Tootfinder

edit_wikibooks: Wikipedia book edits (2010)
Two bipartite user-page networks extracted from Wikipedia, about books. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 13841 nodes and 45536 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

Just learned about NYC Local Law 144 which requires bias audits for hiring decisions
https://www.nyc.gov/site/dca/about/automated-employment-decision-tools.page
(From younger, more principled brother; happy birthday dkg!)
I am really interes…

Built an #aspnetcore tag helper that scans your current page and outputs the assets as preload links in your layout.
This will make your pages feel very snappy and keep images from blocking the processing of the HTML.

📰 Einem US-amerikanischen Konzern Geld aus der Tasche zu leiern, um damit Hosting-Rechnungen für Gratis-Angebote zu bezahlen, kann man machen. Aber schön ist es nicht. Ich würde meine Amazon-Partnerlinks gern loswerden.
Bitte unterstütze meine Arbeit mit einer Steady-Mitgliedschaft: https://steady.page/klimacrew

KlimaCrew
Ich informiere über Zukunftsthemen, um Menschen vor Risiken zu warnen und Fortschritte sichtbar zu machen.

Little Brother is watching us walk and bike around Washington, DC. Gathering and displaying statistics.
https://ddot.dc.gov/page/dc-automated-bicycle-and-pedestrian-counters

Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration
Yuyi Zhang, Peirong Zhang, Zhenhua Yang, Pengyu Yan, Yongxin Shi, Pengwei Liu, Fengjun Guo, Lianwen Jin
https://arxiv.org/abs/2507.05108

Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration
Historical documents represent an invaluable cultural heritage, yet have undergone significant degradation over time through tears, water erosion, and oxidation. Existing Historical Document Restoration (HDR) methods primarily focus on single modality or limited-size restoration, failing to meet practical needs. To fill this gap, we present a full-page HDR dataset (FPHDR) and a novel automated HDR solution (AutoHDR). Specifically, FPHDR comprises 1,633 real and 6,543 synthetic images with chara…

Tell Urban Outfitters to Drop Wool Now! #AnimalRights

Tell Urban Outfitters to Drop Wool Now!
Help sheep who are kicked and cut up for wool.

@… Perhaps of interest?
https://www.islandinnovation.co/events/virtual-island-summit-2025#speakers-page-1…

Island Innovation - Sustainable Development for Islands Worldwide
Island Innovation is a leading consultancy specializing in sustainable development, climate resilience, and innovation for island communities worldwide.

still works .... my #iPod

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/4]:
- Quantum-Informed Machine Learning for Predicting Spatiotemporal Chaos
Maida Wang, Xiao Xue, Mingyang Gao, Peter V. Coveney

Esta wiki de #solarpunk que acabo de ver en lemmy es el amor https://diysolarpunk.miraheze.org/wiki/Main_Page

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
Matteo Poggi, Fabio Tosi
https://arxiv.org/abs/2509.05297 https://arxiv.or…

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
We present FlowSeek, a novel framework for optical flow requiring minimal hardware resources for training. FlowSeek marries the latest advances on the design space of optical flow networks with cutting-edge single-image depth foundation models and classical low-dimensional motion parametrization, implementing a compact, yet accurate architecture. FlowSeek is trained on a single consumer-grade GPU, a hardware budget about 8x lower compared to most recent methods, and still achieves superior cros…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/4]:
- Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation
Xiaoxiong Zhang, Zhiwei Zeng, Xin Zhou, Zhiqi Shen

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
Zizun Li, Jianjun Zhou, Yifan Wang, Haoyu Guo, Wenzheng Chang, Yang Zhou, Haoyi Zhu, Junyi Chen, Chunhua Shen, Tong He
https://arxiv.org/abs/2509.05296

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To address this, we first introduce a sliding window mechanism that ensures sufficient information exchange among frames within the window, thereby improving the quality of geometric predictions without large computation. In addition, we leverage a compact repres…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/4]:
- Q-learning with Posterior Sampling
Priyank Agrawal, Shipra Agrawal, Azmat Azati
htt…

COGITAO: A Visual Reasoning Framework To Study Compositionality & Generalization
Yassine Taoudi-Benchekroun, Klim Troyan, Pascal Sager, Stefan Gerber, Lukas Tuggener, Benjamin Grewe
https://arxiv.org/abs/2509.05249

COGITAO: A Visual Reasoning Framework To Study Compositionality & Generalization
The ability to compose learned concepts and apply them in novel settings is key to human intelligence, but remains a persistent limitation in state-of-the-art machine learning models. To address this issue, we introduce COGITAO, a modular and extensible data generation framework and benchmark designed to systematically study compositionality and generalization in visual domains. Drawing inspiration from ARC-AGI's problem-setting, COGITAO constructs rule-based tasks which apply a set of transfor…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/4]:
- FC-PINO: High Precision Physics-Informed Neural Operators via Fourier Continuation
Ganeshram, Maust, Duruisseaux, Li, Wang, Leibovici, Bruno, Hou, Anandkumar

Symbolic Graphics Programming with Large Language Models
Yamei Chen, Haoquan Zhang, Yangyi Huang, Zeju Qiu, Kaipeng Zhang, Yandong Wen, Weiyang Liu
https://arxiv.org/abs/2509.05208

Symbolic Graphics Programming with Large Language Models
Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored. We study symbolic graphics programming, where the goal is to generate an SGP from a natural-language description. This task also serves as a lens into how LLMs understand the visual world by prompting them to generate images rendered from SGPs. Among various SGPs, our paper sticks to scalable vector graphics (SVGs)…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/4]:
- Robust Model Predictive Control Design for Autonomous Vehicles with Perception-based Observers
Nariman Niknejad, Gokul S. Sankar, Bahare Kiumarsi, Hamidreza Modares

Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet
Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari
https://arxiv.org/abs/2509.05198 https://

Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet
The classification of 3D point clouds is crucial for applications such as autonomous driving, robotics, and augmented reality. However, the commonly used ModelNet40 dataset suffers from limitations such as inconsistent labeling, 2D data, size mismatches, and inadequate class differentiation, which hinder model performance. This paper introduces ModelNet-R, a meticulously refined version of ModelNet40 designed to address these issues and serve as a more reliable benchmark. Additionally, this pap…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/4]:
- Artificial intelligence for representing and characterizing quantum systems
Du, Zhu, Zhang, Hsieh, Rebentrost, Gao, Wu, Eisert, Chiribella, Tao, Sanders

