Robotics
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Wednesday 9 September
Achieving biological-level running speeds has largely been pursued through advances in control algorithms, which improve the utilization of existing hardware. However, the ultimate speed limits remain governed by the underlying force and torque requirements of rapid locomotion, which are typically addressed through increased actuator capacity. Inspired by Huygens' coupled pendulums, we demonstrate that superior locomotion can emerge from principled exploitation of intrinsic dynamics rather than brute-force hardware scaling. Inter-limb inertial coupling redistributes energy across the gait cycle and reduces peak joint torque required for rapid periodic motion, thereby expanding the achievable speed without proportional increases in actuator capability. Incorporating hardware parameters as additional design variables further extends this analysis into a co-optimization framework, enabling the systematic utilization of inertial coupling in robot design. Guided by this framework, a quadruped robot achieves a running speed of 10.74 m/s (Froude number 21.4) and completes a 100-meter sprint in 12.2 seconds, representing the first legged robot to surpass 10 m/s. These results establish inertial coupling as an underlying mechanism governing high-speed legged locomotion and highlight its role in reducing force requirements, offering new insights into the design of agile robotic systems.
Robotics
Extending the Speed Limit of Quadrupedal Locomotion via Refined Actuator Modeling and Adaptive Command Scheduling
Achieving high-speed locomotion in quadrupedal robots remains highly challenging, as actuators operate near their physical limits and exhibit pronounced nonlinearities. However, many existing methods neglect actuator nonlinearities and physical constraints during training, leading to a significant sim-to-real gap under highly dynamic motions and limiting achievable performance. To address this issue, we propose a high-speed locomotion framework that reduces sim-to-real discrepancies and stabilizes learning over a wide command distribution. A refined actuator model explicitly captures high-speed voltage coupling and magnetic saturation, enabling a more accurate representation of the torque-speed envelope. In addition, a reinforcement learning framework incorporating a two-stage curriculum and adaptive command scheduling (ACS) ensures stable training. Experiments on the 36.5 kg quadruped BlackPanther2 (BP2) demonstrate speeds of up to 13.2 m/s on a treadmill and 11.65 m/s outdoors, establishing a new state-of-the-art and, to the best of our knowledge, a world record for quadrupedal robot locomotion. The results further highlight the importance of accurate actuator modeling in preventing non-physical policy exploitation, and show that ACS improves robustness without sacrificing performance.
Read the full abstract
Computer Vision
Target-Checked Reliability Score Refinement for Video Question Answering
Video-language models can answer multiple-choice questions with high confidence yet be wrong. We study whether answer-level reliability scores can be improved under target shift without retraining the models or changing their answers. We collect option-probability lists from three fixed video-language models under four deterministic video samplings and represent cross-view changes and cross-model agreement as a response graph. Using a labeled target pilot, we compare the original score, defined as the probability assigned to the chosen answer, with a histogram-based gradient-boosting (HGB) score trained on the development datasets and a regularized logistic-regression score trained on the target pilot. A candidate replaces the original score only when repeated video-level checks indicate a positive, stable improvement. We develop this rule on public VideoQA benchmarks and Video Hallucination Diagnosis (VHD), a controlled diagnostic dataset for shared high-confidence errors. Ranking quality is measured by the area under the risk-coverage curve (AURC), where lower is better. On a held-out 963-question HERBench split, the method reduces mean AURC across the three models by 16.64% (95% confidence interval (CI), 12.12 to 22.61%); the smallest model-level gain is 11.39%. On a separate held-out 911-question Perception Test split, the mean reduction is 18.87% (95% CI, 15.43 to 22.14%). For InternVL3.5, the target check retains the original scores. Using the same outputs, the method outperforms seven training-free baselines in mean AURC on both datasets. It also improves AUROC, reduces calibration error, and lowers the error rate at 50% coverage by 6.50 and 6.58 percentage points.
