SAP) for Improved Metastatic Bone Disease Segmentation in Whole-Body MRI
Joris Wuts, Jakub Ceranka, Nicolas Michoux, Fr\'ed\'eric Lecouvet, Jef Vandemeulebroucke
https://arxiv.org/abs/2506.19590

Learning from Anatomy: Supervised Anatomical Pretraining (SAP) for Improved Metastatic Bone Disease Segmentation in Whole-Body MRI
The segmentation of metastatic bone disease (MBD) in whole-body MRI (WB-MRI) is a challenging problem. Due to varying appearances and anatomical locations of lesions, ambiguous boundaries, and severe class imbalance, obtaining reliable segmentations requires large, well-annotated datasets capturing lesion variability. Generating such datasets requires substantial time and expertise, and is prone to error. While self-supervised learning (SSL) can leverage large unlabeled datasets, learned generi…

Point Cloud Streaming with Latency-Driven Implicit Adaptation using MoQ
Andrew Freeman, Michael Rudolph, Amr Rizk
https://arxiv.org/abs/2507.15673 https://…

Point Cloud Streaming with Latency-Driven Implicit Adaptation using MoQ
Point clouds are a promising video representation for next-generation multimedia experiences in virtual and augmented reality. Point clouds are notoriously high-bitrate, however, which limits the feasibility of live streaming systems. Prior methods have adopted traditional HTTP-based protocols for point cloud streaming, but they rely on explicit client-side adaptation to maintain low latency under congestion. In this work, we leverage the delivery timeout feature within the Media Over QUIC prot…

Optimizers Qualitatively Alter Solutions And We Should Leverage This
Razvan Pascanu, Clare Lyle, Ionut-Vlad Modoranu, Naima Elosegui Borras, Dan Alistarh, Petar Velickovic, Sarath Chandar, Soham De, James Martens
https://arxiv.org/abs/2507.12224

Optimizers Qualitatively Alter Solutions And We Should Leverage This
Due to the nonlinear nature of Deep Neural Networks (DNNs), one can not guarantee convergence to a unique global minimum of the loss when using optimizers relying only on local information, such as SGD. Indeed, this was a primary source of skepticism regarding the feasibility of DNNs in the early days of the field. The past decades of progress in deep learning have revealed this skepticism to be misplaced, and a large body of empirical evidence shows that sufficiently large DNNs following stand…

ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
Kaiyuan Tan, Yingying Shen, Haohui Zhu, Zhiwei Zhan, Shan Zhao, Mingfei Tu, Hongcheng Luo, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye
https://arxiv.org/abs/2508.15529

ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
Synthesizing extrapolated views from recorded driving logs is critical for simulating driving scenes for autonomous driving vehicles, yet it remains a challenging task. Recent methods leverage generative priors as pseudo ground truth, but often lead to poor geometric consistency and over-smoothed renderings. To address these limitations, we propose ExtraGS, a holistic framework for trajectory extrapolation that integrates both geometric and generative priors. At the core of ExtraGS is a novel R…

Graph Learning for Foreign Exchange Rate Prediction and Statistical Arbitrage
Yoonsik Hong, Diego Klabjan
https://arxiv.org/abs/2508.14784 https://arxiv.or…

Graph Learning for Foreign Exchange Rate Prediction and Statistical Arbitrage
We propose a two-step graph learning approach for foreign exchange statistical arbitrages (FXSAs), addressing two key gaps in prior studies: the absence of graph-learning methods for foreign exchange rate prediction (FXRP) that leverage multi-currency and currency-interest rate relationships, and the disregard of the time lag between price observation and trade execution. In the first step, to capture complex multi-currency and currency-interest rate relationships, we formulate FXRP as an edge-…

Report: Arbiter ruled for NFL in faking injury gripe https://www.espn.com/nfl/story/_/id/45763049/arbiter-ruled-nfl-grievance-vs-nflpa-rb-advice

Maximizing Ariel's Survey Leverage for Population-Level Studies of Exoplanets
Nicolas B. Cowan, Ben Coull-Neveu
https://arxiv.org/abs/2506.06429 https:…

Maximizing Ariel's Survey Leverage for Population-Level Studies of Exoplanets
ESA's Ariel mission will be uniquely suited to performing population-level studies of exoplanets. Most of these studies consist of quantifying trends between an Ariel-measured quantity, y, and an a priori planetary property, x; for example, atmospheric metallicity as inferred from Ariel transit spectroscopy vs. planetary radius. We define the leverage of a survey with N targets as L = sqrt(N)stdev(x) and show that it quantitatively predicts the precision of population-level trends. The target s…

Apple announces the Foundation Models framework, giving developers direct access to its on-device AI models for the first time (Tim Hardwick/MacRumors)
https://www.macrumors.com/2025/06/09/foundation-models-framework/

Apple Announces Foundation Models Framework for Developers to Leverage AI
Apple at WWDC today announced Foundation Models Framework, a new API allowing third-party developers to leverage the large language models at the...

