Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Tuesday 29 September

Computer Vision

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Cong Wei, Xuanchi Ren, Bryan Chu et al. (+8 more)

Unified Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, increasing visual context length and complicating integration with established vision-language pretraining pipelines. Recent advances in pixel-space modeling offer an encoder-free alternative, but extending this paradigm from images to videos is non-trivial: video understanding and generation adopt different temporal representations, leaving the design of a unified visual interface an open question. We present PixelUMM, an encoder-free model for unified image and video understanding and generation directly in pixel space. PixelUMM represents images as spatial patches and videos as spatiotemporal tubelets, connecting raw pixels to a shared multimodal backbone through single-layer linear projections. Its Mixture-of-Transformers architecture combines shared attention with task-specific parameters and extends clean-pixel prediction to video generation, jointly supporting autoregressive text prediction and pixel-space flow matching. Experiments show that PixelUMM achieves competitive performance across image and video understanding and generation tasks. We further conduct empirical studies of key design choices, including decoder design and spatial-temporal patch size, providing insights for future pixel-space unified multimodal models.
Read the full abstract

All authors Cong Wei, Xuanchi Ren, Bryan Chu, Weiming Ren, Huan Ling, Jiahui Huang, Laura Leal-Taixé, Sanja Fidler, Wenhu Chen, Zian Wang, Jay Zhangjie Wu

Operator Algebras

$\mathcal{Z}$-stable and selfless inclusions for the infinite braid group

Tron Omland

Let $B_\infty$ be the braid group on infinitely many strands and $P_\infty$ its pure braid group. We show that $C^*_r(P_\infty)\subseteq C^*_r(B_\infty)$ and all its intermediate inclusions are $\mathcal{Z}$-stable and completely selfless. This gives natural examples of simple nonnuclear $\mathcal{Z}$-stable $C^*$-algebras. Further examples come from $\mathrm{SL}_\infty(\mathbb{Z})$ and $\mathrm{GL}_\infty(\mathbb{Z})$. We also show that $C^*_r(\mathbb{F}_\infty)\subseteq C^*_r(B_\infty)$ is completely selfless for the free group $\mathbb{F}_\infty$ of braids in which only the first strand moves. All results hold for twisted group $C^*$-algebras. In contrast, $\mathcal{Z}$-stability fails for $B_n$ with $n$ finite and for groups that are not inner amenable.
Read the full abstract

Differential Geometry

Compact multi-monopole moduli spaces on Kähler surfaces

Ollie Thakar

We consider the multi-spinor Seiberg-Witten equations on a 4-manifold in a general setting, where we allow the auxiliary bundle to be non-trivial. We show that when the metric is Kähler and the auxiliary connection is unobstructed anti-self-dual Yang-Mills, the moduli space of solutions is compact for all parameters in some open neighborhood of the given metric and auxiliary connection. We use this fact to compute a count of solutions on some examples of Kähler surfaces. These computations have a surprising purely algebro-geometric corollary which may be of independent interest.
Read the full abstract

Robotics

FAST-Sync: Fast Group Synchronization for any Matrix Lie Group

Shane Holmes, Yiran Luo, Firat Taxpulat et al. (+2 more)

Group synchronization (GS) is the problem of estimating a set of $N$ unknown elements $g_1,\ldots, g_N \in \mathcal{G}$ in a group $\mathcal{G}$, given noisy measurements of a subset of their pairwise ratios $g_i^{-1} g_j$. GS problems lie at the core of many state estimation tasks in robotics and computer vision, including 3D vision, robotic mapping, inertial navigation, and molecular reconstruction. Unfortunately, GS problems are typically both high-dimensional and non-convex, and therefore hard to solve in general. In this paper, we present Fast-Sync, a fast linear approximation method for GS that is suitable for initializing local manifold-based optimizers or certifiable global methods. Our approach generalizes chordal initialization to arbitrary matrix Lie groups, and additionally proposes two new key algorithmic enhancements: we show how to exploit both the Kronecker-product structure in the problem data matrix and the topology of the synchronization graph to improve speed, scalability, and accuracy. Experimental evaluation across several GS tasks demonstrates that Fast-Sync provides high-quality initializations that enable local optimizers to efficiently recover globally optimal GS solutions, achieving high success rates even with considerable measurement noise.
Read the full abstract

All authors Shane Holmes, Yiran Luo, Firat Taxpulat, David M. Rosen, Frank Dellaert

Computation and Language

Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions

Bo Ni, Li Li, Ryan A. Rossi et al. (+2 more)

Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incorporating relevant procedural and domain knowledge. Expert-authored skills are expensive to produce, and the resulting artifacts are not optimized for the specific model that consumes them, whose failure modes can vary with version, scale and training. In addition, emerging tasks may fall outside the scope of existing skill libraries, creating a need to develop new skills before curated training data become available. Recent works have explored automated skill optimization through reflection, but they require a curated, in-distribution training set, which users might not always have. To address these limitations, we present Prompt2Skill, a framework that builds skills from natural-language task description alone. From the prompt, the system derives a task specification, discovers or synthesizes datasets, and refines the skill in a closed loop of reflective editing. Across four domains spanning question answering, reading comprehension, spreadsheet manipulation, and mathematical reasoning, Prompt2Skill consistently outperforms the direct prompting baseline, achieving an average improvement of 10.8 across open-source and frontier models.
Read the full abstract

All authors Bo Ni, Li Li, Ryan A. Rossi, Franck Dernoncourt, Tyler Derr

Computer Vision

StereoGaussians: Feed-Forward 3D Gaussian Splatting from Stereo Images

Boyuan Tian, Huangying Zhan, Zhan Li et al. (+4 more)

Feed-forward 3D Gaussian Splatting (3DGS) enables reconstruction without per- scene optimisation, but practical stereo-camera applications require nearby-view extrapolation beyond the input views. Stereo depth anchors visible surfaces, yet rendering newly exposed regions also requires learned appearance and additional scene capacity. We introduce StereoGaussians, which predicts a metric 3DGS representation from a single calibrated stereo pair. It reuses intermediate repre- sentations from frozen pretrained stereo networks to predict Gaussian attributes, while calibrated disparity anchors the geometry. A second Gaussian layer and an expanded image canvas provide capacity for disoccluded and outside-field-of- view content. For training, we construct SceneSplat-Stereo from quality-filtered 3DGS teachers, pairing stereo inputs with nearby target views across 803 training scenes. Experiments on unseen real and photorealistic stereo benchmarks demon- strate improvements over strong view-synthesis baselines, while ablation studies support our main design choices.
Read the full abstract

All authors Boyuan Tian, Huangying Zhan, Zhan Li, Shin-Fang Chng, Hanwen Yang, Zirui Wang, Yi Xu

Computer Vision

Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients

Xin Feng, Jin Zhao, Yizhen Zhang et al. (+3 more)

Adapting image restoration models to a stream of new tasks without revisiting past data remains challenging due to catastrophic forgetting. In this work, we propose Restoring without Forgetting (RwF), a filter-level continual adaptation framework for image restoration built upon a critical observation: task-specific knowledge is centered in a small subset of filters and can be separated from those reconstructing general content. RwF first performs parameter-space integrated gradients attribution to localize degradation-critical filters in a coarse-to-fine manner. It then adapts to new tasks by generating task-specific filters from a filter bank using compact factorized low-rank transformations, further augmented with cross-task attention and prototypical contrastive learning, and lastly assembles them back only at localized positions. Experiments on six restoration tasks show that RwF effectively avoids forgetting and achieves competitive restoration quality against all-in-one methods that have full data access, and outperforms LoRA-style adaptation with $\sim$10$\times$ fewer additional parameters. Code is available at https://github.com/funkdub/Restoring-without-Forgetting.
Read the full abstract

All authors Xin Feng, Jin Zhao, Yizhen Zhang, Wenjie Pei, Fanglin Chen, Guangming Lu

High Energy Astrophysical Phenomena

Chandra X-ray Spectral Evidence of the Dual AGN Nature of the Gravitational lens MG B2016+112 at z=3.273 with 175 pc separation

Daniel A. Schwartz, Julia M. Sisk-Reynes and Anna Barnacka

We use a new 175 ks Chandra X-ray observation of the z=3.273 radio-loud gravitational lens system MG B2016+112 to present definitive X-ray spectral evidence that it contains a dual active galactic nucleus (AGN). With a projected separation of 175 parsecs, this is the tightest separation confirmed AGN pair at high redshift. Prior multi-epoch very long baseline interferometry (VLBI) and archival Chandra data had revealed two distinct emitters, but could not rule out a single AGN with a complex, highly magnified jet. Our new Chandra observations allow a separate spectral analysis of each source. We find strong intrinsic absorption (N_H > 4 x 10^22 cm^-2, 3 sigma confidence) at the source redshift for the highly magnified source inside the caustic. This identifies it as an obscured AGN. In addition to the previously known type II AGN outside the caustic, this confirms a compact dual AGN system in MG B2016+112. On-going and future surveys using facilities such as Euclid, SKA, and the Rubin and Roman observatories will uncover more such systems, probing SMBH evolution and gravitational wave precursors.
Read the full abstract

Human-Computer Interaction

C-LISTEN: Cognitive Load Impacts of Sensory-Triggered Environmental Navigation in Virtual Reality