Read the full abstract
Computer Vision
LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents
Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive for latency-sensitive applications. GUI agents represent a natural testbed for this paradigm, as they must repeatedly perceive screen states and emit structured, spatially grounded actions in real time. However, whether dLLMs can be extended into capable multimodal GUI agents while preserving their parallel decoding advantage remains an open question. We present LLaDA-UI, a 16.7B-parameter MoE-based, block-wise diffusion vision-language GUI agent. LLaDA-UI follows a two-stage training pipeline: general multimodal pre-training aligns a native-resolution vision encoder with the LLaDA2.0-mini-base diffusion language backbone, followed by GUI-agent supervised fine-tuning on diverse mobile, desktop, web, and grounding data. Across widely adopted grounding benchmarks and navigation benchmarks spanning multiple platforms, LLaDA-UI substantially outperforms Qwen2.5-VL-7B and surpasses Qwen3-VL-8B on four of six reported GUI benchmarks. These results establish block-wise diffusion as a practical generative paradigm for multimodal GUI agents.
Read the full abstract
Machine Learning
Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale
Diffusion language models decode tokens in parallel, but their bidirectional denoiser rules out the naive key–value (KV) cache behind fast autoregressive inference. Block diffusion restores caching by decoding block-by-block, and the block caches deployed on it so far are tied to attention: O(L)in memory and, if used as training-free retrofits, only an approximation of the model's computation. Both constraints can be overcome: sequence mixers that summarize finalized blocks into a reusable state support block caching, and the corresponding block-causal training objective makes the cache exact. We study this recipe at scale, pretraining three 3B block-diffusion denoisers (attention, mamba, and hybrid) on 300B tokens under one single-frontier objective and decoding all three through a single cached interface. Only the state-space cache is O(1) in sequence length: its memory and per-step latency stay constant at any context length, while an attention cache remains O(L). At 256k tokens (where attention has grown to 82GB and 29 ms/step), the Mamba cache delivers 4.3x lower latency, 11x less memory, and 2.6x higher single-stream throughput; and because that footprint is constant it scales with batch as well, reaching 14x the aggregate throughput, where attention cannot run beyond a single stream. The same linear-state bias lets the Mamba and hybrid backbones keep retrieving out to 8-16x their training length, whereas attention's retrieval collapses at 2x, at no measured quality cost.
Read the full abstract
Machine Learning
DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning
Learning robust representations for time-series signals under noise and distribution shifts remains challenging, especially in clinical applications such as electroencephalogram (EEG) and electrocardiogram (ECG) analysis. We propose Diffusion-Conditioned Representation Alignment (DCRA), a training framework that repurposes the forward diffusion process as a structured corruption scheduler for representation learning. Different from conventional augmentation and consistency-based methods that rely on independently sampled perturbations, DCRA introduces a structured corruption trajectory via the diffusion forward process, which enables continuous and controlled representation evolution across noise levels. We introduce a feature-level consistency objective that aligns representations across noise levels while preserving class-discriminative structure. This mechanism promotes structure-preserving consistency, which enables smooth and semantically coherent feature trajectories in latent space. The proposed framework is encoder-agnostic and can be integrated with state space models and Transformer architectures. The seizure detection experiments on the CHB-MIT EEG dataset show that DCRA consistently improves performance under multiple noise conditions and achieves higher sensitivity at low false-positive rates. Analysis reveals that DCRA produces more balanced and structured representations compared to baseline and diffusion-only models. These findings highlight the benefit of combining structured corruption with representation alignment for robust time-series learning.
Read the full abstract
Networking
Assured AI-Native Network Control Loops: State of the Art, Research Challenges and the Missing Runtime Assurance Layer
The evolution towards autonomous and AI-native telecommunication networks is transforming network control from predefined automation towards distributed and intelligent decision-making. Advances in closed-loop automation, O-RAN, Network Digital Twins, AI-driven orchestration, and autonomous agents enable multiple specialized control functions to operate concurrently across network domains and timescales. This introduces a system-level assurance challenge: individually acceptable decisions may interact through shared resources and network state, while changes in their operational context may invalidate assumptions under which they were evaluated. This paper presents a state-of-the-art review of AI-native network control, focusing on the composition and runtime assurance of autonomous control loops. It examines closed-loop and zero-touch automation, intelligent controllers, Network Digital Twins, AI-driven orchestration, autonomous agents, trustworthy AI, and runtime assurance. The analysis shows that these directions provide important foundations for autonomous operation but lack a unified mechanism for assuring heterogeneous control loops whose decisions depend on shared and dynamically changing network state. To address this gap, the paper identifies dependency-aware runtime assurance as a research direction for assured composition of AI-native network control loops. The proposed perspective associates decisions with assumptions and dependencies on which their validity relies, monitors changes that may invalidate accepted decisions, and supports runtime resolution of concurrent control interactions. A telecom use case and an initial architecture and formal model illustrate the concept and identify open challenges in dependency representation, runtime validation, conflict resolution, latency-aware assurance, and experimental evaluation.
