Distributed Computing
Concurrent Split Learning Through Stable Client Clustering
Mohammad Kohankhaki, Valentin Rentschler and Anke Schmeink
Training with a fixed global batch limits how many distributed clients can provide examples in any one step. We examine a way to use additional server workers without increasing the batch processed by an individual workload. Global Clustered Parallel Split Learning (GCPSL) assigns clients to fixed clusters, executes a Parallel Split Learning with Global Sampling (GPSL) workload for each cluster concurrently, and periodically fuses the client and server model segments. In simulations with 256 logical clients, dividing the population across more workloads improves direct data participation, while smaller clusters can incur an accuracy cost. A four-H100 implementation of label-aware GCPSL reaches 85% CIFAR-10 validation accuracy in $6.13 \pm 0.15$ minutes over three matched runs, versus $19.09 \pm 0.45$ minutes when the same workloads are serialized. Within the four-GPU allocation, size-balanced and random fixed affiliations reach the target in similar mean times (5.70 and 5.66 minutes); size balancing increases direct participation by 3.25 percentage points. These measurements characterize a trade-off among execution concurrency, assignment information, participation, and accuracy for stable-client split learning.
Read the full abstract ▾
Robotics
RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning
Zexi Li, Yehang Zhang, Haojian Huang et al. (+10 more)
General-purpose
robot agents must learn from experience, transfer to new tasks, and act efficiently. Code as Policies (CaP) methods generate and repair programs at runtime, incurring latency and entangling reusable mechanisms with task-specific decisions. We introduce RACaP, an agentic framework that moves coding to
evolution and uses a
Reasoning-and-Acting (ReAct) loop to call frozen, typed Policy APIs at deployment. A two-phase strategy combines capability curriculum learning with autonomous self-
evolution to improve the APIs, the ReAct harness, and experience
memory. The APIs encode reusable physical mechanisms while exposing arguments for runtime adaptation. ReAct combines task-specific working
memory, long-term experience
memory, and visual feedback to select actions, verify outcomes, and recover from failures without modifying source code. RACaP achieves 54.4% success on LIBERO-90, 45.0% on zero-shot LIBERO-PRO, and 46.0% on LIBERO-Long, compared with at most 4.0% for CaP baselines on long-horizon tasks. On LIBERO-PRO, it achieves 2.5 times the success rate of CaP baselines and a 1.9-fold speedup in median policy time. For efficient on-
robot deployment, rejection-sampled fine-tuning distills GPT-5.6 ReAct decisions into Qwen3-VL-8B-Instruct, yielding a 13.2-fold per-decision inference speedup and reducing repeated physical calls from 16 to 4. These results show that separating reusable code from runtime decisions supports continued
evolution, effective transfer, and efficient long-horizon control.
Read the full abstract ▾
All authors Zexi Li, Yehang Zhang, Haojian Huang, Bohan Zhou, Wenqian Li, Chenxu Wang, Yifan Chang, Yangkai Wei, Tianyi Zhang, Ying-Cong Chen, Kaiwen Zhou, Yinchuan Li, James Cheng
Analysis of PDEs
Serrin-type overdetermined problem for the $p$-Laplacian with Robin boundary conditions
Luca Barbato and Riccardo Molinarolo
Let $\Omega$ be an open bounded connected subset of $\mathbb{R}^N$, $N \geq 2$, of class $C^{2,\alpha}$, for $\alpha \in (0,1)$. Let $p \geq 2$ and $\beta>0$. We prove the
symmetry of the solution of the $p$-torsion problem with Robin boundary condition subject to the natural overdetermined condition coming from a shape derivative argument and to an extra condition on $\beta$ and on the minimum of the principal
curvatures of $\partial\Omega$. The proof is based on some new integral identities, involving the linearized operator of the $p$-
Laplacian applied to the standard $P$-function. In passing we prove some other
rigidity results in the spirit of Serrin's and Alexandrov's
Theorems.
Read the full abstract ▾
Combinatorics
Arrow-Wilf equivalences and enumerative results for short arrow patterns
Robin D.P. Zhou and Xinyang Yu
Arrow patterns, introduced by Berman and Tenner, provide a unified framework for studying permutation classes where both one-line and cycle structure constraints are present. In this paper, we continue the systematic study of arrow pattern avoidance initiated by Archer and Laudone. We establish several structural results, including a key lemma that translates arrow patterns into vincular patterns under certain conditions, and derive a series of arrow-Wilf equivalences arising from reversal, complementation, and insertion operations. We also resolve the two cases $(12;3\to 3)$ and $(21;3\to 3)$ left open by Archer and Laudone, and enumerate the arrow patterns of the form $(\nu; b\to c)$ of size $3$ with $\nu \in \{31, 23, 32\}$ and $b,c\in [3]$, providing explicit formulas connecting the results to Bell numbers, Bessel numbers, Catalan numbers, and derangement numbers. Together with earlier work of Archer and Laudone, this leaves only $(32;1\to 3)$ unresolved for $|\nu|\le 2$, which we pose as an open problem.