SL-SLR: Self-Supervised Representation Learning for Sign Language Recognition
Ariel Basso Madjoukeng, J\'er\^ome Fink, Pierre Poitier, Edith Belise Kenmogne, Benoit Frenay
https://arxiv.org/abs/2509.05188

SL-SLR: Self-Supervised Representation Learning for Sign Language Recognition
Sign language recognition (SLR) is a machine learning task aiming to identify signs in videos. Due to the scarcity of annotated data, unsupervised methods like contrastive learning have become promising in this field. They learn meaningful representations by pulling positive pairs (two augmented versions of the same instance) closer and pushing negative pairs (different from the positive pairs) apart. In SLR, in a sign video, only certain parts provide information that is truly useful for its r…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/4]:
- Bootstrapping Reinforcement Learning with Sub-optimal Policies for Autonomous Driving
Zhihao Zhang, Chengyang Peng, Ekim Yurtsever, Keith A. Redmill

SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing
Chaolei Wang, Yang Luo, Jing Du, Siyu Chen, Yiping Chen, Ting Han
https://arxiv.org/abs/2509.05144

SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing
Accurate 3D instance segmentation is crucial for high-quality scene understanding in the 3D vision domain. However, 3D instance segmentation based on 2D-to-3D lifting approaches struggle to produce precise instance-level segmentation, due to accumulated errors introduced during the lifting process from ambiguous semantic guidance and insufficient depth constraints. To tackle these challenges, we propose splitting and growing reliable semantic mask for high-fidelity 3D instance segmentation (SGS…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/4]:
- Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
Fangzhou Wu, Sandeep Silwal

A Scalable Attention-Based Approach for Image-to-3D Texture Mapping
Arianna Rampini, Kanika Madan, Bruno Roy, AmirHossein Zamani, Derek Cheung
https://arxiv.org/abs/2509.05131 h…

A Scalable Attention-Based Approach for Image-to-3D Texture Mapping
High-quality textures are critical for realistic 3D content creation, yet existing generative methods are slow, rely on UV maps, and often fail to remain faithful to a reference image. To address these challenges, we propose a transformer-based framework that predicts a 3D texture field directly from a single image and a mesh, eliminating the need for UV mapping and differentiable rendering, and enabling faster texture generation. Our method integrates a triplane representation with depth-based…

Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
Xiao Yang, Mehdi Ben Ayed, Longyu Zhao, Fan Zhou, Yuchen Shen, Abe Engle, Jinfeng Zhuang, Ling Leng, Jiajing Xu, Charles Rosenberg, Prathibha Deshikachar
https://arxiv.org/abs/2509.05292

Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
The ranking utility function in an ad recommender system, which linearly combines predictions of various business goals, plays a central role in balancing values across the platform, advertisers, and users. Traditional manual tuning, while offering simplicity and interpretability, often yields suboptimal results due to its unprincipled tuning objectives, the vast amount of parameter combinations, and its lack of personalization and adaptability to seasonality. In this work, we propose a general…

Semi-supervised Deep Transfer for Regression without Domain Alignment
Mainak Biswas, Ambedkar Dukkipati, Devarajan Sridharan
https://arxiv.org/abs/2509.05092 https://

Semi-supervised Deep Transfer for Regression without Domain Alignment
Deep learning models deployed in real-world applications (e.g., medicine) face challenges because source models do not generalize well to domain-shifted target data. Many successful domain adaptation (DA) approaches require full access to source data. Yet, such requirements are unrealistic in scenarios where source data cannot be shared either because of privacy concerns or because it is too large and incurs prohibitive storage or computational costs. Moreover, resource constraints may limit th…

Learning to accelerate distributed ADMM using graph neural networks
Henri Doerks, Paul H\"ausner, Daniel Hern\'andez Escobar, Jens Sj\"olund
https://arxiv.org/abs/2509.05288

Learning to accelerate distributed ADMM using graph neural networks
Distributed optimization is fundamental in large-scale machine learning and control applications. Among existing methods, the Alternating Direction Method of Multipliers (ADMM) has gained popularity due to its strong convergence guarantees and suitability for decentralized computation. However, ADMM often suffers from slow convergence and sensitivity to hyperparameter choices. In this work, we show that distributed ADMM iterations can be naturally represented within the message-passing framewor…

Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
Svetlana Pavlitska, Haixi Fan, Konstantin Ditschuneit, J. Marius Z\"ollner
https://arxiv.org/abs/2509.05086

Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
Robustifying convolutional neural networks (CNNs) against adversarial attacks remains challenging and often requires resource-intensive countermeasures. We explore the use of sparse mixture-of-experts (MoE) layers to improve robustness by replacing selected residual blocks or convolutional layers, thereby increasing model capacity without additional inference cost. On ResNet architectures trained on CIFAR-100, we find that inserting a single MoE layer in the deeper stages leads to consistent im…

Dual-Branch Convolutional Framework for Spatial and Frequency-Based Image Forgery Detection
Naman Tyagi
https://arxiv.org/abs/2509.05281 https://arxiv.org/…

Dual-Branch Convolutional Framework for Spatial and Frequency-Based Image Forgery Detection
With a very rapid increase in deepfakes and digital image forgeries, ensuring the authenticity of images is becoming increasingly challenging. This report introduces a forgery detection framework that combines spatial and frequency-based features for detecting forgeries. We propose a dual branch convolution neural network that operates on features extracted from spatial and frequency domains. Features from both branches are fused and compared within a Siamese network, yielding 64 dimensional em…

Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction
Djamel Eddine Boukhari
https://arxiv.org/abs/2509.05078 https://…

Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction
Automated Facial Beauty Prediction (FBP) is a challenging computer vision task due to the complex interplay of local and global facial features that influence human perception. While Convolutional Neural Networks (CNNs) excel at feature extraction, they often process information at a fixed scale, potentially overlooking the critical inter-dependencies between features at different levels of granularity. To address this limitation, we introduce the Scale-Interaction Transformer (SIT), a novel hy…

SpikingBrain Technical Report: Spiking Brain-inspired Large Models
Yuqi Pan, Yupeng Feng, Jinghao Zhuang, Siyu Ding, Zehao Liu, Bohan Sun, Yuhong Chou, Han Xu, Xuerui Qiu, Anlin Deng, Anjie Hu, Peng Zhou, Man Yao, Jibin Wu, Jian Yang, Guoliang Sun, Bo Xu, Guoqi Li
https://arxiv.org/abs/2509.05276