Read the full abstract
Machine Learning
Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration
Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains challenging in small-cohort health-sensing studies, where task-specific outcome supervision is limited relative to heterogeneous sensing data. Interpretability is also important, as model outputs should reflect meaningful behavioral and physiological patterns rather than predictive scores alone. We develop a Concept-Integrated Transformer (CIT) with LLM-guided concept supervision for explainable prediction from mobile sensing data. CIT uses a pretrained large language model to generate baseline-aware concept abnormality targets with confidence weights without manual concept annotation. Across two longitudinal datasets, CIT achieves the highest F1 score on AFFECT (0.756) and ties for the highest on a PHQ-9 dataset (0.765). The learned concept scores also reveal interpretable behavioral and physiological patterns; in AFFECT, sleep quantity and quality show the clearest difference between high and low negative affect groups. These findings support LLM-guided concept integration for accurate and interpretable prediction in small-cohort mobile sensing studies.
Read the full abstract
Quantitative Methods
PyFLI: A Python Library for Simulation, Parameter Estimation, and Benchmarking in Fluorescence Lifetime Imaging
Fluorescence lifetime imaging (FLI) measures the temporal decay of fluorescence after excitation and provides quantitative information about a fluorophore's local environment and molecular interactions. Depending on the fluorophore and experimental design, lifetime can report changes associated with pH, oxygenation, cellular metabolism, and Forster resonance energy transfer. These properties make FLI useful across microscopy, biophysics, biomedical optics, and preclinical imaging, where the same type of molecular contrast can be studied across different biological scales. FLI measurements, however, are acquired with instruments that record fluorescence in different ways. Intensified charge-coupled device (ICCD) cameras, single-photon avalanche diode (SPAD) arrays, and time-correlated single-photon counting (TCSPC) systems differ in temporal sampling, data organization, detector noise, instrument response, and file format. Lifetime-estimation methods also make different assumptions about the recorded decay, while learning-based approaches require realistic training and validation data for which the underlying parameters are known. PyFLI is an open-source framework for FLI processing and standardized data simulation. It imports measurements from acquisition systems, simulates labeled data under configurable acquisition and noise conditions, and provides complementary approaches for parameter estimation. These include nonlinear least-squares fitting (NLSF), maximum-likelihood estimation (MLE), phasor analysis, rapid lifetime determination (RLD), Laguerre-based estimation, and optional Bayesian and deep-learning inference. CPU and GPU processing support image-scale analysis, while reconstruction, visualization, statistical analysis, and cross-software comparison provide tools for evaluating results. PyFLI includes compressed-sensing reconstruction for single-pixel hyperspectral FLI.
Read the full abstract
Machine Learning
FINESSE: An Agent-Based Simulator and Benchmark Dataset for Multimodal Financial Event Sequences
Machine learning research in financial services is limited by the scarcity of representative open-source datasets. Existing resources are often narrowly focused on a single modality or task and fail to reflect the structured, multimodal, and dynamic nature inherent to many problems in financial services. In this paper, we introduce FINESSE, a Financial Event Sequence Simulation Environment, an agent-based simulation framework for generating synthetic, structured datasets composed of multiple interdependent event streams. Each stream corresponds to a distinct financial behavior such as transactions, payments, account status changes, and policy interventions, each with unique action spaces, schemas and variable types. These streams are coupled through agents' latent evolving states, enabling the simulation of temporally rich interactions. We also introduce FINESSE-Bench, a benchmark dataset generated by the simulator, supporting four representative tasks: balance forecasting, transaction fraud detection, missed payment prediction, and next event prediction. We report baseline results using methods from time series forecasting, event sequence modeling, temporal graphs, and temporal point processes. We release the FINESSE framework, including the simulator and dataset to accelerate research on structured, multimodal event sequence modeling challenges in financial services.