Read the full abstract ▾
Accelerator Physics
Production of a Titanium Ion Beam Using Fluorides and Fluorine-Forming Precursors in an ECR Ion Source
D.K. Pugachev, K.I. Berestov, A.E. Bondarchenko et al. (+7 more)
The production of multiply charged titanium ions is of significant interest for accelerator-based experiments, surface modification technologies, and applications in
nuclear physics. Due to the low saturated vapor pressure of titanium at temperatures below 1000 {\deg}C, the generation of titanium ion beams from an electron cyclotron resonance ion source (ECRIS) remains a challenging task. The choice of titanium vapor injection methods into the ECR
plasma plays a key role in achieving high ionization efficiency,
plasma stability, and reliable long-term source operation. In this work, alternative approaches for the injection of neutral titanium atoms into the ECR
plasma are investigated, focusing on the use of fluorine-containing compounds. Titanium fluorides (TiF3, TiF4) possess a relatively high saturated vapor pressure at moderate temperatures, allowing to use standard resistively heated ovens operating up to 1000 {\deg}C. Another method involves the in-situ formation of titanium fluorides inside the
plasma chamber via chemical reactions between metal titanium and the dissociation products of sulfur hexafluoride (SF6). These approaches enable controlled and efficient titanium injection into the ECRIS
plasma with satisfactory extracted ion beam stability.
Read the full abstract ▾
All authors D.K. Pugachev, K.I. Berestov, A.E. Bondarchenko, V.N. Loginov, A.N. Lebedev, E.Yu. Kidanova, K.I. Kuzmenkov, V.E. Mironov, D.S. Podoinikov, D.S. Yakovlev
Computation and Language
Likelihood Ranking doesn't Scale Like Prompting in LLMs
Alessandro Bondielli, Lucia Passaro, Davide Bacciu et al. (+1 more)
LLM evaluation is commonly performed either by prompting models to produce answers or by scoring candidate outputs with likelihood-based metrics. In multiple-choice QA, however, standard likelihood-based scoring is still conditioned on the question and answer set, and can therefore leverage the same task-conditioned answer-selection interface used in prompting. We study a complementary protocol based on likelihood ranking of declarative statements constructed from the same question–answer pairs. Across 95 decoder-only models, ranging from 0.1B to 104B parameters, and 10 MCQA
datasets, we find a systematic divergence between declarative-statement likelihood ranking and prompted answering. Statement-likelihood accuracy remains comparatively stable across scale, whereas prompted answering improves sharply with scale and instruction-tuning. These results suggest that likelihood preferences over controlled declarative alternatives and task-conditioned answer selection probe distinct aspects of model behavior, and should not be treated as interchangeable.
Read the full abstract ▾
All authors Alessandro Bondielli, Lucia Passaro, Davide Bacciu, Alessandro Lenci
Robotics
Robo-Harness K1: Harnessing Robot-Use Agents via Perception Augmentation
Zexi Li, Yehang Zhang, Wenqian Li et al. (+12 more)
Foundation
vision-
language models (VLMs) understand objects, instructions, and spatial relations, yet translating this capability into robotic manipulation remains difficult.
Vision-
language-action (VLA) models require extensive demonstrations and may compromise pretrained understanding, while direct RGB-only VLM control is costly and strongly dependent on model capability. We introduce Robo-Harness K1, a
robot-use
agent (RUA) framework that exposes perception as tools. The
agent queries calibrated depth, persistent visual anchors, spatial measurements, and grasp hypotheses, then selects generic motions from the returned evidence. This interface makes 3D geometry accessible without changing the VLM architecture or training a depth encoder. On matched LIBERO-PRO tasks, Gemini 3.7 Flash with K1 reaches 77.8% accuracy, surpassing GPT-6 Astra's 61.1% with an RGB-only harness; K1 further improves Astra to 88.9%. Without target fine-tuning, Gemini with K1 transfers to three RoboSuite arms and dual-arm RoboTwin tasks. On RoboTwin, it achieves 32.0% on Easy and 28.0% on Hard, showing resilience to visual and environmental perturbations. K1 also produces tool-call traces aligned with next-
token training. A Qwen3.5-9B student trained on only 107 teacher episodes reaches 44.2% accuracy on new initial states versus 30.2% for OpenVLA, and 13.9% on held-out task conditions versus 0.0% for OpenVLA. These results suggest that perception-augmented RUAs offer a promising route to sample-efficient, generalizable robotic policies that leverage VLM capabilities through an accessible tool interface.
Read the full abstract ▾
All authors Zexi Li, Yehang Zhang, Wenqian Li, Haojian Huang, Chenxu Wang, Shiyuan Deng, Yangkai Wei, Tianyi Zhang, Binghui Xie, Bohan Zhou, Yifan Chang, Kaiwen Zhou, Ying-Cong Chen, James Cheng, Yinchuan Li
Quantum Physics
Differential hierarchy of the Husimi representation
Zacharie Van Herstraeten and Ulysse Chabaud
Phase-space representations reveal the geometry of
quantum mechanics and distinguish
quantum features from classical ones. However, the positivity of a density operator is among the properties of
quantum states that phase-space representations capture least directly: deciding whether a phase-space function describes a physical
quantum state has so far required global conditions coupling distant points in phase space. Here we show that these conditions can in fact be made local, by considering the Husimi representation in phase space. We establish a complete set of conditions which captures when a phase-space function $f$ is the Husimi function of a
quantum state, with each condition involving only the derivatives of the function $f$ evaluated at a single phase-space point. We further show that each condition has an equivalent algebraic characterization, which takes the form of the nonnegativity of a determinant of the underlying operator in a displaced Fock basis. As a result, these conditions obey a recurrence relation organizing them into a differential hierarchy, which terminates based on the rank of the operator. Our results thus show that operator rank and positivity are local properties in phase space, reinforcing the role of phase-space representations as a
geometric description of
quantum mechanics.
