arXiv subjects

Search papers

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

At least 1,369 records · Page 76Linked to original sources

arXiv2026

DISC: Domain-Integrated Similarity Cost for Time-Series Dataset

The growth of time-series datasets and foundation models has made dataset comparison a central part of time-series workflows. Assessing source-target transfer before model adaptation requires similarity estimates that can summarize transfer-related dataset relationships without exhaustive source-target evaluation over every candidate pair. Many metrics have been proposed for measuring similarity between time-series datasets, but they capture different dataset relationships and vary in how well they align with downstream utility across tasks. We evaluate this gap by measuring the correlation between source-target similarity scores and downstream forecasting errors in out-of-distribution and transfer-learning settings. We propose Domain-Integrated Similarity Cost (DISC), a learnable aggregation framework that uses calibration transfer observations to select, weight, and combine similarity metrics for different downstream tasks. By integrating complementary metric values, DISC better distinguishes source-target dataset differences that matter for downstream behavior. After calibration, DISC scores source-target pairs using only their similarity-metric values and yields higher alignment than single-metric references on the reported split. These results show that time-series dataset similarity is task-dependent, and that learned metric integration provides a stronger proxy for downstream transfer behavior than manually selecting one similarity metric.

cs.LG↗

arXiv2026

Cohomology of integral structure sheaves for open varieties

We study the cohomology of integral structure sheaves for two types of open rigid analytic varieties: complements of divisors in quasi-compact varieties, and partially proper spaces. As applications, we prove a strengthened form of the Hebbarkeitssatz (Riemann's extension theorem), involving the almost vanishing of $R^1\lim$, and study pro-étale $G$-torsors on open varieties.

math.AG↗

arXiv2026

Extraction of transverse-momentum-dependent helicity distributions of the nucleon

We present an updated global analysis of the transverse-momentum-dependent (TMD) helicity distributions of the nucleon from measurements of the longitudinal double-spin asymmetry $A_{LL}$ in semi-inclusive deep-inelastic scattering (SIDIS). The analysis incorporates target- and detected-hadron-mass corrections, next-to-next-to-leading-order matching in the small-$b_T$ operator product expansion, and an improved treatment of correlated systematic uncertainties. The present data constrain the up- and down-quark helicity TMDs, whereas the sea-quark and gluon distributions remain weakly constrained. After integration over transverse momenta up to the hard scale, the up- and down-quark distributions agree with collinear helicity distributions within uncertainties. Using the extracted TMDs and the Wandzura-Wilczek-type approximation, we predict the $\cosϕ_h$ modulation of $A_{LL}$ and find agreement with the HERMES and CLAS measurements. We also provide predictions for SIDIS $A_{LL}$ at CLAS12 and for longitudinal single-spin asymmetries in $W^\pm$ production with leptonic decays at STAR kinematics. An impact study with pseudodata for the proposed Electron-Ion Collider in China (EicC) indicates substantial potential to improve constraints on helicity TMDs at intermediate $x$, including the presently weakly constrained sea-quark sector.

hep-ph↗

arXiv2026

Precise Measurement of the Inclusive Cross Sections of Open-Charm Mesons at Energies from 3.80 to 4.95 GeV

Using $e^+e^-$ collision data collected by the BESIII detector at center-of-mass energies from $3.80$ to $4.95~\text{GeV}$, the inclusive production cross sections of open-charm mesons, $σ(e^{+}e^{-}\to D^{0}/D^{+}/D_{s}^{+}+X)$, are measured by tagging a $D^0$, $D^+$, or $D_s^+$ meson, where $X$ denotes any accompanying particles. Open-charm production dominates the total hadronic yield above threshold. Therefore these measurements provide a vital reference for understanding hadron production and for validating global $R$ value results. The results offer crucial inputs for investigating heavier charmonia and exotic states coupled to open-charm final states, while serving as a benchmark for comparison with the sum of measured exclusive channels. This comparison directly evaluates the completeness of current exclusive datasets and clarifies the underlying hadronization mechanisms in the open-charm region.

