Peer Revenue Impact factor: volatile

Papers

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

All of arXiv

Thursday 24 September

Materials Science

Molecular Beam Epitaxy of AgTaO3

Tobias Schwaigert, Joshua Maile, Olivia Peek et al. (+6 more)

We report the first synthesis of single-crystal AgTaO3 thin films using molecular-beam epitaxy (MBE). High-quality epitaxial AgTaO3 films were grown on both (001)- and (111)-oriented SrTiO3 substrates using sequential deposition of atomic silver and TaO2 layers under an ozone/oxygen atmosphere (80 % O3 + 20 % O2). X-ray diffrac- tion and reciprocal space mapping demonstrate that the films are coherently strained to the SrTiO3 substrates with sharp rocking curves comparable to the substrates, indicating high structural perfection. High-angle annular dark-field scanning trans- mission electron microscopy (HAADF-STEM) confirms coherent, low defect growth for (001)pc-oriented films. For (111)pc-oriented films, initial coherent growth proceeds up to 10 nm before transitioning into a Ta-rich surface region. Energy-dispersive X-ray spectroscopy (EDX) reveals a narrow cation intermixing region at the sub- strate interface for both orientations. This work demonstrates an effective synthesis route for single-crystal AgTaO3 thin films, providing a platform to investigate strain engineering and emergent interfacial properties in silver-based tantalates.
Read the full abstract

All authors Tobias Schwaigert, Joshua Maile, Olivia Peek, Eric Biedke, Paul T. Malinowski, Kyle M. Shen, Salva Salmani-Rezaie, Darrell G. Schlom, Kaveh Ahadi

Analysis of PDEs

Scattering below the ground state for the three-dimensional focusing energy-critical NLS

Qingtang Su and Zehua Zhao

We prove global well-posedness and scattering for the three-dimensional focusing energy-critical nonlinear Schrödinger equation with initial data below the ground-state energy and gradient thresholds. This extends the seminal result of Kenig and Merle (Invent. Math., 2006) to general data in $\dot H^1(\mathbb R^3)$. Classical concentration compactness and the exclusion of rapid frequency cascades reduce the problem to the quasi-soliton scenario. The main ingredient is a frequency-localized interaction Morawetz estimate based on an explicit convex weight whose time-dependent radius is determined implicitly by the mass density of the high-frequency component. The ground-state gap controls the focusing contribution with constants independent of the mass of this component. The radius is chosen to retain quartic spacetime control, while the continuity equation expresses the moving-radius contribution as a nonnegative square, up to frequency-truncation errors. We absorb these errors by closing the Morawetz estimate together with an auxiliary spacetime bound for the nonlinearity. The resulting quartic bound excludes the quasi-soliton scenario and completes the proof.
Read the full abstract

Machine Learning

To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech

Debajyoti Mazumder, Mamta and Abhirama Subramanyam Penamakuri

Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VeriSpeak, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VeriSpeak contains 3,879 spoken claims spanning temporal, geographical, and relational facts, with balanced true and false labels. The benchmark is designed to examine whether factual verification ability transfers from text to speech, and whether retrieval-augmented LALMs can use textual evidence to correctly support or refute spoken claims. Our experiments reveal a consistent text-speech modality gap: LALMs that verify written claims reliably often fail on the same claims when spoken. Moreover, retrieval alone provides limited gains because models frequently conflate retrieved evidence with the spoken claim. In contrast, retrieval combined with explicit reasoning improves claim-evidence comparison, with a thinking-tuned LALM reaching 86.1% accuracy. VeriSpeak highlights that effective speech misinformation detection requires not only speech understanding, but also grounded reasoning over retrieved evidence. The dataset is publicly available via Hugging Face at https://huggingface.co/datasets/abhiram4572/VeriSpeak.
Read the full abstract

Machine Learning

PoEM: Predicting RL Outcomes from Existing Policies

Kimia Hamidieh, Giannis Daras and Antonio Torralba

Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as helpfulness, correctness, or instruction following. This post-training process is computationally intensive, sometimes unstable, and has to be run from scratch every time the reward model changes or when we want to combine multiple rewards. We hence ask: given a new reward function, is it possible to predict the policy RL would produce without actually training on that reward? We answer this in the affirmative by introducing PoEM, a framework for predicting RL outcomes using models previously trained on other rewards. First, we build on the fact that if the new reward function can be written as a linear combination of existing ones, then the optimal policy can be expressed as a combination of the existing policies in log-probability space. Surprisingly, even in cases where the rewards are not linearly connected, we observe that policies learned through RL often span an approximately low-rank subspace across rewards. To our benefit, the weights for this combination can be estimated using only the reward or basis policy outputs on the samples. We turn these observations into an algorithm that takes post-trained models and a target reward function, and approximates the target RL policy without any additional RL training. We experimentally evaluate our approach across programmatic and learned rewards for open-ended generation, with additional experiments on math reasoning, tool calling, and image generation.
Read the full abstract

Quantum Physics

Variational Multi-Gaussian Quantum Trajectories

Zejian Li and Jacopo Tosca

We propose a variational framework for the efficient simulation of stochastic quantum dynamics in interacting bosonic systems. Our method generalizes the time-dependent variational principle to accommodate quantum state diffusion processes and is tailored for describing quantum trajectories unraveled from a master equation. We adopt a wavefunction ansatz composed of a coherent superposition of Gaussian wavepackets, which allows the fully analytical assembly of the variational equations of motion while capturing both the quantum trajectory dynamics and the Lindblad evolution beyond semiclassical approximations. The method is carefully benchmarked on a Bose-Hubbard dimer, and applied to extended Bose-Hubbard lattices in both 1D and 2D. In particular, we show the emergence of a symmetry-breaking phase transition in 2D lattices, which is absent in 1D chains.
Read the full abstract