SpikingBrain Technical Report: Spiking Brain-inspired Large Models
Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large models on non-NVIDIA platforms also poses challenges for stable and efficient training. To address this, we introduce SpikingBrain, a family of brain-inspired models designed for efficient long-context training and inference. SpikingBrain leverages the MetaX GPU …

GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting
Yangming Li, Chaoyu Liu, Lihao Liu, Simon Masnou, Carola-Bibian Sch\"onlieb
https://arxiv.org/abs/2509.05075

GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting
A few recent works explored incorporating geometric priors to regularize the optimization of Gaussian splatting, further improving its performance. However, those early studies mainly focused on the use of low-order geometric priors (e.g., normal vector), and they are also unreliably estimated by noise-sensitive methods, like local principal component analysis. To address their limitations, we first present GeoSplat, a general geometry-constrained optimization framework that exploits both first…

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks
Jason Gardner, Ayan Dutta, Swapnoneel Roy, O. Patrick Kreidl, Ladislau Boloni
https://arxiv.org/abs/2509.05273

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks
The growing computational demands of deep reinforcement learning (DRL) have raised concerns about the environmental and economic costs of training large-scale models. While algorithmic efficiency in terms of learning performance has been extensively studied, the energy requirements, greenhouse gas emissions, and monetary costs of DRL algorithms remain largely unexplored. In this work, we present a systematic benchmarking study of the energy consumption of seven state-of-the-art DRL algorithms, …

Systematic Review and Meta-analysis of AI-driven MRI Motion Artifact Detection and Correction
Mojtaba Safari, Zach Eidex, Richard L. J. Qiu, Matthew Goette, Tonghe Wang, Xiaofeng Yang
https://arxiv.org/abs/2509.05071

Systematic Review and Meta-analysis of AI-driven MRI Motion Artifact Detection and Correction
Background: To systematically review and perform a meta-analysis of artificial intelligence (AI)-driven methods for detecting and correcting magnetic resonance imaging (MRI) motion artifacts, assessing current developments, effectiveness, challenges, and future research directions. Methods: A comprehensive systematic review and meta-analysis were conducted, focusing on deep learning (DL) approaches, particularly generative models, for the detection and correction of MRI motion artifacts. Quanti…

A Kolmogorov-Arnold Network for Interpretable Cyberattack Detection in AGC Systems
Jehad Jilan, Niranjana Naveen Nambiar, Ahmad Mohammad Saber, Alok Paranjape, Amr Youssef, Deepa Kundur
https://arxiv.org/abs/2509.05259

Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization
Jingqi Wu, Hanxi Li, Lin Yuanbo Wu, Hao Chen, Deyin Liu, Peng Wang
https://arxiv.org/abs/2509.05034

Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization
Industrial product inspection is often performed using Anomaly Detection (AD) frameworks trained solely on non-defective samples. Although defective samples can be collected during production, leveraging them usually requires pixel-level annotations, limiting scalability. To address this, we propose ADClick, an Interactive Image Segmentation (IIS) algorithm for industrial anomaly detection. ADClick generates pixel-wise anomaly annotations from only a few user clicks and a brief textual descript…

Deep Learning-Enhanced for Amine Emission Monitoring and Performance Analysis in Industrial Carbon Capture Plants
Lokendra Poudel, David Tincher, Duy-Nhat Phan, Rahul Bhowmik
https://arxiv.org/abs/2509.05241

Deep Learning-Enhanced for Amine Emission Monitoring and Performance Analysis in Industrial Carbon Capture Plants
We present data driven deep learning models for forecasting and monitoring amine emissions and key performance parameters in amine-based post-combustion carbon capture systems. Using operational data from the CESAR1 solvent campaign at Technology Center Mongstad, four DL architectures such as Basic Long Short-Term Memory (LSTM), Stacked LSTM, Bi-directional LSTM, and Convolutional LSTM were developed to capture time-dependent process behavior. For emission prediction, models were designed for 2…

LUIVITON: Learned Universal Interoperable VIrtual Try-ON
Cong Cao, Xianhang Cheng, Jingyuan Liu, Yujian Zheng, Zhenhui Lin, Meriem Chkir, Hao Li
https://arxiv.org/abs/2509.05030

LUIVITON: Learned Universal Interoperable VIrtual Try-ON
We present LUIVITON, an end-to-end system for fully automated virtual try-on, capable of draping complex, multi-layer clothing onto diverse and arbitrarily posed humanoid characters. To address the challenge of aligning complex garments with arbitrary and highly diverse body shapes, we use SMPL as a proxy representation and separate the clothing-to-body draping problem into two correspondence tasks: 1) clothing-to-SMPL and 2) body-to-SMPL correspondence, where each has its unique challenges. Wh…

An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data
Jiaojiao Zhang, Yuqi Xu, Kun Yuan
https://arxiv.org/abs/2509.05213 https://arx…

An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data
This work addresses the key challenges of applying federated learning to large-scale deep neural networks, particularly the issue of client drift due to data heterogeneity across clients and the high costs of communication, computation, and memory. We propose FedSub, an efficient subspace algorithm for federated learning on heterogeneous data. Specifically, FedSub utilizes subspace projection to guarantee local updates of each client within low-dimensional subspaces, thereby reducing communicat…

Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition
Mohsine El Khayati, Ayyad Maafiri, Yassine Himeur, Hamzah Ali Alkhazaleh, Shadi Atalla, Wathiq Mansoor
https://arxiv.org/abs/2509.05019

Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition
The study explores the integration of transfer learning (TL) with mobile-enabled convolutional neural networks (MbNets) to enhance Arabic Handwritten Character Recognition (AHCR). Addressing challenges like extensive computational requirements and dataset scarcity, this research evaluates three TL strategies--full fine-tuning, partial fine-tuning, and training from scratch--using four lightweight MbNets: MobileNet, SqueezeNet, MnasNet, and ShuffleNet. Experiments were conducted on three benchma…

RapidGNN: Energy and Communication-Efficient Distributed Training on Large-Scale Graph Neural Networks
Arefin Niam, Tevfik Kosar, M S Q Zulkar Nine
https://arxiv.org/abs/2509.05207

RapidGNN: Energy and Communication-Efficient Distributed Training on Large-Scale Graph Neural Networks
Graph Neural Networks (GNNs) have become popular across a diverse set of tasks in exploring structural relationships between entities. However, due to the highly connected structure of the datasets, distributed training of GNNs on large-scale graphs poses significant challenges. Traditional sampling-based approaches mitigate the computational loads, yet the communication overhead remains a challenge. This paper presents RapidGNN, a distributed GNN training framework with deterministic sampling-…

