Search arXiv⌕ Search

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 73 records · Page 4Linked to original sources
arXiv2026

DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision

Score-based distillation methods train one-step diffusion models in two stages: they first train a teacher score model, then distill it into a one-step student model. However, this distillation process can introduce bias from two sources: errors in the teacher score model and student score estimate. We propose DiffRatio, a new approach for training one-step diffusion models without teacher supervision based on a density-ratio formulation that connects score-based distribution matching and GAN-style adversarial training. Instead of using a teacher score model to provide training targets, DiffRatio directly learns a log density ratio between the student and data distributions across diffusion time steps. As a pre-trained score model is only used to initialize the one-step generator and does not supervise training, this design simplifies the training pipeline, mitigates gradient estimation bias, and reduces the size of auxiliary networks. The learned density ratio can be used as a verifier, enabling a principled inference-time parallel scaling method that further improves sample quality without external rewards or extra sequential computation. DiffRatio achieves strong one-step generation results on CIFAR-10 and ImageNet (64x64 and 512x512), outperforming most teacher-supervised distillation methods.

cs.LG↗
arXiv2026

Models with rank-reducing discrete boundary conditions on $T^2/{\mathbb Z}_4$

We study six-dimensional $SU(n)$ gauge models with rank-reducing discrete boundary conditions on the orbifold $T^2/{\mathbb Z}_4$, without and with continuous Wilson line phases. For the latter case, we find that a minimal model can describe the breakdown of the electroweak symmetry based on an $SU(6)$ gauge group. This model possesses excellent features that two Higgs doublets come from the zero modes of the extra-dimensional gauge field, and the quarks in each generation can be unified into one multiplet, without exotic quarks, as the zero modes of a bulk field in the $\boldsymbol{15}$ representation of $SU(6)$. There exists a vacuum where the electroweak symmetry is slightly broken by the Hosotani mechanism, with the addition of suitable bulk fields.

hep-ph↗
arXiv2026

Generalization of terms via universal algebra

We provide a new foundational approach to the generalization of terms up to equational theories. We interpret generalization problems in a universal-algebraic setting making a key use of projective and exact algebras in the variety associated to the considered equational theory. We prove that the generality poset of a problem and its type (i.e., the cardinality of a complete set of least general solutions) can be studied in this algebraic setting. Moreover, we identify a class of varieties where the study of the generality poset can be fully reduced to the study of the congruence lattice of the 1-generated free algebra. We apply our results to varieties of algebras and to (algebraizable) logics. In particular we obtain several examples of unitary type: abelian groups; commutative monoids and commutative semigroups; all varieties whose 1-generated free algebra is trivial, e.g., lattices, semilattices, varieties without constants whose operations are idempotent; Boolean algebras, Kleene algebras, and Gödel algebras, which are the equivalent algebraic semantics of, respectively, classical, 3-valued Kleene, and Gödel-Dummett logic. Finally, we prove that the variety of MV-algebras, the equivalent algebraic semantics of Lukasiewicz logic, has nullary type.

math.LO↗
arXiv2026

CodeArena: A Collective Evaluation Platform for LLM Code Generation

Large Language Models (LLMs) have reshaped code generation by synergizing their exceptional comprehension of natural language and programming syntax, thereby substantially boosting developer productivity. These advancements have prompted numerous efforts to quantitatively evaluate their coding capabilities. However, persistent challenges, such as benchmark leakage, data dissipation, and limited system accessibility, continue to impede a timely and accurate assessment. To address these limitations, we introduce CodeArena, an online evaluation framework tailored for LLM code generation. The key innovation is a collective evaluation mechanism, which dynamically recalibrates individual model scores based on the holistic performance of all participating models, mitigating score biases caused by widespread benchmark leakage. In addition, CodeArena ensures open access to all submitted solutions and test cases and provides automation-friendly APIs to streamline the code evaluation workflow. Our main contributions are: (1) a collective evaluation system for unbiased assessment, (2) a public repository of solutions and test cases, and (3) automation-ready APIs for seamless integration.

cs.SE↗
arXiv2026

Incorporating graph neural network into route choice model

Route choice models are one of the most important foundations for transportation research. Traditionally, theory-based models have been utilized for their great interpretability, such as logit models and Recursive logit models. More recently, machine learning approaches have gained attentions for their better prediction accuracy. In this study, we propose novel hybrid models that integrate the Recursive logit model with Graph Neural Networks (GNNs) to enhance both predictive performance and model interpretability. To the authors' knowldedge, GNNs have not been utilized for route choice modeling, despite their proven effectiveness in capturing road network features and their widespread use in other transportation research areas. We mathematically show that our use of GNN is not only beneficial for enhancing the prediction performance, but also relaxing the Independence of Irrelevant Alternatives property without relying on strong assumptions. This is due to the fact that a specific type of GNN can efficiently capture multiple cross-effect patterns on networks from data. By applying the proposed models to one-day travel trajectory data in Tokyo, we confirmed their higher prediction accuracy compared to the existing models.