Read the full abstract ▾
Computer Vision
When Misalignment Becomes Supervision: Structured Label Noise in Supervised Synthetic CT Generation
Valentin Boussot, Cedric Hemon, Caroline Lafond et al. (+2 more)
Supervised synthetic CT (sCT) generation is commonly trained and evaluated as voxel-wise regression against registered reference CT images. In practice, MRI-CT and CBCT-CT pairs are aligned through registration procedures that leave residual misalignments. These residuals are not independent intensity noise but spatially coherent
geometric discrepancies that act as structured label noise. We investigate how this registration-induced bias affects supervised MRI-to-CT and CBCT-to-CT synthesis on 1,784 paired patients covering five anatomical regions. Voxel-wise scores strongly depend on the consistency between the registration used to build the training targets and the one used for evaluation: models score best when both conventions match, showing that networks partly learn the
geometric convention of the registration pipeline and that standard metrics reward it. Training on more anatomically consistent registrations reduces prediction variability and improves out-of-distribution robustness, and CT-only controls show that registration alone produces metric errors in the range of top challenge submissions. To mitigate the limits of voxel-wise supervision, we introduce a perceptual loss computed in the feature space of a pretrained Segment Anything encoder. Compared with MAE-only and VGG-based objectives, it improves downstream
segmentation and yields sharper, more structurally coherent sCT. Perceptual and voxel-wise metrics disagree under imperfect
alignment and agree when the evaluation geometry is reliable. These results identify registration-induced bias as a central confounder in supervised sCT generation and argue for complementing voxel-wise agreement with anatomy-oriented evaluation criteria.
Read the full abstract ▾
All authors Valentin Boussot, Cedric Hemon, Caroline Lafond, Jean-Claude Nunes, Jean-Louis Dillenseger
Machine Learning
MORE-PLR: multi-output regression employed for partial label ranking
Santo M. A. R. Thies, Juan C. Alfaro and Viktor Bengs
The partial label ranking problem is a supervised learning scenario that aims to fit a preference model that predicts a bucket order defined over a set of labels for a given input instance. This problem generalizes the well-known label ranking problem, which, in practice, is limited to outputting total orders of labels. Existing partial label ranking methods have primarily extended label ranking approaches to handle ties in predictions. This paper proposes using multi-output regression to address the partial label ranking problem, introducing an encoder that, during the learning phase, transforms the (possibly incomplete) rankings with ties of labels to multivariate regression targets, an underexplored perspective in both label ranking and partial label ranking. Moreover, during the inference phase, we introduce several post-hoc layers that convert the multi-output regression results into the output bucket order to effectively implement this approach. This framework provides learning strategies that are competitive with the current state-of-the-art partial label ranking methods, as demonstrated through experimental evaluations.
Read the full abstract ▾
Quantum Physics
Anisotropic information geometry of entropy production
Tomohiro Nishiyama and Yoshihiko Hasegawa
We reveal that the information geometry of
entropy production exhibits an intrinsic anisotropy, providing a unified origin for the inequivalent
geometric constraints obeyed by its different components. Using a hierarchical projection structure of
quantum relative
entropy, we derive an exact orthogonal decomposition of
entropy production into three distinct
geometric contributions associated with the deviation of the Gibbs projection temperature from the reference temperature, the deviation of the environment from its Gibbs projection state, and system–environment correlations. We demonstrate that these contributions obey fundamentally different
geometric bounds: the first reduces to a classical Kullback–Leibler divergence and admits no universal upper bound in terms of the trace distance and the system and environment dimensions alone, whereas the latter two admit rigorous distance-based bounds with dimension-dependent factors. The framework also applies to classical Markovian dynamics described solely in terms of the system state, for which the system–environment correlation contribution is absent from the decomposition. Combining this
geometric decomposition with dynamical speed limits, we obtain rigorous bounds on
entropy production expressed solely in terms of physically accessible quantities, such as the mean energy and
Hamiltonian variance.
Read the full abstract ▾
Computer Vision
Segment-Level Risk Discovery in Online Handwriting for Alzheimer's Disease Detection
Changqing Gong, Huafeng Qin and Mounîm A. El-Yacoubi
Online handwriting provides a non-invasive and low-cost behavioral biomarker for Alzheimer's disease (AD) detection, as it reflects both cognitive planning and fine motor control. Existing handwriting-based AD detection methods usually rely on global trajectory features or whole-sample representations, which can be strongly affected by individual writing style, task-specific variation, and acquisition noise. In this paper, we propose NormPaST-Risk, a healthy-normative Paper-Air selective trajectory state-space risk network for interpretable AD detection from online handwriting. Instead of treating the entire trajectory as a single holistic representation, our method reformulates AD handwriting detection as local disease-relevant segment discovery. Specifically, a multi-scale temporal encoder captures stroke dynamics at different temporal resolutions, while a selective Paper-Air state-space encoder models long-range handwriting progression and distinguishes on-paper motor execution from in-air planning and transition behaviors. To explicitly characterize abnormal deviations, a healthy normative branch learns normal handwriting dynamics from healthy controls, and a task-aware multi-expert segment-risk module estimates segment-level AD risk calibrated by hidden-state changes and normative deviations. A weakly supervised segment-level objective further enables high-risk segment discovery without manual segment annotations. Experiments on the DARWIN
benchmark demonstrate that the proposed framework achieves superior AD/HC classification performance compared with existing methods. Moreover, the discovered high-risk segments can be projected back to the original handwriting trajectory, providing interpretable evidence associated with AD-related handwriting variations.
