Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Monday 14 September
Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrades pseudo-label quality and leads to suboptimal convergence, particularly for sparse, low-resolution scans such as those from nuScenes. We reveal that registration models intrinsically encode semantic awareness that strongly correlates with registration accuracy, albeit without explicit semantic supervision. However, this native awareness is fragile: noisy supervision arising from geometric ambiguity in unsupervised settings rapidly erodes the learned semantic structure, causing performance collapse. To this end, we propose CAESAR, a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training. We observe that potential inlier matches are often buried just beneath a few spurious neighbors in the noisy feature space, motivating Dual-Cue Guided Re-Matching to recover them through reselection rather than simply rejecting. Building on this, a train-only Semantic-Geometric Label Mining performs lightweight, batch-specific teacher refinement and mines reliable pseudo-labels under semantic guidance. We further introduce Semantic Predictive Distillation to consolidate the student's semantic awareness in the feature space. Extensive experiments on KITTI and nuScenes demonstrate state-of-the-art performance, with pronounced gains on the challenging nuScenes benchmark. Crucially, CAESAR incurs zero inference overhead and requires no semantic annotations on the registration data. Code will be released.
Computer Vision
Closed-form Bayesian homography estimation from noisy point correspondences
While homographies are fundamental to many computer vision tasks, the majority of conventional estimation techniques provide only point estimates without directly quantifying uncertainty introduced by noisy observations. Uncertainty, though, propagates to subsequent processing steps such as camera calibration and 3D reconstruction and is particularly relevant in safety-critical and socially relevant fields including medical imaging, autonomous driving, and defense. We present a fast Bayesian formulation for homography estimation from point correspondences that explicitly incorporates measurement uncertainty and prior knowledge while providing a posterior distribution over the homography parameters. A closed-form solution of the posterior mean of the homography is derived in homogeneous coordinates and supplemented by an iterative Bayesian approach to handle non-linearities. Synthetic experiments demonstrate the applicability to projective transformations and show improved estimation accuracy over DLT under varying noise conditions. Image stitching experiments further demonstrate applicability to real image correspondences while additionally providing uncertainty information.
Read the full abstract
Functional Analysis
Universal $\delta$-functors and relative injective objects in the category of $p$-Banach spaces
Inspired by Grothendieck's foundational work, we establish that the sequence of functors $(Ext^n_{pBan}(E,-))_{n \ge 0}$ on the category of $p$-Banach spaces ($0 < p < 1$) forms a universal $\delta$-functor. To this end, for any pair of $p$-Banach spaces $E$ and $X$, we construct a $p$-Banach space $\mathcal N_E^X$ that renders each functor $Ext^n_{pBan}(E,-)$ effaceable. Furthermore, we show that this space serves as a relative injective object for $E$ and $X$, enabling the construction of relative injective presentations and proving that the functors $Ext^n_{pBan}(E,-)$ are the right derived functors of $\mathcal{L}(E,-)$. We will also examine the situation in the category of quasi-Banach spaces.
Read the full abstract
Computer Vision
Deep Learning-based Intelligent Diagnosis of Congenital Uterine Anomalies in 3D Ultrasound
Objective: To develop an intelligent framework, termed CUA-Net, for the automated classification of congenital uterine anomalies (CUA) without requiring coronal plane reconstruction, and to evaluate its clinical applicability. Methods: CUA-Net was built on 3D ResNet-18, equipped with a dynamic data resampling strategy to mitigate the data imbalance issue and a hard sample mining technique to fully learn from the difficult cases by loss adjustment. We further proposed the self-supervised reconstruction to comprehensively explore the volumes and the online data augmentation to refine the wrong predictions and enhance the model's generalization. We compared the CUA-Net with different deep-learning methods and junior/senior sonographers in the testing set. The evaluation metrics included accuracy, precision, recall, F1-score, micro-AUC, and macro-AUC. Results: The proposed CUA-Net exhibited satisfactory performance in both internal and external test sets. In the internal cohort, the model achieved accuracy of 93.88%, precision of 87.01%, recall of 95.92%, F1-score of 88.09%, and micro-AUC of 0.9982 and macro-AUC of 0.9997. In the external set, it maintained good performance with accuracy of 91.52%, precision of 83.27%, recall of 88.63%, F1-score of 81.49%, micro-AUC of 0.9945 and macro-AUC of 0.9990. Our CUA-Net outperformed the junior sonographers across all performance indicators and achieved performance comparable to that of the senior sonographers across most metrics. Conclusion: The CUA-Net demonstrates favorable accuracy and generalizability in classifying common CUA categories, while showing preliminary potential for recognizing less prevalent anomalies. These capabilities may help optimize clinical workflows and support more standardized diagnosis.
