SEARCH · Searcharxiv

Search Searcharxiv

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

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 217 records · Page 12Linked to original sources

arXiv2026

Towards Effective Orchestration of AI x DB Workloads

AI-driven analytics are increasingly crucial to data-centric decision-making. Executing relational and AI operators in separate runtimes prevents the database optimizer and runtime from coordinating operator ordering, model placement, batching, and state reuse. Integrating AI operators into database engines enables such coordination but raises challenges in jointly optimizing query processing and model execution, scheduling under resource contention, and reusing relational intermediates and AI artifacts. This paper formalizes AIxDB workloads as iterative, concurrent, and shareable executions that interleave relational and AI operators. We then advocate database-native orchestration as a paradigm for redesigning database engines for these workloads and distill two design principles: holistic AIxDB co-optimization and unified AIxDB cache management. We present NeurEngine as a proof-of-concept prototype and report preliminary results illustrating the performance benefits of database-native orchestration

cs.DB↗

arXiv2026

Separators in Enhancing Autoregressive Pretraining for Vision Mamba

The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting considerable attention for its efficient handling of long-sequence tasks. Its inherent causal structure makes it particularly well suited for autoregressive pretraining. However, existing autoregressive pretraining methods in vision are largely limited to short-sequence settings and may not fully use Mamba's capacity to model longer contexts. To investigate this setting, we introduce SeparaTors for AutoRegressive pretraining (STAR), a new autoregressive pretraining method for Vision Mamba that explicitly marks the boundaries between different images. STAR increases the patch-token sequence length from 144 to 640 by packing four images and four separator clusters. This is approximately $4.4\times$ the ARM patch-token sequence length. The increase is achieved without changing the resolution of any individual image: we use $192\times192$ inputs for autoregressive pretraining and $224\times224$ inputs for downstream classification fine-tuning. With this long-sequence pretraining scheme, STAR-B achieves 83.5\% EMA top-1 accuracy on ImageNet-1K after 1,600 epochs of pretraining. The learned representation also transfers beyond in-distribution classification: compared with ARM, STAR-B improves COCO box AP from 46.11 to 46.84 and mask AP from 40.74 to 41.45, while raising the mean top-1 accuracy across five ImageNet robustness benchmarks from 55.1\% to 56.8\%. Under the evaluated four-image setting, these results indicate that separator-based long-sequence pretraining improves recognition robustness and dense visual prediction relative to ARM.

cs.CV↗

arXiv2026

Flat holography for spinor fields

We extend the hyperbolic Milne-slicing construction of flat holography in four-dimensional Minkowski spacetime from scalar fields to massless spin-$\frac{1}{2}$ fields. We solve the massive mode equation and restrict the boundary source-response analysis to the massless sector. Decomposition into harmonics on three-dimensional hyperbolic space, labeled by a continuous principal-series parameter, yields a separated-point nonlocal kernel up to the action normalization and local contact terms. The kernel has the universal form required by two-dimensional conformal covariance for spin-$\frac{1}{2}$ principal-series primaries. Then we construct regular source-normalized conformal-primary wavefunctions in planar and global coordinates on the celestial sphere $S^2$. We show that the planar source-response kernel is naturally identified with the spin-$\frac{1}{2}$ shadow transform, while inverse shadowing recovers the angular delta-function structure of the unshadowed basis. We also analyze radial renormalization by analytic continuation from the principal-series problem to a real-mass AdS$_3$ problem.

hep-th↗

arXiv2026

CAR: Cross-Vehicle Kinodynamics Adaptation via Mobility Representation

Developing autonomous mobile robot systems typically requires either extensive, platform-specific data collection or relies on simplified abstractions, such as unicycle or bicycle models, that fail to capture the complex kinodynamics of diverse platforms, ranging from wheeled to tracked vehicles. This limitation hinders scalability across evolving heterogeneous autonomous robot fleets. To address this challenge, we propose Cross-vehicle kinodynamics Adaptation via mobility Representation (CAR), a novel framework that enables rapid mobility transfer to new vehicles. CAR employs a Transformer encoder with Adaptive Layer Normalization to embed vehicle trajectory transitions and physical configurations into a shared mobility latent space. By identifying and extracting commonality from nearest neighbors within this latent space, our approach enables rapid kinodynamics adaptation to novel platforms with minimal data collection and computational overhead. We evaluate CAR using the Verti-Bench simulator, built on the Chrono multi-physics engine, and validate its performance on four distinct physical configurations of the Verti-4-Wheeler platform. With only one minute of new trajectory data, CAR achieves up to 67.2% reduction in prediction error compared to direct neighbor transfer across diverse unseen vehicle configurations, demonstrating the effectiveness of cross-vehicle mobility knowledge transfer in both simulated and real-world environments.

