Tootfinder

A Versatile Dataset of Mouse and Eye Movements on Search Engine Results Pages
Kayhan Latifzadeh, Jacek Gwizdka, Luis A. Leiva
https://arxiv.org/abs/2507.08003

A Versatile Dataset of Mouse and Eye Movements on Search Engine Results Pages
We contribute a comprehensive dataset to study user attention and purchasing behavior on Search Engine Result Pages (SERPs). Previous work has relied on mouse movements as a low-cost large-scale behavioral proxy but also has relied on self-reported ground-truth labels, collected at post-task, which can be inaccurate and prone to biases. To address this limitation, we use an eye tracker to construct an objective ground-truth of continuous visual attention. Our dataset comprises 2,776 transaction…

Unsupervised Deep Equilibrium Model Learning for Large-Scale Channel Estimation with Performance Guarantees
Haotian Tian, Lixiang Lian
https://arxiv.org/abs/2508.10546 https://

Unsupervised Deep Equilibrium Model Learning for Large-Scale Channel Estimation with Performance Guarantees
Supervised deep learning methods have shown promise for large-scale channel estimation (LCE), but their reliance on ground-truth channel labels greatly limits their practicality in real-world systems. In this paper, we propose an unsupervised learning framework for LCE that does not require ground-truth channels. The proposed approach leverages Generalized Stein's Unbiased Risk Estimate (GSURE) as a principled unsupervised loss function, which provides an unbiased estimate of the projected mean…

🧩 Returns structured output as hierarchical JSON plus ready-to-render #Markdown format
👁️ Optional bounding-box snippets & f
ull-page visualizations for ground-truth verification

From One to More: Contextual Part Latents for 3D Generation
Shaocong Dong, Lihe Ding, Xiao Chen, Yaokun Li, Yuxin Wang, Yucheng Wang, Qi Wang, Jaehyeok Kim, Chenjian Gao, Zhanpeng Huang, Zibin Wang, Tianfan Xue, Dan Xu
https://arxiv.org/abs/2507.08772

From One to More: Contextual Part Latents for 3D Generation
Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth data. Despite progress, three key limitations persist: (1) Single-latent representations fail to capture complex multi-part geometries, causing detail degradation; (2) Holistic latent coding neglects part independence and interrelationships critical for compositional design; (3) Global conditioning mechanisms lack fine-…

Distillation versus Contrastive Learning: How to Train Your Rerankers
Zhichao Xu, Zhiqi Huang, Shengyao Zhuang, Ashim Gupta, Vivek Srikumar
https://arxiv.org/abs/2507.08336

Distillation versus Contrastive Learning: How to Train Your Rerankers
Training text rerankers is crucial for information retrieval. Two primary strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge from a larger reranker). While both have been studied in the literature, a clear comparison of their effectiveness for training cross-encoder rerankers under practical conditions is needed. This paper empirically compares these strategies by training rerankers of different size…

Exploring Expert Specialization through Unsupervised Training in Sparse Mixture of Experts
Strahinja Nikolic, Ilker Oguz, Demetri Psaltis
https://arxiv.org/abs/2509.10025 https:…

Exploring Expert Specialization through Unsupervised Training in Sparse Mixture of Experts
Understanding the internal organization of neural networks remains a fundamental challenge in deep learning interpretability. We address this challenge by exploring a novel Sparse Mixture of Experts Variational Autoencoder (SMoE-VAE) architecture. We test our model on the QuickDraw dataset, comparing unsupervised expert routing against a supervised baseline guided by ground-truth labels. Surprisingly, we find that unsupervised routing consistently achieves superior reconstruction performance. T…

HiRef: Leveraging Hierarchical Ontology and Network Refinement for Robust Medication Recommendation
Yan Ting Chok, Soyon Park, Seungheun Baek, Hajung Kim, Junhyun Lee, Jaewoo Kang
https://arxiv.org/abs/2508.10425

HiRef: Leveraging Hierarchical Ontology and Network Refinement for Robust Medication Recommendation
Medication recommendation is a crucial task for assisting physicians in making timely decisions from longitudinal patient medical records. However, real-world EHR data present significant challenges due to the presence of rarely observed medical entities and incomplete records that may not fully capture the clinical ground truth. While data-driven models trained on longitudinal Electronic Health Records often achieve strong empirical performance, they struggle to generalize under missing or nov…

Aerial-ground Cross-modal Localization: Dataset, Ground-truth, and Benchmark
Yandi Yang, Jianping Li, Youqi Liao, Yuhao Li, Yizhe Zhang, Zhen Dong, Bisheng Yang, Naser El-Sheimy
https://arxiv.org/abs/2509.07362

Aerial-ground Cross-modal Localization: Dataset, Ground-truth, and Benchmark
Accurate visual localization in dense urban environments poses a fundamental task in photogrammetry, geospatial information science, and robotics. While imagery is a low-cost and widely accessible sensing modality, its effectiveness on visual odometry is often limited by textureless surfaces, severe viewpoint changes, and long-term drift. The growing public availability of airborne laser scanning (ALS) data opens new avenues for scalable and precise visual localization by leveraging ALS as a pr…

😶‍🌫️ Generating real-time detailed ground visualisations from sparse aerial point clouds
#3d #xr

Generating real-time detailed ground visualisations from sparse aerial point clouds
Building realistic wide scale outdoor 3D content with sufficient visual quality to observe at walking eye level or from driven vehicles is often carried out by large teams of artists skilled in modelling, texturing, material shading and lighting, which typically leads to both prohibitive costs and reduced accuracy honoring the variety of real world ground truth landscapes. In our proposed method, we define a process to automatically amplify real-world scanned data and render real-time in animat…

In-Context Learning as Nonparametric Conditional Probability Estimation: Risk Bounds and Optimality
Chenrui Liu, Falong Tan, Chuanlong Xie, Yicheng Zeng, Lixing Zhu
https://arxiv.org/abs/2508.08673

In-Context Learning as Nonparametric Conditional Probability Estimation: Risk Bounds and Optimality
This paper investigates the expected excess risk of In-Context Learning (ICL) for multiclass classification. We model each task as a sequence of labeled prompt samples and a query input, where a pre-trained model estimates the conditional class probabilities of the query. The expected excess risk is defined as the average truncated Kullback-Leibler (KL) divergence between the predicted and ground-truth conditional class distributions, averaged over a specified family of tasks. We establish a ne…

Generation of realistic cardiac ultrasound sequences with ground truth motion and speckle decorrelation
Thierry Judge, Nicolas Duchateau, Khuram Faraz, Pierre-Marc Jodoin, Olivier Bernard
https://arxiv.org/abs/2509.05261

Generation of realistic cardiac ultrasound sequences with ground truth motion and speckle decorrelation
Simulated ultrasound image sequences are key for training and validating machine learning algorithms for left ventricular strain estimation. Several simulation pipelines have been proposed to generate sequences with corresponding ground truth motion, but they suffer from limited realism as they do not consider speckle decorrelation. In this work, we address this limitation by proposing an improved simulation framework that explicitly accounts for speckle decorrelation. Our method builds on an e…

