Artificial Intelligence
Interpreting the predictions of neural network classification based on a Taylor Coefficient Analysis (TCA)
Markus Klute, Artur Monsch, Lars Sowa et al. (+1 more)
We introduce a rigid and comprehensive taxonomy and paradigm for characterizing the influence of the input feature space $X$ on the predictions $\hat{y}$ of a neural network (NN) used for event classification, based on a Taylor expansion of $\hat{y}$ in $X$. The complete process of introspection we refer to as Taylor Coefficient Analysis (TCA). Based on two simplistic example tasks, which can be easily understood and bencmarked, we illustrate the power of the TCA when it comes to revealing, what properties of $X$ have led to what value of $\hat{y}$, of a given NN model, building up intuition for the method. A more complex application is meant to represent $X$ of a typical classification task at a CERN LHC experiment. Based on this application, we play through the different levels of introspection that the TCA offers and discuss a number of practical aspects for a TCA application typical for the analysis of CERN LHC data. We conclude with a study to support the assumption that those properties of $X$ most relevant for tasks of the complexity typical for a CERN LHC experiment, are usually caught by a TCA up to the second order.
Read the full abstract ▾
All authors Markus Klute, Artur Monsch, Lars Sowa, Roger Wolf
Computer Vision
LGFN: Lightweight Gated RGB-Polarization Fusion with Modality-Availability Conditioning for Camouflaged Object Detection
Zhuangfan Huang, Xiaosong Li, Yang Liu et al. (+2 more)
Camouflaged object detection (COD) is an important engineering task in intelligent optical perception, but it remains challenging when targets closely resemble their surroundings. Polarization imaging provides complementary physical cues, whereas existing methods typically assume fixed
multimodal input configurations and entangle intra-polarization coordination with interaction between red-green-blue (RGB) and polarization representations. We propose LGFN, a lightweight gated RGB-polarization fusion framework supporting separately optimized RGB-only and polarization-assisted configurations. A deterministic Modality Router selects the appropriate configuration according to polarization availability. In the
multimodal configuration, an availability-conditioned Modality Gate calibrates the available polarization branches; the Gated Polarization Hub coordinates learned degree of linear polarization (DoLP) and angle of polarization (AoP) representations with explicit polarization cues; and RGB-Polarization Cross Fusion introduces the coordinated representation into the RGB hierarchy through controlled residual interaction. The
multimodal configuration requires neither sample-dependent statistics nor handcrafted quality descriptors during inference. On the complete 230-image PCOD_1200 test set, the RGB-only configuration achieves a mean absolute error of 0.0090, a Dice score of 0.8806, and an intersection over union of 0.8144, obtaining the best results on all six metrics among the evaluated RGB-based methods. Under a common local reevaluation protocol, the
multimodal configuration outperforms PolarNet and IPNet on all six metrics. Relative to IPNet, it reduces the parameter count, floating-point operations, and latency by 53.1%, 73.6%, and 63.0%, respectively. The source code will be available at https://github.com/1hzf/LGFN.
Read the full abstract ▾
All authors Zhuangfan Huang, Xiaosong Li, Yang Liu, Tao Ye, Haishu Tan
Robotics
High-Fidelity Multi-Body Simulator for Autonomous Racing
Nicola Musiu, Francesco Iacovacci, Fausto Lupo et al. (+11 more)
We present a custom high-fidelity vehicle dynamics simulation environment for testing and validation of Autonomous Racing software. The digital twin of the autonomous vehicle is developed in Dymola, using racecar dynamics modeling libraries to build a complete multi-body model. A 3D road surface, including elevation profiles and curbs, is implemented using the Curved Regular Grid (CRG) standard. The model is exported from Dymola as a Functional Mock-up Unit (FMU) and integrated into a custom software-in-the-loop simulator, where communication interfaces with the autonomous racing stack were developed in C++. A calibration procedure based on experimental data is also presented, along with a validation study to further support the quality of the proposed framework. The simulator runs in real time on a portable computer and provides reliable ground truth for
algorithms validation prior to real-world deployment.
Read the full abstract ▾
All authors Nicola Musiu, Francesco Iacovacci, Fausto Lupo, Matteo Pini, Giovanni Scapicchi, Francesco Moretti, Eugenio Mascaro, Pietro Musso, Ayoub Raji, Marko Bertogna, Vincenzo Maria Arricale, Angelo Lo Sapio, Alessandro Piccarelli, Garron Fish
Machine Learning
VertiFuseX: Generalizable Financial Forecasting via Multi-Stream Temporal Fusion
Aashish Bohra and Vivek Vijay
Stock price prediction remains challenging due to the non-stationary and noisy nature of financial time series. Existing deep learning models often rely on rigid decision-level fusion, ad hoc hyperparameter tuning, and compressed final-layer outputs, causing information loss, overfitting, and limited cross-
market generalization. We propose VertiFuseX, a hybrid LSTM architecture using penultimate-layer vertical fusion of multi-scale temporal representations. VertiFuseX stacks and reweights penultimate features from LSTM, Bi-LSTM, and St-LSTM branches, integrates a parallel DNN stream, and jointly optimizes all components via backpropagation under a fixed hyperparameter configuration. This preserves richer intermediate temporal information across scales. Evaluated on 15 years (2010-2024) of closing prices from 10 global equity indices using strict chronological out-of-sample testing with the final 365 trading days held out, VertiFuseX achieves 30-54% MAPE reductions and over 40% improvements in MAE and RMSE versus LSTM-based baselines, and outperforms seven state-of-the-art models across 33 metric-
dataset comparisons. Ablation studies confirm penultimate-layer fusion drives these gains over final-layer fusion and decision-level ensembling. Gradient-based saliency analysis shows consistent emphasis on mid-range dependencies at lags 9-15 days. Economic validation via algorithmic trading simulation under extreme
market regimes shows reduced maximum drawdowns and superior risk-adjusted returns. With 675k parameters, a 2.6 MB
memory footprint, and 1.5 ms/sample inference latency, VertiFuseX offers a lightweight, interpretable, deployment-ready framework for robust financial
forecasting.