"Despite good-faith efforts by DSI [dense street imagery] providers to protect individual privacy through blurring faces and license plates, these measures fail to address broader privacy concerns. In this work, we find that increased data density and advancements in artificial intelligence enable harmful group membership inferences from supposedly anonymized data."
via @…

Privacy of Groups in Dense Street Imagery
Spatially and temporally dense street imagery (DSI) datasets have grown unbounded. In 2024, individual companies possessed around 3 trillion unique images of public streets. DSI data streams are only set to grow as companies like Lyft and Waymo use DSI to train autonomous vehicle algorithms and analyze collisions. Academic researchers leverage DSI to explore novel approaches to urban analysis. Despite good-faith efforts by DSI providers to protect individual privacy through blurring faces and l…

Higher Gauge Flow Models
Alexander Strunk, Roland Assam
https://arxiv.org/abs/2507.16334 https://arxiv.org/pdf/2507.16334

Higher Gauge Flow Models
This paper introduces Higher Gauge Flow Models, a novel class of Generative Flow Models. Building upon ordinary Gauge Flow Models (arXiv:2507.13414), these Higher Gauge Flow Models leverage an L$_{\infty}$-algebra, effectively extending the Lie Algebra. This expansion allows for the integration of the higher geometry and higher symmetries associated with higher groups into the framework of Generative Flow Models. Experimental evaluation on a Gaussian Mixture Model dataset revealed substantial p…

Team LA at SCIDOCA shared task 2025: Citation Discovery via relation-based zero-shot retrieval
Trieu An, Long Nguyen, Minh Le Nguyen
https://arxiv.org/abs/2506.18316

Team LA at SCIDOCA shared task 2025: Citation Discovery via relation-based zero-shot retrieval
The Citation Discovery Shared Task focuses on predicting the correct citation from a given candidate pool for a given paragraph. The main challenges stem from the length of the abstract paragraphs and the high similarity among candidate abstracts, making it difficult to determine the exact paper to cite. To address this, we develop a system that first retrieves the top-k most similar abstracts based on extracted relational features from the given paragraph. From this subset, we leverage a Large…

Covariance Decomposition for Distance Based Species Tree Estimation
Georgios Aliatimis, Ruriko Yoshida, Burak Boyak, James Grant
https://arxiv.org/abs/2506.16425

Covariance Decomposition for Distance Based Species Tree Estimation
In phylogenomics, species-tree methods must contend with two major sources of noise; stochastic gene-tree variation under the multispecies coalescent model (MSC) and finite-sequence substitutional noise. Fast agglomerative methods such as GLASS, STEAC, and METAL combine multi-locus information via distance-based clustering. We derive the exact covariance matrix of these pairwise distance estimates under a joint MSC-plus-substitution model and leverage it for reliable confidence estimation, and …

The Dispersion Leverage Coronagraph (DLC): A nulling coronagraph for use on primary objective grating telescopes
Leaf Swordy, Heidi Jo Newberg, Becket Hill, Richard K. Barry, Marina Cousins, Kerrigan Nish, Frank Ravizza, Sarah Rickborn
https://arxiv.org/abs/2507.11745

The Dispersion Leverage Coronagraph (DLC): A nulling coronagraph for use on primary objective grating telescopes
We present the Dispersion Leverage Coronagraph (DLC), a novel variation of the Achromatic Interfero Coronagraph (AIC) that is designed for optical systems featuring large, dispersive primary objective gratings. DLC was originally designed for the Diffractive Interfero Coronagraph Exoplanet Resolver (DICER), a notional 20m class infrared space telescope utilizing the enhanced one-dimensional angular resolution of large diffraction gratings in order to discover and characterize near-Earth exoplan…

How Walmart plans to leverage its $2.3B Vizio acquisition to push shoppable TV experiences; Walmart's ad business had just $4.4B of sales in FY 2025 (Jaewon Kang/Bloomberg)
https://www.bloomberg.com/news/articles/20