cs.RO↗

arXiv2026

Distributed Legal Infrastructure for a Trustworthy Agentic Web

The agentic web marks a structural transition from a human-centered information network to a digital environment populated by artificial intelligence (AI) agents that perceive, decide, and act autonomously. As delegated action unfolds at machine speed, exceeds discrete moments of human judgment, and distributes decision-making across non-human actors, existing legal frameworks face growing strain, creating an urgent need for new mechanisms capable of sustaining legality in this emerging order. A trustworthy agentic web therefore depends on the infrastructuring of legality through interoperable protocols that organize identity, delegation, and accountability across systems, enabling coherent governance beyond isolated platforms. Towards this end, this article advances a distributed legal infrastructure (DLI), a governance paradigm composed of five interlocking layers: (1) self-sovereign, soulbound agent identities; (2) cognitive AI logic and constraint systems; (3) decentralized adjudication mechanisms for dispute resolution; (4) bottom-up agentic market regulation to mitigate information asymmetries and network effects, including insurance-based models; and (5) portable institutional frameworks that enable legal interoperability while preserving plural sources of authority. This reference framework contributes to emerging research on embedding legality within agentic web infrastructure, aligning distributed technical systems with accountability, contestability, and rule-of-law principles.

cs.AI↗

arXiv2026

UNet-AF: Alias-free UNet architectures

The simplicity and effectiveness of UNet architectures make them ubiquitous in image restoration, segmentation, and diffusion models. They are often assumed to be equivariant to translations, yet they traditionally consist of layers that are known to be prone to aliasing, which hinders their equivariance in practice. To overcome this limitation, we show how to build sub-pixel translation-equivariant UNet architectures by appropriately choosing their main components (convolution, pooling, downsampling, activation, and normalization layers) to be alias-free. We evaluate the proposed equivariant architectures against non-equivariant baselines on image restoration tasks and observe competitive performance with a significant increase in measured equivariance. Through extensive ablation studies, we also demonstrate the importance of every architectural choice to achieve high equivariance. Our implementation is available at https://github.com/jscanvic/UNet-AF

cs.CV↗

arXiv2026

Bayesian Modular Inference for Copula Models with Potentially Misspecified Marginals

Copula models of multivariate data are popular because they allow separate specification of marginal distributions and the copula function. These components can be treated as inter-related modules in a modified Bayesian inference approach called ''cutting feedback'' that is robust to their misspecification. Recent work uses a two module approach, where all $d$ marginals form a single module, to robustify inference for the marginals against copula function misspecification, or vice versa. However, marginals can exhibit differing levels of misspecification, making it attractive to assign each its own module with an individual influence parameter controlling its contribution to a joint semi-modular inference (SMI) posterior. This generalizes existing two module SMI methods, which interpolate between cut and conventional posteriors using a single influence parameter. We develop a novel copula SMI method and select the influence parameters using Bayesian optimization. It provides an efficient continuous relaxation of the discrete optimization problem over $2^d$ cut/uncut configurations. We establish theoretical properties of the resulting semi-modular posterior and demonstrate the approach on simulated and real data. The real data application uses a skew-normal copula model of asymmetric dependence between equity volatility and bond yields, where robustifying copula estimation against marginal misspecification is strongly motivated.

stat.ME↗

arXiv2026

Asymmetry of a class of Mellin transforms

We introduce the quantity $μ_η$, defined for every complex $s$ in the critical strip, as a transformation of the Mellin transform associated to the functions $η$. We establish a sufficient condition on $η$ under which $μ_η(s)$ and $μ_η(1-s)$ cannot both vanish outside the critical line. An application is given to the case in which $η$ is the fractional part function, and the zeros of $μ_η$ coincide with the zeros of the Riemann zeta function.

math.DS↗

arXiv2026

Conditional Distributional Treatment Effects: Doubly Robust Estimation and Testing

Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example, by altering the variance or tail risks for specific subpopulations. We propose a novel estimand to capture such conditional distributional treatment effects, and develop a doubly robust estimator that is minimax optimal in the local asymptotic sense. Using this, we develop a test for the global homogeneity of conditional potential outcome distributions that accommodates discrepancies beyond the maximum mean discrepancy (MMD), has provably valid type 1 error, and is consistent against fixed alternatives---the first test, to our knowledge, with such guarantees in this setting. We then provide a test that aggregates evidence across a grid of kernel-bandwidth choices. Furthermore, we derive exact closed-form expressions for two natural discrepancies (including the MMD), and provide a computationally efficient, permutation-free algorithm for our test.

stat.ML↗

arXiv2026

Stellar characterization with photometric colors from J-PLUS and 2MASS surveys

Aims. We aim at deriving stellar atmospheric parameters based on the photometric data from the Javalambre Photometric Local Universe Survey (J-PLUS) in addition to near-infrared photometry from the Two Micron All-Sky Survey (2MASS). Methods. Our method consists of a semi-supervised machine learning approach based on the k-means method combined with a modified k-nearest neighbors algorithm. This method compares the observed photometry to a set of reference data to estimate the stellar effective temperature ($T_{\rm eff}$), surface gravity ($\log{g}$), and metallicity ([Fe/H]) of stars from J-PLUS Data Release 3 (DR3). Results. We estimated $T_{\rm eff}$, $\log{g}$, and [Fe/H], for approximately 5.6 million stars from J-PLUS DR3, along with their errors.Our results were in agreement with spectroscopic estimates from LAMOST and APOGEE.We also applied a dimension reduction method, seeking greater efficiency by reducing the computation time and minimizing the needed information for calculating the stellar parameters, resulting in a subset of 11 colors. From this approach, stellar parameters were obtained for approximately six million stars. Conclusions. Our results demonstrated the potential of using a method built from machine learning algorithms that do not require prior training. Additionally, it was shown that the proposed method allowed estimating reliable atmospheric parameters even when the available photometry did not fulfill all photometric quality criteria. We defined a neighborhood parameter, which assesses the reliability of our estimations and indicates that objects with smaller neighborhoods values have lower uncertainties.

astro-ph.SR↗

arXiv2026

Differential Fault Analysis of Lilliput under Random-Location Nibble Faults

Differential fault analysis (DFA) is an important technique for evaluating the implementation-level security of block ciphers. Many DFA attacks assume that the adversary can inject faults into a selected internal word, nibble, or branch. Such fixed-location assumptions are convenient for deriving key-recovery equations, but they may overestimate the adversary's spatial control and may obscure the branch-dependent leakage behavior of multi-branch structures. In this paper, we study the lightweight block cipher Lilliput under a fixed-timing full-branch random-location nibble fault model. The attacker is assumed to induce a nonzero nibble fault in round 27, while the affected branch is randomly distributed over all sixteen state branches and is unknown to the attacker. The main challenge is to convert faulty ciphertexts with unknown injection locations into usable key-recovery constraints. We analyze the fault propagation induced by the EGFN structure of Lilliput and derive ciphertext-difference conditions for identifying the injected branch. The proposed branch-identification approach has a DDT-based combinatorial estimate of at least 99.9909% and achieves 99.9983% accuracy in 2^{20} random fault simulations. Once the fault branch is determined, we classify the corresponding propagation patterns according to whether the injected fault value and the intermediate S-box output difference can be uniquely determined. For each case, we derive DDT-based constraints on the last-round and penultimate-round subkeys and combine multiple faulty ciphertexts by candidate-set intersection. Simulation experiments over 2^{15} trials show that the attack reaches key-recovery success rates of over 90%, 95%, and 99% with 32, 36, and 46 faulty ciphertexts, respectively. These results show that Lilliput exhibits exploitable branch-dependent leakage even when the attacker cannot control the exact fault location.

cs.CR↗

arXiv2026

Exploiting Full Network Nonlocality From Quantum Key Distribution Perspective

Recently, the notion of full network nonlocality has emerged as some truly quantum network phenomena that cannot be realized in traditional Bell experiments. Present work manifests the utility of such form of truly network non-classicality in designing a four partite network-based entanglement assisted quantum key distribution protocol. Precisely, validity of the QKD protocol relies upon full network nonlocality detection via violation of some suitable trilocal inequality. Based on the quantum bit error rate and violation of trilocal inequality, arbitrary two qubit entangled states are characterized in accordance with their utility in successfully executing the protocol. The protocol is further analyzed from a restricted Eve-aware perspective by quantifying the Eve`s partial side information and discussing its implications for the corresponding Devetak-Winter $1$-way secret key rate. Also, considering Eve's control over the trusted parties' measurement devices, an illustration of the protocol`s resistance to detection loophole is provided. Due to connected structure of entangled sources, any genuine form of network nonlocality may offer advantage over standard Bell nonlocality for designing secure key distribution protocols. To establish such an intuition as a fact, another QKD protocol, relying only upon Bell-CHSH violation, is designed. The former offers more stricter validity checks compared to the latter. Importantly, while the quantum bit error rate can be less than $14.6\%$ exploiting Bell-CHSH nonlocality, it can be reduced below $13.7\%$ by exploiting full network nonlocality.