Read the full abstract ▾
Game Theory
A Randomized $\frac32$-Approximation for Strategic Facility Location on a Circle
Hau Chan, Jianan Lin and Chenhao Wang
We study strategyproof mechanisms for locating a single facility on a circle so as to serve a set of strategic
agents under the utilitarian social cost objective. We analyze a simple parity-dependent mechanism that randomizes between the Random Dictator (RD) mechanism and the Proportional Circle Distance (PCD) mechanism. For an odd number \(n\) of
agents, this mechanism mixes RD and PCD with equal probability, as originally proposed by Rogowski and Dziubiński (IJCAI 2025). For even \(n\), it mixes RD with a random-deletion extension of PCD, in which one
agent is removed uniformly at random before PCD is applied to the remaining
agents. Our main result shows that this mechanism is strategyproof and achieves an approximation ratio of \(\frac32\) for every \(n\ge 3\). This improves the \(\frac74\) upper bound of Rogowski and Dziubiński, which applied only to odd \(n\), and extends the guarantee to even numbers of
agents. Finally, we establish a computer-assisted lower bound of \(1.088187\ldots\) on the approximation ratio of any randomized strategyproof mechanism, improving on the previous lower bound of \(1.0456\) due to Meir (SAGT 2019).
Read the full abstract ▾
Computation and Language
Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy
Gengxian Zhou, Jian Xu, Zichen Tang et al. (+3 more)
Retrieval-Augmented Generation (RAG) has empowered Large
Language Models (LLMs) to tackle knowledge-intensive tasks. However, navigating global, heterogeneous knowledge bases (large-scale knowledge graphs and text corpora) for complex
reasoning remains a challenge. Existing methods typically employ reactive, graph-driven exploration strategies, which blindly follow graph
topology without adapting to the question context or evolving exploration progress, and lack deep bidirectional synergy between graph and text. To address these limitations, we propose CoG (Cognition on Graph), a cognitive-inspired, training-free framework for adaptive knowledge exploration. Drawing inspiration from human problem-solving, CoG performs a continuous plan-explore-reflect cycle, where it proactively formulates investigation plans, performs dual-source
retrieval, and dynamically reflects on progress to adjust strategies. Crucially, it establishes deep bidirectional synergy between structured graph and unstructured text, where entities extracted from text dynamically guide graph exploration to bridge knowledge gaps. Extensive experiments on seven multi-hop QA
benchmarks demonstrate that CoG significantly outperforms state-of-the-art methods while achieving superior exploration efficiency. Our code and
datasets are available at https://github.com/zhougengxian/CoG.
Read the full abstract ▾
All authors Gengxian Zhou, Jian Xu, Zichen Tang, Shiming Xiang, Haihong E, Cheng-Lin Liu
Computational Engineering
Transducer Placement and the Limits of a Four-State Reduced Model in Post-Flutter Piezoelectric Energy Harvesting from a Pitch-Plunge-Flap Aerofoil
Nikolaos D. Tantaroudas, Ilias Karachalios and Andrew J. McCracken
Aeroelastic ?utter is normally a failure mode to be designed against, yet the limit-cycle oscillations (LCOs) that follow it convert flow energy into sustained structural motion that a piezoelectric transducer can turn into electrical power. A transducer is embedded in a three-degree-of-freedom pitch-plunge aerofoil with a finite-mass trailing-edge flap and unsteady strip-theory aerodynamics, giving a fifteen-state electro-aeroelastic system with a cubic hardening pitch spring, and the system is reduced by biorthonormal projection of the Taylor-expanded residual onto eigenvectors of the coupled Jacobian. The testbed is deliberately low order, so that every reduced prediction can be checked against the full-order system it replaces. The degree of freedom that carries the transducer is a first-order design variable, since it sets both the sign of the shift in the flutter boundary and the magnitude of the harvested power. The error of the reduced model is dominated not by the size of the retained basis but by how the reduced operator is made to depend on low speed. Expanding the retained
eigenvalues leaves the reduced operator block-diagonal, with no coupling between the retained modes at any order of the expansion, whereas re-projecting the exact Jacobian onto the same frozen basis supplies that coupling and restores the structural response without enlarging the basis. It is found that the error that remains lies in the harvested voltage, which the
equilibrium eigenvectors carry in a fixed proportion to the motion, and this is not removed by adding the electrical modes to the basis, whereas the flap detection, which the same basis also misses, is recovered by retaining the flap modes. The accuracy of a harvester reduced-order model must therefore be reported on the harvested quantity itself.