Eco-Innovation and Earnings Management: Unveiling the Moderating Effects of Financial Constraints and Opacity in FTSE All-Share Firms
Probowo Erawan Sastroredjo, Marcel Ausloos, Polina Khrennikova
https://arxiv.org/abs/2508.14935

Eco-Innovation and Earnings Management: Unveiling the Moderating Effects of Financial Constraints and Opacity in FTSE All-Share Firms
Our research investigates the relationship between eco-innovation and earnings management among 567 firms listed on the FTSE All-Share Index from 2014 to 2022. By examining how sustainability-driven innovation influences financial reporting practices, we explore the strategic motivations behind income smoothing in firms engaged in environmental initiatives. The findings reveal a positive association between eco-innovation and earnings management, suggesting that firms may leverage ecoinnovation…

Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever
Yixin Chen, Ying Xiong, Shangyu Wu, Yufei Cui, Xue Liu, Nan Guan, Chun Jason Xue
https://arxiv.org/abs/2508.14323

Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever
Tool-augmented large language models (LLMs) leverage external functions to extend their capabilities, but inaccurate function calls can lead to inefficiencies and increased costs.Existing methods address this challenge by fine-tuning LLMs or using demonstration-based prompting, yet they often suffer from high training overhead and fail to account for inconsistent demonstration samples, which misguide the model's invocation behavior. In this paper, we trained a behavior-aligned retriever (BAR), …

Through the Looking Glass: Bitcoin Treasury Companies
B K Meister
https://arxiv.org/abs/2507.14910 https://arxiv.org/pdf/2507.14910

Through the Looking Glass: Bitcoin Treasury Companies
Bitcoin treasury companies have taken stock markets by storm amassing billions of dollars worth of tokens. More than a hundred companies active in various crypto-tokens, not just Bitcoin, are listed. The ability to generate leverage, for example stemming from borrowing collateralized by stock portfolios, helps to understand this phenomenon. In addition, the extension of the binary-choice Kelly criterion to incorporate uncertainty in the form of the Kullback-Leibler divergence or more generall…

Polarforming Design for Movable Antenna Systems
Zijian Zhou, Jingze Ding, Rui Zhang
https://arxiv.org/abs/2507.16311 https://arxiv.or…

Polarforming Design for Movable Antenna Systems
Polarforming has emerged as a promising technique to enable the antenna to shape its polarization into a desired state for aligning with that of the received electromagnetic (EM) wave or reconfiguring that of the transmitted EM wave. In this letter, we investigate polarforming design for the movable antenna (MA)-enabled communication system. Specifically, we consider a single-input single-output (SISO) system with reconfigurable antenna positions and polarizations to leverage both spatial and p…

Code Clone Detection via an AlphaFold-Inspired Framework
Changguo Jia, Yi Zhan, Tianqi Zhao, Hengzhi Ye, Minghui Zhou
https://arxiv.org/abs/2507.15226 http…

Code Clone Detection via an AlphaFold-Inspired Framework
Code clone detection, which aims to identify functionally equivalent code fragments, plays a critical role in software maintenance and vulnerability analysis. Substantial methods have been proposed to detect code clones, but they fall short in capturing code semantics or relying on language-specific analyzers. Inspired by the remarkable success of AlphaFold in predicting three-dimensional protein structures from protein sequences, in this paper, we leverage AlphaFold for code clone detection ba…

Zelensky says Ukraine making gains near Dobropillya: https://benborges.xyz/2025/08/15/zelensky-says-ukraine-making-gains.html

MExECON: Multi-view Extended Explicit Clothed humans Optimized via Normal integration
Fulden Ece U\u{g}ur, Rafael Redondo, Albert Barreiro, Stefan Hristov, Roger Mar\'i
https://arxiv.org/abs/2508.15500

MExECON: Multi-view Extended Explicit Clothed humans Optimized via Normal integration
This work presents MExECON, a novel pipeline for 3D reconstruction of clothed human avatars from sparse multi-view RGB images. Building on the single-view method ECON, MExECON extends its capabilities to leverage multiple viewpoints, improving geometry and body pose estimation. At the core of the pipeline is the proposed Joint Multi-view Body Optimization (JMBO) algorithm, which fits a single SMPL-X body model jointly across all input views, enforcing multi-view consistency. The optimized body …

Mitigating Exponential Mixed Frequency Growth through Frequency Selection and Dimensional Separation in Quantum Machine Learning
Michael Poppel, David Bucher, Maximilian Zorn, Nico Kraus, Jonas Stein, Claudia Linnhoff-Popien
https://arxiv.org/abs/2508.10533