hep-ex↗

arXiv2026

Spark-Audio 1.0 Technical Report

This paper introduces Spark-Audio 1.0, a speech foundation model trained on domestically produced computing infrastructure. The model accepts text and speech inputs and generates text outputs. It supports multilingual (99 languages) and multi-dialect (202 dialects) speech recognition, speech translation, audio perception and understanding, and both text- and speech-based dialogue, marking a shift from merely ``hearing clearly'' to genuinely ``understanding'' speech. Architecturally, Spark-Audio 1.0 couples a 0.65B-parameter dense audio encoder with a 30B-A3B Mixture-of-Experts (MoE) large language model (LLM). The audio encoder is pretrained with representation-enhanced BEST-RQ and then refined through multi-task supervised training. The audio--LLM is trained through staged pretraining, followed by post-training that combines supervised fine-tuning with on-policy distillation. In total, the model is trained on 13 million hours of audio data together with large-scale text data. We evaluate Spark-Audio 1.0 on mainstream audio and text benchmarks, as well as on in-house test sets drawn from real-world application scenarios. Despite using substantially less audio training data than Qwen3.5-Omni-Flash, Spark-Audio 1.0 achieves comparable performance on most audio and text tasks, outperforms it in multilingual speech recognition, spoken dialogue, and real-world application scenarios, and approaches the performance of larger closed-source models. Nevertheless, there remains room for improvement in instruction following and complex audio reasoning. Finally, the successful training of Spark-Audio 1.0 on domestic hardware, including Huawei Ascend 910B and Hygon BW1000 chips, demonstrates the feasibility of a domestic technical pathway for building speech foundation models.

eess.AS↗

arXiv2026

RecallGS: Geometry-Grounded Recall for Online Semantic Gaussian Splatting

Online semantic 3D Gaussian Splatting (3DGS) enables open-vocabulary scene understanding from streaming observations. However, existing methods recover geometric context missing from image-derived semantic features using an additionally learned 3D network, incurring extra training and runtime overhead. We observe that such geometric-semantic evidence may already exist in the agent's observation history and can be retrieved rather than learned. Based on this insight, we introduce RecallGS (Geometry-Grounded Recall for Online Semantic Gaussian Splatting), a lightweight, training-free mechanism that treats past observations as a non-parametric geometric-semantic prior. RecallGS follows a recall-ground-fuse pipeline: CLIP retrieves relevant observations, alpha-compositing weights identify geometrically supported views, and aggregate their semantic features over each Gaussian's rendered footprint. On ScanNet and ScanNet++, RecallGS achieves strong semantic segmentation performance at 2.48 FPS, demonstrating that geometric-semantic context can be effectively recovered from observation history without an additional learned 3D branch.

cs.CV↗

arXiv2026

Practical Auditing of Differentially Private Graph Release Mechanisms: Methodology, Toolkit, and Case Study

Differential Privacy (DP) has become a prominent approach for protecting graph data releases, yet empirical auditing methodologies have largely been developed for tabular datasets and machine learning pipelines rather than graph-structured outputs. We present a methodology for empirically auditing DP graph release mechanisms, identifying two graph-specific audit design problems: canary construction and witness statistic selection. We combine these components with an established statistically certified testing procedure and implement the resulting methodology as an open-source Python toolkit. To demonstrate the approach, we audit a published state-of-the-art Node-DP graph release mechanism. Across a series of synthetic and real-world canary pairs, we obtain certified lower bounds on the privacy parameter {\varepsilon} that exceed the claimed value, yielding counterexamples sufficient to falsify the claimed guarantee for the audited implementation. The violations persist under progressively stronger restrictions on the input domain, including non-empty and connected graphs. We also show that witness selection can materially affect whether a violation is detected, highlighting the importance of evaluating a diverse battery of statistics when auditing DP graph release mechanisms.

cs.CR↗

arXiv2026

Phase-Matched Chirps for Energy-Efficient Excitation of Magneto-Mechanical Resonators

Magneto-mechanical resonators (MMRs) are a recently proposed class of passive, wireless devices used for sensing and tracking. The operating principle of MMRs relies on an excitation of the sensor by oscillating magnetic fields, followed by an inductive readout to measure the sensor's dynamics. One challenge lies in generating efficient excitation signals to ensure maximum energy harvesting by the sensor. In this simulation study, we focus on chirped magnetic-field excitations and compare their performance with conventional constant-frequency excitation for both sinusoidal and rectangular waveforms. The results indicate varying levels of efficiency, with a sinusoidal linear down-chirp excitation signal yielding the largest deflection angle, offering the best potential for reducing the energy consumption and improving the temporal resolution of the measurement.