quant-ph↗

arXiv2026

Variable-Resolution Virtual Maps for Autonomous Exploration with Unmanned Surface Vehicles (USVs)

Autonomous exploration by unmanned surface vehicles (USVs) in near-shore waters requires reliable localisation and consistent mapping over extended areas, but this is challenged by GNSS degradation, environment-induced localisation uncertainty, and limited on-board computation. Virtual map-based methods explicitly model localisation and mapping uncertainty by tightly coupling factor-graph SLAM with a map uncertainty criterion. However, their storage and computational costs scale poorly with fixed-resolution workspace discretisations, leading to inefficiency in large near-shore environments. Moreover, overvaluing feature-sparse open-water regions can increase the risk of SLAM failure as a result of imbalance between exploration and exploitation. To address these limitations, we propose a Variable-Resolution Virtual Map (VRVM), a computationally efficient method for representing map uncertainty using bivariate Gaussian virtual landmarks placed in the cells of an adaptive quadtree. The adaptive quadtree enables an area-weighted uncertainty representation that keeps coarse, far-field virtual landmarks deliberately uncertain while allocating higher resolution to information-dense regions, and reduces the sensitivity of the map valuation to local refinements of the tree. An expectation-maximisation (EM) planner is adopted to evaluate pose and map uncertainty along frontiers using the VRVM, balancing exploration and exploitation. We evaluate VRVM against several state-of-the-art exploration algorithms in the VRX Gazebo simulator, using a realistic marina environment across different testing scenarios with an increasing level of exploration difficulty. The results indicate that our method offers safer behaviour and better utilisation of on-board computation in GNSS-degraded near-shore environments.

cs.RO↗

arXiv2026

Benzo-bis(imidazole) self-assembled monolayers molecular junctions in meta or para conformation: effects of protonation on the electrical and thermal conductances

We report the thermal conductances of molecular junctions made of self-assembled monolayers of benzo-bis(imidazole) molecules, without side groups or functionalized with two phenylamine side groups. In the two cases, when the molecules are connected to the electrodes by thiol anchoring groups in the meta-position, the thermal conductance is decreased compared to the same molecules connected in the para-position (ca. 16-29 nW/K and ca. 37-40 nW/K, respectively) in agreement with the theoretically predicted phonon interference effect in molecular junctions. Upon protonation, the thermal conductances of the meta-connected molecular junction increase by about 50% (reversible behavior upon deprotonation). The fact that only the thermal conductance of the meta-connected molecular junction is sensitive to the protonation/deprotonation is tentatively related to modifications of the structural organization of the molecules in the monolayer, which modifies the thermal conductance at the molecule/electrode interfaces. The electrical conductance is lower for the meta-connected molecule than for the para-connected one, due to destructive quantum interferences, as expected and reported for other molecular junctions. The conductance further decreases (reversibly) upon protonation. The energy position of the molecular orbital involved in the electron transport is not modified by the protonation and the decrease in current is related to changes in the molecule organization in the monolayer, which modulate the electronic coupling energy at the molecule/electrode interfaces.

cond-mat.mes-hall↗

arXiv2026

Calibrated Confidence Expression for Radiology Report Generation

Safe deployment of Large Vision-Language Models (LVLMs) in radiology report generation requires not only accurate predictions but also clinically interpretable indicators of when outputs should be thoroughly reviewed, enabling selective radiologist verification and reducing the risk of hallucinated findings influencing clinical decisions. One intuitive approach to this is verbalized confidence, where the model explicitly states its certainty. However, current state-of-the-art language models are often overconfident, and research on calibration in multimodal settings such as radiology report generation is limited. To address this gap, we introduce ConRad (Confidence Calibration for Radiology Reports), a reinforcement learning framework for fine-tuning medical LVLMs to produce calibrated verbalized confidence estimates alongside radiology reports. We study two settings: a single report-level confidence score and a sentence-level variant assigning a confidence to each claim. Both are trained using the GRPO algorithm with reward functions based on the logarithmic scoring rule, which incentivizes truthful self-assessment by penalizing miscalibration and guarantees optimal calibration under reward maximization. Experimentally, ConRad substantially improves calibration and outperforms competing methods. In a clinical evaluation we show that ConRad's report level scores are well aligned with clinicians' judgment. By highlighting full reports or low-confidence statements for targeted review, ConRad can support safer clinical integration of AI-assistance for report generation.