Mitigating Exponential Mixed Frequency Growth through Frequency Selection and Dimensional Separation in Quantum Machine Learning
To leverage the potential computational speedup of quantum computing (QC), research in quantum machine learning (QML) has gained increasing prominence. Angle encoding techniques in QML models have been shown to generate truncated Fourier series, offering asymptotically universal function approximation capabilities. By selecting efficient feature maps (FMs) within quantum circuits, one can leverage the exponential growth of Fourier frequencies for improved approximation. In multi-dimensional set…

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Hengyu An, Jinghuai Zhang, Tianyu Du, Chunyi Zhou, Qingming Li, Tao Lin, Shouling Ji
https://arxiv.org/abs/2508.15310

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching information from public websites), tool responses may contain injected instructions that covertly influence agent behaviors and lead to malicious outcomes, a threat referred to as Indirect Prompt Injection (IPI). Existing defenses typically rely on advanced pro…

Leveraging Hardware-Aware Computation in Mixed-Precision Matrix Multiply: A Tile-Centric Approach
Qiao Zhang, Rabab Alomairy, Dali Wang, Zhuowei Gu, Qinglei Cao
https://arxiv.org/abs/2508.14848

Leveraging Hardware-Aware Computation in Mixed-Precision Matrix Multiply: A Tile-Centric Approach
General Matrix Multiplication (GEMM) is a critical operation underpinning a wide range of applications in high-performance computing (HPC) and artificial intelligence (AI). The emergence of hardware optimized for low-precision arithmetic necessitates a reevaluation of numerical algorithms to leverage mixed-precision computations, achieving improved performance and energy efficiency. This research introduces an adaptive mixed-precision GEMM framework that supports different precision formats at …

Can Common VLMs Rival Medical VLMs? Evaluation and Strategic Insights
Yuan Zhong, Ruinan Jin, Xiaoxiao Li, Qi Dou
https://arxiv.org/abs/2506.17337 https://…

Can Common VLMs Rival Medical VLMs? Evaluation and Strategic Insights
Medical vision-language models (VLMs) leverage large-scale pretraining for diverse imaging tasks but require substantial computational and data resources. Meanwhile, common or general-purpose VLMs (e.g., CLIP, LLaVA), though not trained for medical use, show promise with fine-tuning. This raises a key question: Can efficient fine-tuned common VLMs rival generalist medical VLMs for solving specific medical imaging tasks? This study systematically evaluates common and medical VLMs across disease …

Towards Quantum Accelerated Large-scale Topology Optimization
Zisheng Ye, Wenxiao Pan
https://arxiv.org/abs/2507.14478 https://arxiv.…

Towards Quantum Accelerated Large-scale Topology Optimization
We present a new method that efficiently solves TO problems and provides a practical pathway to leverage quantum computing to exploit potential quantum advantages. This work targets on large-scale, multi-material TO challenges for three-dimensional (3D) continuum structures, beyond what have been addressed in prior studies. Central to this new method is the modified Dantzig-Wolfe (MDW) decomposition, which effectively mitigates the escalating computational cost associated with using classical M…

Machine learning revolution for exoplanet direct imaging detection: transformer architectures
Yu-Chia Lin
https://arxiv.org/abs/2508.14508 https://arxiv.or…

Machine learning revolution for exoplanet direct imaging detection: transformer architectures
Directly imaging exoplanets is a formidable challenge due to extreme contrast ratios and quasi-static speckle noise, motivating the exploration of advanced post-processing methods. While Convolutional Neural Networks (CNNs) have shown promise, their inherent limitations in capturing long-range dependencies in image sequences hinder their effectiveness. This study introduces a novel hybrid deep learning architecture that combines a CNN feature extractor with a Transformer encoder to leverage tem…

Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering
Muhammad Fadhil Ginting, Dong-Ki Kim, Xiangyun Meng, Andrzej Reinke, Bandi Jai Krishna, Navid Kayhani, Oriana Peltzer, David D. Fan, Amirreza Shaban, Sung-Kyun Kim, Mykel J. Kochenderfer, Ali-akbar Agha-mohammadi, Shayegan Omidshafiei
https://

Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering
As robots become increasingly capable of operating over extended periods -- spanning days, weeks, and even months -- they are expected to accumulate knowledge of their environments and leverage this experience to assist humans more effectively. This paper studies the problem of Long-term Active Embodied Question Answering (LA-EQA), a new task in which a robot must both recall past experiences and actively explore its environment to answer complex, temporally-grounded questions. Unlike tradition…