Read the full abstract ▾
Machine Learning
Lightweight Probabilistic Downscaling from a Deterministic Base Model
Joseph McLean, Tiffany Vlaar, Sigrid Passano Hellan et al. (+1 more)
Climate data downscaling is the task of increasing the spatial resolution of
climate data, typically by generating fine-resolution regional
climate data from coarse global model output. Recent machine learning (ML) work in the related task of weather
forecasting has seen significant improvements due to newly devised training methods and architectural components, but these have not yet benefited downscaling. We adapt two of these methods to create a family of lightweight probabilistic ML downscaling models built on a modified U-Net backbone and evaluate them on the CORDEX-ML-Bench suite for daily maximum temperature and precipitation across three geographic regions: the Alps, New Zealand and South Africa. We find that a two-stage training curriculum, combining deterministic pretraining with probabilistic tuning, transfers well to downscaling, beating the state-of-the-art for RMSE. Our work provides an advancement towards lightweight, probabilistic downscaling models, reducing the current trade-off between computational intensity and distributional fit.
Read the full abstract ▾
All authors Joseph McLean, Tiffany Vlaar, Sigrid Passano Hellan, Linus Ericsson
Robotics
Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs
Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro et al. (+3 more)
Flow-matching
Vision-
Language-Action (VLA) models have emerged as a potential solution for generalist
robot control, designed by combining a pretrained
Vision-
Language Model (VLM) backbone with an action expert that generates continuous
robot actions. While these models exhibit impressive capabilities, due to their very high number of parameters, their computational requirements are often prohibitive for robotics control. To mitigate these inefficiencies, existing methods predominantly skip VLM backbone layers with early exits or reduce denoising steps, while leaving action expert depth untouched. We propose a framework that exposes backbone depth $V$, action expert depth $A$, and denoising steps $D$ as three jointly configurable compute axes in a VLA. Starting from a pretrained VLA, we attach lightweight Exit
Transformers (ET) at intermediate depths in both the backbone and the action expert, trained to distil the last layer of the policy into each exit. Furthermore, we introduce a KV Cache synthesis mechanism that manages the missing keys and values of the skipped backbone layers, allowing the action expert to exit deeper than the backbone. Finally, we show that the optimal compute budget is task-dependent, with different tasks benefiting from different axes and depths. Notably, our method does not require training the original policy from scratch, and for each exit, it increases the number of parameters by only $2.1\%$ for SmolVLA and $4.1\%$ for $\pi_{0.5}$. We validate our approach across two flow-matching VLAs (SmolVLA, $\pi_{0.5}$) and two
benchmarks (LIBERO, Meta-World), revealing complementary effects: $V$ and $A$ respectively reduce FLOPs and latency, while $D$ improves both. Our joint configurations $(V,A,D)$ reduce latency by $79.2\%$ and computation (FLOPs) by $31.8\%$, while improving mean success rate by $5.6\%$.
Read the full abstract ▾
All authors Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro, Subramanian Ramamoorthy, Matteo Matteucci, Alessandro Suglia
Artificial Intelligence
An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer
Daoyun Wang, Zhicheng Huang, Huaiyuan Sun et al. (+39 more)
Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effective support must make explicit how patient conditions govern pathway eligibility, deferral and redirection. MedGPT Clinical Explorer (MCE) organizes alternatives, decision-changing unknowns, safety constraints and fallback into a conditional strategy for clinician review. To evaluate this representation in physician-authored strategies, multidisciplinary experts established case-specific references for 40 cases within a purposive 100-case corpus, and 250 physicians from 98 institutions produced 2,250 strategies under unaided,
retrieval-reference and MCE-assisted conditions. MCE-assisted strategies expressed more applicable clinical requirements, measured by the Admissible Pathway Attainment Score (APAS; 0-100), than unaided strategies (adjusted difference, 12.87; 95% CI, 11.18-14.55) and
retrieval-reference strategies (5.22; 3.52-6.93). With the same knowledge base available in the
retrieval-reference and MCE-assisted conditions, the additional content centered on candidate pathways, decision-critical information and safety constraints. Physicians' whole-strategy acceptability judgments correlated with APAS (Spearman's rho = 0.671), while a complementary relationship audit assessed whether candidates, conditions and subsequent actions were coherently connected. Together, these findings identify two complementary dimensions of open-ended decision support: coverage of clinically relevant content and coherent links among pathways, conditions and subsequent actions. MCE provides a shared decision object that makes consequential omissions and pathway contingencies visible before action; prospective studies should evaluate its effects on clinical workflow and patient outcomes.