Md. Monowar Hossain and M. Rasel Mahmud

Nowadays, Virtual Reality (VR) systems are more helpful for making decisions, training, and rehabilitation. Multimodal settings in these systems impose a significant balance and cognitive difficulties. Additionally, decreased performance, higher cognitive load, user overwhelm, and limited accessibility of VR technology can be caused by excessive auditory, visual, and sensory stimulation. In our pilot study, we examine the strategic design of directional auditory cues to improve cognitive load and enhance user experience in virtual environments. This research also enhances fundamental knowledge that auditory feedback reduces cognitive load in VR, with statistical analysis confirming this improvement (p = .0011). This study investigates how postural balance and pupil diameter correlate with cognitive load while the users navigate. Moreover, this study provides realistic overview design guidelines for accessibility, which will make VR experiences safer and more useful for everyone, including people with cognitive impairments.
Read the full abstract

Robotics

Drone Soccer: Learning to Manipulate with Multicopter Downwash

Neelay Joglekar, Bavin Saravanan, Yutong Wang et al. (+3 more)

Although multicopter drones are traditionally designed for "perception-only" tasks, like mapping and exploration, recent work has sought to develop Unmanned Aerial Manipulators (UAMs) to solve mobile manipulation tasks. Aerial manipulation performance can be impacted by "downwash," the airflow produced by propellers, but current state-of-the-art UAMs either ignore downwash or treat it as a disturbance. Instead, is it possible to actively use downwash as a tool during manipulation? We design a drone soccer task to explore the feasibility of downwash-based manipulation. Specifically, we develop a simplified downwash dynamics model which we use to train an RL policy to dribble a soccer ball. We further demonstrate that our policy transfers to real world deployment. This work provides key insights into novel manipulation capabilities for multicopters.
Read the full abstract

All authors Neelay Joglekar, Bavin Saravanan, Yutong Wang, Varun Kandiyappan, Junyi Geng, Sebastian Scherer

Machine Learning

NeurDuo-EEG: A Long-Sequence EEG Foundation Model with Persistent State and Explicit Memory

Yifan Wang, Haiping Liu, Yang Cui et al. (+13 more)

Electroencephalography (EEG) is recorded continuously over hours, with relevant dynamics spanning timescales from milliseconds to hours. Most EEG foundation models nevertheless process fixed windows independently, limiting their ability to capture information encoded in long-timescale dynamics. State-space architectures enable persistent recurrent processing, but long-range information remains implicitly compressed in recurrent states. We present NeurDuo-EEG, a causal EEG foundation model with channel-resolved persistent memory. NeurDuo-EEG introduces multi-timescale memory management with learned consolidation and selective retrieval, enabling persistent modelling of continuous EEG with fixed-size state. It is pre-trained on 3,955 hours of EEG from 17 public datasets using multichannel autoregressive prediction of discrete spectral codes. Across three short-window and two long-sequence downstream tasks, NeurDuo-EEG achieves the best performance on four of five benchmarks, including all three short-window tasks and seizure detection, where AUC-PR improves from $0.285$ to $0.471$ over the strongest non-NeurDuo baseline. NeurDuo-EEG also remains competitive on sleep staging and supports efficient streaming inference, with nearly constant per-chunk latency as the available history grows to one hour. Notably, the Small variant achieves this with only 4.7M backbone parameters. These results demonstrate the value of persistent, multi-timescale modelling for both long-sequence and short-window EEG analysis. Our code is available at https://github.com/YifaNNW/NeurDuo-EEG.
Read the full abstract

All authors Yifan Wang, Haiping Liu, Yang Cui, Wenhao Cai, Shuhang Li, Xiaoyang Huang, Xianyang Liu, Jingyu Sun, Yizheng Sun, Cunhang Fan, Tianming Du, Jiancheng Yang, Zhenhong Li, Yunhao Zhang, Hongpeng Zhou, Jingyuan Sun

Statistical Methodology

Fraud Detection via Bayesian Positive-Unlabeled Learning with Gaussian Processes and Multilayer Networks

Konstantinos Bourazas, Angelos Alexopoulos, Petros Dellaportas et al. (+1 more)

Tax fraud remains a central challenge for public revenue authorities worldwide, imposing fiscal losses estimated to reach up to 1 trillion euros annually in the EU alone. Fraudulent firms intentionally manipulate reported figures to conceal their activity. Business networks can provide complementary information and reveal fraud that covariates alone may miss. We propose a Bayesian positive-unlabeled (PU) classification framework that combines firm-level covariates with multilayer network information. As a policy relevant case study, we apply the framework to firms in a regulated segment of the Greek energy market, a sector exposed to excise tax evasion. Confirmed fraud labels exist only for audited cases, while the remaining observations are unlabeled rather than verified compliant. We develop a Bayesian Gaussian process (GP) classifier integrating covariates with multilayer network information through a Product of Experts (PoE) construction and incorporating a nondetection probability for missed positives. We derive identification bounds for the nondetection rate under an anchor condition and show that, for a fixed latent risk function, a common nondetection rate affects calibration but not ranking. Simulations show strong ranking performance relative to PU and network-based alternatives, while illustrating the difficulty of estimating the nondetection rate. In real audit data, the method identifies high risk firms with posterior uncertainty, estimates the number of undetected fraudulent cases, and identifies whether risk is driven by covariates, networks, or both. Of the six highest ranked firms, the two that had already been reinspected independently were both confirmed as noncompliant, providing an independent validation of these cases. The remaining four were selected by the tax authority for follow-up inspection.
Read the full abstract