EventSSEG: Event-driven Self-Supervised Segmentation with Probabilistic Attention
Lakshmi Annamalai, Chetan Singh Thakur
https://arxiv.org/abs/2508.14856 https://

EventSSEG: Event-driven Self-Supervised Segmentation with Probabilistic Attention
Road segmentation is pivotal for autonomous vehicles, yet achieving low latency and low compute solutions using frame based cameras remains a challenge. Event cameras offer a promising alternative. To leverage their low power sensing, we introduce EventSSEG, a method for road segmentation that uses event only computing and a probabilistic attention mechanism. Event only computing poses a challenge in transferring pretrained weights from the conventional camera domain, requiring abundant labeled…

Arintra, whose AI medical coding system translates clinical documentation into insurance codes for healthcare providers, raised a $21M Series A led by Peak XV (Erin Brodwin/Axios)
https://www.axios.com/pro/health-tech-deals/2025/08/12/arintra-21m…

Exclusive: Arintra raises $21M to expand into denials prevention
As financial pressure mounts on U.S. health systems, Arintra aims to leverage gen-AI to secure reimbursement while reducing dependency on human coders.

Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation
Hengyu Zhang, Chunxu Shen, Xiangguo Sun, Jie Tan, Yanchao Tan, Yu Rong, Hong Cheng, Lingling Yi
https://arxiv.org/abs/2507.15395

Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation
In real-world recommendation scenarios, users typically engage with platforms through multiple types of behavioral interactions. Multi-behavior recommendation algorithms aim to leverage various auxiliary user behaviors to enhance prediction for target behaviors of primary interest (e.g., buy), thereby overcoming performance limitations caused by data sparsity in target behavior records. Current state-of-the-art approaches typically employ hierarchical design following either cascading (e.g., vi…

Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction
Xinhe Li, Jiajun Liu, Peng Wang
https://arxiv.org/abs/2508.13037

Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction
Recent studies have demonstrated that Large Language Models (LLMs) have strong mathematical reasoning abilities but rely on hundreds of billions of parameters. To tackle the challenge of poor reasoning in Small Language Models (SLMs), existing methods typically leverage LLMs to generate massive amounts of data for cramming training. In psychology, they are akin to System 1 thinking, which resolves reasoning problems rapidly based on experience and intuition. However, human learning also require…

Quantum Blockchain Survey: Foundations, Trends, and Gaps
Saurav Ghosh
https://arxiv.org/abs/2507.13720 https://arxiv.org/pdf/2507.137…

Quantum Blockchain Survey: Foundations, Trends, and Gaps
Quantum computing poses fundamental risks to classical blockchain systems by undermining widely used cryptographic primitives. In response, two major research directions have emerged: post-quantum blockchains, which integrate quantum-resistant algorithms, and quantum blockchains, which leverage quantum properties such as entanglement and quantum key distribution. This survey reviews key developments in both areas, analyzing their cryptographic foundations, architectural designs, and implementat…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/8]:
Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling

Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration
Yifei Chen, Guanting Dong, Yutao Zhu, Zhicheng Dou
https://arxiv.org/abs/2508.13828

Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration
Retrieval-Augmented Generation (RAG) technology has been widely applied in recent years. However, despite the emergence of various RAG frameworks, a single RAG framework still cannot adapt well to a broad range of downstream tasks. Therefore, how to leverage the advantages of multiple RAG systems has become an area worth exploring. To address this issue, we have conducted a comprehensive and systematic investigation into ensemble methods based on RAG systems. Specifically, we have analyzed the …

Learning to Restore Heisenberg Limit in Noisy Quantum Sensing via Quantum Digital Twin
Hang Xu, Tailong Xiao, Jingzheng Huang, Jianping Fan, Guihua Zeng
https://arxiv.org/abs/2508.11198

Learning to Restore Heisenberg Limit in Noisy Quantum Sensing via Quantum Digital Twin
Quantum sensors leverage nonclassical resources to achieve sensing precision at the Heisenberg limit, surpassing the standard quantum limit attainable through classical strategies. However, a critical issue is that the environmental noise induces rapid decoherence, fundamentally limiting the realizability of the Heisenberg limit. In this Letter, we propose a quantum digital twin protocol to overcome this issue. The protocol first establishes observable-constrained state reconstruction to infer …

Quantization Meets Spikes: Lossless Conversion in the First Timestep via Polarity Multi-Spike Mapping
Hangming Zhang, Zheng Li, Qiang Yu
https://arxiv.org/abs/2508.14520 https:/…