cs.LG↗
arXiv2026

PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simultaneously preserving semantic fidelity across multiple heterogeneous control signals while maintaining high visual quality, where they employ separate control branches that often introduce conflicting guidance during the denoising process, leading to structural distortions and artifacts in generated images. To address this issue, we present PixelPonder, a novel unified control framework, which allows for effective control of multiple visual conditions under a single control structure. Specifically, we design a patch-level adaptive condition selection mechanism that dynamically prioritizes spatially relevant control signals at the sub-region level, enabling precise local guidance without global interference. Additionally, a time-aware control injection scheme is deployed to modulate condition influence according to denoising timesteps, progressively transitioning from structural preservation to texture refinement and fully utilizing the control information from different categories to promote more harmonious image generation. Extensive experiments demonstrate that PixelPonder surpasses previous methods across different benchmark datasets, showing superior improvement in spatial alignment accuracy while maintaining high textual semantic consistency.

cs.CV↗
arXiv2026

Aligned Delta-Triplane Transformers as Occupancy World Models

Occupancy World Models (OWMs) aim to predict future 3D occupancy scenes from historical observations and future ego motions, providing a useful world simulation tool for autonomous driving. Existing methods usually rely on large networks to implicitly align multi-frame historical states and predict future occupancy in a full-state manner, which is costly and redundant because most scene regions remain unchanged over short time intervals. In this paper, we propose Aligned Delta-Triplane Transformer (ADTT), a compact 4D OWM that explicitly aligns historical triplanes with ego-motion compensation and predicts only future scene changes. Based on the aligned triplane prior, a query-conditioned Transformer predicts residual changes, where ego-motion queries guide controllable future motion and learnable external queries capture scene changes beyond ego motion. The predicted changes are added to the aligned prior and decoded into future occupancy scenes. Experiments on Occ3D-nus show that ADTT achieves state-of-the-art forecasting performance with fewer parameters and higher FPS. Our code is publicly available online: https://github.com/kyoran/ADTT.

cs.RO↗
arXiv2026

Covariant derivatives in the representation-valued Bott-Shulman-Stasheff and Weil complex

For a Lie groupoid $G$, the differential forms on its nerve comprise a double complex. A natural question is if this statement extends to forms with values in a representation $V$ of $G$. In this paper, we research two types of covariant derivatives which commute with the simplicial differential, yielding two types of curved double complexes of forms with coefficients in $V$. The naive approach is to consider a linear connection $\nabla$ on $V$, in which case $d^\nabla$ commutes with the simplicial differential if and only if $\nabla$ satisfies a certain (restrictive) invariance condition. The heart of this paper focuses on another, more compelling approach: using a multiplicative Ehresmann connection for a bundle of ideals. In this case, we obtain a geometrically richer curved double complex, where the cochain map is given by the horizontal exterior covariant derivative $D$, which generalizes the well-known operator from the theory of principal bundles. Moreover, both differential operators $d^\nabla$ and $D$ are researched in the infinitesimal setting of Lie algebroids, as well as their relationship with the van Est map. We conclude by using the operator $D$ to study the curvature of an (infinitesimal) multiplicative Ehresmann connection.

math.DG↗
arXiv2026

EarthScape: A Multimodal Benchmark for Geologic Mapping and Surface-Aware Learning under Geographic Domain Shift

Understanding natural Earth surface processes requires integrating topography, imagery, hydrology, and human infrastructure while remaining robust to geographic variation, yet few benchmarks support both challenges. We introduce EarthScape, a multimodal benchmark for geologic mapping and surface-aware learning under geographic domain shift. EarthScape combines aerial imagery, LiDAR-derived elevation, multi-scale terrain derivatives, and contextual vector data into 37 co-registered input channels per sample, together with pixel-level geologic masks. Its geographically separated regions share a common label space, enabling controlled evaluation of in-domain and cross-region generalization under realistic class imbalance and spatial complexity. Benchmark experiments show that engineered terrain representations transfer more robustly than raw elevation, while spatial support and multimodal terrain inputs strongly influence performance. Fusion effectiveness depends on backbone and evaluation domain, with more complex cross-attention providing no consistent advantage over simpler strategies. These representation trends extend across geospatial foundation models and semantic segmentation, while class-level results show that no single terrain feature or scale is optimal across geologic classes. Together, EarthScape provides a benchmark for studying representation design, multimodal fusion, and geographic robustness in surface-aware geospatial learning. Our source code is available at https://github.com/masseygeo/earthscape and the dataset at https://doi.org/10.13023/kgs.data.05.01.2025.