Read the full abstract
Computer Vision
Long-to-Short Video Evidence Reasoning for Grounded Question Answering
We present LOVER, a \underline{L}ong to sh\underline{O}rt \underline{V}ideo \underline{E}vidence \underline{R}einforced model for grounded question answering (GQA). LOVER highlights three innovations over existing reinforcement-learning (RL) based video reasoning models: (1) Long-to-short Video Evidence Curriculum Learning, which organizes RL training according to evidence duration and progressively adapts the model from long-range grounding to short-term reasoning; (2) GQA Rewards, which underscore the benefit of IoP reward over IoU for evidence spotting rather than strict temporal span overlap; (3) Adaptive Timestamp Rendering, which adaptively renders timestamps onto video frames using background-aware position and color selection to enhance temporal observability. The three designs are model-agnostic and reciprocal. They effectively improve QA, grounding, and grounded QA performance over different backbones. Notably, LOVER built on Time-R1 achieves new state-of-the-art (SOTA) results among open-source models on popular GQA benchmarks: NExT-GQA and ReXTime. Comprehensive ablation studies further validate the effectiveness of our three innovative components.
Read the full abstract
Numerical Analysis
Structure-Preserving Augmented Lagrangian Finite Element Methods for Cavitation in Reynolds and Stokes Flows
In this paper we propose augmented Lagrangian finite element methods for cavitation in the Reynolds and Stokes models of lubrication, for which the discrete complementarity conditions hold exactly and the augmentation parameter drops out of the method. For the Reynolds equation this follows from nodal quadrature in a mixed piecewise linear method, for which we prove the classical first-order error estimate. We also determine the computable stability threshold of a multiplier-free stabilised alternative. For Stokes flow we show that the constrained scalar is the mechanical pressure when the deviatoric stress, with zero bulk viscosity, is used, but not with the customary incompressible stress. We discretise with a jump-stabilised Crouzeix-Raviart element and piecewise constant pressure, and prove well-posedness, stability in two and three dimensions, and a first-order error estimate. We present numerical examples which verify these properties and show that close pressure profiles in the two models do not imply close cavity predictions, the latter also being sensitive to the end conditions of the computational domain.
Read the full abstract
Probability
Bipodal optimizers in the upper-tail variational problem for regular subgraph densities
Let $H$ be a fixed $d$-regular graph with $d\ge2$, and let $t(H,\cdot)$ denote its homomorphism density. We study the upper-tail event $t(H,G(n,p))\ge r^{|E(H)|}$ for fixed $0<p<r<1$ in a dense Erdős–Rényi random graph $G(n,p)$. Near the Lubetzky–Zhao replica-symmetric phase boundary and away from the exceptional target density $(d-1)/d$, we prove that the optimizer of the Chatterjee–Varadhan variational problem on the symmetry-breaking side is bipodal (two-block) and unique up to relabeling. Its block parameters depend analytically on $(p,r)$. To treat the exceptional boundary point, where the nonexceptional theory degenerates, we construct an analytic curve approaching that point from the symmetry-breaking side along which the unique optimizers are nonconstant rank-one bipodal graphons. In both settings, we derive asymptotic expansions of the edge-density deficit and the rate function that governs the exponential decay of the upper-tail probability. Moreover, the conditioned random graph converges in cut distance to the corresponding bipodal optimizer as $n\to\infty$. As $(p,r)$ approaches the phase boundary from the symmetry-breaking side, the optimizers converge to their constant limits through two distinct mechanisms. For each fixed nonexceptional target density, one block shrinks to zero measure, giving convergence in $L^1$ but not in $L^\infty$. Along the exceptional curve, both blocks remain macroscopic: their sizes tend to $1/2$ and all three block densities tend to $(d-1)/d$, yielding convergence in $L^\infty$.