physics.app-ph↗

arXiv2026

Exact stress-tensor generators distinguish integrable continuations

The same leading $T\bar T$ interaction can coexist with sharply different strong-field responses, even within causal, classically integrable sigma models. We reconstruct exact autonomous stress-tensor generators for prescribed one-scale Courant--Hilbert families in two dimensions. Separating the invariant stress scale from a signed trace ratio reduces reconstruction to one scalar inversion on each invertible physical branch. The resulting profile determines both the deformation law and the relation between local energy density and pressure. For generalized Born--Infeld and logarithmic models, the leading interactions coincide, yet pressure saturates in the former and grows without bound in the latter. Their exact generators are respectively quadratic and nonpolynomial, the latter involving Lambert $W_{-1}$. A regular Legendre transformation gives the same profile in the auxiliary potential formulation. The flows commute locally with root-$T\bar T$ within a common smooth branch and retain a common classical Lax form. Exact reconstruction thus quantifies the nonlinear freedom left by leading-order matching.

hep-th↗

arXiv2026

Strong Duality Thresholds and Minimum Curvature for the Nearest Rectangular Symplectic Matrix Problem

We study the nearest rectangular symplectic matrix problem in the squared Frobenius norm for arbitrary targets $T\in\mathbb R^{2n\times2k}$, with $n\ge k$. We prove that its semidefinite relaxation is exact for every target if and only if $n\ge2k-1$. Under this condition, the primal problem, the relaxation, and both Lagrangian dual problems attain the same optimal value. In this range, we derive the exact minimum Rayleigh quotient of the Riemannian Hessian at every feasible point under the Euclidean induced metric, and prove that all second-order stationary points are global minimizers. We also obtain global objective error bounds. We extend the strong-duality and minimum-curvature results to Hermitian positive definite row weights, proving that strong duality holds for every target if and only if the lowest eigenvalue of the weight has complex multiplicity at least $2k-1$. The dual formulation leads to a method whose main iterations use matrices of order $2k$, with $O(k^2)$ iterative storage apart from the full input and output. Across six tested sizes, mean-time speedups are $2.55$--$12.60$ over a Riemannian first-order method and $4.61$--$43.93$ over Jensen--Zimmermann R--TR2; batching gives a further factor of $3.45$--$23.53$ over sequential calls. The theoretical results complete the critical dimensions not covered by Gram convexification and quadratic matrix programming.

math.OC↗

arXiv2026

PiHand: Latent Hand-Object Interaction Priors for Physics-Based Policy Learning

Synthesizing physically grounded dexterous hand-object interactions is important for VR/AR, gaming, and robotics, yet remains challenging because subtle contact dynamics, diverse object geometries, and target trajectories must be jointly respected while maintaining natural grasps. Existing methods either track mocap trajectories with limited transfer to novel objects, or rely on hand-only generative priors that fail to capture coupled hand-object motion, sacrificing contact fidelity and sample efficiency. To tackle these challenges, we introduce PiHand, a Physically grounded Interaction-aware Hand motion synthesis framework. PiHand first trains expert policies that track mocap demonstrations in simulation, distills them into a unified hand-object interaction prior using a goal-conditioned VAE, and finally solve diverse dexterous manipulation tasks through bounded residual exploration in its latent space. With only a single reward and no complex curriculum training, this yields general tabletop manipulation policies that generalize to unseen objects and trajectories on GRAB and DexYCB. The same prior transfers to object catching and bimanual handover, two tasks that are rarely seen in its training data. Across all tasks, PiHand consistently outperforms baselines in all metrics. We will release the processed data and model checkpoints.

cs.CV↗

arXiv2026

Breaking the symmetry: X-ray polarization from a spreading layer on a tilted weakly magnetized neutron star