Quantization Meets Spikes: Lossless Conversion in the First Timestep via Polarity Multi-Spike Mapping
Spiking neural networks (SNNs) offer advantages in computational efficiency via event-driven computing, compared to traditional artificial neural networks (ANNs). While direct training methods tackle the challenge of non-differentiable activation mechanisms in SNNs, they often suffer from high computational and energy costs during training. As a result, ANN-to-SNN conversion approach still remains a valuable and practical alternative. These conversion-based methods aim to leverage the discrete …

Fast, low noise CCD systems for future strategic x-ray missions
Haley R. Stueber, Abigail Y. Pan, Tanmoy Chattopadhyay, Steven W. Allen, Marshall W. Bautz, Kevan Donlon, Catherine E. Grant, Sven Herrmann, Beverly J. LaMarr, Andrew Malonis, Eric D. Miller, R. Glenn Morris, Peter Orel, Artem Poliszczuk, Gregory Y. Prigozhin, Daniel R. Wilkins
https://

Fast, low noise CCD systems for future strategic x-ray missions
Future strategic X-ray missions, such as the Advanced X-ray Imaging Satellite (AXIS) and those targeted by the Great Observatories Maturation Program (GOMaP), require fast, low-noise X-ray imaging spectrometers. To achieve the speed and noise capabilities required by such programs, the X-ray Astronomy and Observational Cosmology (XOC) Group at Stanford, in collaboration with the MIT Kavli Institute (MKI) and MIT Lincoln Laboratory (MIT-LL), is developing readout systems that leverage the high s…

ATK: Automatic Task-driven Keypoint Selection for Robust Policy Learning
Yunchu Zhang, Shubham Mittal, Zhengyu Zhang, Liyiming Ke, Siddhartha Srinivasa, Abhishek Gupta
https://arxiv.org/abs/2506.13867

ATK: Automatic Task-driven Keypoint Selection for Robust Policy Learning
Visuomotor policies often suffer from perceptual challenges, where visual differences between training and evaluation environments degrade policy performance. Policies relying on state estimations, like 6D pose, require task-specific tracking and are difficult to scale, while raw sensor-based policies may lack robustness to small visual disturbances.In this work, we leverage 2D keypoints - spatially consistent features in the image frame - as a flexible state representation for robust policy le…

Mobile Application Review Summarization using Chain of Density Prompting
Shristi Shrestha, Anas Mahmoud
https://arxiv.org/abs/2506.14192 https://

Mobile Application Review Summarization using Chain of Density Prompting
Mobile app users commonly rely on app store ratings and reviews to find apps that suit their needs. However, the sheer volume of reviews available on app stores can lead to information overload, thus impeding users' ability to make informed app selection decisions. To address this challenge, we leverage Large Language Models (LLMs) to summarize mobile app reviews. In particular, we use the Chain of Density (CoD) prompt to guide OpenAI GPT-4 to generate abstractive, semantically dense, and easil…

Sources: Google, Meta, and other tech firms have met with Brazilian officials as new regulations on tech are being shaped, with Trump's tariffs as a backdrop (Ana Ionova/New York Times)
https://www.nytimes.com/2025/08/11/world/americas/brazil-big-tech…

Brazil Clamped Down on Big Tech. Trump’s Tariffs Could Change That.
With President Trump on their side, U.S. technology companies now have more leverage in Brazil, where they seek to influence new rules policing their platforms.

Enhanced Dermatology Image Quality Assessment via Cross-Domain Training
Ignacio Hern\'andez Montilla, Alfonso Medela, Paola Pasquali, Andy Aguilar, Taig Mac Carthy, Gerardo Fern\'andez, Antonio Martorell, Enrique Onieva
https://arxiv.org/abs/2506.16116

Enhanced Dermatology Image Quality Assessment via Cross-Domain Training
Teledermatology has become a widely accepted communication method in daily clinical practice, enabling remote care while showing strong agreement with in-person visits. Poor image quality remains an unsolved problem in teledermatology and is a major concern to practitioners, as bad-quality images reduce the usefulness of the remote consultation process. However, research on Image Quality Assessment (IQA) in dermatology is sparse, and does not leverage the latest advances in non-dermatology IQA,…

Overview of the TREC 2022 deep learning track
Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, Jimmy Lin, Ellen M. Voorhees, Ian Soboroff
https://arxiv.org/abs/2507.10865