Read the full abstract
Sound
MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training
Passive acoustic monitoring can measure biodiversity at larger scales, but time–frequency annotation of animal vocalizations is expensive, site-specific, and difficult to sustain at scale. We present a label-efficient sound detection framework that combines masked audio pretraining with a lightweight detector on mel spectrograms, then further improves robustness through iterative self-training on unlabeled audio. We first pretrain a ViT-based encoder on unlabeled recordings via masked reconstruction and transfer the encoder to a detection backbone. To better separate animal sounds from confounding background, we add a box-level contrastive loss that pulls matched event regions together while pushing noisy negatives apart. We then apply a two-stage pseudo-labeling curriculum to exploit large unlabeled pools without additional annotation. We evaluate the performance on two ecologically distinct domains: tropical rainforest soundscapes (Indonesia) and bird vocalizations in Mediterranean habitats (Spain). On both domains, masked audio pretraining and contrastive learning consistently improve time–frequency detection under temporal and cross-site distribution shift, and self-training yields further gains in out-of-distribution performance. On the rainforest domain, MAST with self-training achieves +0.22 mAP and +0.24 F1 over the strongest baseline under cross-site shift. On the bird domain, self-training achieves +0.12 mAP and +0.10 F1 over the strongest baseline under cross-site shift. Overall, our results show that MAST can effectively extend self-supervised audio representations from clip-level tasks to robust box-level localization across diverse bioacoustic settings, providing a practical path for biodiversity monitoring with limited labels.
Read the full abstract
Data Structures and Algorithms
A Deterministic $(2+\varepsilon)$-Approximation for Weighted Feedback Vertex Set in Tournaments
We study the weighted feedback vertex set problem in tournaments. For every fixed integer $k\geq 2$, we give a deterministic $(2+1/k)$-approximation algorithm with running time $n^{2^{O(k)}}$, apart from polynomial dependence on the encoding length of the weights. Consequently, for every fixed $\varepsilon>0$, weighted feedback vertex set in tournaments has a deterministic $(2+\varepsilon)$-approximation running in time $n^{2^{O(1/\varepsilon)}}$. The algorithm combines two ingredients. When the triangle graph of the tournament has bounded clique number, a chain decomposition of its transitive complement yields an exact dynamic program for a maximum-weight transitive subtournament. When the clique number is large, a structural theorem for triangle graphs supplies a constant-size strongly good cost vector. A local-ratio reduction with this cost vector gives the claimed guarantee. As a by-product, the dynamic program solves weighted feedback vertex set exactly in $\mathcal B_7$-free tournaments in time $O(n^7)$, where $\mathcal B_7$ is the family of seven-vertex tournaments with feedback vertex set number at least three.
Read the full abstract
Artificial Intelligence
From Ideas to Actions: A Public-Data Decision-Support Toolchain Across the Venture Lifecycle
Founders face two linked decisions: whether to pursue an idea before founding, and which operating actions and capital partners fit afterward. We present a public-data decision-support toolchain combining time-bounded proposal profiling, market and moat checks, and deterministic aggregation with auditable investor-company event chains for retrospective analysis. Pre-founding: (a) After threshold selection on 198 development companies, the frozen pipeline achieves F0.5=0.5357 [0.412, 0.655] on an independent, row-disjoint 198-company validation sample. On the combined 396 rows, the Full Pipeline scores 0.6301 versus 0.2734 for a paired Raw LLM baseline. Post-stratification of 1,027 completed cases in a separate scale cohort yields 0.6506 [0.598, 0.707]; the run remains incomplete. A 377-row composition-matched check yields 0.6573. (b) The AI-inference study identifies distribution-layer businesses as a replicable path to independent profitability with a limited revenue ceiling, and frontier-model ownership as a path to capital-market upside at exceptional capital cost. Post-founding: (a) Public sources support auditable event-chain analysis. (b) In the chip-company study, sustained product, customer, and supply-chain progress is associated with better observed outcomes; financing alone does not establish operating progress. (c) Financing comprises 79% of confirmed visible post-investment actions. Evidence tentatively favors acquisition-experienced strategic corporate investors for acquisition-oriented founders and financing-led institutional VCs with fewer observed control events for independence-oriented founders. Findings are developmental and observational, not causal guarantees or investment advice. We release shared ontology, provenance-bearing EventChain data, schemas, benchmarks, and executable skills for audit, reuse, and extension.