A biologically inspired separable learning vision model for real-time traffic object perception in Dark
Hulin Li, Qiliang Ren, Jun Li, Hanbing Wei, Zheng Liu, Linfang Fan
https://arxiv.org/abs/2509.05012

A biologically inspired separable learning vision model for real-time traffic object perception in Dark
Fast and accurate object perception in low-light traffic scenes has attracted increasing attention. However, due to severe illumination degradation and the lack of reliable visual cues, existing perception models and methods struggle to quickly adapt to and accurately predict in low-light environments. Moreover, there is the absence of available large-scale benchmark specifically focused on low-light traffic scenes. To bridge this gap, we introduce a physically grounded illumination degradation…

Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
Bastien Dubail, Stefan Stojanovic, Alexandre Prouti\`ere
https://arxiv.org/abs/2509.05193 htt…

Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
Low-rank structure is a common implicit assumption in many modern reinforcement learning (RL) algorithms. For instance, reward-free and goal-conditioned RL methods often presume that the successor measure admits a low-rank representation. In this work, we challenge this assumption by first remarking that the successor measure itself is not low-rank. Instead, we demonstrate that a low-rank structure naturally emerges in the shifted successor measure, which captures the system dynamics after bypa…

Interpretable Deep Transfer Learning for Breast Ultrasound Cancer Detection: A Multi-Dataset Study
Mohammad Abbadi, Yassine Himeur, Shadi Atalla, Wathiq Mansoor
https://arxiv.org/abs/2509.05004

Interpretable Deep Transfer Learning for Breast Ultrasound Cancer Detection: A Multi-Dataset Study
Breast cancer remains a leading cause of cancer-related mortality among women worldwide. Ultrasound imaging, widely used due to its safety and cost-effectiveness, plays a key role in early detection, especially in patients with dense breast tissue. This paper presents a comprehensive study on the application of machine learning and deep learning techniques for breast cancer classification using ultrasound images. Using datasets such as BUSI, BUS-BRA, and BrEaST-Lesions USG, we evaluate classica…

Accuracy-Constrained CNN Pruning for Efficient and Reliable EEG-Based Seizure Detection
Mounvik K, N Harshit
https://arxiv.org/abs/2509.05190 https://arxiv…

Accuracy-Constrained CNN Pruning for Efficient and Reliable EEG-Based Seizure Detection
Deep learning models, especially convolutional neural networks (CNNs), have shown considerable promise for biomedical signals such as EEG-based seizure detection. However, these models come with challenges, primarily due to their size and compute requirements in environments where real-time detection or limited resources are available. In this study, we present a lightweight one-dimensional CNN model with structured pruning to improve efficiency and reliability. The model was trained with mild …

Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework
Tianpei Zhang, Jufeng Zhao, Yiming Zhu, Guangmang Cui
https://arxiv.org/abs/2509.05000

Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework
Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual selection and sequential application of multiple pre-enhancement steps. This decoupled pre-enhancement-to-fusion pipeline inevitably leads to error accumulation and performance degradation. To overcome these limitations, we propose Guided Dual-Domain Fusion (GD^2Fusion), a novel framework that synergistically integrate…

KVCompose: Efficient Structured KV Cache Compression with Composite Tokens
Dmitry Akulov, Mohamed Sana, Antonio De Domenico, Tareq Si Salem, Nicola Piovesan, Fadhel Ayed
https://arxiv.org/abs/2509.05165

KVCompose: Efficient Structured KV Cache Compression with Composite Tokens
Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache compression methods either enforce rigid heuristics, disrupt tensor layouts with per-attention-head variability, or require specialized compute kernels. We propose a simple, yet effective, KV cache compression framework based on attention-guided, layer-adap…

Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper
Gehui Chen, Guan'an Wang, Xiaowen Huang, Jitao Sang
https://arxiv.org/abs/2509.04957 https://

Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper
Recent Video-to-Audio (V2A) generation relies on extracting semantic and temporal features from video to condition generative models. Training these models from scratch is resource intensive. Consequently, leveraging foundation models (FMs) has gained traction due to their cross-modal knowledge transfer and generalization capabilities. One prior work has explored fine-tuning a lightweight mapper network to connect a pre-trained visual encoder with a text-to-audio generation model for V2A. Inspi…

Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights
Cosmin-Andrei Hatfaludi, Alex Serban
https://arxiv.org/abs/2509.05142 https://

Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights
Federated learning has the potential to unlock siloed data and distributed resources by enabling collaborative model training without sharing private data. As more complex foundational models gain widespread use, the need to expand training resources and integrate privately owned data grows as well. In this article, we explore the intersection of federated learning and foundational models, aiming to identify, categorize, and characterize technical methods that integrate the two paradigms. As a …

UniView: Enhancing Novel View Synthesis From A Single Image By Unifying Reference Features
Haowang Cui, Rui Chen, Tao Luo, Rui Li, Jiaze Wang
https://arxiv.org/abs/2509.04932 ht…

UniView: Enhancing Novel View Synthesis From A Single Image By Unifying Reference Features
The task of synthesizing novel views from a single image is highly ill-posed due to multiple explanations for unobserved areas. Most current methods tend to generate unseen regions from ambiguity priors and interpolation near input views, which often lead to severe distortions. To address this limitation, we propose a novel model dubbed as UniView, which can leverage reference images from a similar object to provide strong prior information during view synthesis. More specifically, we construct…

On the Learnability of Distribution Classes with Adaptive Adversaries
Tosca Lechner, Alex Bie, Gautam Kamath
https://arxiv.org/abs/2509.05137 https://arxiv…

On the Learnability of Distribution Classes with Adaptive Adversaries
We consider the question of learnability of distribution classes in the presence of adaptive adversaries -- that is, adversaries capable of intercepting the samples requested by a learner and applying manipulations with full knowledge of the samples before passing it on to the learner. This stands in contrast to oblivious adversaries, who can only modify the underlying distribution the samples come from but not their i.i.d.\ nature. We formulate a general notion of learnability with respect to …

Evaluating Multiple Instance Learning Strategies for Automated Sebocyte Droplet Counting
Maryam Adelipour, Gustavo Carneiro, Jeongkwon Kim
https://arxiv.org/abs/2509.04895 https…