Read the full abstract
Materials Science
Crystallographic and Electronic Phase Changes in TiTe2 via Atmospheric and Electron Beam Exposure
In this study, we examine the surface sensitivity of a transition metal dichalcogenide (TiTe2) grown using the Chemical Vapor Transport (CVT) technique at high pressure and study the surface changes in the sample upon exposure to air as well as its crystallographic properties upon e-beam exposure. We examine the local density of States (LDOS) of the mechanically exfoliated sample surface before and after exposure using Scanning Tunneling Microscopy/Spectroscopy (STM/STS) and find a metal-to-semiconductor transition at the surface. The STM analysis shows a clear change in surface roughness which indicates the formation of an adlayer on the surface of the sample. The crystal structure was examined using X-ray Diffraction (XRD) and Transmission Electron Microscopy (TEM), indicating a phase transition from a single-crystalline hexagonal phase to a polycrystalline state via a distorted monoclinic phase. Furthermore, the presence of a possible superlattice suggests non-stoichiometric TixTey at the surface of the exposed layer.
Read the full abstract
Cryptography and Security
A Survey on Quantum-Safe Cryptographic Mechanisms: Building Blocks and Applications
The possible emergence of fault-tolerant quantum computers may enable widely used cryptographic algorithms to be broken. These algorithms for public key encryption and digital signatures could be exposed if an efficient algorithm is employed. This poses a threat to existing infrastructure, motivating the development of mechanisms that can withstand quantum-computer cybersecurity risks. However, the transition to new security mechanisms is still underway and faces many challenges, including identifying which applications are under threat and implementing agile, scalable migration processes. In this work, we survey the state of the art in quantum-safe cryptographic mechanisms, existing applications targeting migration, and open challenges. We examine the building blocks commonly used to integrate quantum-safe mechanisms into existing applications and categorize them by the security mechanisms they employ. Next, we systematically review existing migrations into quantum-safe schemes and categorize them by application domain, including Telecommunications, the Internet of Things, and Blockchains. Finally, we summarize the challenges that must be addressed to enable a successful migration to quantum-resistant mechanisms, as well as the motivations for pursuing this migration.
Read the full abstract
Image and Video Processing
Seamless Whole Slide Label-Free Virtual Staining
Label-free virtual staining offers a compelling, non-destructive alternative to standard histopathology; however, its clinical adoption is hindered by the computational bottlenecks inherent to processing gigapixel Whole Slide Images (WSIs). Current deep learning approaches require patch-based inference to avoid memory constraints, which disrupts global tissue continuity and introduces tiling artifacts–displaying visible seams and color shifts. To address this, we introduce the Consistency Memory Bank (COMB), a novel label-free virtual staining framework that enforces spatial and channel consistency across tiles without memory bottlenecks. COMB decouples context storage from computation, utilizing a dynamic retrieval mechanism to fetch feature representations from adjacent tiles. This enables a retrieval-based context integration strategy that adopts local padding to resolve spatial discontinuities and neighbor-aware channel attention to stabilize statistical drift. Further optimized with a sliding window schedule to ensure minimal memory overhead, our method demonstrates superior performance over state-of-the-art baselines, achieving significant improvements in both perceptual fidelity and tiling consistency, while suggesting its downstream utility in tumor segmentation. Code is available at https://github.com/dou0000/COMB.