Read the full abstract
Audio and Speech Processing
Word Timestamps and Speaker Attribution with a Non-Autoregressive LLM
Timestamps and speaker attribution are useful additions to speech recognition, creating a rich text transcript. This information can either be extracted during transcription or aligned to a given transcript. In this paper we present models that add timestamps and speaker information to a given transcript using a non-autoregressive LLM-based architecture. Compared to an autoregressive model built from similar components, the models are more accurate and annotate a given transcript one to two orders of magnitude faster. Compared to other models, our models achieve state-of-the-art timestamp accuracy and the best cpWER for speaker attribution.
Read the full abstract
Distributed Computing
Accelerating the Solving of Many Tiny General Linear Systems on GPUs: Application to Constitutive Laws
Many applications require solving large numbers of independent linear systems on GPUs. While this need is well addressed for small to large systems, tiny ones, understood here as systems of dimension below 32, remain challenging. This is especially relevant in constitutive law evaluation, where millions of integration points are handled independently, and where each constitutive update generally relies on a Newton iterative method. Each iteration then requires the double-precision solution of a tiny general square linear system using LU factorization with partial pivoting (LUpp). The present study was conducted within a closed-source prototype, which serves as a demonstrator for porting to NVIDIA GPUs constitutive law evaluations currently provided on CPUs by TFEL/MFront, an open-source code generation tool for material knowledge. We compare several double-precision LUpp solvers, including implementations from GPU linear algebra libraries as well as custom-designed CUDA kernels. The comparison is performed first on large batches of standalone linear systems, and then within the full constitutive-law evaluation workflow, where each integration point requires a sequence of distinct linear systems, one per iteration of its own Newton loop. The study shows that the best LUpp solving strategy strongly depends on several factors including system size and application context. We discuss several key aspects, including register pressure, occupancy, the ability to invoke the LUpp solver directly from device code, and whether assigning several threads to each system is the most efficient strategy. Experiments on an NVIDIA H100 GPU show that the specialized LUpp solvers proposed in this work can outperform existing state-of-the-art approaches for this class of workloads, with speedups of up to 6.5x over cuSolverDx, and up to 17.7x over MAGMA.
Read the full abstract
Logic
Intuitionistic Implication in Elementary Team Logics
The logic FOT is a team-based logic whose expressive power coincides with first-order logic at the level of both sentences and open formulas. In contrast to dependence and independence logics, which can define stronger second-order team properties, FOT is designed to capture exactly elementary team properties, modulo the empty team. In this paper we consider two modifications of FOT. First, we investigate essentially the inclusion atom free fragment of FOT. Our main result establishes quantifier elimination for the fragment in the empty signature. Second, we study an extension of FOT by the intuitionistic implication. The main conclusion is that adding this single connective increases the expressive strength so that every second-order sentence can be encoded by an open formula evaluated on the full team. Consequently, validity of formulas is equivalent to validity of full second-order logic.