Overview of the TREC 2022 deep learning track
This is the fourth year of the TREC Deep Learning track. As in previous years, we leverage the MS MARCO datasets that made hundreds of thousands of human annotated training labels available for both passage and document ranking tasks. In addition, this year we also leverage both the refreshed passage and document collections that were released last year leading to a nearly $16$ times increase in the size of the passage collection and nearly four times increase in the document collection size. U…

Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models
Wei Song, Haonan Zhong, Ziqi Ding, Jingling Xue, Yuekang Li
https://arxiv.org/abs/2508.12566 ht…

Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models
The Model Context Protocol (MCP) enables large language models (LLMs) to access external resources on demand. While commonly assumed to enhance performance, how LLMs actually leverage this capability remains poorly understood. We introduce MCPGAUGE, the first comprehensive evaluation framework for probing LLM-MCP interactions along four key dimensions: proactivity (self-initiated tool use), compliance (adherence to tool-use instructions), effectiveness (task performance post-integration), and o…

Leveraging Quantum Layers in Classical Neural Networks
Silvie Ill\'esov\'a
https://arxiv.org/abs/2507.12505 https://arxiv.org…

Leveraging Quantum Layers in Classical Neural Networks
Hybrid quantum-classical neural networks represent a promising frontier in the search for improved machine learning models. This thesis explores the integration of quantum layers within classical convolutional neural network architectures, aiming to leverage quantum entanglement and feature mapping to enhance learning capabilities. A detailed methodology for constructing and training such hybrid models is presented, using PyTorch and Qiskit Machine Learning frameworks. Experiments investigate t…

Diffusion-based Inverse Observation Model for Artificial Skin
Ante Maric, Julius Jankowski, Giammarco Caroleo, Alessandro Albini, Perla Maiolino, Sylvain Calinon
https://arxiv.org/abs/2506.13986

Diffusion-based Inverse Observation Model for Artificial Skin
Contact-based estimation of object pose is challenging due to discontinuities and ambiguous observations that can correspond to multiple possible system states. This multimodality makes it difficult to efficiently sample valid hypotheses while respecting contact constraints. Diffusion models can learn to generate samples from such multimodal probability distributions through denoising algorithms. We leverage these probabilistic modeling capabilities to learn an inverse observation model conditi…

Reinforcing Video Reasoning Segmentation to Think Before It Segments
Sitong Gong, Lu Zhang, Yunzhi Zhuge, Xu Jia, Pingping Zhang, Huchuan Lu
https://arxiv.org/abs/2508.11538 htt…

Reinforcing Video Reasoning Segmentation to Think Before It Segments
Video reasoning segmentation (VRS) endeavors to delineate referred objects in videos guided by implicit instructions that encapsulate human intent and temporal logic. Previous approaches leverage large vision language models (LVLMs) to encode object semantics into tokens for mask prediction. However, this paradigm suffers from limited interpretability during inference and suboptimal performance due to inadequate spatiotemporal reasoning. Drawing inspiration from seminal breakthroughs in r…

Diffusion is a code repair operator and generator
Mukul Singh, Gust Verbruggen, Vu Le, Sumit Gulwani
https://arxiv.org/abs/2508.11110 https://arxiv.org/pdf…

Diffusion is a code repair operator and generator
Code diffusion models generate code by iteratively removing noise from the latent representation of a code snippet. During later steps of the diffusion process, when the code snippet has almost converged, differences between discrete representations of these snippets look like last-mile repairs applied to broken or incomplete code. We evaluate the extent to which this resemblance can be exploited to leverage pre-trained code diffusion models for the problem of last-mile repair by considering tw…

FMC: Formalization of Natural Language Mathematical Competition Problems
Jiaxuan Xie, Chengwu Liu, Ye Yuan, Siqi Li, Zhiping Xiao, Ming Zhang
https://arxiv.org/abs/2507.11275

FMC: Formalization of Natural Language Mathematical Competition Problems
Efficient and accurate autoformalization methods, which leverage large-scale datasets of extensive natural language mathematical problems to construct formal language datasets, are key to advancing formal mathematical reasoning. In this paper, we propose an autoformalization pipeline based on large language models with error feedback, achieving a fully automatic and training-free formalization approach. Using this pipeline, we curate an Olympiad-level dataset aligning natural language problems …

[Social] Allostasis: Or, How I Learned To Stop Worrying and Love The Noise
Imran Khan
https://arxiv.org/abs/2508.12791 https://arxiv.org/pdf/2508.12791