Read the full abstract
Sound
Learned Continuous Synthesis of Quadratic Difference Tone Spectra
Quadratic difference tones (QDTs) are a species of auditory distortion product in which a "phantom" pure tone, absent from the acoustic signal, is clearly audible to listeners. Exploiting this phenomenon, one can synthesize harmonically rich tones for musical purposes, a technique called Quadratic Difference Tone Spectrum (QDTS) synthesis. Previous works have introduced numerical methods to synthesize QDTS based on the distortion function, which links a target QDTS and an overtone-structured carrier signal. While accurate, these methods were stochastic and discontinuous, making them difficult to control for musical purposes and effectively limiting them to stationary signals. This paper proposes a neural network-based approach that learns an approximate inverse of the distortion mapping in an autoencoder-like configuration, producing a continuous approximation that addresses prior limitations. Experimental results show that, although slightly less numerically precise, the method is sufficient for perceptual and musical applications. We also implement a real-time version in Max and evaluate its performance. Various sound examples demonstrate its expressive and musical potential. The source code, audio examples, tutorials, and software accompanying this work are available at https://cordutie.github.io/projects/qdts.html
Read the full abstract
Category Theory
Joinings in Markov categories
Dynamical systems theory primarily concerns the study of different forms of invariance, such as invariant sets, densities, measures, and observables. Ergodic systems are a special class of dynamical systems which are measure theoretically irreducible. In spite of this specialized property they dominate most discussions on ergodic theory because of the ergodic decomposition theorem. The viewpoint that any dynamical system is a composite of multiple ergodic components enables us to partition the face space into the basins of the different measures. The coexistence and mutual connections between these various coexisting subsystems are illuminated very effectively using the language of Category theory (CT). Some recent advancements have shown how the essence of measure theoretic dynamical systems can be captured through the formalism of Markov categories. This formalism captures the essential features of invariance and ergodicity through the language of limits and colimits. This article continues that formalism by studying the concept of joins using the language of spans and push-outs. A classical result is re-proven which establishes the connection between joins, ergodicity and mixing. In the process, the categorical language is refined to capture the notion of sub sigma-algebras and their invariance.
Read the full abstract
Representation Theory
Weak Bruhat interval modules of the 0-Hecke algebras for stable Grothendieck polynomials
For a partition $\lambda$, let $G_\lambda^{(\beta)}$ be the stable $\beta$-Grothendieck polynomial attached to $\lambda$. Each homogeneous component of the $\beta = 1$ specialization $G_\lambda^{(1)}$ is Schur-positive and hence positive in the fundamental basis of quasisymmetric functions. For $m\ge|\lambda|$, let $G_{\lambda,m}^{(1)}$ be the homogeneous degree $m$ component of $G_\lambda^{(1)}$. In this paper, we first give a direct proof of an expansion of $G_{\lambda,m}^{(1)}$ in the fundamental basis in terms of standard set-valued tableaux. We then use these tableaux as a basis to define a module of the $0$-Hecke algebra and show that the quasisymmetric characteristic of the resulting module is $G_{\lambda,m}^{(1)}$. We further show that this module decomposes as a direct sum of weak Bruhat interval modules.
Read the full abstract
Biological Physics
Double-well potentials and crucial estimations in nonlinear dynamics of microtubules
In the present work, we study the two-component model of microtubules, the basic components of the eukaryotic cytoskeleton. We introduce a couple of estimations, which tremendously simplified the model. The paper is devoted to tangential oscillations of dimers, but we explain that the model can explain the radial oscillations as well. Finally, we study the stability of all solutions of differential equations, describing the dynamics of the microtubules.
Read the full abstract
Symplectic Geometry
The First Correction Term in the Asymptotic Expansion of Bohr–Sommerfeld Lagrangian States
Let $\Lambda$ be a compact Bohr–Sommerfeld Lagrangian submanifold of a compact Kähler manifold equipped with a holomorphic prequantum line bundle. We study the asymptotic expansion of the Lagrangian states associated with $\Lambda$. In particular, we compute explicitly the first nontrivial correction term and show that it is expressed in terms of geometric invariants of the ambient Kähler manifold and the Lagrangian submanifold, including their scalar curvatures, the second fundamental form, and the mean curvature. As a consequence, we obtain the corresponding second-order asymptotic formula for the $L^2$-norm of the Lagrangian states.
Read the full abstract
Numerical Analysis
A virtual element method for Kelvin–Voigt viscoelasticity
Considering the computational advantages of virtual element methods (VEM), this work employs a conforming VEM for the numerical approximation of the Kelvin–Voigt model of viscoelasticity. For clarity and simplicity, we focus on the primal formulation. The spatial discretization is carried out using the virtual element method, while the temporal discretization is handled via the {second-order Crank–Nicolson} scheme. We establish the well-posedness of both the semi-discrete and fully discrete problems and derive a priori error estimates. Several representative numerical examples are presented to validate the theoretical results and to demonstrate the effectiveness of the proposed formulation.