Read the full abstract
Sound
Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception
Large Audio-Language Models (LALMs) have substantially advanced general audio understanding, yet they remain limited in fine-grained temporal perception, particularly in precise event localization. Existing approaches primarily post-train LALMs to predict event boundaries as timestamp tokens. However, this generative formulation lacks explicit correspondence between the timestamp predictions and fine-grained acoustic evidence, limiting the precision and reliability of temporal localization. To address this issue, we augment the LALM with a dedicated frame-level grounding model while leveraging its semantic modeling capability to represent the event query. Specifically, the frozen LALM encodes the event query with audio as context, and the grounding model combines these query representations with fine-grained audio features to localize the target event at the frame level. Extensive experiments across diverse temporal grounding benchmarks demonstrate strong and consistent improvements over existing methods. Further evaluation shows that the grounding model can provide temporal evidence to support downstream reasoning.
Read the full abstract
Digital Libraries
Toward non-textual representation of social anthropology: Modeling cultures as knowledge graphs
The study examines the emerging field of knowledge representation in the context of the semantic web and linked data, with a focus on knowledge produced within the social sciences - particularly in sociocultural anthropology. It starts from the premise that natural language, especially its textualized form, has long been the primary vehicle for producing and communicating anthropological research. Informed by theoretical approaches from information science, the study explores how computational methods may offer alternative modes of structuring and representing anthropological knowledge. It challenges the dominance of text as the sole representational medium and highlights the potential of semantic modeling to open new epistemological pathways. At the same time, it acknowledges the conceptual and methodological challenges involved in such a transition. This approach shifts emphasis away from metrics and programming, foregrounding processes of conceptualization, semantics, meaning, and reasoning as key to engaging with anthropological knowledge in digital environments.
Read the full abstract
Robotics
X-WBC: A Cross-Embodiment Foundation Model for Humanoid Whole-Body Control
Scaling humanoid whole-body control toward general-purpose deployment requires large human motion corpora and training experience shared across robot bodies. Existing methods usually train one policy per robot, leaving motion experience isolated across embodiments. We introduce X-WBC, a cross-embodiment foundation framework that separates relatively shared human motion semantics from embodiment-specific physical execution. Human-centered command tokens align full human motion, robot reference motion, and sparse VR observations. A causal Transformer learns reusable temporal structure from mixed multi-robot rollouts, while lightweight robot-specific modules map the shared representation to each robot's proprioception and action space. Across nine simulated embodiments, external motions, and four real robots, experiments show that joint training improves tracking, the aligned representation supports consistent control across command sources, and the learned policy remains competitive beyond the training corpus. These results support heterogeneous humanoids as joint data sources and establish cross-embodiment joint training as a practical route toward whole-body control foundation models.
Read the full abstract
Quantum Physics
Comment on J.Qin et al., Unconditional and Robust Quantum Metrological Advantage beyond N00N States, PRL 130, 070801 (2023) and J.A. H. Nielsen et.al., Deterministic Quantum Phase Estimation beyond N00N States. PRL 130, 123603 (2023)
The papers by Qin et al. [1] and Nielsen et al. [2] report an unconditional quantum metrological advantage based on squeezed-vacuum phase sensing. The principal evidence for this claim is the Quantum Fisher Information (QFI) evaluated per trial or per detected photon, which is subsequently interpreted as a measure of metrological performance. This interpretation is statistically unjustified because it does not account for the total experimental resources required to construct an estimator. Consequently, the reported protocols do not provide an unconditional metrological advantage over classical phase-sensing strategies when resource accounting is performed consistently.
Read the full abstract
Solar and Stellar Astrophysics
Results on young stellar clusters with the WEAVE LIFU
We present the first results of two Spanish TAC programs using the WEAVE LIFU that have been obtaining data since October 2023. The first one is obtaining high-resolution multi-epoch spectroscopy of the nine stellar clusters that contain a minimum number of 3 O-type stars (and many more B stars) within the field of view of the WEAVE LIFU and that are accessible from La Palma with the purpose of studying the spectroscopic multiplicity of the OB stars. The second program is obtaining single-shot low-resolution spectroscopy of as many stellar clusters with OB stars as possible with the purpose of characterizing the OB-star population in those regions that are too crowded to be properly studied with the guaranteed time SCIP program. That program has already observed 54 clusters in a wide range of environments, from H II regions to gas-free clusters, and distances, from clusters in the solar neighbourhood to (nearby) extragalactic systems. We also present the tools developed for this program, which include a data cube processing and visualisation utility and UNWIND, a code that fits and subtracts the ISM signature in the observed spectra.