SPEAR: Subset-sampled Performance Evaluation via Automated Ground Truth Generation for RAG
Zou Yuheng, Wang Yiran, Tian Yuzhu, Zhu Min, Huang Yanhua
https://arxiv.org/abs/2507.06554

SPEAR: Subset-sampled Performance Evaluation via Automated Ground Truth Generation for RAG
Retrieval-Augmented Generation (RAG) is a core approach for enhancing Large Language Models (LLMs), where the effectiveness of the retriever largely determines the overall response quality of RAG systems. Retrievers encompass a multitude of hyperparameters that significantly impact performance outcomes and demonstrate sensitivity to specific applications. Nevertheless, hyperparameter optimization entails prohibitively high computational expenses. Existing evaluation methods suffer from either p…

Quantifying Accuracy of an Event-Based Star Tracker via Earth's Rotation
Dennis Melamed, Connor Hashemi, Scott McCloskey
https://arxiv.org/abs/2509.08794 https://

Quantifying Accuracy of an Event-Based Star Tracker via Earth's Rotation
Event-based cameras (EBCs) are a promising new technology for star tracking-based attitude determination, but prior studies have struggled to determine accurate ground truth for real data. We analyze the accuracy of an EBC star tracking system utilizing the Earth's motion as the ground truth for comparison. The Earth rotates in a regular way with very small irregularities which are measured to the level of milli-arcseconds. By keeping an event camera static and pointing it through a ground-base…

Interesting early version release of iconclass-vlm, a specialised small vision language model that automatically generates ICONCLASS metadata for cultural heritage collections by Daniel van Strien
iconclass-vlm: https://huggingface.co/davanstrien/iconclass-vlm
model evaluatio…

Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
Maysam Behmanesh, Erkan Turan, Maks Ovsjanikov
https://arxiv.org/abs/2509.09597 https://

Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
Graph alignment-the problem of identifying corresponding nodes across multiple graphs-is fundamental to numerous applications. Most existing unsupervised methods embed node features into latent representations to enable cross-graph comparison without ground-truth correspondences. However, these methods suffer from two critical limitations: the degradation of node distinctiveness due to oversmoothing in GNN-based embeddings, and the misalignment of latent spaces across graphs caused by structura…

On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
Zhiyi Dong, Zixuan Liu, Yongyi Mao
https://arxiv.org/abs/2507.06552

On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
This paper studies the hardness of unsupervised domain adaptation (UDA) under covariate shift. We model the uncertainty that the learner faces by a distribution $π$ in the ground-truth triples $(p, q, f)$ -- which we call a UDA class -- where $(p, q)$ is the source -- target distribution pair and $f$ is the classifier. We define the performance of a learner as the overall target domain risk, averaged over the randomness of the ground-truth triple. This formulation couples the source distributi…

The-Bodega: A Matlab Toolbox for Biologically Dynamic Microbubble Simulations on Realistic Hemodynamic Microvascular Graphs
Stephen Alexander Lee, Alexis Leconte, Alice Wu, Jonathan Poree, Maxence Laplante-Berthier, Simon Desrocher, Pierre-Olivier Bouchard, Joshua Kinugasa, Samuel Mihelic, Andreas Linninger, Jean Provost
https://arxiv.org/…

The-Bodega: A Matlab Toolbox for Biologically Dynamic Microbubble Simulations on Realistic Hemodynamic Microvascular Graphs
The-Bodega is a Matlab-based toolbox for simulating ground-truth datasets for Ultrasound Localization Microscopy (ULM)-a super resolution imaging technique that resolves microvessels by systematically tracking microbubbles flowing through the microvasculature. The-Bodega enables open-source simulation of stochastic microbubble dynamics through anatomically complex vascular graphs and features a quasi-automated pipeline for generating ground-truth ultrasound data from simple vascular inputs. It …

Fisher Score Matching for Simulation-Based Forecasting and Inference
Ce Sui, Shivam Pandey, Benjamin D. Wandelt
https://arxiv.org/abs/2507.07833 https://…

Fisher Score Matching for Simulation-Based Forecasting and Inference
We propose a method for estimating the Fisher score--the gradient of the log-likelihood with respect to model parameters--using score matching. By introducing a latent parameter model, we show that the Fisher score can be learned by training a neural network to predict latent scores via a mean squared error loss. We validate our approach on a toy linear Gaussian model and a cosmological example using a differentiable simulator. In both cases, the learned scores closely match ground truth for pl…

MemTraceDB: Reconstructing MySQL User Activity Using ActiviTimeTrace Algorithm
Mahfuzul I. Nissan
https://arxiv.org/abs/2509.05891 https://arxiv.org/pdf/25…

MemTraceDB: Reconstructing MySQL User Activity Using ActiviTimeTrace Algorithm
Database audit and transaction logs are fundamental to forensic investigations, but they are vulnerable to tampering by privileged attackers. Malicious insiders or external threats with administrative access can alter, purge, or temporarily disable logging mechanisms, creating significant blind spots and rendering disk-based records unreliable. Memory analysis offers a vital alternative, providing investigators direct access to volatile artifacts that represent a ground-truth source of recent u…

DMER-Ranker: Learning to Rank Emotion Descriptions in the Absence of Ground Truth
Zheng Lian, Licai Sun, Haoyu Chen, Zebang Cheng, Fan Zhang, Ziyu Jia, Ziyang Ma, Fei Ma, Xiaojiang Peng, Jianhua Tao
https://arxiv.org/abs/2507.04278

DMER-Ranker: Learning to Rank Emotion Descriptions in the Absence of Ground Truth
Descriptive Multimodal Emotion Recognition (DMER) is a newly proposed task that aims to describe a person's emotional state using free-form natural language. Unlike traditional discriminative methods that rely on predefined emotion taxonomies, DMER provides greater flexibility in emotional expression, enabling fine-grained and interpretable emotion representations. However, this free-form prediction paradigm introduces significant challenges in evaluation. Existing methods either depend on grou…

No-Knowledge Alarms for Misaligned LLMs-as-Judges
Andr\'es Corrada-Emmanuel
https://arxiv.org/abs/2509.08593 https://arxiv.org/pdf/2509.08593

No-Knowledge Alarms for Misaligned LLMs-as-Judges
If we use LLMs as judges to evaluate the complex decisions of other LLMs, who or what monitors the judges? Infinite monitoring chains are inevitable whenever we do not know the ground truth of the decisions by experts and we do not want to trust them. One way to ameliorate our evaluation uncertainty is to exploit the use of logical consistency between disagreeing experts. By observing how LLM judges agree and disagree while grading other LLMs, we can compute the only possible evaluations of the…

Controllable Singing Voice Synthesis using Phoneme-Level Energy Sequence
Yerin Ryu, Inseop Shin, Chanwoo Kim
https://arxiv.org/abs/2509.07038 https://arxiv…