cs.CL↗

arXiv2026

Sampling at intermediate temperatures is optimal for training large language models in protein structure prediction

Using a statistical mechanics framework, we investigate the parameter space of transformer models trained on protein sequence data. We sample the loss landscape at varying temperatures using Langevin dynamics to characterize the low-loss manifold, and to understand the mechanisms underlying transformers' superior performance in protein structure prediction. We find that, at variance with networks not based on the attention mechanism, the lack of a first--order--like transition in the loss of the transformer produces a range of intermediate temperatures with good learning properties; this is true both for synthetic and natural protein sequences. We also show that the parameters of most layers are highly conserved at these temperatures if the dimension of the embedding is optimal, and we provide an operative way to find this dimension. Additionally, we show that the attention matrix is more predictive of the contact maps of the protein at higher temperatures and for higher dimensions of the embedding than those optimal for learning. Finally, we showed that the models sampled at intermediate temperatures can predict the free-energy variation upon mutation, better than models obtained through standard optimization techniques.

cond-mat.dis-nn↗

arXiv2026

A SAT-based Filtering Framework for Exact Coverings of K33 by Cliques of Order 3, 4 or 5

We investigate the minimum number of cliques of orders $3$, $4$, and $5$ needed to cover the edges of $K_{33}$ with zero excess. General covering results yield the lower bound 57. The main result of the paper is that no decomposition of $K_{33}$ into $57$ blocks from $\{K_3,K_4,K_5\}$ exists. Our approach is algorithmic and relies on a layered exact-search pipeline rather than a single monolithic solver. We combine symmetry reduction, enumeration of local signatures, arithmetic profile restrictions, geometric tests for partial configurations, SAT realisation on reduced instances, and final decoding checks. The benchmark comparison shows that this structured approach is substantially more effective than direct ILP, DLX, or SAT formulations on the full problem. As a consequence, we obtain $C^ξ(33,\{3,4,5\},2)\ge 58$. A short additional counting argument further strengthens this to $C^ξ(33,\{3,4,5\},2)\ge 59$. We also give new compressed proofs for the known exceptional cases $K_{18}$ and $K_{19}$ in the setting of $\{K_3,K_4\}$-decompositions, illustrating the same combination of theoretical reduction and exact computation. Finally, we explain the relevance of the $K_{33}$ result to the open packing problem of determining the packing number $D(33,5,2)$. A packing of $51$ copies of $K_5$ in $K_{33}$ would leave a $4$-regular graph on $9$ vertices, and our exclusion already rules out two natural candidate leave structures.

math.CO↗

arXiv2026

Learning Diagnostic Reasoning for Decision Support in Toxicology

Acute poly-substance intoxication requires rapid, life-saving decisions under substantial uncertainty, as clinicians must rely on incomplete ingestion details and nonspecific symptoms. Effective diagnostic reasoning in this chaotic environment requires fusing unstructured, non-medical narratives (e.g. paramedic scene descriptions and unreliable patient self-reports or known histories), with structured medical data like vital signs. While Large Language Models (LLMs) show potential for processing such heterogeneous inputs, they struggle in this setting, often underperforming simple baselines that rely solely on patient histories. To address this, we present DeToxR (Decision-support for Toxicology with Reasoning), the first adaptation of Reinforcement Learning (RL) to emergency toxicology. We design a robust data-fusion engine for multi-label prediction across 14 substance classes based on an LLM finetuned with Group Relative Policy Optimization (GRPO). We optimize the model's reasoning directly using a clinical performance reward. By formulating a multi-label agreement metric as the reward signal, the model is explicitly penalized for missing co-ingested substances and hallucinating absent poisons. Our model significantly outperforms its unadapted base LLM counterpart and supervised baselines. Furthermore, in a preliminary clinical validation study, the model indicates a clinical advantage by achieving higher micro-F1 (0.644 vs 0.473) and recall in identifying the correct poisons. These results demonstrate the potential of RL-aligned LLMs to synthesize unstructured pre-clinical narratives and structured medical data for decision support in high-stakes environments.

cs.CL↗