Read the full abstract
Solar and Stellar Astrophysics
Riemann Map Operator for Solar Front Diagnostics
Identifying a shock from a moving solar brightness front requires relating the observed emission to changes in the plasma state. The Riemann framework describes shocks, rarefactions and other waves as parts of a pattern connecting different states. We present the Riemann Map Operator (RMO), an inverse diagnostic framework implemented as a web application to help observers identify magnetohydrodynamic (MHD) shock families from incomplete measurements. RMO tests candidate local connections against conservation laws, entropy requirements and characteristic conditions, while retaining observational uncertainties and model assumptions. We demonstrate the approach with five solar examples and a complementary in-situ comparison. An event combining extreme-ultraviolet (EUV) imaging and spectroscopy admits both fast and slow shock connections within the tested conditions. For an EUV-radio event, we derive an upstream-flow constraint that would exclude ordinary slow shocks within the adopted model, provided both diagnostics sample the same front. A flare-loop benchmark reproduces the published spectral profiles and recovers slow-shock ordering in the isothermal limit. The Solar Orbiter comparison recovers an Alfvenic relation between measured velocity and magnetic-field changes. Together, the examples show how RMO connects observations to admissible MHD interpretations and identifies the additional measurements needed to distinguish them.
Read the full abstract
Software Engineering
Failure-Guided Co-Evolution of Prompts and Training Data
Automatic prompt optimization (APO) improves language-model programs by revising prompts from task feedback, yet it typically holds its training data fixed. Repeatedly optimizing against the same instances confines feedback to weaknesses already represented in those data, leaving related failure conditions unexplored. We therefore view each failure as a dual signal: it indicates both how the prompt should be revised and what new training evidence should be synthesized. We introduce FORGE, a failure-guided framework that co-evolves prompts and training data. FORGE abstracts imperfect executions into reusable failure modes and synthesizes new training data through four complementary mutation strategies. Verified instances are fed back into prompt search, allowing updated prompts to expose the next data needs. Across eight heterogeneous benchmarks, FORGE improves the aggregate score over the unoptimized baseline by 16.52 percentage points and outperforms all evaluated APO baselines. The synthesized data also transfer beyond FORGE: in a transfer study, they improve all nine APO comparisons by 2–9 points and all three GRPO comparisons by 4–8 points under matched optimization budgets. These results establish failures as a shared interface between prompt optimization and data synthesis, and show the benefit of jointly adapting what a model is instructed to do and what it learns from.
Read the full abstract
Game Theory
Tight Subsidy Bounds for Weighted Proportional Allocation of Mixed Manna
We study the problem of fairly allocating m indivisible items among n agents with possibly unequal entitlements in the mixed manna setting, where each item may be perceived as a good or a chore by different agents. We focus on the fundamental fairness notion of proportionality. Since proportional allocations need not exist in this setting, we allow monetary subsidies to restore proportionality while minimizing the total subsidy. When each item's (dis)utility is bounded by 1, a total subsidy of at least \tau(n) \approx n/4 may be necessary. For goods-only or chores-only instances, the best previously known upper bound was n/3-1/6 due to Wu and Zhou~(2024). We close this gap by proving that a total subsidy of at most \tau(n) always suffices, thereby establishing the tight subsidy bound. Our results hold even in the more general setting of weighted mixed manna, resolving an open question posed by~Wu et al. (2023) and Garg et al. (2026). The allocation also satisfies weighted proportionality up to one item (WPROP1). Our proof develops a novel application of the Knaster-Kuratowski-Mazurkiewicz (KKM) fixed-point theorem, extending the KKM framework to share-based fairness notions. Finally, we design a polynomial-time algorithm to compute such allocations for any fixed number of agents.