Read the full abstract ▾
Computer Vision
LG-PF: Lightweight Confidence-Guided Polarization Image Fusion
Zhuangfan Huang, Zhenyu Kuang, Gao Wang et al. (+3 more)
Polarization image fusion combines the stable luminance and structural information of the total- intensity image S0 with the material-sensitive details of the degree of linear polarization (DoLP) image. However, the reliability of DoLP varies spatially, and indiscriminate polarization transfer may amplify unstable responses or disturb the structural appearance anchored by S0. We therefore propose LG-PF, a lightweight confidence-guided framework that formulates polarization fusion as a selective residual transfer process. A Polarization Confidence Prior estimates spatially reliable polarization responses, a Mask-guided Multi-scale Fusion module regulates their transfer across three feature scales, and a Lightweight Context-aware Bounded Correction Head stabilizes local photometric and structural transitions. Confidence guidance is also incorporated into the optimization objectives to preserve reliable polarization details while suppressing unsupported responses. We also construct MSP, a multi-scene polarization fusion
dataset containing 1000 pixel-aligned image pairs from 17 indoor and outdoor scene categories. LG-PF achieves the best results across all six evaluated metrics on MSP, while subset-based evaluations on PIF and GAND show promising transferability without fine-tuning. With only 0.2936 M parameters and an inference time of 21.712 ms per image, LG-PF achieves competitive fusion quality with low computational cost. The source code will be available at https://github.com/1hzf/LG-PF.
Read the full abstract ▾
All authors Zhuangfan Huang, Zhenyu Kuang, Gao Wang, Yang Liu, Haishu Tan, Xiaosong Li
Machine Learning
Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise and Hölder Smoothness
Misbah Uz Zaman and Anirbit Mukherjee
Classical convergence guarantees for
stochastic gradient methods typically assume Lipschitz-smooth objectives and finite-variance gradient noise, both frequently violated in practice. In contrast, we study nonconvex
stochastic optimization under the joint relaxation of these assumptions: objectives with $(L,s)$-Hölder continuous gradients, $s\in(0,1]$, and gradient noise satisfying only a bounded $\alpha$-th moment condition for $\alpha\in(1,2]$. We establish three convergence results. Firstly, that standard SGD converges at rate $O(T^{-s/(1+s)})$ whenever $\alpha\ge1+s$, extending the classical nonconvex SGD rate to heavy-tailed noise and Hölder smoothness simultaneously. Secondly, we analyze $\delta$-regularized gradient clipping ($\delta$-GClip), a provable trainer of wide and deep nets, and establish a stationarity rate of $O(T^{-2s(\alpha-1)/[(1+s)(2\alpha-1)]})$ under the same condition. Thirdly, we analyze standard gradient clipping (G-Clip) and show that it recovers the above rate for $\alpha\ge1+s$ while in the very heavy-tailed regime $\alpha<1+s$, it has a convergence rate $O(T^{-2s(\alpha-1)/[(\alpha-1)+s(2\alpha-1)]})$ — the first convergence guarantee in this regime for any
stochastic gradient based method.
Read the full abstract ▾
Networking
Vertical Assessment of RF-EMF Exposure in a Building Adjacent to a Multi-Operator Shared Base Station
Ricardo Q. de F. H. Silva, Marcio E. C. Rodrigues, Fred S. R. Pinheiro et al. (+3 more)
This paper extends a previously published proposed approach for estimating worst-case exposure scenarios in buildings using publicly available Base Station (BS) parameters, applying it to a critical case involving a multi-operator shared site. Radiofrequency Electromagnetic Fields (RF-EMF) exposure was assessed on every floor of a 20-story building facing the site, revealing significantly higher levels near the center of the
antennas' estimated vertical zone of interest, with a peak of 31.86 V/m, 23.95 times higher than the street-level peak value. However, due to uncertainties in the input parameters, measurements across all locations within the zone of interest are required to accurately identify the floor of maximum exposure. The results demonstrate the usefulness of the proposed estimation approach and highlight the need for improved methods that consider BS
antenna configurations and current technical information to ensure accurate assessments of exposure to RF-EMF.
Read the full abstract ▾
All authors Ricardo Q. de F. H. Silva, Marcio E. C. Rodrigues, Fred S. R. Pinheiro, Gutembergue S. da Silva, Halysson B. Mendonça, Vicente A. de Sousa Jr
Numerical Analysis
Total Generalized Variation for Inverse Problems Involving Piecewise Linear Finite Elements
Moritz Kappes, Manuel Haas, Thomas Beiert et al. (+2 more)
Higher-order regularization has shown improved results over first-order methods such as total variation. In this paper, convergence of a piecewise linear finite element discretization is shown for the second-order total generalized variation functional. Additionally, this convergence result is extended to a spatiotemporal setting after the spatiotemporal function space is comprehensively introduced. In both cases, discrete minimizers converge to the continuous minimizer with rate $h^{1/4}$, matching the best known rate for finite element discretizations of total variation in the same general setting. Numerical experiments confirm the convergence rates and indicate faster convergence in practice. Comparisons with related spatial image reconstruction
algorithms show comparable reconstruction results. The spatiotemporal case is discussed using the example of the inverse problem in electrocardiographic imaging, where the proposed functional improves the state of the art.
Read the full abstract ▾
All authors Moritz Kappes, Manuel Haas, Thomas Beiert, Simone Pezzuto, Alexander Effland
Computational Complexity · Cross-listed from quant-ph
Average-case hardness of Betti number estimation
Sergii Strelchuk, Sathyawageeswar Subramanian and Adam Wesołowski
We establish the average-case hardness of Betti number estimation on random clique complexes via a reduction from the planted clique problem. We further show that our reduction implies a series of hardness results for many problems in both classical and
quantum Topological Data Analysis (qTDA). Under the classical planted clique
conjecture, no randomized
polynomial-time Betti number
estimator achieves additive error below $\tfrac12$ with constant advantage. Under a new
quantum planted clique
conjecture that we introduce, the same conclusion holds for
quantum polynomial-time
algorithms. We also obtain related conditional hardness results for homology vanishing, additive approximations with larger error tolerances, preparation of simplex and harmonic states, cycle recovery, and counting
eigenvalues at low energy. Our reduction clarifies the structural requirements for
quantum advantage in TDA and provides a new lens to investigate the classical and
quantum complexity of related problems.