When modeling the emission from an X-ray binary system, we often assume that the rotational axis of the compact object is aligned with that of the binary system. While often considered irrelevant for spectroscopic observations, the orientation of the binary system is crucial for polarimetric properties. With the recent advent of X-ray polarimetric observations enabled by the Imaging X-ray Polarimetry Explorer (IXPE), indications of a possible misalignment of the neutron star rotational axis with respect to the binary axis have been reported. Following these indications, we present an analytical model for the polarimetric properties of emission arising from a spreading layer on an inclined weakly magnetized neutron star (WMNS). We discuss the expected polarimetric properties and study the impact of geometrical parameters of the system on the polarization of WMNS emission. We compare our results with those for aligned systems. Finally, we discuss applications of the model to recent and upcoming X-ray polarimetric observations with IXPE and mention the suggestions for further development of the model.

astro-ph.HE↗

arXiv2026

Mathematical AI Predicts 40% and 57% Influenza Vaccine Effectiveness Against H1N1 and H3N2, Respectively, for the 2026--2027 U.S. Season

Background: Clinical influenza vaccine effectiveness (VE) has often been low over the past two decades, highlighting the need for preseason VE forecasting. Timely forecasts could help health authorities plan prevention strategies and allocate healthcare resources. However, preseason forecasting of clinical influenza VE remains relatively uncommon. Methods: We obtained hemagglutinin (HA) sequences from GISAID for U.S. specimens collected in August--September before each influenza season from 2010--2011 through 2024--2025. After quality screening, we compared each virus with the corresponding vaccine target strain for the same season and subtype or lineage using two mathematical distances based on amino acid patterns in the HA protein. We calculated mean distances for each season and subtype or lineage and paired them with published clinical VE estimates, yielding 26 observations across 13 seasons. Using a mathematical AI approach, we fitted linear regression models of VE against each distance and evaluated their predictive performance by forecasting later seasons using data from earlier seasons, with the historical mean VE for each subtype or lineage as a reference. We then applied the same approach to 87 HA sequences collected in August--September 2026 to forecast VE for the 2026--2027 season. Results: We generated component-specific forecasts of influenza VE for the upcoming 2026--2027 U.S. season. Both mathematical distances were negatively associated with historical VE, indicating that greater differences between circulating viruses and vaccine strains were associated with lower VE. The topological model forecast VE of 40.3%, 56.9%, and 47.1% against A(H1N1)pdm09, A(H3N2), and B/Victoria, respectively, whereas the geometric model forecast corresponding VE values of 34.0%, 56.8%, and 51.1%.

math.AT↗

arXiv2026

Whole-Body Motion Guided Reference Generation for Uncertainty-Aware Compliant Assistance

Exoskeletons have shown great potential for augmenting human physical capabilities, yet generating reliable assistance remains challenging because human motion patterns and interaction requirements vary substantially in practice. To address this problem, a dual-loop assistance strategy is proposed to couple multimodal exoskeleton trajectory generation with variable admittance control, where trajectory variance links the outer-loop generator and the inner-loop controller. The generator synthesizes future exoskeleton trajectories through denoising, primarily using whole-body human motion and exoskeleton proprioception, with task descriptions as auxiliary semantic cues. To reduce cross-modal representation mismatch, a three-stage training pipeline is introduced to progressively optimize the human motion encoder, the exoskeleton proprioception encoder, and the trajectory generator. In the inner loop, multiple future trajectories are sampled from the generator to estimate the trajectory mean and variance. The mean is used as the control reference, while the variance provides an uncertainty measure for prediction reliability. This measure is further incorporated into a stiffness regulation law, enabling compliant assistance with input-to-state stability under bounded lumped interaction input. Experimental results demonstrate that the proposed method significantly reduces muscle activation levels compared with standard baselines, while also decreasing users' metabolic energy expenditure relative to the unassisted condition.

cs.RO↗

arXiv2026

The Value of Memory in Language Agents

Memory enables language agents to carry useful distinctions from past experience into future decisions. Its value depends on which distinctions survive, whether a bounded agent can use them, and what can be recovered or revised as demands evolve. We develop a decision-theoretic framework that follows this value from raw history through persistent state, operational use, and costly recovery and revision. Original and retained value are expressed in units of avoided task loss; risk-cost frontiers describe attainable recovery and preservation across uses. Unknown demand yields value profiles, while interactive feedback changes the distribution of future work. A cost-aware simulation condition and five minimal counterexamples expose the roles of information timing, retrieval access, component interaction, feedback and demand uncertainty. In particular, a pointer with zero mutual information about the answer can still reduce the cost of exact recovery. Diagnostics on LoCoMo, a two-project update task and longitudinal cases exhibit failures of preservation, use and measurement. At fixed retrieved evidence, a saved ledger changes subsequent answers; at fixed agent outputs, an evaluator revision changes scores. The framework connects these distinctions to operational risk bounds and testable principles for allocating memory, preserving recovery options and revising evidence dependencies.