All authors Konstantinos Bourazas, Angelos Alexopoulos, Petros Dellaportas, Konstantinos Kalogeropoulos

Machine Learning

FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing

Wang Wei, Harry Yang, Tiankai Yang et al. (+6 more)

Existing Large Language Model (LLM) routing methods score LLMs independently to select top-$k$ models. However, this ignores model correlations and enforces a rigid computational budget. Consequently, routers often select redundant models that share failure modes, limiting the overall probability of success. To address this, we propose FlexRouter, a routing framework that explicitly models model complementarity. FlexRouter optimizes for answer coverage, maximizing the probability that at least one selected model yields a correct response. This objective aligns with practical inference pipelines where multiple candidate outputs are generated and a downstream verifier or user selects the final one. We formulate routing as a coverage-oriented subset selection problem and model the routing policy using Determinantal Point Processes (DPPs), which naturally capture both model competence and redundancy. To directly optimize coverage without requiring a ground-truth target subset, we introduce a training objective based on marginalizing over failure sets. During inference, we employ a greedy strategy based on marginal log-determinant gains, enabling the router to adaptively determine subset sizes without a predefined budget. Extensive experiments on the large-scale RouterEval benchmark demonstrate that our proposed FlexRouter achieves higher coverage with lower redundancy across both in-domain and out-of-domain tasks than strong baselines while maintaining flexible inference cost.
Read the full abstract

All authors Wang Wei, Harry Yang, Tiankai Yang, Samyadeep Basu, Hongjie Chen, Andy Zhao, Franck Dernoncourt, Ryan A. Rossi, Hoda Eldardiry

Analysis of PDEs

Non Existence of the Stable 2D Boussinesq Equations in $H^2$ via Density-Vorticity Feedback

Roberta Bianchini and Luis Martínez-Zoroa

We establish instantaneous $H^2$ norm explosion for the two-dimensional Boussinesq equations around the linearly stable background profile $-x_2$. While previous ill-posedness results for this system relied on $L^\infty$-type spaces, this work provides the first strong ill-posedness result in the energy-critical space, where stable background stratification acts to suppress deformation growth. We adapt an idea from our previous work on the IPM equation \cite{BCMZ2025} and select an initial density perturbation vanishing near the origin to neutralize the stable stratification. Crucially, unlike the IPM setting, the evolution is here driven by the non-linear coupling between density and vorticity. Since the initial vorticity vanishes identically, the instantaneous loss of regulari\-ty is driven by density-vorticity feedback - a mechanism fundamentally distinct from both $H^1$ Euler ill-posedness of Bourgain & Li and the IPM evolution. Through an iterative scheme yielding a sequence of approximations with strong deformation at the origin, we construct a strong solution $(\rho (t), \omega (t))$ originating from data with arbitrarily small $H^2 \times (H^1\cap \dot H^{-1})$ norm, which immediately exhibits $H^2 \times H^1$ norm explosion for all $t > 0$ while maintaining uniqueness within the energy class.
Read the full abstract

Probability

Martingale and analytic dimensions

Sylvester Eriksson-Bique and Mathav Murugan

These notes introduce the martingale dimension of a strongly local regular Dirichlet form and the analytic dimension of a Lipschitz differentiability space. We explain why these dimensions coincide under two-sided Gaussian heat kernel estimates and discuss their relationships with other notions of dimension. We also introduce the energy image density property, its recent resolution, and its applications to martingale dimension. Finally, we show that spaces carrying diffusions with two-sided sub-Gaussian heat kernel estimates of walk dimension greater than two are not Lipschitz differentiability spaces.
Read the full abstract

Statistical Methodology

A tree-based scan statistic for database studies with time-to-event outcomes

Massimiliano Russo, Georg Hahn, Krista F. Huybrechts et al. (+1 more)

Tree-based scan statistics (TBSSs) are machine learning methods for disproportionality analyses. They simultaneously scan for thousands of hierarchically related health outcomes to detect potential signals of harm from drugs and vaccines, controlling for multiplicity. TBSSs have been extensively used to mine insurance claims databases to detect potential drug adverse events. Current TBSS implementations do not allow comparative safety evaluations with time-to-event outcomes. Explicitly accounting for event timing in analyses can improve power to detect signals compared to methods that use only event counts. We propose three TBSS methods that explicitly leverage event timing to detect potentially harmful effects of drugs. The first assumes proportional hazard rates for each node of the outcome hierarchy and uses a permutation scheme for inference. The second builds on exponential survival models for the terminal nodes of the hierarchy, assuming constant hazard rates at each node, and uses a parametric bootstrap for inference. The third uses robust asymptotic approximations of the hazard rates in connection with an approximate parametric bootstrap. We compare the proposed methods with standard event count based TBSSs in simulation scenarios. Finally, we present results from a database study comparing two glucose-lowering medications among adults with type 2 diabetes.
Read the full abstract