cs.CV↗
arXiv2026

CMADiff: Cross-Modal Aligned Diffusion for Controllable Protein Generation

AI-assisted protein design has emerged as a critical tool for advancing biotechnology, as deep generative models have demonstrated their reliability in this domain. However, most existing models primarily utilize protein sequence or structural data for training, neglecting the physicochemical properties of proteins.Moreover, they are deficient to control the generation of proteins in intuitive conditions. To address these limitations,we propose CMADiff here, a novel framework that enables controllable protein generation by aligning the physicochemical properties of protein sequences with text-based descriptions through a latent diffusion process. Specifically, CMADiff employs a Conditional Variational Autoencoder (CVAE) to integrate physicochemical features as conditional input, forming a robust latent space that captures biological traits. In this latent space, we apply a conditional diffusion process, which is guided by BioAligner, a contrastive learning-based module that aligns text descriptions with protein features, enabling text-driven control over protein sequence generation. Validated by a series of evaluations including AlphaFold3, the experimental results indicate that CMADiff outperforms protein sequence generation benchmarks and holds strong potential for future applications. The implementation and code are available at https://github.com/HPC-NEAU/PhysChemDiff.

cs.CE↗
arXiv2026

A Complete Mental Temporal Logic for Intelligent Agents

In this paper, we present a mental temporal logic BPICTL together with a sound and complete axiomatization, which generalizes CTL by introducing mental modalities. A sound and complete inference system of BPICTL is given. We also prove the finite model property and decidability of BPICTL. Furthermore, we present a model checking algorithm for BPICTL.

cs.LO↗
arXiv2026

On the minimax optimality of Flow Matching through the connection to kernel density estimation

Flow Matching has recently gained attention in generative modeling as a simple and flexible alternative to diffusion models. While existing statistical guarantees adapt tools from the analysis of diffusion models, we take a different perspective by connecting Flow Matching to kernel density estimation. We first verify that the kernel density estimator matches the optimal rate of convergence in Wasserstein distance up to logarithmic factors, improving existing bounds for the Gaussian kernel. Based on this result, we prove that for sufficiently large networks, Flow Matching achieves the optimal rate up to logarithmic factors. If the target distribution lies on a lower-dimensional manifold, we show that the kernel density estimator profits from the smaller intrinsic dimension on a small tube around the manifold. The faster rate also applies to Flow Matching, providing a theoretical foundation for its empirical success in high-dimensional settings.

stat.ML↗
arXiv2026

Four-Fermion Deformations on Line Defects in QED$_4$ with Yukawas

We elucidate the dynamics induced by a Wilson Line of charge $q$ and electron charge $e$ in $QED_4$ coupled to a real scalar via Yukawa interactions. We observe that there is a range of the fixed product $e^2 q$ with $e\rightarrow 0$ and $q\rightarrow \infty$ for which four-fermion operators play a dominant role for the dynamics of the theory. We uncover the fixed-point dynamics of the theory and analyze their critical behavior.

hep-th↗
arXiv2026

Prekosmic Grothendieck/Galois Categories

We establish a generalized version of the duality between groups and the categories of their representations on sets. Given an abstract symmetric monoidal category $K$ called Galois prekosmos, we define pre-Galois objects in $K$ and study the categories of their representations internal to $K$. The motivating example of $K$ is the cartesian monoidal category $\textit{Set}$ of sets, and pre-Galois objects in $\textit{Set}$ are groups. We present an axiomatic definition of pre-Galois $K$-categories, which is a complete abstract characterization of the categories of representations of pre-Galois objects in $K$. The category of covering spaces over a well-connected topological space is a prototype of a pre-Galois $\textit{Set}$-category. We establish a perfect correspondence between pre-Galois objects in $K$ and pre-Galois $K$-categories pointed with pre-fiber functors. We also establish a generalized version of the duality between flat affine group schemes and the categories of their linear representations. Given an abstract symmetric monoidal category $K$ called Grothendieck prekosmos, we define what are pre-Grothendieck objects in $K$ and study the categories of their representations internal to $K$. The motivating example of $K$ is the symmetric monoidal category $\textit{Vec}_k$ of vector spaces over a field $k$, and pre-Grothendieck objects in $\textit{Vec}_k$ are affine group $k$-schemes. We present an axiomatic definition of pre-Grothendieck $K$-categories, which is a complete abstract characterization of the categories of representations of pre-Grothendieck objects in $K$. The indization of a neutral Tannakian category over a field $k$ is a prototype of a pre-Grothendieck $\textit{Vec}_k$-category. We establish a perfect correspondence between pre-Grothendieck objects in $K$ and pre-Grothendieck $K$-categories pointed with pre-fiber functors.