Read the full abstract
Optics
Quantum eraser enables single-shot quantum holography with undetected photons
Quantum holography with undetected photons (QHUP) enables the complex amplitude of infrared to be acquired beyond the sensitivity range of silicon based sensors, through induced coherence withoud induced emission. QHUP generally requires multiple phase-shifted holograms to retrieve the complex-amplitude distribution of an object, which limits measurement stability and temporal resolution. Although classical parallel phase-shifting holography provides a favorable balance between temporal and spatial resolution, it has not previously been implemented in QHUP because of the constraints imposed by photon distinguishability. In this study, we propose a quantum eraser-based geometric phase-shifting QHUP. By accurately erasing not only polarization distinguishability but also temporal distinguishability arising from differences in the optical paths, the complex-amplitude distribution of an object can be retrieved in a single shot using a silicon-based image sensor equipped with a polarization-filter array. This single-shot acquisition, combined with real-time processing, enables the observation of dynamic objects in the near-infrared spectral region. To the best of our knowledge, these experimental results constitute the first real-time acquisition of the complex-amplitude distribution of a near-infrared object using QHUP with a silicon-based image sensor equipped with a polarization-filter array. Furthermore, to enhance the reproducibility and applicability of this study, the experimental optical setup, bill of materials, and source code for real-time imaging have been made openly available. The ability to retrieve the complex-amplitude information carried by undetected photons in real time is expected to extend the applicability of QHUP to a wide range of fields, including spectroscopic imaging and semiconductor inspection.
Read the full abstract
Numerical Analysis
Preserving Structure in Variational Data Assimilation of Hyperbolic Conservation Laws via Regularization
Hyperbolic conservation laws pose a challenging setting for variational data assimilation, since the Gaussian assumption imposes a smoothness that smears jump discontinuities. A sparsity promoting regularization can help to mitigate this problem by incorporating a structural prior into the variational objective. Care must be taken when choosing this prior because it serves to counterbalance both a structurally misspecified background-error covariance, which introduces spurious oscillations over smooth regions, as well as spatially sparse observations, which leave too little data to constrain the state. Moreover, state variables of hyperbolic conservation laws typically do not have piecewise constant structure, which is an assumption made when using standard sparsity-promoting operators, such as total variation. Indeed the underlying variability of hyperbolic conservation law solutions are neither known in advance nor fixed. Hence using higher order total variation is also not suitable. Here we introduce a new regularization term for data assimilation, built on the sparsity promoting residual transform that neither commits to a fixed smoothness order nor requires the underlying variability to be known a priori. We solve the resulting nonconvex objective within a three-dimensional variational framework using generalized sparse Bayesian learning. This approach replaces a global \(\ell _{1}\) penalty with a hierarchical conditional Gaussian prior on the residual transform, where a learned hyper-prior yields location-specific weights attached to each spatial point. Numerical experiments across scalar, shallow-water, and Euler test problems show that this regularization term resolves discontinuities more accurately than total variation, and that its advantage grows as the background-error covariance becomes misspecified and the observations become sparser.
Read the full abstract
Robotics
Planning along Differentiable Charts of Constraint Manifolds with General-Purpose IK Solvers
Planning trajectories for robot manipulators under kinematic equality constraints restricts feasible motions to a measure-zero submanifold of the configuration space, requiring special algorithmic treatment. A promising strategy is parametrizing the set of feasible configurations using analytic inverse kinematics (IK). Bespoke analytic IK functions can be written to be differentiable, a necessary property for gradient-based trajectory optimization. But the vast majority of IK functions are computed by automated meta-solvers like IKFast, and are difficult to modify for differentiability. We present a new approach for computing gradients of analytic IK parameterizations: we leverage the inverse function theorem to recover the desired gradients from the ordinary forward kinematic Jacobian. Furthermore, we present a least-squares domain extension and an optimization-amenable description of the reachability constraint, which preserves gradient signal outside the reachable workspace. We demonstrate the efficacy of our approach through numerical experiments and downstream tasks, including a hardware demonstration of an RB-Y1 picking up a box and placing it on a table. Project website: https://cohnt.github.io/inverse-function-theorem-parameterization/
Read the full abstract
Statistical Methodology
Agnostic Model-Assisted Estimation with Machine Learning for Survey Data
Model-assisted estimation uses prediction rules to improve the efficiency of estimators of finite population parameters while retaining design-based inference. Although flexible prediction methods have been considered, existing theoretical results are largely method-specific. We develop a learner-agnostic framework that replaces separate analyses for individual learners with general conditions on the sampling design and prediction error. We connect design-aware and design-agnostic cross-fitting and characterize the sampling designs under which they yield conditional independence across folds. Under suitable conditions, conditional weighting gives exact design-unbiasedness. We establish first-order equivalence to oracle estimators, leading to design consistency and asymptotic normality, and clarify when conditional and original inclusion probabilities yield the same first-order behavior. We propose consistent variance estimators based on cross-fitted residuals and construct asymptotically valid confidence intervals. Under additional model and regularity conditions, we establish asymptotic optimality through attainment of the Godambe–Joshi lower bound. Simulations show that cross-fitting substantially reduces finite-sample bias and improves variance estimation and coverage with adaptive learners.