All authors Massimiliano Russo, Georg Hahn, Krista F. Huybrechts, Shirley V. Wang

Strongly Correlated Electrons

Theory of criticality-enabled $U(1)$ symmetry breaking in a class of 1+1D systems

E. S. Andriyakhina, A. S. Shankar, T. Senthil et al. (+1 more)

We develop an analytic theory of the recently proposed $U(1)$ symmetry breaking at interacting 1+1D Lifshitz quantum critical points. The low-energy theory contains two compact fields, $\theta$ and $\phi$, coupled by a Berry term that makes $\theta$ canonically conjugate to the conserved density $\partial_x\phi$. Within a controlled large-$N$ limit, we establish long-range order (LRO) of $e^{i\beta\theta}$ and stretched-exponential decay of the conjugate vertex, $\log\langle e^{i\beta\phi(x)}e^{-i\beta\phi(0)}\rangle\propto-|\beta|^{4/3}|x|^{2/3}$. Beyond large $N$, we argue that $U(1)$ LRO follows if the dynamical exponent satisfies $z\neq1$, consistent with existing calculations. Using finite-size and infinite-system DMRG, we study an itinerant-electron chain with $U(1)\rtimes\mathbb{Z}_2$ symmetry, whose spin sector realizes this theory at a ferromagnetic quantum critical point. We find spin-nematic LRO in $S_i^+S_{i+1}^+$ and stretched-exponential electron Green's functions, revealing distinctive non-Gaussian signatures of criticality-enabled order.
Read the full abstract

All authors E. S. Andriyakhina, A. S. Shankar, T. Senthil, Z. D. Shi

Quantum Physics

Algebraic Characterization of Biphoton Spatial-Mode Entanglement in Higher-Order Laguerre–Gaussian-Pumped SPDC

Takumi Jinushi and Hirokazu Kobayashi

High-dimensional spatial entanglement generated via spontaneous parametric down-conversion (SPDC) provides a powerful resource for quantum information processing, yet its mode structure becomes increasingly complex when the pump occupies a higher-order Laguerre–Gaussian (LG) mode. Here, we develop an algebraic framework for characterizing biphoton spatial-mode entanglement by factorizing LG-pumped SPDC into a spatial-mode beam-splitter transformation followed by spatial two-mode squeezing. By choosing the biphoton LG basis radius as the geometric mean of the pump-beam radius and the crystal-induced correlation width, we obtain a natural modal basis in which the two operations can be treated separately. When the pump-beam radius matches the correlation width, spatial squeezing vanishes, and the two circular-mode components of the pump are independently conserved across the signal and idler photons, leading to conservation of both orbital angular momentum and the total spatial mode number. We further derive an analytical expression for the Schmidt number for arbitrary LG pump modes and squeezing strengths, revealing how the radial and azimuthal pump indices govern the dimensionality of the spatial entanglement. This algebraic characterization provides a unified description of the mode structure, conservation laws, and entanglement dimensionality of higher-order-LG-pumped SPDC.
Read the full abstract

Nuclear Theory

Effective Contact Theory for Exotic Loosely Bound States in Strongly Interacting Expanding Matter

Xiaofeng Wang, Zebo Tang, Zhangbu Xu et al. (+2 more)

Short-distance correlations generate universal relations that can be independent of microscopic details. Tan's contact is a prominent example, connecting close pairs, high-momentum constituents, and bound-state formation across atomic, condensed-matter, and nuclear systems. Whether an analogous universality governs the nonequilibrium freeze-out of relativistic QCD matter is an open question. We develop an effective contact theory that relates the production of loosely bound states to continuum two-particle correlations in heavy-ion collisions. The construction replaces the hard relative-momentum cutoff of conventional coalescence by a regulated Bethe–Peierls kernel: freeze-out localization fixes its momentum scale, while the composite yield fixes its contact residue. Bound and continuum observables then become projections of a common two-particle density matrix rather than independent phenomena. Coulomb-bound $K\mu$ atoms provide an ideal realization because their atomic, production, and source scales are widely separated. A contact-theory analysis of STAR $d\Lambda$ correlations supplies a first bound–continuum consistency test and demonstrates how inferred near-threshold parameters can depend on the finite expanding source. The framework establishes a general strategy for relating coalescence, correlations, and exotic bound states in strongly interacting expanding matter.
Read the full abstract