Read the full abstract ▾
All authors Daoyun Wang, Zhicheng Huang, Huaiyuan Sun, Jiaqi Xu, Xiaowei Xu, Zhibo Zheng, Zhongxing Bing, Yuxiao Lin, Yicheng Liang, Chao Gao, Bowen Xue, Kai Zhang, Song Xu, Wanpu Yan, Hui Xia, Lin Li, Xiang Yan, Mu Hu, Qianli Ma, Zhiqiang Xue, Xiaofang Liu, Zhihai Han, Nan Zhang, Chuanhao Tang, Tongmei Zhang, Lan Song, Zhaohui Zhu, Xuan Zeng, Shafei Wu, Hui Guan, Lei Deng, Huaxia Yang, Zeliang Lian, Wubin Sun, Yongxin Wang, Xiaohui Shen, Binlin Wang, Tiantian Gu, Yu Cui, Li Zhang, Shirui Wang, Naixin Liang
Logic in Computer Science
Scenes: A Meta-Logical Algebra for Mutable State
Simon Foster, Carlos Isasa and Christian Pardillo Laursen
Modelling of mutable state spaces and precisely describing how variables are manipulated in a program is a fundamental problem in compositional verification. Though we can make use of the embedded abstract syntax of a program for such analysis, this runs contrary to the shallow-
embedding approach, and hampers efficient proof automation. On the other hand, lenses and prisms provide an elegant algebraic foundation for modelling state, which provide sufficient structure to provide meta-logical program analysis, but without requiring a deep
embedding. Nevertheless lenses, as complex algebraic objects, cannot easily be combined, complemented, or collected in sets. In this paper we contribute an accompanying algebraic structure called the scene, which allows us to characterise the set of variables, or coordinates, in a state space. Scenes intuitively correspond to sets of lenses, but like lenses they are purely semantic algebraic objects. We demonstrate that scenes provide us with sufficient structure to characterise the lens-based meta-logical properties, like independence and equivalence. Moreover, we introduce the notion of a scene space, analogous to a vector space, which allows us to recover a set-like algebraic structure. Finally, we show how scenes allow us to characterise the free and bound variables of expressions and programs, without any need for syntax, and demonstrate their use for
reasoning about programs by deriving
reasoning principles for the parallel composition operator.
Read the full abstract ▾
Machine Learning
On the second-order optimization for spiking neural networks
Ngoc Phu Doan and Ihsen Alouani
Spiking Neural Networks (SNNs) offer an energy-efficient alternative to conventional neural networks by exploiting sparse, binary spikes, and event-driven computation. However, the training of SNNs remains challenging, as spiking activations create a sharp loss landscape that hinders training, and diagonal-
curvature optimizers such as the Adam family may fail to capture this geometry. The extension of
curvature-based optimization methods to SNNs is further complicated by the sparse, discrete, and temporally recurrent nature of their underlying dynamics. To address these limitations, we propose SpiKFAX, a second-order optimization method that formulates a computationally tractable, Kronecker-factored approximation of the Fisher information
matrix specifically adapted to the structure of SNNs. Empirical evaluation across five architectures and seven
datasets demonstrates that SpiKFAX consistently yields improvements in test accuracy and training stability relative to other popular optimizers.
Read the full abstract ▾
Earth and Planetary Astrophysics
Exoplanet Detection Techniques: Radial Velocity
Rafael Luque and Matthew R. Standing
The radial velocity (RV) technique enabled the discovery of the first
exoplanets orbiting Sun-like
stars. Since then, improvements in precision and sensitivity have enabled the detection of smaller
planets, bringing us closer to the goal of discovering Earth analogs in the coming years. In this chapter, we provide an overview of the radial velocity method. We begin with a detailed description of the technique, including how precise radial velocities are measured and what limitations must be addressed to achieve reliable detection of small signals. We examine the unique challenges associated with the detection of circumbinary
planets and outline the developments that have, for the first time, made their detection feasible using the radial velocity method. With over 2,000
planets detected to date, the radial velocity method remains one of the most reliable techniques, offering valuable insights into the demographics of
exoplanets, especially at long orbital distances. As an example of its applications, we provide an analysis and interpretation of three publicly available radial velocity
datasets: one from a single
star, one for a circumbinary
planet system, and another from a single
star with transiting
planets. Furthermore, we compile information on the spectrographs currently and soon-to-be available worldwide for radial velocity observations and a list of open-source tools designed for their analysis. In the Supplementary Material, we include a sample
telescope proposal for obtaining radial velocity data, along with practical tips on writing a competitive proposal to aid early-career researchers entering the field. This chapter serves as a comprehensive guide for understanding the capabilities and applications of the radial velocity method, equipping readers with the knowledge and resources to address their own scientific questions using this technique.