Read the full abstract
High Energy Physics (Phenomenology)
Unitarity dressing of the dynamical gluon mass scale
We examine how $s$-channel unitarization changes the dynamical gluon mass scale $m_g$ inferred from high-energy elastic $pp$ scattering. The Born input is the Reggeized Landshoff–Nachtmann exchange of two nonperturbative gluons in a color-singlet state. We fit the ATLAS and TOTEM forward data separately, using eikonal and $U$-matrix unitarizations with logarithmic and power-law running masses derived from Schwinger–Dyson analyses. At the common reference cut $|t|_{\rm max}=0.12~\GeV^2$, the Born fits give $m_g=297$–$427~\MeV$; the eikonal and $U$-matrix fits give $265$–$360~\MeV$ and $243$–$328~\MeV$, respectively. Unitarization changes the fitted values of the intercept parameter $\epsilon$, $m_g$, and the exponential slope $a_1$ of the proton form factor together. Over $0.10\leq |t|_{\rm max}\leq0.14~\GeV^2$, the $U$-matrix parameters vary less with the cut, while the eikonal fits to TOTEM show a pronounced drift. Replacing the infrared continuation of the logarithmic effective charge by a Curci–Ferrari prescription changes $m_g$ by a mean absolute relative shift of $1.77\%$ over twenty comparisons, with a maximum of $2.17\%$. The inferred scale remains in the few-hundred-MeV region, but its fitted value depends on the nonperturbative input and on the unitarization prescription.
Read the full abstract
Number Theory
Sums of distinct divisors of factorials
For practical $N$ let $h(N)$ be the least $k$ such that every integer $1\le m\le N$ is a sum of at most $k$ distinct divisors of $N$. We prove $h(n!)\le(2\log2+o(1))\,n/\log n$. This improves the bounds of order $n/(\log n)^{1/2-\varepsilon}$ established in Tenenbaum-Yokota's Lemma 4 and Yokota's 1995 knapsack note. We combine their decreasing greedy construction with the sharper factorial divisor-gap estimate of Berend-Harmse. Counting the steps separately below and above $\sqrt{n!}$, with the upper range handled through reciprocal divisors, retains the leading coefficient in the gap exponent and yields the explicit constant $2\log2$.
Read the full abstract
Computation and Language
SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs
LLM search agents are often evaluated on final-answer accuracy, overlooking the process. Analyzing a search strategy requires understanding how credible evidence is retrieved to address question constraints. This valuable information is buried in raw search trajectories that are long and difficult to parse. We introduce SearchAtlas, a framework that converts search trajectories into structured graphs whose edges represent how evidence is propagated across the reasoning trace, from the query that retrieves it to the final answer. Our automated parsing pipeline achieves a mean edge F1 of 86.0% against human-annotated graphs and remains consistent across repeated runs. We analyze five search agents on three benchmarks, revealing systematic differences in search scale and evidence aggregation. SearchAtlas exposes fragmented answer support, question constraints that do not reach the answer, and unverified parametric knowledge entering the response. These process failures are strongly associated with incorrect answers, even more so than an LLM judge given either the raw trajectory or the ordered query list, suggesting that the constructed graphs provide useful interpretability. Moreover, an audit of cases in which process-diagnostic scores disagree with final-answer correctness shows that they capture information not reducible to answer accuracy.