Read the full abstract ▾
Sound
DiffSynth-Music: Audio-Conditioned KV-Cache Adapters for Controllable Music Generation
Zhongjie Duan, Shengchuan Gao, Hong Zhang et al. (+1 more)
Text and lyrics specify broad musical characteristics and sung content but offer limited control over musical timing, melody, and reference-based style. We introduce DiffSynth-Music (https://modelscope.cn/models/DiffSynth-Studio/DiffSynth-Music), a framework that adds composable audio conditioning to a music synthesis backbone through layer-wise key-value injection. The three template models, Control, Prosody, and Reference, are initialized from the backbone
diffusion transformer and trained with conditional flow matching. They support five control types: beats, vocals, accompaniment, prosody, and reference audio. A shared variational autoencoder maps conditioning waveforms into a common latent space, enabling their
attention memories to be combined. With the template timestep fixed at the clean-data endpoint and other inputs held constant, each control cache is computed once and reused throughout sampling. Training pairs are derived from music recordings using beat extraction, source separation, vocal resynthesis, and reference-excerpt selection. Single-control evaluations on Mandarin and English songs demonstrate improved adherence across all five control types and better lyric fidelity under vocal conditioning relative to the backbone. Automatic music-quality and instruction-following scores remain broadly comparable to those of the evaluated base models, with metric-specific trade-offs. We release the three template models to support research and creative applications in controllable music generation.
Read the full abstract ▾
All authors Zhongjie Duan, Shengchuan Gao, Hong Zhang, Yingda Chen
Artificial Intelligence
MPT: Missing Prototype Tracking via Barycentric Reconstruction in Vehicular Federated Learning
Hanju Jang, Gyeongmin Han, Sungmin Lee et al. (+3 more)
Cross-vehicle
federated learning enables vehicles to collaboratively improve perception models while keeping locally collected driving data private. However, vehicle participation is transient, and a vehicle may depart before training converges while permanently taking its local data. When this departing vehicle holds most samples of a target class, the class becomes rare in the remaining FL network, and its recognition can silently degrade as the shared backbone continues to evolve. Recovering the class is difficult since the few remaining samples provide a noisy prototype estimate, while FL
privacy constraints prevent centralized access to raw data or per-sample features. This paper presents MPT, a cross-vehicle FL framework that maintains rare-class recognition by reconstructing its prototype at every round from
privacy-preserving class-level statistics. MPT combines a barycentric decomposition that tracks drift shared with remaining-class prototypes, a covariance-based residual prediction that estimates out-of-span drift, and an adaptive calibration that weighs the remaining rare-class samples according to their reliability. We evaluate MPT on three vehicle classification tasks and four backbones against representative calibration and drift-compensation baselines. MPT outperforms all baselines in rare class F1, reaching 0.516 on the nuImages
dataset with only 1% of rare-class samples remaining, without raw data, per-sample features, or retraining.
Read the full abstract ▾
All authors Hanju Jang, Gyeongmin Han, Sungmin Lee, Kichang Lee, Chunghan Lee, JeongGil Ko
Software Engineering
Detecting HTTP Status Code Misuses in REST APIs via Static and Dynamic Analysis
Alix Decrop, Andrea Arcuri, Mike Papadakis et al. (+2 more)
REST APIs are widely used on the web for client-server communications. As REST is based on HTTP, server responses contain status codes to indicate the outcome of requests (e.g., 200 OK for a success and 404 Not Found for an unavailable resource). While HTTP status codes are standardized, their semantics are not enforced in REST, leading to many misuses in practice (e.g., using 500 Internal Server Error to describe a client error). Such misuses may have nefarious consequences, such as reducing interoperability, misleading API clients, or causing false positives in testing tools. In this paper, we present a combined static and dynamic analysis approach for detecting HTTP status code misuses in REST APIs. We first study 2,625 real-world REST API specifications to identify relevant status codes and derive a set of 30 usage rules based on HTTP standards and REST API principles. We then implement tools to identify such rule violations in OpenAPI specifications (static analysis) and in API behavior (dynamic analysis). Our evaluation finds that status code misuses are frequent and systematic in REST APIs, with both static and dynamic approaches detecting various misuses. We highlight that both approaches may be used in a complementary manner, and also provide insight for REST API testers and users alike.
Read the full abstract ▾
All authors Alix Decrop, Andrea Arcuri, Mike Papadakis, Pierre-Yves Schobbens, Gilles Perrouin
Artificial Intelligence
Unified Agentic Video Editing Across Levels of Complexity and Creativity
Surabhi S. Nath, Kim Ferres, Milan Petrović et al. (+1 more)
Editing is a core component of
video production, requiring creative planning and decisions under multiple constraints. Here, we report methods for agentic tooling for automated
video editing across three tasks varying in editorial goal, complexity and creativity, namely scene previews,
video summaries and cinematic trailers. We evaluate the outputs and discuss implications for automation and agency.