Read the full abstract ▾
General Relativity and Quantum Cosmology
Joint Model-independent Constraints on the Post-Newtonian Parameter and Cosmic Curvature from Galaxy-scale Strong Lensing, SNe Ia, BAO, and Cosmic Chronometers
Fu-you Zheng, Xiao-jun Gao, Hou-bing Tang et al. (+1 more)
This investigation aims to test the validity of general relativity (GR) on kiloparsec scales via
galaxy-scale strong gravitational
lensing (SGL) combined with multiple cosmological probes. To circumvent the circularity problem induced by the presumption of a cosmological model based on GR, we apply the distance sum rule in the Friedmann-Lemaitre-Robertson-Walker (FLRW) metric to constrain the post-Newtonian parameter gamma PPN and spatial
curvature Omega k independently of any cosmological model. The study introduces two methodological improvements: (i) parameterizing the dark-energy
evolution factor with second-order Chebyshev orthogonal
polynomials, which ensures uniformly high convergence across the full
redshift baseline while retaining Omega k as an explicit free parameter; (ii) extending the original two-probe configuration (SGL + Type Ia
supernovae) to a four-probe joint analysis that includes
baryon acoustic oscillations and
cosmic chronometers. Our results show that gamma PPN = 1.119 (+0.072/-0.072) and Omega k = 0.101 (+0.077/-0.076) at 68% confidence. The gamma PPN value is consistent with the GR prediction of unity at 1.7 sigma, while Omega k favors a mildly open universe, with flatness consistent at 2 sigma. Taking model-independent constraints as a
benchmark, we quantify the systematic shift in gamma PPN induced by eight representative dark energy models, and find that all offsets are negligible, well below the baseline 1 sigma uncertainty, with no significant bias at current precision. These results confirm that conventional strong-
lensing gravity tests introduce no measurable systematic bias, validating our model-independent framework.
Read the full abstract ▾
All authors Fu-you Zheng, Xiao-jun Gao, Hou-bing Tang, Wei Xiang
Computer Vision
A Hybrid CNN–State-Space–Attention Backbone with Joint-Embedding Predictive Pretraining for 12-Lead ECG Classification
Yakoub Bazi, Sarah Aljuhani, Mohamad M. Al Rahhal et al. (+2 more)
Automatic 12-lead electrocardiogram (ECG) classification requires representations that jointly capture local waveform morphology, long-range temporal dynamics, and cross-lead dependencies, yet integrating these properties within a single efficient architecture remains challenging. This paper introduces a hybrid CNN-SSM-
Attention backbone for 12-lead ECG classification. A convolutional stem performs early waveform tokenization and temporal reduction, mixed state-space and depthwise-convolutional blocks model temporal dynamics and local morphology, and a late self-
attention stage enables global
token interaction at reduced resolution. To improve transfer from unlabeled data, we further develop an ECG-oriented Joint-
Embedding Predictive Pretraining (JEPA) framework. Unlike ViT-based JEPA methods that mask patch
tokens before the encoder, the proposed method samples span masks at the latent temporal resolution and projects them back to the waveform domain, then predicts clean latent targets from a momentum encoder without waveform reconstruction. Experiments on CPSC2018, Chapman-Shaoxing, and PTB-XL, with pretraining on approximately 350K unlabeled CODE-15 recordings, show that the proposed backbone provides strong supervised baselines under a compact parameter budget. JEPA pretraining further improves transfer, particularly in reduced-label settings and under both full fine-tuning and LoRA-based adaptation. Code: https://github.com/yakoubbazi/Hybrid_ECG_Jepa
Read the full abstract ▾
All authors Yakoub Bazi, Sarah Aljuhani, Mohamad M. Al Rahhal, Mansour Zuair, Naif Alajlan
Robotics
Free-Init: Scan-Free, Motion-Free, and Correspondence-Free Initialization for Doppler LiDAR-Inertial Systems
Mingle Zhao, Jiahao Wang, Tianxiao Gao et al. (+2 more)
Robust initialization is crucial for online systems. In the letter, a high-frequency and resilient initialization framework is designed for
LiDAR-inertial systems, leveraging both inertial sensors and Doppler
LiDAR. The innovative FMCW Doppler
LiDAR opens up a novel avenue for robotic sensing by capturing not only point range but also Doppler velocity via the intrinsic Doppler effect. By fusing point-wise Doppler velocity with inertial measurements under non-inertial kinematics, the proposed framework, Free-Init, eliminates reliance on motion undistortion of
LiDAR scans, excitation motions, and map correspondences during the initialization phase. Free-Init is also plug-and-play compatible with typical
LiDAR-inertial systems and is versatile to handle a wide range of initial motions when the system starts, including stationary, dynamic, and even violent motions. The embedded Doppler-inertial velocimeter ensures fast convergence and high-frequency performance, delivering outputs exceeding 10 kHz. Comprehensive experiments on diverse platforms and across myriad motion scenes validate the framework's effectiveness. The results demonstrate the superior performance of Free-Init, highlighting the necessity of fast, resilient, and dynamic initialization for online systems.
Read the full abstract ▾
All authors Mingle Zhao, Jiahao Wang, Tianxiao Gao, Chengzhong Xu, Hui Kong
Robotics
FMCW-LIO: A Doppler LiDAR-Inertial Odometry
Mingle Zhao, Jiahao Wang, Tianxiao Gao et al. (+2 more)
Conventional
LiDAR-inertial odometry (LIO) or simultaneous localization and mapping (SLAM) methods heavily rely on
geometric features of environments, as
LiDARs primarily provide range measurements instead of motion measurements. From now on, however, the situation changes thanks to the novel Frequency Modulated Continuous Wave (FMCW) Doppler
LiDARs. FMCW Doppler
LiDARs not only offer the point range with high resolution but also capture the instant point Doppler velocity through the Doppler effect. In the letter, we propose FMCW-LIO, a novel and robust LIO, leveraging intrinsic Doppler measurements from FMCW Doppler
LiDARs. To correctly exploit Doppler velocities, a motion compensation method is designed, and a Doppler-aided observation model is applied for on-
manifold state estimation. Then, dynamic points can be effectively removed by the Doppler criteria, deriving more consistent
geometric observations. FMCW-LIO eventually achieves accurate state estimation and static mapping, even in structure-degenerated environments. Extensive experiments in diverse scenes are performed and FMCW-LIO outperforms other
algorithms on both accuracy and robustness.