[Social] Allostasis: Or, How I Learned To Stop Worrying and Love The Noise
The notion of homeostasis typically conceptualises biological and artificial systems as maintaining stability by resisting deviations caused by environmental and social perturbations. In contrast, (social) allostasis proposes that these systems can proactively leverage these very perturbations to reconfigure their regulatory parameters in anticipation of environmental demands, aligning with von Foerster's ``order through noise'' principle. This paper formulates a computational model of allostat…

MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems
Yu Cui, Hongyang Du
https://arxiv.org/abs/2507.13038 https://

MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems
Multi-agent debate (MAD) systems leverage collaborative interactions among large language models (LLMs) agents to improve reasoning capabilities. While recent studies have focused on increasing the accuracy and scalability of MAD systems, their security vulnerabilities have received limited attention. In this work, we introduce MAD-Spear, a targeted prompt injection attack that compromises a small subset of agents but significantly disrupts the overall MAD process. Manipulated agents produce mu…

GTool: Graph Enhanced Tool Planning with Large Language Model
Wenjie Chen, Wenbin Li, Di Yao, Xuying Meng, Chang Gong, Jingping Bi
https://arxiv.org/abs/2508.12725 https://

GTool: Graph Enhanced Tool Planning with Large Language Model
Tool planning with large language models (LLMs), referring to selecting, organizing, and preparing the tools necessary to complete a user request, bridges the gap between natural language understanding and task execution. However, current works treat different tools as isolated components and fail to leverage the inherent dependencies of tools, leading to invalid planning results. Since tool dependencies are often incomplete, it becomes challenging for LLMs to accurately identify the appropriat…

Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving
Boris Ivanovic, Cristiano Saltori, Yurong You, Yan Wang, Wenjie Luo, Marco Pavone
https://arxiv.org/abs/2506.12251

Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving
Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures, owing to their scalability and potential to leverage internet-scale pretraining for generalization. Accordingly, tokenizing sensor data efficiently is paramount to ensuring the real-time feasibility of such architectures on embedded hardware. To this end, we present an efficient triplane-based multi-camera tokenization strategy that leverages recent advances in 3D ne…

DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
Hayat Ullah, Muhammad Ali Shafique, Abbas Khan, Arslan Munir
https://arxiv.org/abs/2507.12426

DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
The landscape of video recognition has evolved significantly, shifting from traditional Convolutional Neural Networks (CNNs) to Transformer-based architectures for improved accuracy. While 3D CNNs have been effective at capturing spatiotemporal dynamics, recent Transformer models leverage self-attention to model long-range spatial and temporal dependencies. Despite achieving state-of-the-art performance on major benchmarks, Transformers remain computationally expensive, particularly with dense …

Landmark-Assisted Monte Carlo Planning
David H. Chan, Mark Roberts, Dana S. Nau
https://arxiv.org/abs/2508.11493 https://arxiv.org/pdf/2508.11493

Landmark-Assisted Monte Carlo Planning
Landmarks$\unicode{x2013}$conditions that must be satisfied at some point in every solution plan$\unicode{x2013}$have contributed to major advancements in classical planning, but they have seldom been used in stochastic domains. We formalize probabilistic landmarks and adapt the UCT algorithm to leverage them as subgoals to decompose MDPs; core to the adaptation is balancing between greedy landmark achievement and final goal achievement. Our results in benchmark domains show that well-chosen la…

MMIS-Net for Retinal Fluid Segmentation and Detection
Nchongmaje Ndipenocha, Alina Mirona, Kezhi Wanga, Yongmin Li
https://arxiv.org/abs/2508.13936 https://

MMIS-Net for Retinal Fluid Segmentation and Detection
Purpose: Deep learning methods have shown promising results in the segmentation, and detection of diseases in medical images. However, most methods are trained and tested on data from a single source, modality, organ, or disease type, overlooking the combined potential of other available annotated data. Numerous small annotated medical image datasets from various modalities, organs, and diseases are publicly available. In this work, we aim to leverage the synergistic potential of these datasets…

QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents
Eliott Thomas, Mickael Coustaty, Aurelie Joseph, Gaspar Deloin, Elodie Carel, Vincent Poulain D'Andecy, Jean-Marc Ogier
https://arxiv.org/abs/2506.14568

QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents
Automating table extraction (TE) from business documents is critical for industrial workflows but remains challenging due to sparse annotations and error-prone multi-stage pipelines. While semi-supervised learning (SSL) can leverage unlabeled data, existing methods rely on confidence scores that poorly reflect extraction quality. We propose QUEST, a Quality-aware Semi-supervised Table extraction framework designed for business documents. QUEST introduces a novel quality assessment model that ev…