All authors Xiaofeng Wang, Zebo Tang, Zhangbu Xu, Chi Yang, Wangmei Zha

Computer Vision

Retargeting Motions to Diverse Skeletons via Learnable Flattening

Kia-Jüng Yang, Fabian H. Sinz and Paweł A. Pierzchlewicz

Cross-structural motion retargeting aims to transfer motion between different skeletal topologies. Despite recent progress, existing state-of-the-art models struggle with reliability in zero-shot settings, i.e. skeletons with different topologies which were unseen during training, and recent Transformer-based attempts have failed to outperform specialized geometric methods. We bridge this gap with a Transformer Autoencoder that learns a topology- and translation-invariant latent space. Our core contribution is a learnable flattening of skeletal graphs that captures both local dependencies and global structure. Unlike the standard transformer architecture, which adds positional information to token content, we integrate graph-based positional encodings multiplicatively, a design choice that follows directly from our flattening formulation. The resulting model handles diverse skeletal topologies within a single unified architecture and trains in a fully unsupervised manner, requiring no paired retargeting data. Ablation studies show, that the graph encodings, multiplicative formulation, and Transformer backbone is critical for the performance. In zero-shot evaluations, our method reduces global joint position error by $43-47\%$ over current benchmarks. A user study ($n = 37$), including expert animators, further ranks our approach highest in motion alignment and physical plausibility ($p < 0.05$). These results demonstrate that our model design is key to making transformer architectures effective for motion retargeting, outperforming existing approaches.
Read the full abstract

Artificial Intelligence

Conditional Generation of Creative Chess Puzzles with Diffusion Models

Aatu Selkee, Severi Rissanen, Xidong Feng et al. (+2 more)

While modern language models demonstrate impressive generative capabilities, they often struggle with constrained, counter-intuitive creative tasks. To address this limitation, we explore chess puzzle generation as a rigorous testbed for computational creativity and reasoning, a domain where altering a single piece can invalidate an entire solution. We propose a novel approach for conditional generation of creative chess puzzles using masked diffusion models. Unlike previous methods, our non-directional diffusion approach allows for conditioning on specific tactical themes and partial board positions. We introduce a novel auxiliary task of simultaneous best-move prediction, which improves solution uniqueness by 11.6% and theme-conditioning accuracy by 2.5%. To further optimize solution uniqueness and theme conditioning, we establish a reinforcement learning framework adapted from Denoising Diffusion Policy Optimization (DDPO). This RL training increases the yield of unique and theme-matching positions by 89.1%. Finally, we release the first open-weights models (Appendix B) for chess puzzle generation, offering a new pathway for controllable, creative generation.
Read the full abstract

All authors Aatu Selkee, Severi Rissanen, Xidong Feng, Tom Zahavy, Eric Malmi

Quantum Physics

Normal-ordered perturbative expansion for matter systems interacting with continuous-mode quantum photon fields

Liwen Ko, Robert L. Cook and K. Birgitta Whaley

We develop a normal-ordered perturbative expansion method to compute the reduced dynamics of a matter system interacting with a general continuous-mode photon field state. In this expansion, all field correlation functions are automatically normal-ordered, while the free evolution is modified by spontaneous emission. Our normal-ordered expansion elucidates the physical meaning of non-normal-ordered correlation terms in the conventional expansion. Furthermore, under intermediate coupling strengths, the normal-ordered expansion converges significantly faster than the conventional expansion, allowing one to extend the applicability of perturbative expansion to much larger matter-light coupling strengths. Interestingly, given an $m$-photon Fock state input, the normal-ordered expansion truncates exactly at the $2m$-th order. For special classes of input states, we show the normal-ordered expansion is consistent with the corresponding master equations. We demonstrate the normal-ordered expansion numerically for a two-level system interacting with coherent state, $m$-photon Fock state, and cat state inputs.
Read the full abstract

Solar and Stellar Astrophysics

Sunrise III/SUSI reveals extended and spectrally structured Ca II K emission above the solar limb

Ivan Milić, Christopher M. J. Osborne, Francisco A. Iglesias et al. (+32 more)

The Sunrise III/SUSI instrument performed a sit-and-stare observation of the off-limb emission in the Ca II K line core, with a combination of excellent temporal and spectral resolution. The emission reaches up to 6 Mm above the solar limb, indicating the existence of off-limb structures akin to spicules. In this letter, we describe the spatio-spectral properties of the observed emission, focusing on the spectral line shape resolved in detail by Sunrise III/SUSI, and compare the observation with simple modeling that relies on a numerical simulation of the solar chromosphere. We find that the simulation contains enough cool and dense material at Mm heights to produce off-limb emission, but that the spectral width of these features is slightly lower than observed, necessitating more detailed modeling.
Read the full abstract