cs.AI↗

arXiv2026

Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation

Hierarchical language generation separates continuous semantic modeling from discrete text realization, but its effectiveness depends on what the latent space compresses and how the discrete generator uses it. We propose Cola2, a framework that jointly studies continuous semantic compression, the balance between reconstruction and generation, and continuous-discrete co-adaptation. Cola2 dynamically segments text into semantic spans, controls the compression rate through auxiliary-loss-free negative feedback, and combines reconstruction and generation supervision to learn compact, predictive latent representations. A block-causal masked diffusion decoder is trained with clean, noisy, and dropped latent conditions, while classifier-free guidance adjusts the balance between semantic reconstruction and autonomous generation. Token-prediction gradients update the encoder through the latents, whereas Flow Matching prior learning is decoupled from representation learning by stop-gradient. During inference, generated text is re-encoded under a fixed span layout to keep the latent history consistent with the actual text context. Experiments on five downstream tasks with about 210 billion training tokens validate the core designs and show competitive, unsaturated scaling. With 346.03 billion source tokens, an unconverged checkpoint reaches a 60.10 average across eight tasks and surpasses Llama-3-8B on HellaSwag and StoryCloze despite its reported pretraining budget being over 43 times larger. These results demonstrate the potential of continuous-latent hierarchical language generation.

cs.CL↗

arXiv2026

Superintelligent Software Engineering: Governance That Scales with Capability

Software agents are being trained to exceed human engineers; we argue that capability alone does not produce better software engineering. We define superintelligent software engineering as the discipline of building and evolving software with agents whose capability exceeds that of human engineers, in which governance (gates, contracts, decisions and decay control) scales with capability. The argument rests on three claims. First, correctness in a project rests on decisions and contracts that the code does not carry. Second, knowledge decays. Third, once an agent outpaces its reviewers, reading catches a shrinking share of the changes built on stale knowledge. A simple model shows that, past a fixed review capacity, escaping changes grow linearly with throughput while the share that reading catches falls toward zero; governance can lower the slope, capability alone cannot. An exploratory snapshot of 452 of the most-starred public GitHub repositories finds a root-level or .github agent context file in 48.67% (95% confidence interval 44.1 to 53.3); in the median file that names repository paths, 9.5% to 22% of those paths do not resolve, depending on how a reference is read. We then present OSTEON, a discipline for the regime, released with a DOI (10.5281/zenodo.23436020): each project gets a governed knowledge repository of decisions and contracts, every change is checked mechanically against it, and the knowledge itself is checked for decay at every session start; planning is gated, and sessions record what they learn without writing rules. We report no measured effect of OSTEON, mark claims about its mechanisms as opinion and the author's practice heuristics as design rationale, and state the questions that would falsify the thesis.

cs.SE↗

arXiv2026

Subgoal-aware Memory Graph for GUI Agent

GUI agents aim to automate complex user tasks by interacting with mobile interfaces, but ef- fective decision-making in long-horizon set- tings requires reusing prior experience rather than relying solely on the environment ob- servations. Existing memory-based methods typically store experience either at the single- action level or as entire trajectories. Single- step actions are often too fine-grained to carry meaningful semantics, since the success of an individual action does not necessarily imply progress towards the overall goal. In contrast, whole trajectories are often too coarse-grained and difficult to reuse across different tasks. We propose a subgoal-aware memory graph that distils past trajectories into structured, reusable evidence at the level of subgoals. We define a subgoal as consecutive actions shar- ing a single intent, the granularity at which progress toward the task becomes meaning- ful. To reduce redundancy and support cross- task reuse, we organise subgoal experiences as nodes in a graph, where related memories can be merged, extended, and retrieved based on the environment observation. On SPA-Bench, our method improves success rate by 11.11% over the baseline.

cs.AI↗