Read the full abstract ▾
All authors Mingle Zhao, Jiahao Wang, Tianxiao Gao, Chengzhong Xu, Hui Kong
Computer Vision
Shadow Reduction in Ultrasound Imaging Using Differentiable Simulation and Radiance Field Decomposition
Valentin Bacher, Pak Hei Yeung, Bernhard Kainz et al. (+4 more)
Acoustic shadows from bone and other highly attenuating tissues obscure clinically important structures in ultrasound. In fetal
brain imaging, skull-induced artefacts disproportionately degrade the hemisphere closer to the transducer (proximal), limiting symmetric assessment of the two hemispheres. Existing correction methods require raw scanner data, impose restrictive assumptions on tissue properties, or rely on generative models that may hallucinate anatomy. We present RFlash, a physics-informed post-processing method that decomposes beamformed ultrasound images into explicit attenuation and scatter-intensity maps using a differentiable radiance-field formulation of image formation. Attenuation-adaptive re-rendering then removes the dependence of the signal at each depth on the intervening tissue, equivalent to virtually advancing the transducer into the tissue. Across 1,261 3D fetal
brain volumes, 143 real 2D curvilinear abdominal scans, and 1,200 simulated 2D linear-probe liver scans, RFlash reduces shadow-related intensity differences more effectively than classical Hughes-Duck attenuation correction. For a gestational-age model trained on the distal hemisphere (further from the transducer) and applied to the proximal hemisphere, prediction error decreases by 5.1 days (40%) relative to the original images. The estimated attenuation maps also yield shadow-confidence maps that improve random-forest bone-shadow
segmentation over the image alone and receive greater SHAP importance than an existing neural confidence-map baseline, suggesting greater physical consistency. RFlash requires neither hardware modification nor access to raw scanner data and supports 2D and 3D acquisitions with linear and curvilinear probes, making it widely applicable allowing clinicians to use our method on their already acquired scanners and images.
Read the full abstract ▾
All authors Valentin Bacher, Pak Hei Yeung, Bernhard Kainz, Madeleine K. Wyburd, Nicola K. Dinsdale, Michael Gray, Ana I. L. Namburete
Audio and Speech Processing
WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection
Kwok-Ho Ng, Tingting Song, Bingwen Feng et al. (+1 more)
The acoustic front-end determines which forensic cues a
speech deepfake detector can exploit. The wavelet scattering transform (WST) provides stable multiscale coefficients with explicit coordinates, yet direct flattening obscures the parent relation between paths. We introduce WST-Graph, reconstructing these paths as a sparse modulation-carrier grid for an AASIST graph backend. Modulation-level normalization and length-aware adaptive local
attention pooling produce fixed relative-time representations while retaining the acoustic axes before learned adaptation. This yields a waveform-to-graph interface with a fixed, parameter-free WST. Our configurations remain competitive with AASIST while using approximately 60% fewer trainable parameters and show clear gains on selected out-of-domain
benchmarks. These results underscore the value of preserving parent-child relations within the carrier-modulation
topology when constructing a compact, physically grounded interface for graph-based
speech deepfake detection. Code will be released at https://github.com/saki-ciallo/wst-graph.
Read the full abstract ▾
All authors Kwok-Ho Ng, Tingting Song, Bingwen Feng, Zhihua Xia
Computation and Language
BanglaTurn: A Benchmark and Whisper-Based Model for End-of-Turn Detection in Bangla Speech
Mizbaul Haque Maruf
This paper presents BanglaTurn, a corpus for end-of-turn detection in Bangla conversational
speech, and a model trained on it. The corpus holds 35,374 samples of 3 to 15 s of podcast
speech, labelled for turn state by combining speaker diarization with an LLM pass, with every label then checked by a human annotator. The model pairs a Whisper encoder with task-specific classification heads. On a class-balanced test set drawn from a held-out podcast, it reaches 84.33% accuracy (95% CI 80.3 to 88.1) against 69.28% for the Smart-Turn v3 baseline, and lowers the false negative rate from 51.57% to 7.55% at the cost of a higher false positive rate. We report what encoder layer fine-tuning, multi-scale pooling and INT8 quantization each contribute, and latency stays within 165 to 191 ms end to end on CPU.