All authors Ivan Milić, Christopher M. J. Osborne, Francisco A. Iglesias, Juan Sebastián Castellanos Durán, Damien F. Przybylski, Lakshmi Pradeep Chitta, Sanghita Chandra, Andreas Lagg, Sami K. Solanki, Tino L. Riethmüller, Achim Gandorfer, Alex Feller, Johannes Hoelken, H. N. Smitha, Jose Carlos del Toro Iniesta, Yukio Katsukawa, Pietro Bernasconi, Thomas Berkefeld, Alberto Álvarez-Herrero, Masahito Kubo, Valentín Martínez Pillet, David Orozco Suárez, Bianca Grauf, Michael Carpenter, Alexander Bell, Hanna Strecker, Azaymi L. Siu-Tapia, Pablo Santamarina Guerrero, Julian Blanco Rodríguez, Yusuke Kawabata, Takuma Matsumoto, Ryohtaroh T. Ishikawa, Edvarda Harnes, Takayoshi Oba, Dušan Vukadinović

Artificial Intelligence

Towards Model as a Library: Offline, Community-Sourced AI for Low-Resource African Languages

Fendji K. E. Jean Louis

Large language models are frequently proposed as a route to AI-powered services for African communities, but they are least reliable exactly where the need is greatest: all African languages remain low-resource by any standard measure, and models trained on scraped, standardised text systematically misrepresent the dialectal and regional variation of how people actually speak. We introduce Model as a Library (MaaL), a software architecture that packages small, community-enrolled speech models as versioned on-device dependencies, enabling offline structured data collection that cannot generatively hallucinate, for populations that current language models serve worst. Rather than relying on web-scraped corpora, MaaL's vocabulary is enrolled directly from a small number of example recordings by the speakers themselves, at the point of deployment. We describe the architecture and its central mechanism - keyword spotting that turns a closed-vocabulary text form into a voice form, filled and submitted entirely on-device - and propose transpiling the closed-vocabulary elements already present in widely-deployed digital form tools into MaaL schemas, a low-friction path to voice-first, offline data collection for the low-literacy populations these tools already reach. This is a position and system-design paper: we describe the concept, the mechanism, and an analytical feasibility case, and identify what a working implementation still requires.
Read the full abstract

High Energy Astrophysical Phenomena

Angular structure of finite-field vacuum birefringence in magnetars

Shahram Abbassi and S. R. Valluri

Vacuum birefringence in a strong magnetic field is often modelled by combining the finite-field splitting for perpendicular propagation with the familiar $\sin^2\theta$ angular factor. That separation is exact only at leading response order. Continuing our previous study of the field-strength dependence of the birefringence, we examine the angular dependence of the full one-loop refractive indices in the local Heisenberg–Euler theory. We show analytically that, on the positive-birefringence branch, the usual factorized form systematically overestimates the exact splitting away from perpendicular propagation. The relative correction is largest close to the magnetic-field direction, where the absolute birefringence itself vanishes. Compact analytic expansions expose the sign, scaling, and angular location of the correction throughout the magnetar-relevant range $B/B_{\rm cr}\le100$, while an independent proper-time calculation verifies the underlying one-loop coefficients. In centred-dipole applications the correction is sub-percent for moderate magnetar fields but reaches several percent for the strongest sources; surface averaging and radial phase accumulation reduce its physical weight as the field decreases away from the stellar surface. The result separates finite-field amplitude and angular corrections and provides controlled analytic benchmarks for precision polarization transport in strongly magnetized environments.
Read the full abstract

Algebraic Geometry

Finite automorphism groups of hypersurfaces via Bott vanishing

Dominic Bunnett and Caroline Namanya

We give a cohomological criterion for the automorphism group scheme of a hypersurface in a smooth Deligne-Mumford stack to be discrete in tame characteristics. The criterion converts Bott-type vanishing on the ambient stack into vanishing of infinitesimal automorphisms of every quasismooth hypersurface in a linear system. We apply it to toric orbifolds, obtain uniform finiteness results for quasismooth weighted-projective hypersurfaces in tame characteristic and hypersurfaces in products of projective spaces, and identify the precise exceptional windows in which the method fails.
Read the full abstract

Computers and Society

Drowning in AI Slop: How Social Media Platforms (Do Not) Label AI and Deepfake Content under EU law

Bram Rijsbosch, Luka Bekavac, Henry Tari et al. (+2 more)