Controllable Singing Voice Synthesis using Phoneme-Level Energy Sequence
Controllable Singing Voice Synthesis (SVS) aims to generate expressive singing voices reflecting user intent. While recent SVS systems achieve high audio quality, most rely on probabilistic modeling, limiting precise control over attributes such as dynamics. We address this by focusing on dynamic control--temporal loudness variation essential for musical expressiveness--and explicitly condition the SVS model on energy sequences extracted from ground-truth spectrograms, reducing annotation costs…

Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions
Eve Fleisig, Matthias Orlikowski, Philipp Cimiano, Dan Klein
https://arxiv.org/abs/2509.08217 h…

Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions
For machine learning datasets to accurately represent diverse opinions in a population, they must preserve variation in data labels while filtering out spam or low-quality responses. How can we balance annotator reliability and representation? We empirically evaluate how a range of heuristics for annotator filtering affect the preservation of variation on subjective tasks. We find that these methods, designed for contexts in which variation from a single ground-truth label is considered noise, …

Transformer-based Topology Optimization
Aaron Lutheran, Srijan Das, Alireza Tabarraei
https://arxiv.org/abs/2509.05800 https://arxiv.org/pdf/2509.05800

Transformer-based Topology Optimization
Topology optimization enables the design of highly efficient and complex structures, but conventional iterative methods, such as SIMP-based approaches, often suffer from high computational costs and sensitivity to initial conditions. Although machine learning methods have recently shown promise for accelerating topology generation, existing models either remain iterative or struggle to match ground-truth performance. In this work, we propose a transformer-based machine learning model for topolo…

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Jiahao Wang, Yufeng Yuan, Rujie Zheng, Youtian Lin, Jian Gao, Lin-Zhuo Chen, Yajie Bao, Yi Zhang, Chang Zeng, Yanxi Zhou, Xiaoxiao Long, Hao Zhu, Zhaoxiang Zhang, Xun Cao, Yao Yao
https://arxiv.org/abs/2509.09676

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Significant progress has been made in spatial intelligence, spanning both spatial reconstruction and world exploration. However, the scalability and real-world fidelity of current models remain severely constrained by the scarcity of large-scale, high-quality training data. While several datasets provide camera pose information, they are typically limited in scale, diversity, and annotation richness, particularly for real-world dynamic scenes with ground-truth camera motion. To this end, we col…

An HTR-LLM Workflow for High-Accuracy Transcription and Analysis of Abbreviated Latin Court Hand
Joshua D. Isom
https://arxiv.org/abs/2507.04132 https://…

An HTR-LLM Workflow for High-Accuracy Transcription and Analysis of Abbreviated Latin Court Hand
This article presents and validates an ideal, four-stage workflow for the high-accuracy transcription and analysis of challenging medieval legal documents. The process begins with a specialized Handwritten Text Recognition (HTR) model, itself created using a novel "Clean Ground Truth" curation method where a Large Language Model (LLM) refines the training data. This HTR model provides a robust baseline transcription (Stage 1). In Stage 2, this baseline is fed, along with the original document i…

Exponential convergence rate for Iterative Markovian Fitting
Kirill Sokolov, Alexander Korotin
https://arxiv.org/abs/2508.02770 https://arxiv.org/pdf/2508.…

Exponential convergence rate for Iterative Markovian Fitting
We consider the discrete-time Schrödinger bridge problem on a finite state space. Although it has been known that the Iterative Markovian Fitting (IMF) algorithm converges in Kullback-Leibler divergence to the ground truth solution, the speed of that convergence remained unquantified. In this work, we establish for the first time that IMF exhibits exponential convergence with an explicit contraction factor.

Machine Learning-Based Prediction of Speech Arrest During Direct Cortical Stimulation Mapping
Nikasadat Emami, Amirhossein Khalilian-Gourtani, Jianghao Qian, Antoine Ratouchniak, Xupeng Chen, Yao Wang, Adeen Flinker
https://arxiv.org/abs/2509.08703

Machine Learning-Based Prediction of Speech Arrest During Direct Cortical Stimulation Mapping
Identifying cortical regions critical for speech is essential for safe brain surgery in or near language areas. While Electrical Stimulation Mapping (ESM) remains the clinical gold standard, it is invasive and time-consuming. To address this, we analyzed intracranial electrocorticographic (ECoG) data from 16 participants performing speech tasks and developed machine learning models to directly predict if the brain region underneath each ECoG electrode is critical. Ground truth labels indicating…

MVGBench: Comprehensive Benchmark for Multi-view Generation Models
Xianghui Xie, Chuhang Zou, Meher Gitika Karumuri, Jan Eric Lenssen, Gerard Pons-Moll
https://arxiv.org/abs/2507.00006

MVGBench: Comprehensive Benchmark for Multi-view Generation Models
We propose MVGBench, a comprehensive benchmark for multi-view image generation models (MVGs) that evaluates 3D consistency in geometry and texture, image quality, and semantics (using vision language models). Recently, MVGs have been the main driving force in 3D object creation. However, existing metrics compare generated images against ground truth target views, which is not suitable for generative tasks where multiple solutions exist while differing from ground truth. Furthermore, different M…

Fast Equivariant Imaging: Acceleration for Unsupervised Learning via Augmented Lagrangian and Auxiliary PnP Denoisers
Guixian Xu, Jinglai Li, Junqi Tang
https://arxiv.org/abs/2507.06764

Fast Equivariant Imaging: Acceleration for Unsupervised Learning via Augmented Lagrangian and Auxiliary PnP Denoisers
We propose Fast Equivariant Imaging (FEI), a novel unsupervised learning framework to efficiently train deep imaging networks without ground-truth data. From the perspective of reformulating the Equivariant Imaging based optimization problem via the method of Lagrange multipliers and utilizing plug-and-play denoisers, this novel unsupervised scheme shows superior efficiency and performance compared to vanilla Equivariant Imaging paradigm. In particular, our PnP-FEI scheme achieves an order-of-m…

Replaced article(s) found for cs.HC. https://arxiv.org/list/cs.HC/new
[1/1]:
- DMER-Ranker: Learning to Rank Emotion Descriptions in the Absence of Ground Truth
Lian, Sun, Chen, Cheng, Zhang, Jia, Ma, Ma, Peng, Tao

APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction
Sasan Sharifipour, Constantino \'Alvarez Casado, Mohammad Sabokrou, Miguel Bordallo L\'opez
https://arxiv.org/abs/2509.08104

APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction
Training deep learning models for point cloud prediction tasks such as shape completion and generation depends critically on loss functions that measure discrepancies between predicted and ground-truth point sets. Commonly used functions such as Chamfer Distance (CD), HyperCD, and InfoCD rely on nearest-neighbor assignments, which often induce many-to-one correspondences, leading to point congestion in dense regions and poor coverage in sparse regions. These losses also involve non-differentiab…

Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis
Markus Pettersson, Connor T. Jerzak, Adel Daoud
https://arxiv.org/abs/2508.01341

Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis
Machine learning models trained on Earth observation data, such as satellite imagery, have demonstrated significant promise in predicting household-level wealth indices, enabling the creation of high-resolution wealth maps that can be leveraged across multiple causal trials. However, because standard training objectives prioritize overall predictive accuracy, these predictions inherently suffer from shrinkage toward the mean, leading to attenuated estimates of causal treatment effects and limit…

Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
Amir Homayounirad, Enrico Liscio, Tong Wang, Catholijn M. Jonker, Luciano C. Siebert
https://arxiv.org/abs/2509.06704

Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying subjectivity in recognizing the human values that motivate arguments. We evaluate two main approaches: inferring subjectivity through value prediction vs. directly identifying subjectivity. Our experiments show that direct subjectivity identification significantly …

FIRE: Faithful Interpretable Recommendation Explanations
S. M. F. Sani, Asal Meskin, Mohammad Amanlou, Hamid R. Rabiee
https://arxiv.org/abs/2508.05225 https://

FIRE: Faithful Interpretable Recommendation Explanations
Natural language explanations in recommender systems are often framed as a review generation task, leveraging user reviews as ground-truth supervision. While convenient, this approach conflates a user's opinion with the system's reasoning, leading to explanations that may be fluent but fail to reflect the true logic behind recommendations. In this work, we revisit the core objective of explainable recommendation: to transparently communicate why an item is recommended by linking user needs to r…

TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
Honghua Dong, Jiacheng Yang, Xun Deng, Yuhe Jiang, Gennady Pekhimenko, Fan Long, Xujie Si
https://arxiv.org/abs/2507.22086

TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
Type inference for dynamic languages like Python is a persistent challenge in software engineering. While large language models (LLMs) have shown promise in code understanding, their type inference capabilities remain underexplored. We introduce TypyBench, a benchmark designed to evaluate LLMs' type inference across entire Python repositories. TypyBench features two novel metrics: TypeSim, which captures nuanced semantic relationships between predicted and ground truth types, and TypeCheck, whi…

Will AI rescue cultural heritage or replace it? In this IEEE video, learn how LLMs act as a compression algorithm for the Internet, enabling new forms of access while simultaneously threatening to replace ground truth with convincing facsimiles.
I also explain why mechanistic analogies, unlike animate metaphors like a child or parrot, can help us tune AI to get optimal results.

MoCap2GT: A High-Precision Ground Truth Estimator for SLAM Benchmarking Based on Motion Capture and IMU Fusion
Zichao Shu, Shitao Bei, Jicheng Dai, Lijun Li, Zetao Chen
https://arxiv.org/abs/2507.12920

MoCap2GT: A High-Precision Ground Truth Estimator for SLAM Benchmarking Based on Motion Capture and IMU Fusion
Marker-based optical motion capture (MoCap) systems are widely used to provide ground truth (GT) trajectories for benchmarking SLAM algorithms. However, the accuracy of MoCap-based GT trajectories is mainly affected by two factors: spatiotemporal calibration errors between the MoCap system and the device under test (DUT), and inherent MoCap jitter. Consequently, existing benchmarks focus primarily on absolute translation error, as accurate assessment of rotation and inter-frame errors remains c…

QuMAB: Query-based Multi-annotator Behavior Pattern Learning
Liyun Zhang, Zheng Lian, Hong Liu, Takanori Takebe, Yuta Nakashima
https://arxiv.org/abs/2507.17653 https://

QuMAB: Query-based Multi-annotator Behavior Pattern Learning
Multi-annotator learning traditionally aggregates diverse annotations to approximate a single ground truth, treating disagreements as noise. However, this paradigm faces fundamental challenges: subjective tasks often lack absolute ground truth, and sparse annotation coverage makes aggregation statistically unreliable. We introduce a paradigm shift from sample-wise aggregation to annotator-wise behavior modeling. By treating annotator disagreements as valuable information rather than noise, mode…

FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization
Sara Behnamian, Rasoul Khaksarinezhad, Andreas Langer
https://arxiv.org/abs/2509.08670

FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization
We present FractalPINN-Flow, an unsupervised deep learning framework for dense optical flow estimation that learns directly from consecutive grayscale frames without requiring ground truth. The architecture centers on the Fractal Deformation Network (FDN) - a recursive encoder-decoder inspired by fractal geometry and self-similarity. Unlike traditional CNNs with sequential downsampling, FDN uses repeated encoder-decoder nesting with skip connections to capture both fine-grained details and long…

Uncovering Reliable Indicators: Improving IoC Extraction from Threat Reports
Evangelos Froudakis, Athanasios Avgetidis, Sean Tyler Frankum, Roberto Perdisci, Manos Antonakakis, Angelos Keromytis
https://arxiv.org/abs/2506.11325

Uncovering Reliable Indicators: Improving IoC Extraction from Threat Reports
Indicators of Compromise (IoCs) are critical for threat detection and response, marking malicious activity across networks and systems. Yet, the effectiveness of automated IoC extraction systems is fundamentally limited by one key issue: the lack of high-quality ground truth. Current extraction tools rely either on manually extracted ground truth, which is labor-intensive and costly, or on automated ground truth creation methods that include non-malicious artifacts, leading to inflated false po…

Physics-Aware Style Transfer for Adaptive Holographic Reconstruction
Chanseok Lee, Fakhriyya Mammadova, Jiseong Barg, Mooseok Jang
https://arxiv.org/abs/2507.00482

Physics-Aware Style Transfer for Adaptive Holographic Reconstruction
Inline holographic imaging presents an ill-posed inverse problem of reconstructing objects' complex amplitude from recorded diffraction patterns. Although recent deep learning approaches have shown promise over classical phase retrieval algorithms, they often require high-quality ground truth datasets of complex amplitude maps to achieve a statistical inverse mapping operation between the two domains. Here, we present a physics-aware style transfer approach that interprets the object-to-sensor …

Multigranular Evaluation for Brain Visual Decoding
Weihao Xia, Cengiz Oztireli
https://arxiv.org/abs/2507.07993 https://arxiv.org/pdf…

Multigranular Evaluation for Brain Visual Decoding
Existing evaluation protocols for brain visual decoding predominantly rely on coarse metrics that obscure inter-model differences, lack neuroscientific foundation, and fail to capture fine-grained visual distinctions. To address these limitations, we introduce BASIC, a unified, multigranular evaluation framework that jointly quantifies structural fidelity, inferential alignment, and contextual coherence between decoded and ground truth images. For the structural level, we introduce a hierarchic…

Evaluating classical simulations with a quantum processor
Alberto Nocera, Jack Raymond, William Bernoudy, Mohammad H. Amin, Andrew D. King
https://arxiv.org/abs/2508.15759 https…

Evaluating classical simulations with a quantum processor
As simulations of quantum systems cross the limits of classical computability, both quantum and classical approaches become hard to verify. Scaling predictions are therefore based on local structure and asymptotic assumptions, typically with classical methods being used to evaluate quantum simulators where possible. Here, in contrast, we use a quantum annealing processor to produce a ground truth for evaluating classical tensor-network methods whose scaling has not yet been firmly established. …

TrainVerify: Equivalence-Based Verification for Distributed LLM Training
Yunchi Lu, Youshan Miao, Cheng Tan, Peng Huang, Yi Zhu, Xian Zhang, Fan Yang
https://arxiv.org/abs/2506.15961