Read the full abstract
Artificial Intelligence
Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before elections. With growing evidence that they influence users' opinions, it is increasingly important to understand the views and positions of these tools. To better understand these views, we examine the stances supplied by six LLMs on a variety of Swedish-language writing tasks ahead of the 2026 Swedish parliamentary election. We cross 107 policy propositions with 77 writing templates and neutral, positive, and negative prompt framings, producing 24,717 prompts per model and 148,302 responses. To study these, we look at the models' default stance tendencies, compare how they respond to similar issues, and compare their responses with those of each of Sweden's eight parliamentary parties on the same issue. We find that Claude, DeepSeek, Gemini, and Mistral have similar profiles; ChatGPT more often supplies neutral or ambivalent text; and Grok differs most on topics such as migration, crime, and gender. When comparing the political parties, we find that the Social Democrats are closest to all six models. Still, after correcting for multiple comparisons, none of the within-model differences in party distances remains significant. Overall, we find that no model has a clear preference, nor a clear preference for a party, but that this depends on the specific issue or task the user asks about.
Read the full abstract
Representation Theory
Quantization of Preprojective Algebras and the Type A Rational Cherednik Algebra
For the Jordan quiver, we construct a radial quantum trace morphism from the quantum preprojective algebra to the algebra of invariant differential operators on the Cartan subalgebra. Its classical limit recovers the classical trace morphism associated with the commuting quotient, and we prove that both the quantum and classical trace morphisms are surjective. We further relate noncommutative quantizations of the Jordan preprojective algebra to the spherical rational Cherednik algebra of type A. Finally, we derive explicit formulas for the Harish–Chandra homomorphism and its radial part in power-sum coordinates.
Read the full abstract
Databases
TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models
Table extraction from texts is an important task for information systems, and recent approaches that prompt large language models (LLMs) with instructions have drawn great attention for their strong performance. Existing works have assumed the input texts to be table descriptions or specialized documents. However, these efforts have largely overlooked another prevalent category of texts, commonly found in news reports and social media: naturally occurring texts. Extracting tabular information from such texts poses two distinct challenges. First, high variability and the absence of explicit structural cues make fixed heuristic LLM prompts limited in precisely delineating extraction boundaries. Second, manually predefined schemas cannot capture open-ended, unseen attributes in naturally occurring text. In this paper, we propose a framework, TEAR, to address these challenges. It comprises two synergistic workflows: a Table Extraction Workflow that dynamically adapts instructions to overcome the limitation of heuristic instructions, and an Attribute Recommendation Workflow that discovers new attributes from texts to complement the heuristic schema. To our knowledge, TEAR is the first framework that supports automated text-driven attribute recommendation, enabling exploratory schema design for table extraction. To evaluate TEAR, we establish the benchmark for table extraction and attribute recommendation on naturally occurring texts, including two real-world datasets, manual annotations, appropriate metrics, and baseline comparisons. Experiments show that TEAR achieves state-of-the-art performance on both tasks, and the recommended attributes effectively enhance extraction performance in exploratory scenarios.
Read the full abstract
Statistics Theory
Fractional Cumulative Past Inaccuracy in the Quantile Framework and its Applications
Fraction-based information measures have received considerable attention for describing complex systems, as they enable the investigation of signals with high sensitivity \citep{machado2014fractional}. In this paper, we introduce quantile versions of fractional cumulative past inaccuracy (FCPI) and dynamic fractional cumulative past inaccuracy (DFCPI) measures based on the inverse Mittag-Leffler function (MLF) or fractional logarithm function, which are the extensions of the fractional cumulative past and dynamic fractional cumulative past entropies, respectively. The various properties of quantile-based FCPI and its dynamic version are provided. We also propose a nonparametric estimator for the proposed measure, and simulation studies are carried out for validation. Finally, we bring out real data application of the newly introduced quantile-based FCPI.