AI labels are emerging as a primary safeguard for transparency about AI-generated content on social media, including under the EU Digital Services Act and AI Act. Yet, limited systematic evidence exists on how platforms implement such labels in practice. We conduct a legally grounded audit of AI labelling across Instagram, TikTok, X, and YouTube, drawing on the European Commission's July 2026 guidelines on deepfakes. To this end, we analyse platform policies and detection approaches, 10,722 posts collected via systemic-risk and AI-related keywords, an expert-annotated subset of 500 posts, and controlled uploads to the four platforms of outputs from ten popular generative AI tools. We find that AI labelling is now broadly established. All four platforms apply labels automatically and a greater share of labels are platform-applied than in earlier audits. However, coverage remains incomplete where labelling arguably matters most: only 33% of expert-identified deepfakes in systemic risk contexts carried a platform-applied AI label, while reaching a median of 160,000 views. In controlled uploads of AI-generated content carrying standard AI provenance signals, platforms labelled only 61% of uploads, and commonly strip those signals after uploading. Overall, platform rules, label designs, detection approaches, and reporting diverge substantially. In response, we identify concrete opportunities to improve the uptake, clarity and efficacy of AI labelling.
Read the full abstract

All authors Bram Rijsbosch, Luka Bekavac, Henry Tari, Gijs van Dijck, Konrad Kollnig

Robotics

Data-Efficient Adaptation of a Driving VLA to Class 8 Trucks

Satyajeet Das, Aaron Buxbaum, Niels Joubert et al. (+1 more)

Class 8 trucks differ from passenger cars in geometry, dynamics, and maneuvering requirements. As a result, vision-language-action (VLA) models trained for passenger vehicles do not readily transfer to Class 8 trucks, particularly in unstructured scenarios such as accident scenes and construction zones. Rather than training a truck-driving VLA from scratch, we propose an adapt-then-steer strategy that adapts an off-the-shelf VLA to generate trajectories for Class-8 trucks in these challenging scenarios. In the adapt stage, we use NVIDIA's Alpamayo 1.5 as the base model, fine-tuning only its action-generation stack on a few hundred real-world construction and accident-related highway scenarios. In the steer stage, we introduce Flow Velocity Steering (FVS) to further refine the model's predictions while holding the adapted VLA fixed. FVS is a compact, flow-time-conditioned residual module that adds learned corrections to the action-space flow velocity used to update the action sequence at each generation step. In open-loop evaluation on a scenario-disjoint held-out set, targeted fine-tuning more than halves single-candidate average displacement error (ADE) and final displacement error (FDE) over the entire 6.4 s horizon compared to the base model. Using the same targeted demonstrations, FVS further reduces the fine-tuned model's full-horizon ADE and FDE by 13.9% and 16.5%, respectively. At matched data budgets, targeted supervision yields 19-26% lower full-horizon ADE than general truck-driving supervision, while the targeted model remains competitive with a model fine-tuned on approximately 65 times as many general truck-driving scenarios. These results support adapt-then-steer for data-efficient vehicle-domain transfer to Class 8 trucks. Our project website is available at https://truckvla.github.io.
Read the full abstract

All authors Satyajeet Das, Aaron Buxbaum, Niels Joubert, Gaurav S. Sukhatme

Lattice Field Theory

MORE Thermal Gauge Theories at Finite $\theta$ and $\mu$ from Real-Time Quantum Simulation

Henry Lamm

Imaginary-time evolution can be reconstructed from real-time quantum simulations using exact integral transforms. We identify the construction of Guo, Shibu, Lin, and Zhao as a continuous linear combination of Hamiltonian simulations and show that its slow $1/t_{\rm cut}$ convergence arises from a redundant kernel component. We extend the construction from pure-state matrix elements to thermal traces and correlators. One real-time dataset then reconstructs targeted inverse temperatures, Euclidean separations, and chemical potentials through classical post-processing, bringing finite-$(T,\theta,\mu)$ physics within reach of real-time quantum simulation without thermal-state preparation. We benchmark the method on one- and two-flavor lattice Schwinger models, including circuit-level simulations with depolarizing noise.
Read the full abstract

General Relativity and Quantum Cosmology

Non-Metricity Trace Forms and Weak-Field Light Deflection: A Geometric Optical Formulation

Sabutay Ugur

This paper develops a weak-field, non-metric operational account of gravitational light deflection. In the isotropic formulation of the Schwarzschild weak field, the non-metricity trace 1-forms W and P are computed explicitly and shown to determine the optical response through the exact relation $d\ln n=W-4P$, $n=g/f$. Thus the effective refractive index governing null propagation is not introduced as an external optical analogy, but is tied directly to the trace sector of non-metricity. To connect the trace geometry with matter, an effective scalar calibration potential $\chi$ is sourced by an observer-projected macroscopic dilation current, yielding $\nabla^2\chi=-\kappa\rho$ in the static weak-field limit. The point-mass calibration fixes $\Phi=\chi/C_0\simeq 2GM/(rc^2)$, and the resulting optical calculation gives the Eddington deflection angle $4GM/(bc^2)$. The significance of the result is not a modified numerical prediction, but a closed weak-field chain from macroscopic dilation sourcing to non-metricity traces, effective refractive index, and light deflection, without postulating a microscopic deformation law for material rods or clocks.
Read the full abstract