Evaluating Multiple Instance Learning Strategies for Automated Sebocyte Droplet Counting
Sebocytes are lipid-secreting cells whose differentiation is marked by the accumulation of intracellular lipid droplets, making their quantification a key readout in sebocyte biology. Manual counting is labor-intensive and subjective, motivating automated solutions. Here, we introduce a simple attention-based multiple instance learning (MIL) framework for sebocyte image analysis. Nile Red-stained sebocyte images were annotated into 14 classes according to droplet counts, expanded via data augme…

Should We Always Train Models on Fine-Grained Classes?
Davide Pirovano, Federico Milanesio, Michele Caselle, Piero Fariselli, Matteo Osella
https://arxiv.org/abs/2509.05130 http…

Should We Always Train Models on Fine-Grained Classes?
In classification problems, models must predict a class label based on the input data features. However, class labels are organized hierarchically in many datasets. While a classification task is often defined at a specific level of this hierarchy, training can utilize a finer granularity of labels. Empirical evidence suggests that such fine-grained training can enhance performance. In this work, we investigate the generality of this observation and explore its underlying causes using both real…

SynGen-Vision: Synthetic Data Generation for training industrial vision models
Alpana Dubey, Suma Mani Kuriakose, Nitish Bhardwaj
https://arxiv.org/abs/2509.04894 https://

SynGen-Vision: Synthetic Data Generation for training industrial vision models
We propose an approach to generate synthetic data to train computer vision (CV) models for industrial wear and tear detection. Wear and tear detection is an important CV problem for predictive maintenance tasks in any industry. However, data curation for training such models is expensive and time-consuming due to the unavailability of datasets for different wear and tear scenarios. Our approach employs a vision language model along with a 3D simulation and rendering engine to generate synthetic…

HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions
Rafael Bischof, Michal Piovar\v{c}i, Michael A. Kraus, Siddhartha Mishra, Bernd Bickel
https://arxiv.org/abs/2509.05117

HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions
We present HyPINO, a multi-physics neural operator designed for zero-shot generalization across a broad class of parametric PDEs without requiring task-specific fine-tuning. Our approach combines a Swin Transformer-based hypernetwork with mixed supervision: (i) labeled data from analytical solutions generated via the Method of Manufactured Solutions (MMS), and (ii) unlabeled samples optimized using physics-informed objectives. The model maps PDE parametrizations to target Physics-Informed Neura…

SpiderNets: Estimating Fear Ratings of Spider-Related Images with Vision Models
Dominik Pegler, David Steyrl, Mengfan Zhang, Alexander Karner, Jozsef Arato, Frank Scharnowski, Filip Melinscak
https://arxiv.org/abs/2509.04889

SpiderNets: Estimating Fear Ratings of Spider-Related Images with Vision Models
Advances in computer vision have opened new avenues for clinical applications, particularly in computerized exposure therapy where visual stimuli can be dynamically adjusted based on patient responses. As a critical step toward such adaptive systems, we investigated whether pretrained computer vision models can accurately predict fear levels from spider-related images. We adapted three diverse models using transfer learning to predict human fear ratings (on a 0-100 scale) from a standardized da…

Recurrent State Encoders for Efficient Neural Combinatorial Optimization
Tim Dernedde, Daniela Thyssens, Lars Schmidt-Thieme
https://arxiv.org/abs/2509.05084 https://

Recurrent State Encoders for Efficient Neural Combinatorial Optimization
The primary paradigm in Neural Combinatorial Optimization (NCO) are construction methods, where a neural network is trained to sequentially add one solution component at a time until a complete solution is constructed. We observe that the typical changes to the state between two steps are small, since usually only the node that gets added to the solution is removed from the state. An efficient model should be able to reuse computation done in prior steps. To that end, we propose to train a recu…

Cryo-RL: automating prostate cancer cryoablation planning with reinforcement learning
Trixia Simangan, Ahmed Nadeem Abbasi, Yipeng Hu, Shaheer U. Saeed
https://arxiv.org/abs/2509.04886

Cryo-RL: automating prostate cancer cryoablation planning with reinforcement learning
Cryoablation is a minimally invasive localised treatment for prostate cancer that destroys malignant tissue during de-freezing, while sparing surrounding healthy structures. Its success depends on accurate preoperative planning of cryoprobe placements to fully cover the tumour and avoid critical anatomy. This planning is currently manual, expertise-dependent, and time-consuming, leading to variability in treatment quality and limited scalability. In this work, we introduce Cryo-RL, a reinforcem…

MultiSurv: A Multimodal Deep Survival Framework for Prostrate and Bladder Cancer
Noorul Wahab, Ethar Alzaid, Jiaqi Lv, Adam Shephard, Shan E Ahmed Raza
https://arxiv.org/abs/2509.05037

MultiSurv: A Multimodal Deep Survival Framework for Prostrate and Bladder Cancer
Accurate prediction of time-to-event outcomes is a central challenge in oncology, with significant implications for treatment planning and patient management. In this work, we present MultiSurv, a multimodal deep survival model utilising DeepHit with a projection layer and inter-modality cross-attention, which integrates heterogeneous patient data, including clinical, MRI, RNA-seq and whole-slide pathology features. The model is designed to capture complementary prognostic signals across modali…

CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
Hannah Schieber, Dominik Frischmann, Simon Boche, Victor Schaack, Angela Schoellig, Stefan Leutenegger, Daniel Roth
https://arxiv.org/abs/2509.04859

CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
Mobile reconstruction for autonomous aerial robotics holds strong potential for critical applications such as tele-guidance and disaster response. These tasks demand both accurate 3D reconstruction and fast scene processing. Instead of reconstructing the entire scene in detail, it is often more efficient to focus on specific objects, i.e., points of interest (PoIs). Mobile robots equipped with advanced sensing can usually detect these early during data acquisition or preliminary analysis, reduc…

Depth-Aware Initialization for Stable and Efficient Neural Network Training
Vijay Pandey
https://arxiv.org/abs/2509.05018 https://arxiv.org/pdf/2509.05018

Depth-Aware Initialization for Stable and Efficient Neural Network Training
In past few years, various initialization schemes have been proposed. These schemes are glorot initialization, He initialization, initialization using orthogonal matrix, random walk method for initialization. Some of these methods stress on keeping unit variance of activation and gradient propagation through the network layer. Few of these methods are independent of the depth information while some methods has considered the total network depth for better initialization. In this paper, comprehe…

Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
Enze Ye, Wei Lin, Shaochi Ren, Yakun Liu, Xiaoping Li, Hao Wang, He Sun, Feng Pan
https://arxiv.org/abs/2509.04848

Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
High-throughput 3D quantitative phase imaging (QPI) in flow cytometry enables label-free, volumetric characterization of individual cells by reconstructing their refractive index (RI) distributions from multiple viewing angles during flow through microfluidic channels. However, current imaging methods assume that cells undergo uniform, single-axis rotation, which require their poses to be known at each frame. This assumption restricts applicability to near-spherical cells and prevents accurate …

Directed Evolution of Proteins via Bayesian Optimization in Embedding Space
Matou\v{s} Sold\'at, Ji\v{r}\'i Kl\'ema
https://arxiv.org/abs/2509.04998 https://

Directed Evolution of Proteins via Bayesian Optimization in Embedding Space
Directed evolution is an iterative laboratory process of designing proteins with improved function by iteratively synthesizing new protein variants and evaluating their desired property with expensive and time-consuming biochemical screening. Machine learning methods can help select informative or promising variants for screening to increase their quality and reduce the amount of necessary screening. In this paper, we present a novel method for machine-learning-assisted directed evolution of pr…

TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution
Yifei Jia, Shiyu Cheng, Yu Dong, Guan Li, Dong Tian, Ruixiao Peng, Xuyi Lu, Yu Wang, Wei Yao, Guihua Shan
https://arxiv.org/abs/2509.04834

TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution
Understanding the complex combustion dynamics within scramjet engines is critical for advancing high-speed propulsion technologies. However, the large scale and high dimensionality of simulation-generated temporal flow field data present significant challenges for visual interpretation, feature differentiation, and cross-case comparison. In this paper, we present TemporalFlowViz, a parameter-aware visual analytics workflow and system designed to support expert-driven clustering, visualization, …

Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
Shuaicheng Niu, Guohao Chen, Deyu Chen, Yifan Zhang, Jiaxiang Wu, Zhiquan Wen, Yaofo Chen, Peilin Zhao, Chunyan Miao, Mingkui Tan
https://arxiv.org/abs/2509.04977

Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
Test-time adaptation (TTA) may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, 3) online imbalanced label distribution shifts. This is often a key obstacle preventing existing TTA methods from being deployed in the real world. In this paper, we investigate the unstable reasons and find that the batch norm layer is a crucial factor hindering TTA stability. Conversely, TTA can perform more stably with batch-agnostic norm …

PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
Ming Dai, Wenxuan Cheng, Jiedong Zhuang, Jiang-jiang Liu, Hongshen Zhao, Zhenhua Feng, Wankou Yang
https://arxiv.org/abs/2509.04833

PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
Recent advances in visual grounding have largely shifted away from traditional proposal-based two-stage frameworks due to their inefficiency and high computational complexity, favoring end-to-end direct reference paradigms. However, these methods rely exclusively on the referred target for supervision, overlooking the potential benefits of prominent prospective targets. Moreover, existing approaches often fail to incorporate multi-granularity discrimination, which is crucial for robust object i…

Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks
Yuxi Wang, Heyao Liu, Guanzi Yao, Nyutian Long, Yue Kang
https://arxiv.org/abs/2509.04973 https…

Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks
This paper proposes a topology-aware graph reinforcement learning approach to address the routing policy optimization problem in cloud server environments. The method builds a unified framework for state representation and structural evolution by integrating a Structure-Aware State Encoding (SASE) module and a Policy-Adaptive Graph Update (PAGU) mechanism. It aims to tackle the challenges of decision instability and insufficient structural awareness under dynamic topologies. The SASE module mod…

Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution
Haosong Liu, Xiancheng Zhu, Huanqiang Zeng, Jianqing Zhu, Jiuwen Cao, Junhui Hou
https://arxiv.org/abs/2509.04824

Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution
Recently, Mamba-based methods, with its advantage in long-range information modeling and linear complexity, have shown great potential in optimizing both computational cost and performance of light field image super-resolution (LFSR). However, current multi-directional scanning strategies lead to inefficient and redundant feature extraction when applied to complex LF data. To overcome this challenge, we propose a Subspace Simple Scanning (Sub-SS) strategy, based on which we design the Subspace …

Neuro-Spectral Architectures for Causal Physics-Informed Networks
Arthur Bizzi, Leonardo M. Moreira, M\'arcio Marques, Leonardo Mendon\c{c}a, Christian J\'unior de Oliveira, Vitor Balestro, Lucas dos Santos Fernandez, Daniel Yukimura, Pavel Petrov, Jo\~ao M. Pereira, Tiago Novello, Lucas Nissenbaum
https://arxiv.org/abs/2509.04966

Neuro-Spectral Architectures for Causal Physics-Informed Networks
Physics-Informed Neural Networks (PINNs) have emerged as a powerful neural framework for solving partial differential equations (PDEs). However, standard MLP-based PINNs often fail to converge when dealing with complex initial-value problems, leading to solutions that violate causality and suffer from a spectral bias towards low-frequency components. To address these issues, we introduce NeuSA (Neuro-Spectral Architectures), a novel class of PINNs inspired by classical spectral methods, designe…

Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation
Svetlana Pavlitska, Beyza Keskin, Alwin Fa{\ss}bender, Christian Hubschneider, J. Marius Z\"ollner
https://arxiv.org/abs/2509.04816

Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation
Estimating accurate and well-calibrated predictive uncertainty is important for enhancing the reliability of computer vision models, especially in safety-critical applications like traffic scene perception. While ensemble methods are commonly used to quantify uncertainty by combining multiple models, a mixture of experts (MoE) offers an efficient alternative by leveraging a gating network to dynamically weight expert predictions based on the input. Building on the promising use of MoEs for sema…

On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
Johan Erbani, Pierre-Edouard Portier, Elod Egyed-Zsigmond, Sonia Ben Mokhtar, Diana Nurbakova
https://arxiv.org/abs/2509.04959

On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
The confusion matrix is a standard tool for evaluating classifiers by providing insights into class-level errors. In heterogeneous settings, its values are shaped by two main factors: class similarity -- how easily the model confuses two classes -- and distribution bias, arising from skewed distributions in the training and test sets. However, confusion matrix values reflect a mix of both factors, making it difficult to disentangle their individual contributions. To address this, we introduce b…