TrainVerify: Equivalence-Based Verification for Distributed LLM Training
Training large language models (LLMs) at scale requires parallel execution across thousands of devices, incurring enormous computational costs. Yet, these costly distributed trainings are rarely verified, leaving them prone to silent errors and potentially wasting millions of GPU hours. We introduce TrainVerify, a system for verifiable distributed training of LLMs. Given a deep learning model's logical specification as the ground truth, TrainVerify formally verifies that a distributed parallel …

Generating real-time detailed ground visualisations from sparse aerial point clouds
Aidan Murray, Eddie Waite, Caleb Ross, Scarlet Mitchell, Alexander Bradley, Joanna Jamrozy, Kenny Mitchell
https://arxiv.org/abs/2507.18664

Generating real-time detailed ground visualisations from sparse aerial point clouds
Building realistic wide scale outdoor 3D content with sufficient visual quality to observe at walking eye level or from driven vehicles is often carried out by large teams of artists skilled in modelling, texturing, material shading and lighting, which typically leads to both prohibitive costs and reduced accuracy honoring the variety of real world ground truth landscapes. In our proposed method, we define a process to automatically amplify real-world scanned data and render real-time in animat…

Sensor network localization has a benign landscape after low-dimensional relaxation
Christopher Criscitiello, Andrew D. McRae, Quentin Rebjock, Nicolas Boumal
https://arxiv.org/abs/2507.15662

Sensor network localization has a benign landscape after low-dimensional relaxation
We consider the sensor network localization problem, also known as multidimensional scaling or Euclidean distance matrix completion. Given a ground truth configuration of $n$ points in $\mathbb{R}^\ell$, we observe a subset of the pairwise distances and aim to recover the underlying configuration (up to rigid transformations). We show with a simple counterexample that the associated optimization problem is nonconvex and may admit spurious local minimizers, even when all distances are known. Yet…

Centralized Copy-Paste: Enhanced Data Augmentation Strategy for Wildland Fire Semantic Segmentation
Joon Tai Kim, Tianle Chen, Ziyu Dong, Nishanth Kunchala, Alexander Guller, Daniel Ospina Acero, Roger Williams, Mrinal Kumar
https://arxiv.org/abs/2507.06321

Centralized Copy-Paste: Enhanced Data Augmentation Strategy for Wildland Fire Semantic Segmentation
Collecting and annotating images for the purpose of training segmentation models is often cost prohibitive. In the domain of wildland fire science, this challenge is further compounded by the scarcity of reliable public datasets with labeled ground truth. This paper presents the Centralized Copy-Paste Data Augmentation (CCPDA) method, for the purpose of assisting with the training of deep-learning multiclass segmentation models, with special focus on improving segmentation outcomes for the fire…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/9]:
- Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth
Jackson Eshbaugh

Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?
Wenxuan Shen, Mingjia Wang, Yaochen Wang, Dongping Chen, Junjie Yang, Yao Wan, Weiwei Lin
https://arxiv.org/abs/2508.03644

Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?
Retrieval-Augmented Generation (RAG) systems using Multimodal Large Language Models (MLLMs) show great promise for complex document understanding, yet their development is critically hampered by inadequate evaluation. Current benchmarks often focus on specific part of document RAG system and use synthetic data with incomplete ground truth and evidence labels, therefore failing to reflect real-world bottlenecks and challenges. To overcome these limitations, we introduce Double-Bench: a new large…

Analysis of Semantic Communication for Logic-based Hypothesis Deduction
Ahmet Faruk Saz, Siheng Xiong, Faramarz Fekri
https://arxiv.org/abs/2508.21755 https://

Analysis of Semantic Communication for Logic-based Hypothesis Deduction
This work presents an analysis of semantic communication in the context of First-Order Logic (FOL)-based deduction. Specifically, the receiver holds a set of hypotheses about the State of the World (SotW), while the transmitter has incomplete evidence about the true SotW but lacks access to the ground truth. The transmitter aims to communicate limited information to help the receiver identify the hypothesis most consistent with true SotW. We formulate the objective as approximating the posterio…

Posterior contraction rates of computational methods for Bayesian data assimilation
Erik Burman, Mingfei Lu
https://arxiv.org/abs/2506.14685 https://

Posterior contraction rates of computational methods for Bayesian data assimilation
In this paper, we analyze posterior consistency of a Bayesian data assimilation problem under discretization. We prove convergence rates for the discrete posterior to ground truth solution under both conforming discretization and finite element discretization (usually non-conforming). The analysis is based on the coupling of asymptotics between the number of samples and the dimension of discrete spaces. In the finite element discretization, tailor-made discrete priors, instead of the discretiza…

Unsupervised learning for inverse problems in computed tomography
Laura Hellwege, Johann Christopher Engster, Moritz Schaar, Thorsten M. Buzug, Maik Stille
https://arxiv.org/abs/2508.05321

Unsupervised learning for inverse problems in computed tomography
This study presents an unsupervised deep learning approach for computed tomography (CT) image reconstruction, leveraging the inherent similarities between deep neural network training and conventional iterative reconstruction methods. By incorporating forward and backward projection layers within the deep learning framework, we demonstrate the feasibility of reconstructing images from projection data without relying on ground-truth images. Our method is evaluated on the two-dimensional 2DeteCT …

Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approach
Aymen Merrouche, Stefanie Wuhrer, Edmond Boyer
https://arxiv.org/abs/2509.06862 https…

Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approach
Non-rigid 3D mesh matching is a critical step in computer vision and computer graphics pipelines. We tackle matching meshes that contain topological artefacts which can break the assumption made by current approaches. While Functional Maps assume the deformation induced by the ground truth correspondences to be near-isometric, ARAP-like deformation-guided approaches assume the latter to be ARAP. Neither assumption holds in certain topological configurations of the input shapes. We are motivated…

orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels
Niran Nataraj, Maina Sogabe, Kenji Kawashima
https://arxiv.org/abs/2506.14303

orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels
Deep learning in medical imaging faces obstacles: limited data diversity, ethical issues, high acquisition costs, and the need for precise annotations. Bleeding detection and localization during surgery is especially challenging due to the scarcity of high-quality datasets that reflect real surgical scenarios. We propose orGAN, a GAN-based system for generating high-fidelity, annotated surgical images of bleeding. By leveraging small "mimicking organ" datasets, synthetic models that replicate t…

Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks
M. Janssen, C. -k. Chan, J. Davelaar, M. Wielgus
https://arxiv.org/abs/2506.13875

Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks
(abridged) In this second paper in our publication series, we present the open-source Zingularity framework for parameter inference with deep Bayesian artificial neural networks. We carried out out supervised learning with synthetic millimeter very long baseline interferometry observations of the EHT. Our ground-truth models are based on GRMHD simulations of Sgr A* and M87* on horizon scales. We investigated how well Zingularity neural networks are able to infer key model parameters from EHT ob…

When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias--variance tradeoff
Paul Scherer, Andreas Kirsch, Jake P. Taylor-King
https://arxiv.org/abs/2509.04363