Read the full abstract
Audio and Speech Processing
Interpreting hierarchical organisation of speaker embeddings
Speaker recognition neural networks recognise speaker identities from input utterances by learning latent representations (i.e. speaker embeddings). However, these networks' internal mechanisms remain largely opaque, motivating research in explainable artificial intelligence (XAI) to understand them. Existing studies have analysed how speaker embeddings are organised, but rarely frame these analyses within XAI. This work proposes to explain and interpret the organisation of speaker embeddings from an XAI perspective. To this end, we apply a hierarchical clustering algorithm, Single-Linkage Clustering (SLINK), to analyse whether our prepared speaker embeddings naturally form clusters with hierarchical relationships. The resulting hierarchical organisation (i.e. hierarchical clusters) is evaluated using the Cluster-Class Matching (CCM) method. Moreover, we propose a new method, termed Hierarchical Cluster-Class Matching (HCCM), to identify which hierarchical clusters best match individual semantic classes like male and conjunctive semantic classes like UK & male, thereby interpreting the clusters using their matched classes. We quantify the matching degree with a new metric called the L-score, which makes imperfect matches diagnosable. HCCM's results reveal that the hierarchical clusters analysed by SLINK are well interpreted using classes related to speaker identity, gender, and nationality, showing the semantics inside the hierarchical organisation of the examined speaker embeddings.
Read the full abstract
Functional Analysis
Higher order pointwise estimates for intermediate derivative
The estimates of intermediate derivative play important role in the theory of partial differential equations. The modern approach to this problem is via pointwise estimates, since this allows to obtain results for various function norms. The paper aims to extend the pointwise estimate for intermediate derivative in terms of the averaging operator for higher orders derivatives.
Read the full abstract
Combinatorics
Real-Rootedness and Gamma-Positivity for a Variation of the Morris Constant Term
Beck and Pixton expressed the Ehrhart polynomial of the Birkhoff polytope as a weighted sum of constant terms of several multivariate rational functions. Xin and Zhang studied a class of constant terms $h_n(t)$, which can be regarded as a variation of the Morris constant term. They proved that $h_n(t)$ is a polynomial of degree $(n-1)^2$ and obtained many nice properties involving the Morris constant term identity. Let $h_n^*(y)=(1-y)^{(n-1)^2+1}\sum_{t\geq0}h_n(t)y^t$. For fixed $n\geq 3$, we obtain the following results for $h_n^*(y)$: (i): $h_n^*(y)$ is a polynomial with positive integer coefficients. (ii): $h_n^*(y)$ is real-rooted. In particular, all its roots are non-positive real numbers. (iii): $h_n^*(y)$ is Gamma-positive. Furthermore, $h_n^*(y)$ is palindromic, unimodal, and ultra log-concave. This confirms Xin and Zhang's conjecture regarding $h_n^*(y)$. In order to resolve this conjecture, we also developed an operator on the space of symmetric polynomials that preserves real stability. As a byproduct, we prove that every root of a Gamma polynomial associated with $h_n^*(y)$ is a negative real number.
Read the full abstract
Optics
Subwavelength exceptional points in dispersive resonator arrays
Exceptional points provide a mechanism for producing strong spectral sensitivity in non-Hermitian wave systems. For subwavelength resonators with highly dispersive material parameters, however, the resonance problem is not a linear eigenvalue problem in the frequency. In this paper, we use the Lippmann-Schwinger formulation and the associated volume-potential reduction to study exceptional points in dispersive resonator arrays. The reduction leads to a finite-dimensional nonlinear matrix pencil whose entries encode both the local material response and the volume-mediated interaction between the resonators. We characterize exceptional points as defective characteristic values of this pencil and derive explicit conditions for dimers and higher-order systems. We show that passive damping and detuning can generate exceptional points without imposed gain, and we formulate an inverse-design condition for placing such degeneracies at prescribed frequencies. We also prove the corresponding Puiseux splitting laws and identify how material dispersion enters the leading sensitivity prefactor. Numerical experiments, including halide-perovskite-inspired dimers and trimers, illustrate the theory and show that the exceptional-point mechanism persists for explicit highly dispersive passive material laws.
Read the full abstract
Probability
Independence properties for tree beta models
This paper is devoted to introduce new probabilistic tree-based models complementing already known Matsumoto-Yor and Hamza-Vallois tree models with two tree beta-type models.