math.AG↗
arXiv2026

From Events to Enhancement: A Survey on Event-Based Imaging Technologies

Event cameras offering high dynamic range and low latency have emerged as disruptive technologies in imaging. Despite growing research on leveraging these benefits for different imaging tasks, a comprehensive study of recently advances and challenges are still lacking. This limits the broader understanding of how to utilize events in universal imaging applications. In this survey, we first introduce a physical model and the characteristics of different event sensors as the foundation. Following this, we highlight the advancement and interaction of image/video enhancement tasks with events. Additionally, we explore advanced tasks, which capture richer light information with events, \eg~light field estimation, multi-view generation, and photometric. Finally, we discuss new challenges and open questions offering a perspective for this rapidly evolving field. More continuously updated resources are at this link: https://github.com/yunfanLu/Awesome-Event-Imaging

cs.CV↗
arXiv2026

Joint Detection of Fraud and Concept Drift inOnline Conversations with LLM-Assisted Judgment

Detecting fake interactions in digital communication platforms remains a challenging and insufficiently addressed problem. These interactions may appear as harmless spam or escalate into sophisticated scam attempts, making it difficult to flag malicious intent early. Traditional detection methods often rely on static anomaly detection techniques that fail to adapt to dynamic conversational shifts. One key limitation is the misinterpretation of benign topic transitions referred to as concept drift as fraudulent behavior, leading to either false alarms or missed threats. We propose a two stage detection framework that first identifies suspicious conversations using a tailored ensemble classification model. To improve the reliability of detection, we incorporate a concept drift analysis step using a One Class Drift Detector (OCDD) to isolate conversational shifts within flagged dialogues. When drift is detected, a large language model (LLM) assesses whether the shift indicates fraudulent manipulation or a legitimate topic change. In cases where no drift is found, the behavior is inferred to be spam like. We validate our framework using a dataset of social engineering chat scenarios and demonstrate its practical advantages in improving both accuracy and interpretability for real time fraud detection. To contextualize the trade offs, we compare our modular approach against a Dual LLM baseline that performs detection and judgment using different language models.

cs.CL↗
arXiv2026

Structure of the Cayley-Dickson algebras

Viewing the Cayley-Dickson process as a graded construction provides a rigorous definition of associativity consisting of three classes, which divides the non-associative parts into four types. These simplify the Moufang loop identities and Malcev's identity and categorise non-associative loops. Analysing the non-associativity structure of sedenions and higher level Cayley-Dickson algebras uncovers octonion and three quasi-octonion, power-associative subalgebras. Power-associativity is proved to grow by multiples of seven that introduce zero divisors in factors of 84 for all Cayley-Dickson algebras. It is convenient to replace the terminology hypercomplex numbers with ultracomplex numbers to capture the quasi-algebras and since sedenions and higher level Cayley-Dickson algebras contain quasi-algebras these are ultracomplex. The non-associative types reduce the 84 zero divisors in sedenions via three cycles and four modes down to seven primary zero divisor pairs providing new techniques to analyse the seven quasi-octonions loops in sedenions. The graded notation allows the eight octonion and seven quasi-octonion subalgebras of sedenions to be uniquely derived, up to representation. The zero divisors for split sedenion algebras are analysed and mappings between three of these are provided showing 180 zero divisors and the other split algebra is analogous to sedenions with 84 zero divisors. These split algebras are shown to involve quasi-octonion algebras with mixed signature.

math.RA↗
arXiv2026

Towards Functional Correctness of Code Models with Selective Generation

The hallucination of code generation models hinders their applicability to systems requiring higher safety standards. One critical bottleneck in addressing code hallucination is the difficulty of identifying the functional correctness of generated code, due to its unnatural form. We address this core bottleneck by automatically generating unit tests using dynamic code analysis tools, leveraging the \emph{executable nature} of code. Accordingly, we propose a \emph{selective code generator} that abstains from uncertain generations -- based on the functional correctness evaluated by generated unit tests -- to theoretically control the correctness among non-abstained answers, \ie the false discovery rate. Finally, we propose to use generated unit tests in evaluation as well as in learning for precise code evaluation, calling this paradigm \emph{FuzzEval}. We demonstrate the efficacy of our method along with the controllability of code hallucination and reasonable selection efficiency.

cs.SE↗