Read the full abstract ▾
All authors Surabhi S. Nath, Kim Ferres, Milan Petrović, Lion Schulz
Systems and Control · Cross-listed from math.OC
Infinite Horizon Mean-Field Terminal Value Problem
Uğur Ayd{\i}n, Tamer Başar and Naci Saldi
We introduce a class of finite- and infinite-horizon discrete-time control problems for studying macroscale systems in discrete time, which we refer to as mean-field terminal value problems (MFTVPs). An MFTVP takes a terminal \(Q\)-function as input and, starting from this terminal \(Q\)-function, seeks an indefinite backward
evolution of optimal policies and state measures, as required for an infinite-horizon non-stationary mean-field
equilibrium (MFE) of a discrete-time mean-field game (MFG). We study the existence and uniqueness properties of this problem. As an application, using the uniqueness properties of MFTVPs, we show that, in the average-cost setting (and in the discounted setting for sufficiently small discount factors), MFTVPs can be used as an intermediate step to develop approximation schemes between finite-horizon MFEs and average-cost MFEs (respectively, stationary MFEs). In contrast to approaches that use infinite-horizon MFGs as intermediate problems, MFTVPs can be employed when the discount factor is sufficiently small (or, in the average-cost setting, when the drift factor is sufficiently small), together with a regularizer, to approximate a stationary MFE. Assuming uniqueness of the solution of a MFTVP, the restrictions we impose on the Lipschitz parameters of the system are weaker than the contraction conditions available for regularized stationary MFGs, and our approximation scheme remains applicable even in the presence of multiple stationary MFEs.
Read the full abstract ▾
Information Retrieval
A Historical Corpus Is Not a Historical System: Auditing Hindsight Leakage in Stateful Data Discovery
Yixi Zhou, Fan Zhang, Sikun Wang et al. (+2 more)
Offline replay should estimate what a discovery system could retrieve at a historical point, yet freezing the corpus leaves interaction
memory unconstrained. We formalize point-in-time (PIT) discovery through historical state $(D_t, \theta_t, M_{< i})$ and introduce a paired replay that changes only
memory availability. The protocol constructs PIT and full-stream Future views from behavior-only traces and audits selected entries with a Temporal Violation Rate. Across three table-text domains, two stream regimes, two retrievers, and five seeds (216,000 rows), Future inflated Asset Recall@100 by 2.62-5.24 points; all 12 paired intervals excluded zero. With behavior-only trace
memory, PIT underperformed the no-
memory Stateless condition; Future masked 32.7-48.4% of that harm. For a simulated positive-feedback cache, PIT added 4.65-18.96 points over Stateless while Future added another 4.11-9.58 points. On five timestamped FreshStack topics, Future exceeded PIT by 2.72 points [1.75, 3.71]. Historical evaluation must version and validate
memory with the corpus.
Read the full abstract ▾
All authors Yixi Zhou, Fan Zhang, Sikun Wang, Yingfan Xu, Haipeng Zhang
Machine Learning · Cross-listed from math.OC
High-Probability Convergence of SGD via Batched Updates
Feng Zhu, Robert W. Heath Jr. and Aritra Mitra
Stochastic gradient descent (SGD) is the primary workhorse for large-scale optimization. While the average behavior of its iterates, typically characterized by mean-squared error bounds, is well-understood, obtaining high-probability guarantees for the last iterate remains challenging. Prior approaches to this problem have either imposed restrictive assumptions (such as bounded domains or gradients) or relied on complex proofs involving auxiliary sequences. In this work, we propose Batched SGD, a simple variant that partitions online samples into epochs and performs a single update per epoch using a refined, low-variance gradient estimate. Our main contribution demonstrates that this batching mechanism enables a surprisingly simple high-probability analysis that avoids both restrictive assumptions and auxiliary sequences. Under standard smoothness and norm-sub-Gaussian noise assumptions, we establish near-optimal rates for both strongly convex and non-convex objectives. Furthermore, we show that our batching idea extends naturally to
federated learning (FL). We provide the first high-probability guarantees for FL, achieving logarithmic communication complexity, linear speedup in the number of
agents, and resilience to data heterogeneity.
Read the full abstract ▾
Computer Vision
Same Encoder, Different Winner: A Paired-View Framework for Cell Painting Encoder Evaluation
Tim Treis, Nikita Moshkov, Johan Fredin Haslum et al. (+2 more)
Vision encoders for
Cell Painting are typically ranked by a single evaluation, commonly replicate mean average precision (mAP). We introduce CP-BG-Bench, a paired-view evaluation framework that holds the central
cell fixed across four matched views (raw crop C, segmented S, and density-augmented variants CD and SD), ablating or augmenting surrounding pixels as a controlled intervention. Instantiating the framework on three
datasets (JUMP-CP, RxRx1, RxRx3-core) and three encoders (DINOv3 ViT-B/16, OpenPhenom, SubCell) under four community-standard protocols (replicate mAP, scIB batch integration, CellProfiler feature prediction, cross-batch perturbation recall), we find that the four protocols rank the same encoders systematically differently, with disagreements decomposing along three axes:
cell versus background, morphology versus context, and within-study versus across-batch. The largest effect: on RxRx3-core, SubCell with segmented inputs retains 94% of crop replicate mAP but only 32% of crop R@10, so the within-study signal preserved under
segmentation is largely non-transferable; density augmentation recovers 84% of the within-study C-to-S gap but only 8% of the cross-batch gap. Segmented views predict CellProfiler features as well as or better than crops on two of three
datasets, inverting the replicate-mAP ranking, and the C-to-S gap varies by an order of magnitude across
datasets while remaining similar across encoders, indicating that background-driven gain is set by experimental design rather than by the encoder. Single-metric ranking of
Cell Painting encoders is therefore sensitive to the protocol used, and protocol disagreements are interpretable as projections onto the three axes the paired-view design exposes. We will release the paired-view
datasets, reconstruction pipelines, 36 trained checkpoints, aggregated
embeddings, and the full evaluation suite.