Toward Accessible Dermatology: Skin Lesion Classification Using Deep Learning Models on Mobile-Acquired Images
Asif Newaz, Masum Mushfiq Ishti, A Z M Ashraful Azam, Asif Ur Rahman Adib
https://arxiv.org/abs/2509.04800

Toward Accessible Dermatology: Skin Lesion Classification Using Deep Learning Models on Mobile-Acquired Images
Skin diseases are among the most prevalent health concerns worldwide, yet conventional diagnostic methods are often costly, complex, and unavailable in low-resource settings. Automated classification using deep learning has emerged as a promising alternative, but existing studies are mostly limited to dermoscopic datasets and a narrow range of disease classes. In this work, we curate a large dataset of over 50 skin disease categories captured with mobile devices, making it more representative o…

Detecting Blinks in Healthy and Parkinson's EEG: A Deep Learning Perspective
Artem Lensky, Yiding Qiu
https://arxiv.org/abs/2509.04951 https://arxiv.or…

Detecting Blinks in Healthy and Parkinson's EEG: A Deep Learning Perspective
Blinks in electroencephalography (EEG) are often treated as unwanted artifacts. However, recent studies have demonstrated that blink rate and its variability are important physiological markers to monitor cognitive load, attention, and potential neurological disorders. This paper addresses the critical task of accurate blink detection by evaluating various deep learning models for segmenting EEG signals into involuntary blinks and non-blinks. We present a pipeline for blink detection using 1, 3…

Comparative Evaluation of Traditional and Deep Learning Feature Matching Algorithms using Chandrayaan-2 Lunar Data
R. Makharia, J. G. Singla, Amitabh, N. Dube, H. Sharma
https://arxiv.org/abs/2509.04775

Comparative Evaluation of Traditional and Deep Learning Feature Matching Algorithms using Chandrayaan-2 Lunar Data
Accurate image registration is critical for lunar exploration, enabling surface mapping, resource localization, and mission planning. Aligning data from diverse lunar sensors -- optical (e.g., Orbital High Resolution Camera, Narrow and Wide Angle Cameras), hyperspectral (Imaging Infrared Spectrometer), and radar (e.g., Dual-Frequency Synthetic Aperture Radar, Selene/Kaguya mission) -- is challenging due to differences in resolution, illumination, and sensor distortion. We evaluate five feature …

Ontology-Aligned Embeddings for Data-Driven Labour Market Analytics
Heinke Hihn, Dennis A. V. Dittrich, Carl Jeske, Cayo Costa Sobral, Helio Pais, Timm Lochmann
https://arxiv.org/abs/2509.04942

Ontology-Aligned Embeddings for Data-Driven Labour Market Analytics
The limited ability to reason across occupational data from different sources is a long-standing bottleneck for data-driven labour market analytics. Previous research has relied on hand-crafted ontologies that allow such reasoning but are computationally expensive and require careful maintenance by human experts. The rise of language processing machine learning models offers a scalable alternative by learning shared semantic spaces that bridge diverse occupational vocabularies without extensive…

Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
Bangxiang Lan, Ruobing Xie, Ruixiang Zhao, Xingwu Sun, Zhanhui Kang, Gang Yang, Xirong Li
https://arxiv.org/abs/2509.04773

Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
The Text-to-Video Retrieval (T2VR) task aims to retrieve unlabeled videos by textual queries with the same semantic meanings. Recent CLIP-based approaches have explored two frameworks: Two-Tower versus Single-Tower framework, yet the former suffers from low effectiveness, while the latter suffers from low efficiency. In this study, we explore a new Hybrid-Tower framework that can hybridize the advantages of the Two-Tower and Single-Tower framework, achieving high effectiveness and efficiency si…

A transformer-BiGRU-based framework with data augmentation and confident learning for network intrusion detection
Jiale Zhang, Pengfei He, Fei Li, Kewei Li, Yan Wang, Lan Huang, Ruochi Zhang, Fengfeng Zhou
https://arxiv.org/abs/2509.04925

A transformer-BiGRU-based framework with data augmentation and confident learning for network intrusion detection
In today's fast-paced digital communication, the surge in network traffic data and frequency demands robust and precise network intrusion solutions. Conventional machine learning methods struggle to grapple with complex patterns within the vast network intrusion datasets, which suffer from data scarcity and class imbalance. As a result, we have integrated machine learning and deep learning techniques within the network intrusion detection system to bridge this gap. This study has developed Trai…

FloodVision: Urban Flood Depth Estimation Using Foundation Vision-Language Models and Domain Knowledge Graph
Zhangding Liu, Neda Mohammadi, John E. Taylor
https://arxiv.org/abs/2509.04772

FloodVision: Urban Flood Depth Estimation Using Foundation Vision-Language Models and Domain Knowledge Graph
Timely and accurate floodwater depth estimation is critical for road accessibility and emergency response. While recent computer vision methods have enabled flood detection, they suffer from both accuracy limitations and poor generalization due to dependence on fixed object detectors and task-specific training. To enable accurate depth estimation that can generalize across diverse flood scenarios, this paper presents FloodVision, a zero-shot framework that combines the semantic reasoning abilit…

Scaling Law for Large-Scale Pre-Training Using Chaotic Time Series and Predictability in Financial Time Series
Yuki Takemoto
https://arxiv.org/abs/2509.04921 https://

Scaling Law for Large-Scale Pre-Training Using Chaotic Time Series and Predictability in Financial Time Series
Time series forecasting plays a critical role in decision-making processes across diverse fields including meteorology, traffic, electricity, economics, finance, and so on. Especially, predicting returns on financial instruments is a challenging problem. Some researchers have proposed time series foundation models applicable to various forecasting tasks. Simultaneously, based on the recognition that real-world time series exhibit chaotic properties, methods have been developed to artificially g…

Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
Kaname Yokoyama, Chihiro Nakatani, Norimichi Ukita
https://arxiv.org/abs/2509.04758 https://

Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
This paper proposes dynamic human group detection in videos. For detecting complex groups, not only the local appearance features of in-group members but also the global context of the scene are important. Such local and global appearance features in each frame are extracted using a Vision-Language Model (VLM) augmented for group detection in our method. For further improvement, the group structure should be consistent over time. While previous methods are stabilized on the assumption that grou…

Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
Qiang Xu, Leon Stok, Rolf Drechsler, Xi Wang, Grace Li Zhang, Igor L. Markov
https://arxiv.org/abs/2509.04905

Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
Recent breakthroughs in Large Language Models (LLMs) and Large Circuit Models (LCMs) have sparked excitement across the electronic design automation (EDA) community, promising a revolution in circuit design and optimization. Yet, this excitement is met with significant skepticism: Are these AI models a genuine revolution in circuit design, or a temporary wave of inflated expectations? This paper serves as a foundational text for the corresponding ICCAD 2025 panel, bringing together perspectives…

MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment using UAV Imagery
Zhangding Liu, Neda Mohammadi, John E. Taylor
https://arxiv.org/abs/2509.04757 …

MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment using UAV Imagery
Rapid and accurate post-hurricane damage assessment is vital for disaster response and recovery. Yet existing CNN-based methods struggle to capture multi-scale spatial features and to distinguish visually similar or co-occurring damage types. To address these issues, we propose MCANet, a multi-label classification framework that learns multi-scale representations and adaptively attends to spatially relevant regions for each damage category. MCANet employs a Res2Net-based hierarchical backbone t…

An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning
Wonseo Jang, Dongjae Kim
https://arxiv.org/abs/2509.04815 https://

An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning
Deep reinforcement learning (RL) models, despite their efficiency in learning an optimal policy in static environments, easily loses previously learned knowledge (i.e., catastrophic forgetting). It leads RL models to poor performance in continual reinforcement learning (CRL) scenarios. To address this, we present an arbitration control mechanism over an ensemble of RL agents. It is motivated by and closely aligned with how humans make decisions in a CRL context using an arbitration control of m…

WatchHAR: Real-time On-device Human Activity Recognition System for Smartwatches
Taeyoung Yeon, Vasco Xu, Henry Hoffmann, Karan Ahuja
https://arxiv.org/abs/2509.04736 https://…

WatchHAR: Real-time On-device Human Activity Recognition System for Smartwatches
Despite advances in practical and multimodal fine-grained Human Activity Recognition (HAR), a system that runs entirely on smartwatches in unconstrained environments remains elusive. We present WatchHAR, an audio and inertial-based HAR system that operates fully on smartwatches, addressing privacy and latency issues associated with external data processing. By optimizing each component of the pipeline, WatchHAR achieves compounding performance gains. We introduce a novel architecture that unifi…

Graph Unlearning: Efficient Node Removal in Graph Neural Networks
Faqian Guan, Tianqing Zhu, Zhoutian Wang, Wei Ren, Wanlei Zhou
https://arxiv.org/abs/2509.04785 https://…

Graph Unlearning: Efficient Node Removal in Graph Neural Networks
With increasing concerns about privacy attacks and potential sensitive information leakage, researchers have actively explored methods to efficiently remove sensitive training data and reduce privacy risks in graph neural network (GNN) models. Node unlearning has emerged as a promising technique for protecting the privacy of sensitive nodes by efficiently removing specific training node information from GNN models. However, existing node unlearning methods either impose restrictions on the GNN …

Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
Dharsan Ravindran, Kevin Wang, Zhuoyuan Cao, Saleh Abdelrahman, Jeffery Wu
https://arxiv.org/abs/2509.04735

Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
Recent advances in vision foundation models, such as the Segment Anything Model (SAM) and its successor SAM2, have achieved state-of-the-art performance on general image segmentation benchmarks. However, these models struggle in adverse weather conditions where visual ambiguity is high, largely due to their lack of uncertainty quantification. Inspired by progress in medical imaging, where uncertainty-aware training has improved reliability in ambiguous cases, we investigate two approaches to en…

VARMA-Enhanced Transformer for Time Series Forecasting
Jiajun Song, Xiaoou Liu
https://arxiv.org/abs/2509.04782 https://arxiv.org/pdf/2509.04782

VARMA-Enhanced Transformer for Time Series Forecasting
Transformer-based models have significantly advanced time series forecasting. Recent work, like the Cross-Attention-only Time Series transformer (CATS), shows that removing self-attention can make the model more accurate and efficient. However, these streamlined architectures may overlook the fine-grained, local temporal dependencies effectively captured by classical statistical models like Vector AutoRegressive Moving Average model (VARMA). To address this gap, we propose VARMAformer, a novel …

Exploiting Unlabeled Structures through Task Consistency Training for Versatile Medical Image Segmentation
Shengqian Zhu, Jiafei Wu, Xiaogang Xu, Chengrong Yu, Ying Song, Zhang Yi, Guangjun Li, Junjie Hu
https://arxiv.org/abs/2509.04732

Exploiting Unlabeled Structures through Task Consistency Training for Versatile Medical Image Segmentation
Versatile medical image segmentation (VMIS) targets the segmentation of multiple classes, while obtaining full annotations for all classes is often impractical due to the time and labor required. Leveraging partially labeled datasets (PLDs) presents a promising alternative; however, current VMIS approaches face significant class imbalance due to the unequal category distribution in PLDs. Existing methods attempt to address this by generating pseudo-full labels. Nevertheless, these typically req…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/5]:
- Attention on flow control: transformer-based reinforcement learning for lift regulation in highly...
Zhecheng Liu, Jeff D. Eldredge

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/3]:
- AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anom...
Hao Ju, Hu Zhang, Zhedong Zheng

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/5]:
- Scaling Laws For Mixed Quantization
Zeyu Cao, Boyang Gu, Cheng Zhang, Pedro Gimenes, Jianqiao Lu, Jianyi Cheng, Xitong Gao, Yiren Zhao

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/3]:
- Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
Guo, Liu, Chen, Mao, Hu, Jiang, Yu, Xu, Liu, Xu, Chen, Guo

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/5]:
- Data Leakage and Redundancy in the LIT-PCBA Benchmark
Amber Huang, Ian Scott Knight, Slava Naprienko

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/3]:
- Representation-Centric Survey of Skeletal Action Recognition and the ANUBIS Benchmark
Liu, Yang, Perera, Ji, Kim, Xu, Wang, Anwar, Gedeon, Wang, Qin

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/5]:
- Towards Scalable Bayesian Optimization via Gradient-Informed Bayesian Neural Networks
Georgios Makrygiorgos, Joshua Hang Sai Ip, Ali Mesbah

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/1]:
- Sample-efficient Integration of New Modalities into Large Language Models
Osman Batur \.Ince, Andr\'e F. T. Martins, Oisin Mac Aodha, Edoardo M. Ponti

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- Guided Random Forest and its application to data approximation
Prashant Gupta, Aashi Jindal, Jayadeva, Debarka Sengupta

[2025-07-07 Mon (UTC), no new articles found for cs.LG Machine Learning]
toXiv_bot_toot