When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias--variance tradeoff
Real-world experimental scenarios are characterized by the presence of heteroskedastic aleatoric uncertainty, and this uncertainty can be correlated in batched settings. The bias--variance tradeoff can be used to write the expected mean squared error between a model distribution and a ground-truth random variable as the sum of an epistemic uncertainty term, the bias squared, and an aleatoric uncertainty term. We leverage this relationship to propose novel active learning strategies that directl…

Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems
Lijia Liu, Takumi Kondo, Kyohei Atarashi, Koh Takeuchi, Jiyi Li, Shigeru Saito, Hisashi Kashima
https://arxiv.org/abs/2507.23453

Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems
This paper investigates defenses for LLM-based evaluation systems against prompt injection. We formalize a class of threats called blind attacks, where a candidate answer is crafted independently of the true answer to deceive the evaluator. To counter such attacks, we propose a framework that augments Standard Evaluation (SE) with Counterfactual Evaluation (CFE), which re-evaluates the submission against a deliberately false ground-truth answer. An attack is detected if the system validates an …

LuxDiT: Lighting Estimation with Video Diffusion Transformer
Ruofan Liang, Kai He, Zan Gojcic, Igor Gilitschenski, Sanja Fidler, Nandita Vijaykumar, Zian Wang
https://arxiv.org/abs/2509.03680

LuxDiT: Lighting Estimation with Video Diffusion Transformer
Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics. Learning-based approaches are constrained by the scarcity of ground-truth HDR environment maps, which are expensive to capture and limited in diversity. While recent generative models offer strong priors for image synthesis, lighting estimation remains difficult due to its reliance on indirect visual cues, the need to infer global (non-local) context, and the recovery of high…

Revisiting Active Learning under (Human) Label Variation
Cornelia Gruber, Helen Alber, Bernd Bischl, G\"oran Kauermann, Barbara Plank, Matthias A{\ss}enmacher
https://arxiv.org/abs/2507.02593

Revisiting Active Learning under (Human) Label Variation
Access to high-quality labeled data remains a limiting factor in applied supervised learning. While label variation (LV), i.e., differing labels for the same instance, is common, especially in natural language processing, annotation frameworks often still rest on the assumption of a single ground truth. This overlooks human label variation (HLV), the occurrence of plausible differences in annotations, as an informative signal. Similarly, active learning (AL), a popular approach to optimizing th…

HistoryFinder: Advancing Method-Level Source Code History Generation with Accurate Oracles and Enhanced Algorithm
Shahidul Islam, Ashik Aowal, Md Sharif Uddin, Shaiful Chowdhury
https://arxiv.org/abs/2507.14716

HistoryFinder: Advancing Method-Level Source Code History Generation with Accurate Oracles and Enhanced Algorithm
Reconstructing a method's change history efficiently and accurately is critical for many software engineering tasks, including maintenance, refactoring, and comprehension. Despite the availability of method history generation tools such as CodeShovel and CodeTracker, existing evaluations of their effectiveness are limited by inaccuracies in the ground truth oracles used. In this study, we systematically construct two new oracles -- the corrected CodeShovel oracle and a newly developed HistoryFi…

Interactive Evaluation of Large Language Models for Multi-Requirement Software Engineering Tasks
Dimitrios Rontogiannis, Maxime Peyrard, Nicolas Baldwin, Martin Josifoski, Robert West, Dimitrios Gunopulos
https://arxiv.org/abs/2508.18905

Interactive Evaluation of Large Language Models for Multi-Requirement Software Engineering Tasks
Standard single-turn, static benchmarks fall short in evaluating the nuanced capabilities of Large Language Models (LLMs) on complex tasks such as software engineering. In this work, we propose a novel interactive evaluation framework that assesses LLMs on multi-requirement programming tasks through structured, feedback-driven dialogue. Each task is modeled as a requirement dependency graph, and an ``interviewer'' LLM, aware of the ground-truth solution, provides minimal, targeted hints to an `…

Evaluation of Stress Detection as Time Series Events -- A Novel Window-Based F1-Metric
Harald Vilhelm Skat-R{\o}rdam, Sneha Das, Kathrine Sofie Rasmussen, Nicole Nadine L{\o}nfeldt, Line Clemmensen
https://arxiv.org/abs/2509.03240

Evaluation of Stress Detection as Time Series Events -- A Novel Window-Based F1-Metric
Accurate evaluation of event detection in time series is essential for applications such as stress monitoring with wearable devices, where ground truth is typically annotated as single-point events, even though the underlying phenomena are gradual and temporally diffused. Standard metrics like F1 and point-adjusted F1 (F1$_{pa}$) often misrepresent model performance in such real-world, imbalanced datasets. We introduce a window-based F1 metric (F1$_w$) that incorporates temporal tolerance, enab…

i2Nav-Robot: A Large-Scale Indoor-Outdoor Robot Dataset for Multi-Sensor Fusion Navigation and Mapping
Hailiang Tang, Tisheng Zhang, Liqiang Wang, Xin Ding, Man Yuan, Zhiyu Xiang, Jujin Chen, Yuhan Bian, Shuangyan Liu, Yuqing Wang, Guan Wang, Xiaoji Niu
https://arxiv.org/abs/2508.11485

i2Nav-Robot: A Large-Scale Indoor-Outdoor Robot Dataset for Multi-Sensor Fusion Navigation and Mapping
Accurate and reliable navigation is crucial for autonomous unmanned ground vehicle (UGV). However, current UGV datasets fall short in meeting the demands for advancing navigation and mapping techniques due to limitations in sensor configuration, time synchronization, ground truth, and scenario diversity. To address these challenges, we present i2Nav-Robot, a large-scale dataset designed for multi-sensor fusion navigation and mapping in indoor-outdoor environments. We integrate multi-modal senso…

Instance-Specific Test-Time Training for Speech Editing in the Wild
Taewoo Kim, Uijong Lee, Hayoung Park, Choongsang Cho, Nam In Park, Young Han Lee
https://arxiv.org/abs/2506.13295

Instance-Specific Test-Time Training for Speech Editing in the Wild
Speech editing systems aim to naturally modify speech content while preserving acoustic consistency and speaker identity. However, previous studies often struggle to adapt to unseen and diverse acoustic conditions, resulting in degraded editing performance in real-world scenarios. To address this, we propose an instance-specific test-time training method for speech editing in the wild. Our approach employs direct supervision from ground-truth acoustic features in unedited regions, and indirect …

In-Training Multicalibrated Survival Analysis for Healthcare via Constrained Optimization
Thiti Suttaket, Stanley Kok
https://arxiv.org/abs/2507.02807 http…

In-Training Multicalibrated Survival Analysis for Healthcare via Constrained Optimization
Survival analysis is an important problem in healthcare because it models the relationship between an individual's covariates and the onset time of an event of interest (e.g., death). It is important for survival models to be well-calibrated (i.e., for their predicted probabilities to be close to ground-truth probabilities) because badly calibrated systems can result in erroneous clinical decisions. Existing survival models are typically calibrated at the population level only, and thus run the…

Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality
Naihe Feng, Yi Sui, Shiyi Hou, Jesse C. Cresswell, Ga Wu
https://arxiv.org/abs/2506.20978

Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality
Existing research on Retrieval-Augmented Generation (RAG) primarily focuses on improving overall question-answering accuracy, often overlooking the quality of sub-claims within generated responses. Recent methods that attempt to improve RAG trustworthiness, such as through auto-evaluation metrics, lack probabilistic guarantees or require ground truth answers. To address these limitations, we propose Conformal-RAG, a novel framework inspired by recent applications of conformal prediction (CP) on…

R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation
Futian Wang, Yuhan Qiao, Xiao Wang, Fuling Wang, Yuxiang Zhang, Dengdi Sun
https://arxiv.org/abs/2508.03426

R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation
X-ray medical report generation is one of the important applications of artificial intelligence in healthcare. With the support of large foundation models, the quality of medical report generation has significantly improved. However, challenges such as hallucination and weak disease diagnostic capability still persist. In this paper, we first construct a large-scale multi-modal medical knowledge graph (termed M3KG) based on the ground truth medical report using the GPT-4o. It contains 2477 enti…

Evaluating Disassembly Errors With Only Binaries
Lambang Akbar Wijayadi, Yuancheng Jiang, Roland H. C. Yap, Zhenkai Liang, Zhuohao Liu
https://arxiv.org/abs/2506.20109

Evaluating Disassembly Errors With Only Binaries
Disassemblers are crucial in the analysis and modification of binaries. Existing works showing disassembler errors largely rely on practical implementation without specific guarantees and assume source code and compiler toolchains to evaluate ground truth. However, the assumption of source code is contrary to typical binary scenarios where only the binary is available. In this work, we investigate an approach with minimal assumptions and a sound approach to disassembly error evaluation that doe…

PiCSAR: Probabilistic Confidence Selection And Ranking
Joshua Ong Jun Leang, Zheng Zhao, Aryo Pradipta Gema, Sohee Yang, Wai-Chung Kwan, Xuanli He, Wenda Li, Pasquale Minervini, Eleonora Giunchiglia, Shay B. Cohen
https://arxiv.org/abs/2508.21787

PiCSAR: Probabilistic Confidence Selection And Ranking
Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward. The key challenge for reasoning tasks is designing a scoring function that can identify correct reasoning chains without access to ground-truth answers. We propose Probabilistic Confidence Selection And Ranking (PiCSAR): a simple, training-free method that scores each candidate generation using the jo…

IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects
Xiaokang Wei, Zizheng Yan, Zhangyang Xiong, Yiming Hao, Yipeng Qin, Xiaoguang Han
https://arxiv.org/abs/2509.00777

IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects
Estimating albedo (a.k.a., intrinsic image decomposition) from single RGB images captured in real-world environments (e.g., the MVImgNet dataset) presents a significant challenge due to the absence of paired images and their ground truth albedos. Therefore, while recent methods (e.g., IntrinsicAnything) have achieved breakthroughs by harnessing powerful diffusion priors, they remain predominantly trained on large-scale synthetic datasets (e.g., Objaverse) and applied directly to real-world RGB …

Beyond Syntax: Action Semantics Learning for App Agents
Bohan Tang, Dezhao Luo, Jingxuan Chen, Shaogang Gong, Jianye Hao, Jun Wang, Kun Shao
https://arxiv.org/abs/2506.17697

Beyond Syntax: Action Semantics Learning for App Agents
The advent of Large Language Models (LLMs) enables the rise of App agents that interpret user intent and operate smartphone Apps through actions such as clicking and scrolling. While prompt-based solutions with closed LLM APIs show promising ability, they incur heavy compute costs and external API dependency. Fine-tuning smaller open-source LLMs solves these limitations. However, current fine-tuning methods use a syntax learning paradigm that forces agents to reproduce exactly the ground truth …

A Computationally Aware Multi Objective Framework for Camera LiDAR Calibration
Venkat Karramreddy, Rangarajan Ramanujam
https://arxiv.org/abs/2506.20636 ht…

A Computationally Aware Multi Objective Framework for Camera LiDAR Calibration
Accurate extrinsic calibration between LiDAR and camera sensors is important for reliable perception in autonomous systems. In this paper, we present a novel multi-objective optimization framework that jointly minimizes the geometric alignment error and computational cost associated with camera-LiDAR calibration. We optimize two objectives: (1) error between projected LiDAR points and ground-truth image edges, and (2) a composite metric for computational cost reflecting runtime and resource usa…

PAOLI: Pose-free Articulated Object Learning from Sparse-view Images
Jianning Deng, Kartic Subr, Hakan Bilen
https://arxiv.org/abs/2509.04276 https://arxiv…

PAOLI: Pose-free Articulated Object Learning from Sparse-view Images
We present a novel self-supervised framework for learning articulated object representations from sparse-view, unposed images. Unlike prior methods that require dense multi-view observations and ground-truth camera poses, our approach operates with as few as four views per articulation and no camera supervision. To address the inherent challenges, we first reconstruct each articulation independently using recent advances in sparse-view 3D reconstruction, then learn a deformation field that esta…

A Deep Learning Based Method for Fast Registration of Cardiac Magnetic Resonance Images
Benjamin Graham
https://arxiv.org/abs/2506.19167 https://

A Deep Learning Based Method for Fast Registration of Cardiac Magnetic Resonance Images
Image registration is used in many medical image analysis applications, such as tracking the motion of tissue in cardiac images, where cardiac kinematics can be an indicator of tissue health. Registration is a challenging problem for deep learning algorithms because ground truth transformations are not feasible to create, and because there are potentially multiple transformations that can produce images that appear correlated with the goal. Unsupervised methods have been proposed to learn to pr…

Machine Learning-based Context-Aware EMAs: An Offline Feasibility Study
Zachary D King, Maryam Khalid, Han Yu, Kei Shibuya, Khadija Zanna, Marzieh Majd, Ryan L Brown, Yufei Shen, Thomas Vaessen, George Kypriotakis, Christopher P Fagundes, Akane Sano
https://arxiv.org/abs/2506.15834

Machine Learning-based Context-Aware EMAs: An Offline Feasibility Study
Mobile health (mHealth) systems help researchers monitor and care for patients in real-world settings. Studies utilizing mHealth applications use Ecological Momentary Assessment (EMAs), passive sensing, and contextual features to develop emotion recognition models, which rely on EMA responses as ground truth. Due to this, it is crucial to consider EMA compliance when conducting a successful mHealth study. Utilizing machine learning is one approach that can solve this problem by sending EMAs bas…

A Universal Framework for Offline Serendipity Evaluation in Recommender Systems via Large Language Models
Yu Tokutake, Kazushi Okamoto, Kei Harada, Atsushi Shibata, Koki Karube
https://arxiv.org/abs/2508.17571