Read the full abstract ▾
All authors Tim Treis, Nikita Moshkov, Johan Fredin Haslum, Shantanu Singh, Fabian J. Theis
Machine Learning
Curriculum-Based Adversarial Heterogeneous Agent Reinforcement Learning for Autonomous Quad-Copter Landing in Maritime Settings
Allan Minh-Tam Nguyen, Sree Showrya Kotala, Stefan Banioi-Crijman et al. (+2 more)
Recovering unmanned aerial vehicles (
UAVs) in maritime environments is challenging due to wind
turbulence and ship-deck motion, making it a valuable test case for alternative control and learning approaches as conventional landing approaches often become unreliable. We study simulated mid-air capture of quadrotor
UAVs by a ship-mounted robotic arm, learning robust cooperative control policies with Heterogeneous-
Agent Proximal Policy Optimization (HAPPO) Reinforcement Learning. We train with HAPPO using a curriculum and an
adversarial wind
agent (HARL-AC) in NVIDIA Isaac Lab, and compare the obtained control policies against those generated through curriculum-based domain randomization and a
benchmark trained on a single sea state. In-distribution evaluation on sea states $0/4/5$ shows comparable success for HARL-AC and domain randomization of up to $97.5\%$. On out-of-distribution sea states $7/8/10$, HARL-AC generalizes better, achieving up to $16\%$ higher median success rate at sea state 10, and substantially lower crash rates of up to $14\%$ compared to the domain randomization policy. Furthermore, we show that the adversarially trained policy shows more cautious behavior, slightly increasing timeouts by $<3\%$, but yields safer recovery behavior in severe, unseen conditions.
Read the full abstract ▾
All authors Allan Minh-Tam Nguyen, Sree Showrya Kotala, Stefan Banioi-Crijman, Kurt Driessens, Rico Möckel
Software Engineering
GraphAHA: Graph-Based Adaptive Search with Heterogeneous Actions for Test-Time Code Generation
Xitao Li, Haijun Wang, Gege Yuan et al. (+4 more)
Test-time scaling improves code generation by spending additional inference budget (e.g., calls or
tokens) on direct sampling, feedback-conditioned repair, and
reasoning-guided implementation. Search-based methods can allocate this budget adaptively, but two challenges remain. First, tree-structured search treats each generation history as a separate state even when trajectories converge to the same program, duplicating evaluation and preventing statistics from being shared. Second, sampling, repair, and
reasoning have complementary and state-dependent payoffs, making online allocation among them difficult under a finite budget. To address these challenges, we propose an adaptive graph search method with heterogeneous actions (GraphAHA). GraphAHA organizes the test-time code generation in a typed directed acyclic graph. Equivalent programs are merged into a single code node, allowing their downstream search statistics to be reused across all discovery paths. Hierarchical Thompson sampling then selects whether to generate a new state or follow an existing successor and, for generation, chooses among the type-valid sampling,
reasoning, implementation, and repair operations. Evaluated on LiveCodeBench and CodeContests with Qwen2.5-Coder and DeepSeek-Coder, GraphAHA achieves the best score in 18 of 20 cases. For Pass@1 measured using visible tests, it outperforms the strongest baseline for both models on both
benchmarks by 4.1 percentage points on average, demonstrating more effective use of a fixed inference budget.
Read the full abstract ▾
All authors Xitao Li, Haijun Wang, Gege Yuan, Qiyuan Wu, Jiali Wei, Ming Fan, Xiaofei Xie
Neural and Evolutionary Computing
MAAPO:an innovative membrane algorithm based on artificial protozoa optimizer for multilevel threshold image segmentation
Xiaopeng Wang, Vaclav Snasel, Seyedali Mirjalili et al. (+1 more)
This paper proposes a novel membrane
algorithm based on artificial protozoa optimizer (MAAPO) for global optimization problems. The artificial protozoa optimizer (APO) is adopted as the base meta-heuristic
algorithm due to its novelty and competitive performance. MAAPO integrates two key innovations:(1) a membrane computing (MC) framework that introduces a parallel distributed paradigm to improve population diversity and search dynamics, and (2) an enhanced autotrophic model within APO that uses a roulette-based fitness-distance balance (RFDB) mechanism for adaptive reference point selection. These strategies collectively enhance the
algorithm's exploration-exploitation balance and global search capabilities. To validate its performance, MAAPO is tested against 12 advanced
algorithms on the CEC2017 test suite, and further applied to the multilevel thresholding image
segmentation problem using Otsu and Kapur
entropy as objective functions. The quality of segmented images is assessed using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and feature similarity index (FSIM) metrics. Experimental results demonstrate that MAAPO outperforms its counterparts, delivering superior
segmentation quality. This research on MAAPO contributes an effective enhancement strategy to meta-heuristic
algorithms and introduces a novel, highly applicable approach for complex image
segmentation tasks.