Read the full abstract
Instrumentation and Methods for Astrophysics
Towards High-Throughput Visible Photonic Lanterns for the EMARCOT Project
Photonic EMARCOT is an innovative project involving Spanish, German and Australian research institutes that aims to integrate multiple Optical Tube Assemblies (OTAs) using photonic lanterns. The "Pathfinder" prototype, featuring seven OTAs with a 1.1-meter effective aperture, will feed a spectrograph at the Calar Alto Observatory, with first light expected in 2026. We report the fabrication and experimental evaluation of a custom 7x1 multi-mode photonic lantern (MMPL) developed for this framework, featuring seven 25 um core multi-mode inputs merging into a single 50 um core multi-mode output optimized for the visible wavelength range (400-700 nm). Optical characterization centered at 600 nm reveals exceptional channel-to-channel uniformity, with statistical variations close to zero across both bare-fiber and connectorized MMPL configurations. However, the total baseline throughput of this initial device was limited to below 4%. From the refractive index studies, this low throughput is attributed to severe refractive index mismatch between the internal fiber cladding geometry and the structural capillary, which suppresses total internal reflection during the tapering transition. This work establishes an important diagnostic baseline that highlights the necessary fabrication tolerances needed to improve future high-throughput manufacturing processes for precision radial-velocity astronomy.
Read the full abstract
Probability
Quantitative universality for products of i.i.d. random matrices
Using estimates established in a previous paper, we prove quantitative universality results for cokernels of products of i.i.d. random matrices and for flags associated to k-tuples of random i.i.d. matrices, over finite local rings. In the case when the ring is a quotient of $\mathbb{Z}_p$, this gives a quantitative analogue of some previous results of Huang, Nguyen and Van Peski.
Read the full abstract
Computer Vision
Symmetry-aware super-resolution of crystal orientation maps via invariant latent-space learning
Crystal-orientation maps are physical fields defined only up to crystal symmetry; electron backscatter diffraction (EBSD) resolves them experimentally, but acquisition-time constraints limit spatial resolution. Unlike conventional images, EBSD data lie on the quotient space $\mathrm{SO}(3)/G$, where $G$ is the crystal-symmetry group. Standard Euclidean interpolation can therefore mix symmetry-equivalent representations and blur grain boundaries. We introduce the Symmetry-Group-Aware Super-Resolution Attention Network (SG-SRAN), which incorporates crystal symmetry and boundary preservation by design. A frozen, locally isometric encoder maps equivalent orientations to a common latent representation in which Euclidean distance approximates misorientation. Super-resolution is performed in this space, with each high-resolution token restricted to a feature-consistent local support to prevent cross-boundary mixing. A dictionary-based decoder then recovers valid orientations. Across FCC and HCP benchmarks, SG-SRAN matches 15-16 million parameter backbones using only 27-49k trainable parameters, while achieving the lowest p68 errors, highest inverse-pole-figure fidelity, and zero-shot transfer to unseen alloys.
Read the full abstract
Astrophysics of Galaxies
Impact of LSST systematics on stellar-stream density fluctuations for dark matter
The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) is expected to significantly advance the study of Milky Way stellar streams. In particular, the deep, precise photometry from LSST should greatly increase the statistical sensitivity to density fluctuations in stellar streams, which can be used to probe the small-scale distribution of dark matter. However, current forecasts generally neglect the impact of observational systematics that will be imprinted on stream density measurements. In this study, we develop a realistic forward-modeling framework to inject stellar streams into LSST-like observations including photometric uncertainties, survey depth variations, background contamination, and imperfect star-galaxy classification. We develop a likelihood-ratio analysis to assess the detectability of gaps in stellar streams in the presence of these observational systematics. In the presence of realistic survey systematics, we find that after four years of operations, LSST will be sensitive to density reductions of $\sim50\%$ for gaps with widths of $5$ deg in streams with surface brightness of $\sim33$ mag arcsec$^{-2}$. Relative to the ideal case, this corresponds to a degradation in gap depth sensitivity by a factor of $\sim5$ due to the combined impact of background contamination and observational systematics. Assuming a simplified analytical mapping between gap depth and dark matter subhalo properties, these estimates correspond to a minimum detectable subhalo mass of $\sim1\times10^7$ M$_\odot$. Observational effects shift this accessible mass scale upward by a factor of $\sim16$, with background contamination contributing a factor of $\sim5$ and survey systematics a further factor of $\sim3$, dominated by star-galaxy classification.