Read the full abstract ▾
Computation and Language
From Policy Documents to Structured Survey Responses: Evaluating Large Language Models for Policy Monitoring
Carolyn Cole, Matthias Deschryvere, Toqeer Ehsan et al. (+1 more)
Science, technology, and innovation policies are crucial for competitiveness, yet their diversity and scale make them difficult to map and monitor consistently. Existing approaches rely heavily on manual survey efforts, which are costly and challenging to scale across countries. Large
language models (LLMs) enable new possibilities for extracting and structuring information from long and unstructured policy documents. This paper presents an application of LLMs as "AI respondents" for generating structured survey responses from policy texts. We develop a data extraction pipeline based on long-context in-context learning to map information from public web sources into predefined survey categories, including policy instruments, target groups, and thematic areas. The pipeline integrates a validation step using a secondary LLM to assess relevance and evidence, alongside comparisons with human-provided responses. Using a multi-country
dataset, we evaluate the
alignment between LLM-generated and human-generated outputs through overlap measures and cross-validation. Results show that LLMs achieve high agreement for structured indicators (84-95%), while differences remain in free-text fields, where models tend to provide more detailed procedural descriptions. These findings highlight the potential of hybrid human-AI workflows for policy monitoring, improving both efficiency and scalability while maintaining the need for human validation and contextual interpretation.
Read the full abstract ▾
All authors Carolyn Cole, Matthias Deschryvere, Toqeer Ehsan, Arash Hajikhani
General Relativity and Quantum Cosmology
Emergence of Horndeski gravity from asymptotic safety?
Astrid Eichhorn, Pedro G. S. Fernandes and Fabian Willaschek
There are strong motivations to modify
gravity in the ultraviolet as well as the infrared. Such modifications are usually pursued independently from one another. Using the predictive power of asymptotically safe
quantum gravity, we can constrain the effective-field-theory coefficients of scalar-tensor theories and thereby connect ultraviolet and infrared modifications of
gravity. We focus on two non-minimal couplings, which are naturally generated in asymptotic safety and belong to the Horndeski Lagrangian only if the couplings satisfy a specific ratio. A priori, one would expect to find a negative answer to the question in our title. Surprisingly, we find that despite the constraints from asymptotic safety, this ratio can be achieved for a specific value of the cosmological constant. We interpret this as a non-trivial hint that asymptotically safe scalar-tensor theories could be free of extra propagating degrees of freedom in the infrared. We further find that the same result holds in an effective asymptotic safety scenario, where asymptotic safety is not a fundamental theory and
quantum scale
symmetry, the
symmetry underlying asymptotic safety, only holds over an intermediate range of scales. Finally, we report novel non-trivial indications of approximate radiative stability in the aforementioned Horndeski sector for a range of coupling values, independently of any particular UV completion.
Read the full abstract ▾
Optimization and Control
Policy iteration for Hamilton-Jacobi-Isaacs equations with control constraints and comparison with Hamilton-Jacobi-Bellman equations
Sudeep Kundu and Karl Kunisch
Convergence of the bilevel policy iteration
algorithm for the value function, satisfying the Hamilton-Jacobi-Isaacs (HJI) equation, is analyzed in the presence of control constraints. Both first and second-order HJI equations corresponding to the deterministic and
stochastic systems are considered. For numerical tests, a semi-implicit upwind scheme for backward HJI PDEs is applied and a thorough comparison between the solutions to first and second-order Hamilton-Jacobi-Bellman (HJB) equations is presented for both the unconstrained and the constrained control cases.
Read the full abstract ▾
Image and Video Processing
Graph-Based Semi-Supervised Hyperspectral Image Classification with Distance-Aware Spatial Measure
Sérgio J. M. Almeida and José C. M. Bermudez
The classification of hyperspectral images (HIs) still presents several challenges. One of them is the difficulty to obtain a large set of labeled samples to train the classifier. Semi-supervised learning methods have received much
attention recently, as they require the initial labeling of a reduced number of image pixels and lead to very good results for practical application. One of the open problems in graph-based semi-supervised HI classification is the need to consider relative spatial relationship between pixels in the image to improve the smoothness of the solution. Kernel-based approaches using composite kernels have led to very good results, in which one kernel addresses the spectral properties of the pixels while a second kernel addresses some spatial properties. Most available solutions employ a spectral-spatial kernel which considers the spectral properties of a spatial region about each pixel. This work proposes a composite kernel approach that includes a third kernel dealing exclusively with the relative spatial position of the pixels. Experiments with real HI images show that the use of the new spatial kernel has led to improved classification results when compared to those previously reported in the literature. These results also shed some light on the relative contributions of the spectral and spectral-spatial kernels in semi-supervised HI classification.
Read the full abstract ▾
Artificial Intelligence
Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination
Mehdi Nasiri, Mohammad Saeed Arvenaghi, Sadegh Vaezi et al. (+1 more)
Multi-
agent large
language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens of multi-
agent systems theory, several shortcomings come to light: a lack of social intelligence, the absence of coordination mechanisms among
agents, unknown emergent behavior, and interactions between
agents that are bounded by natural
language. We address two of these gaps: the absence of social behavior and the lack of mechanisms for inter-
agent coordination. We introduce Epistemic Probabilistic
Language Agents (EPLA), a neuro-symbolic architecture for multi-
agent coordination under uncertainty. A Symbolic Guard provides structured diagnostic feedback. The LLM generates typed actions, and the Guard controls their execution against an authoritative symbolic state. We formalize the epistemic layer in a gossip testbed through epistemic lottery gossip models, which combine view-based call histories with
agent-indexed probability weights. We argue that implementing such a formalism can address shortcomings of agentic LLMs.
Read the full abstract ▾
All authors Mehdi Nasiri, Mohammad Saeed Arvenaghi, Sadegh Vaezi, Ebrahim Ardeshir-Larijani