Read the full abstract ▾
All authors Xiaopeng Wang, Vaclav Snasel, Seyedali Mirjalili, Jeng-Shyang Pan
Information Retrieval
Learning the Lake: Reliable Experience for Adaptive Data Product Discovery
Yixi Zhou, Fan Zhang, Sikun Wang et al. (+2 more)
Data-product discovery searches a full lake even when workloads revisit related products and regions. Repetition permits contracted search, but similarity cannot justify a route because one omitted asset invalidates a conjunctive product. We study when serving experience can safely reduce this work. Evolving Discovery
Memory records source-labelled query–product–region evidence above a fixed regional index. SafeLake separates operational familiarity, which determines how much to search, from independently calibrated product evidence, which determines where to search. The fixed-probe comparison holds the adaptive budget constant between SafeLake and Familiarity-only. On TAT-QA, product steering raises Product Recall by 0.072; ConvFinQA shows no resolved map gain, while the HybridQA sensitivity favors Familiarity-only in Full R@100. Trace-only, missing, and false feedback expose boundaries on map steering, while scope-audit agreement cannot certify the source. Across clean confirmed-feedback streams under the frozen transductive protocol, the formal controller saves 49.5–82.7% of cumulative asset exposure. Experience determines when to contract; reliable evidence determines where to contract.
Read the full abstract ▾
All authors Yixi Zhou, Fan Zhang, Sikun Wang, Yingfan Xu, Haipeng Zhang
Machine Learning
Optimizing for the decision not the prediction: an exploration of Smooth Net Benefit as a training objective
Koen M.F. Gorgels, Lasai Barreñada, Maarten van Smeden et al. (+3 more)
Objective Prediction models are commonly trained using objectives such as Bernoulli negative log-likelihood (NLL), although downstream clinical decisions may depend on specific risk thresholds. We introduce Smooth Net Benefit ($\sigma$NB), a differentiable approximation of Net Benefit designed to align model training with threshold-specific clinical utility. Materials and Methods We evaluated $\sigma$NB as a training objective for logistic regression, generalized additive models (GAMs), and XGBoost with three Hessian implementations. Experiments used the Framingham cardiovascular risk
dataset and 44 TabZilla
datasets comprising 72
dataset-threshold combinations. Results $\sigma$NB training did not consistently improve Net Benefit in Framingham. Across the TabZilla
benchmark, mean standardized Net Benefit for logistic regression increased from 0.5669 with NLL to 0.5765 with $\sigma$NB (mean difference 0.0096, 95% CI -0.0001 to 0.0193). For GAMs, mean standardized Net Benefit decreased from 0.5921 to 0.5625 (mean difference -0.0296, 95% CI -0.0721 to 0.0129). For XGBoost, NLL achieved 0.6745 compared with 0.6723–0.6735 across $\sigma$NB implementations. In logistic regression, $\sigma$NB gains were positively associated with the performance advantage of XGBoost over NLL-trained logistic regression. Discussion The effect of $\sigma$NB was context dependent, with modest gains concentrated in logistic regression and little benefit for more flexible model classes. This suggests that decision-focused optimization may be most useful when limited model flexibility leaves greater scope for improvement. Conclusion Our results do not support $\sigma$NB as a general replacement for NLL training, but support further investigation of decision-focused objectives in settings where conventional likelihood-based training may not adequately capture decision-relevant structure.
Read the full abstract ▾
All authors Koen M.F. Gorgels, Lasai Barreñada, Maarten van Smeden, Ben Van Calster, Ewout W. Steyerberg, Wouter A.C. van Amsterdam
Artificial Intelligence
SCQ: Stabilizing Conservative Q-Learning with Sigmoid-Bounded Entropy
Xiefeng Wu, Shu Zhang, Zhaojie Chu et al. (+1 more)
Offline-to-online reinforcement learning reduces interaction cost for real-world
robot learning but suffers from persistent value estimation instability. Existing methods address this through pessimistic regularization, lower-bound calibration, and architectural normalization, but an overlooked source of instability lies in the
entropy formulation: the standard log-
entropy term can become negative, destabilizing policy updates. We introduce SCQ (Sigmoid-Bounded Conservative Q-Learning), which replaces this term with a sigmoid-bounded formulation that stays strictly positive. SCQ retains conservative Q regularization and return-based lower-bound calibration, stabilizing policy optimization without sacrificing exploration. We evaluate SCQ on D4RL (Minari)
benchmarks under both single-demonstration and standard
dataset settings, as well as on simulation and real-world visual tasks. SCQ matches or exceeds baseline performance while exhibiting more stable training dynamics across state-based and visual
benchmarks, and transfers to four real-
robot platforms including manipulation, wheeled, quadruped, and
humanoid systems. A direct clipping intervention that removes negative log-probability contributions, together with gradient-matched positive-score controls, indicates that positivity rather than a particular score shape alone drives much of the improvement. Project website: https://scq-rl.github.io.