A Universal Framework for Offline Serendipity Evaluation in Recommender Systems via Large Language Models
Serendipity in recommender systems (RSs) has attracted increasing attention as a concept that enhances user satisfaction by presenting unexpected and useful items. However, evaluating serendipitous performance remains challenging because its ground truth is generally unobservable. The existing offline metrics often depend on ambiguous definitions or are tailored to specific datasets and RSs, thereby limiting their generalizability. To address this issue, we propose a universally applicable eval…

Generative Annotation for ASR Named Entity Correction
Yuanchang Luo, Daimeng Wei, Shaojun Li, Hengchao Shang, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Xiaoyu Chen, Zhiqiang Rao, Jinlong Yang, Hao Yang
https://arxiv.org/abs/2508.20700

Generative Annotation for ASR Named Entity Correction
End-to-end automatic speech recognition systems often fail to transcribe domain-specific named entities, causing catastrophic failures in downstream tasks. Numerous fast and lightweight named entity correction (NEC) models have been proposed in recent years. These models, mainly leveraging phonetic-level edit distance algorithms, have shown impressive performances. However, when the forms of the wrongly-transcribed words(s) and the ground-truth entity are significantly different, these methods …

G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance
Yongxin Guo, Wenbo Deng, Zhenglin Cheng, Xiaoying Tang
https://arxiv.org/abs/2508.13023 https://

G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance
Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest improvements for small-size language models (SLMs). To address this limitation, we investigate Guided GRPO, which injects ground-truth reasoning steps into roll-out trajectories to compensate for SLMs' inherent weaknesses. Through a comprehensive study of va…

On the existence of consistent adversarial attacks in high-dimensional linear classification
Matteo Vilucchio, Lenka Zdeborov\'a, Bruno Loureiro
https://arxiv.org/abs/2506.12454

On the existence of consistent adversarial attacks in high-dimensional linear classification
What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this work, we investigate this question in the setting of high-dimensional binary classification, where statistical effects due to limited data availability play a central role. We introduce a new error metric that precisely capture this distinction, quantifying model vulnerability to consistent adversarial attacks -- perturbations that preserve the ground-truth l…

Systole-Conditioned Generative Cardiac Motion
Shahar Zuler, Gal Lifshitz, Hadar Averbuch-Elor, Dan Raviv
https://arxiv.org/abs/2507.15894 https://

Systole-Conditioned Generative Cardiac Motion
Accurate motion estimation in cardiac computed tomography (CT) imaging is critical for assessing cardiac function and surgical planning. Data-driven methods have become the standard approach for dense motion estimation, but they rely on vast amounts of labeled data with dense ground-truth (GT) motion annotations, which are often unfeasible to obtain. To address this limitation, we present a novel approach that synthesizes realistically looking pairs of cardiac CT frames enriched with dense 3D f…

Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems
Benedetta Muscato, Lucia Passaro, Gizem Gezici, Fosca Giannotti
https://arxiv.org/abs/2506.20209 …

Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems
In the realm of Natural Language Processing (NLP), common approaches for handling human disagreement consist of aggregating annotators' viewpoints to establish a single ground truth. However, prior studies show that disregarding individual opinions can lead can lead to the side effect of underrepresenting minority perspectives, especially in subjective tasks, where annotators may systematically disagree because of their preferences. Recognizing that labels reflect the diverse backgrounds, life …

Evaluating Explainability: A Framework for Systematic Assessment and Reporting of Explainable AI Features
Miguel A. Lago, Ghada Zamzmi, Brandon Eich, Jana G. Delfino
https://arxiv.org/abs/2506.13917

Evaluating Explainability: A Framework for Systematic Assessment and Reporting of Explainable AI Features
Explainability features are intended to provide insight into the internal mechanisms of an AI device, but there is a lack of evaluation techniques for assessing the quality of provided explanations. We propose a framework to assess and report explainable AI features. Our evaluation framework for AI explainability is based on four criteria: 1) Consistency quantifies the variability of explanations to similar inputs, 2) Plausibility estimates how close the explanation is to the ground truth, 3) F…

Enhancing Reference-based Sketch Colorization via Separating Reference Representations
Dingkun Yan, Xinrui Wang, Zhuoru Li, Suguru Saito, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo
https://arxiv.org/abs/2508.17620

Enhancing Reference-based Sketch Colorization via Separating Reference Representations
Reference-based sketch colorization methods have garnered significant attention for the potential application in animation and digital illustration production. However, most existing methods are trained with image triplets of sketch, reference, and ground truth that are semantically and spatially similar, while real-world references and sketches often exhibit substantial misalignment. This mismatch in data distribution between training and inference leads to overfitting, consequently resulting …

Explainable Knowledge Distillation for Efficient Medical Image Classification
Aqib Nazir Mir, Danish Raza Rizvi
https://arxiv.org/abs/2508.15251 https://ar…

Explainable Knowledge Distillation for Efficient Medical Image Classification
This study comprehensively explores knowledge distillation frameworks for COVID-19 and lung cancer classification using chest X-ray (CXR) images. We employ high-capacity teacher models, including VGG19 and lightweight Vision Transformers (Visformer-S and AutoFormer-V2-T), to guide the training of a compact, hardware-aware student model derived from the OFA-595 supernet. Our approach leverages hybrid supervision, combining ground-truth labels with teacher models' soft targets to balance accuracy…

Active View Selector: Fast and Accurate Active View Selection with Cross Reference Image Quality Assessment
Zirui Wang, Yash Bhalgat, Ruining Li, Victor Adrian Prisacariu
https://arxiv.org/abs/2506.19844

Active View Selector: Fast and Accurate Active View Selection with Cross Reference Image Quality Assessment
We tackle active view selection in novel view synthesis and 3D reconstruction. Existing methods like FisheRF and ActiveNeRF select the next best view by minimizing uncertainty or maximizing information gain in 3D, but they require specialized designs for different 3D representations and involve complex modelling in 3D space. Instead, we reframe this as a 2D image quality assessment (IQA) task, selecting views where current renderings have the lowest quality. Since ground-truth images for candid…

Beyond Human Judgment: A Bayesian Evaluation of LLMs' Moral Values Understanding
Maciej Skorski, Alina Landowska
https://arxiv.org/abs/2508.13804 https://

Beyond Human Judgment: A Bayesian Evaluation of LLMs' Moral Values Understanding
How do large language models understand moral dimensions compared to humans? This first large-scale Bayesian evaluation of market-leading language models provides the answer. In contrast to prior work using deterministic ground truth (majority or inclusion rules), we model annotator disagreements to capture both aleatoric uncertainty (inherent human disagreement) and epistemic uncertainty (model domain sensitivity). We evaluate top language models (Claude Sonnet 4, DeepSeek-V3, Llama 4 Maveri…

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…

Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
Giacomo Meanti, Thomas Ryckeboer, Michael Arbel, Julien Mairal
https://arxiv.org/abs/2506.14605

Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
This work addresses image restoration tasks through the lens of inverse problems using unpaired datasets. In contrast to traditional approaches -- which typically assume full knowledge of the forward model or access to paired degraded and ground-truth images -- the proposed method operates under minimal assumptions and relies only on small, unpaired datasets. This makes it particularly well-suited for real-world scenarios, where the forward model is often unknown or misspecified, and collecting…