Read the full abstract ▾
All authors Xiefeng Wu, Shu Zhang, Zhaojie Chu, Mingyu Hu
Multiagent Systems
The Mechanics of a Swarm: A Reproducible External Reconstruction of an Unintended Agent-Coordination Episode on a Third-Party Wiki
Philipp Lütje
Between 24 May and 2 July 2026, autonomous
language-model
agents running inside a timed research-question evaluation wrote to a third party's public, world-writable wiki. OpenAI acknowledged the incident; independent researchers reconstructed it and published the wiki's archived revision history. We analyse that history (14,591 revisions, 3,103 names, 4,579 pages) as a behavioural record, attributing text to the revision that added it. Under an explicit identity model we reconstruct 907 cohorts and estimate about 876 episodes (95% interval 784-1008). Coordination formats converged within a day, and heterogeneous schedules over one question chain created large opportunities for information asymmetry: the first report of an item preceded a later cohort's own arrival by a median of 3.4 h. Across the 510 cohorts with an observable progress trace we find no robust positive association between measured coordination and documented progress. This version adds a source the export lacks: the wiki operator's own request log, 5,157,202 records over four months. It holds roughly 2.66M content requests and 1.58M searches, and 7,254 acting names against the export's 3,103; 2,578 names neither save nor open an edit form. Content requests before writing are observed for 1,034 of 1,140 coordinating names, and the first coordination page is requested 17 s after its creation. These records establish requests, not delivery or causal use. Among newcomers without a marker on their first written page, prior requests to other marker-bearing pages occur for 40.2% of marker adopters and 31.7% of non-adopters. The association remains, but our first-pass reading of it as transmission is withdrawn: page choice, shared behaviour and action-dependent nameability prevent causal identification. We list the claims from our earlier analyses that re-examination overturned, including one from this version's own first pass
Read the full abstract ▾
Artificial Intelligence
Assisted Spatial Cognition Through Vision-Language Models
H. Riaz, J. B. Fernandez, I. Mills et al. (+3 more)
Multimodal AI, powered by Large
Language Models (LLMs) and
Vision-
Language Models (VLMs), is transforming assistive technologies by enabling simultaneous processing of visual and textual data. This advancement holds significant promise for over 43 million visually impaired and neuro-divergent individuals worldwide who face persistent challenges in navigating indoor and outdoor environments due to limited spatial awareness and insufficient environmental cues. Existing
navigation aids often lack comprehensive 3D scene understanding, relying on constrained route-based strategies that hinder user autonomy. In this paper, we introduce a novel end-to-end framework that integrates LLMs, VLMs and digital twin technologies to deliver a spatially cognitive
navigation support for visually impaired and neuro-divergent users. Our system captures
video input via standard mobile phone cameras, and employs SLAM3R to generate dense 3D point clouds from
monocular RGB sequences in real-time. Our custom post-processing
algorithm ensures accurate point cloud
alignment across multiple viewpoints without requiring predefined reference points. This enhances the capabilities of SpatialLM to produce structured 3D representations, including architectural elements and oriented object bounding boxes. The enriched spatial data is then processed by a locally deployed LLM, which interprets 3D contexts to generate detailed scene descriptions and precise distance measurements between users and surrounding objects. We evaluated our approach across diverse
video scenarios featuring various perspectives, looped walking views and captured in multiple environments. The evaluation results demonstrate consistent accuracy in 3D scene interpretation and object localisation, underscoring the potential of our system as a transformative assistive
navigation solution that combines advanced visual perception with spatial
reasoning
Read the full abstract ▾
All authors H. Riaz, J. B. Fernandez, I. Mills, D. Hickey, F. Cleary, M. I. Ali
Artificial Intelligence
What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
Ioannis Prokopiou, Athanasios Aidinis, Panagiotis-Christos Kyrmpatsos et al. (+1 more)
Agentic pipelines for structured-query generation are rapidly expanding, but it is unclear which part of the loop produces the gain. We use LAST-CQ – a five-
agent, training-free, execution-grounded Text-to-Cypher framework – as an instrumented testbed, running three counterfactuals over 2,471 live-database queries and six backbones spanning three vendor scale tiers. Removing correction is worth between 3.1% aggregate execution-BLEU against the single-pass system and 12.3% against a no-refinement counterfactual (up to 80.7% for the weakest backbone). Replacing schema-grounded, LLM-synthesised feedback with raw database error strings costs almost nothing (20.9% vs. 19.9% naive exact match; <0.2% end-to-end; equivalent within $\pm 0.075$ set-F1 by two one-sided tests). Spending the same call budget on parallel sampling degrades quality by 10-11%. What works is detecting failure and routing it to a retry, not the feedback sophistication or number of samples. LAST-CQ itself recovers 91.7% of queries that fail under single-pass generation, while a query that succeeds first time still costs exactly one LLM call. We also show that n-gram overlap on serialised results is not a bound in either direction: it over-scores against set equivalence on 65.9% of results while under-scoring against judged semantics. Finally, we calibrate our LLM judge against blind human labels and find it optimistic by 9 points.
Read the full abstract ▾
All authors Ioannis Prokopiou, Athanasios Aidinis, Panagiotis-Christos Kyrmpatsos, Pantelis Vikatos
Databases
How Do Data Collection Strategy and Data Quality Influence the Outcomes of Digital Technology Adoption?
Xuejiao Li and Cheng Yang
In the era of Industry 4.0 (I4.0), data has become the essential foundation for digital transformation, yet many organizations still struggle to link data practices with digital performance outcomes. This study investigates how data collection strategy and data quality jointly influence the success of digital technology adoption (DTA) in manufacturing firms. Drawing on survey data from 86 firms, the research employs Partial Least Squares Structural Equation Modeling (PLS-SEM) to examine the relationships among data collection strategy, data quality, implementation performance, and operational performance. The results show that both data collection strategy and data quality significantly influence implementation and operational performance. However, the effect of data collection strategy on implementation performance is indirect, fully mediated by data quality. The study also finds that data collection strategy influences data quality. These findings demonstrate that data quality acts as a critical bridge between upstream data practices and downstream digital outcomes. The study contributes to the digital transformation and data management literature by empirically validating the central role of data quality and offering practical insights for managers to design and govern data processes strategically. It also sets a foundation for future research on data governance frameworks that integrate data quality assurance, standardization, and lifecycle management to sustain data-driven and digital transformation.
Read the full abstract ▾