Optics

Efficient simulation of millimeter-scale complex-modulated integrated Bragg gratings via hierarchical locally periodic eigenmode expansion

Rui Cheng, Jia Meng, Ping Yu et al. (+2 more)

We propose a structure-aware, hierarchical locally periodic eigenmode expansion (HLP-EME) framework for efficiently simulating millimeter-scale integrated Bragg gratings (IBGs) with complex modulation on silicon-on-insulator platforms. HLP-EME discretizes continuously varying grating parameter profiles into piecewise-constant blocks and exploits the resulting local periodicity of the physical grating structure by reusing the S-matrix of a representative period within each block. This strategy reduces full-device simulation times for millimeter-scale IBGs to a few minutes, providing a speedup exceeding three orders of magnitude over conventional 3D-FDTD simulations. The method accommodates diverse IBG configurations, including intra-mode gratings, mode-converting multimode gratings and grating-assisted contra-directional couplers. Experimental results validate the predicted reflection spectra of several complex-modulated IBGs and the reflection phase response of one representative design. The framework is further extended to curved waveguides and successfully captures curvature-induced spectral distortions in millimeter-long, Gaussian-apodized spiral IBGs. Combining full-vectorial modeling with high computational efficiency, HLP-EME provides a powerful tool for designing and optimizing long, complex IBG-based photonic devices.
Read the full abstract

All authors Rui Cheng, Jia Meng, Ping Yu, Jihao Wang, Zikun Xie

Computer Vision

BiCC: Bidirectional Connected-Component Loss for Instance-Aware Segmentation

Luc Bouteille, Frederic Jonske, Jens Kleesiek et al. (+1 more)

Common segmentation losses aggregate errors voxel-wise, so lesions influence the objective in proportion to their volume, giving small but clinically critical lesions disproportionately little weight. Instance-aware losses aim to address this mismatch by assigning each lesion its own term. However, blob loss and CC-DiceCE derive their regions solely from annotations, so false-positive components receive no instance-level term. This matters in computer-assisted review, where each false-positive component may require separate inspection, making precision and false-positive burden important alongside recall. We introduce the bidirectional connected-component loss (BiCC), which pairs annotation- and prediction-derived partitions to score predicted components on their own scale. By deriving instances from the predictions, this branch directly penalizes false-positive components regardless of their size. The balance parameter $\alpha$ allows control over the lesion-wise precision-recall trade-off. Across five datasets with five-fold cross-validation using nnU-Net, BiCC outperforms CC-DiceCE in lesion-wise F1 on four datasets and blob loss on all five. It significantly improves over DiceCE on three datasets and matches it on two; CC-DiceCE instead loses up to 0.363 precision by favoring recall. Code is available at https://github.com/TIO-IKIM/BiCC-Loss.
Read the full abstract

All authors Luc Bouteille, Frederic Jonske, Jens Kleesiek, Alexander Jaus

Computer Vision

TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations

Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta et al. (+5 more)

Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips. We introduce TrackEverything, a 3D point tracker that breaks this trade-off by representing videos as persistent 3D scene tracks in world coordinates. Grounded in the insight that videos are 2D projections of an underlying 3D world, TrackEverything decouples model complexity from video duration, allowing it to scale with unique physical scene geometry instead. Our approach introduces three key innovations. First, we employ a voxelization-based de-duplication mechanism at sliding-window boundaries to merge co-located tracks, preventing repeated observations of the same surface from redundantly accumulating. Second, we decompose tracking into an endpoint refiner that predicts each point's destination and static-versus-dynamic classification, followed by a lightweight trajectory refiner that decodes dense trajectories exclusively for dynamic points. Third, we propose 3D WAFT, replacing memory-prohibitive 4D correlation volumes with efficient feature sampling in the scene cloud. To the best of our knowledge, TrackEverything is the first 3D tracker capable of tracking all visible points across videos exceeding 1000 frames within 40 GB of GPU memory. On TAPVid-3D, TrackEverything outperforms all open-source all-frame dense 3D trackers by more than 20% APD on short clips, while remaining competitive with state-of-the-art sparse trackers on long sequences, despite tracking far more points.
Read the full abstract

All authors Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta, Fan Zhang, Tanner Schmidt, Jakob Engel, Katerina Fragkiadaki, Adam W. Harley

Computer Vision

WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation

Yubo Zhu, Yawen Shao, Ziyun Dai et al. (+27 more)

Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 seconds and faithfully follow complex conditions, the textual prompt largely directs the production, planning how actions, camera trajectories, lighting, and sound unfold across multi-shot sequences. In this paper, we present WanPE, a 397B-parameter prompt enhancement model trained on 1.05M real-world videos to master director-level cinematic planning. WanPE formulates shot-level cinematic plans via video-grounded reverse construction and employs Semantic-Consistency GRPO (SC-GRPO) to faithfully preserve user requirements across shots and over time. To benchmark this capability, we curate WanPEval, a human-annotated testbed covering durations from 5 to 30 seconds across varying intent granularities, supported by approximately 11K blind pairwise assessments. When powering Wan3.0's video generator, WanPE-397B boosts human preference over raw user prompts by 10.66-18.84 points at 5-15 seconds and by a dramatic 50.86 points in the 30-second arena. Ablation studies show that reverse construction demonstrates clear superiority over forward rewriting, while SC-GRPO robustly preserves semantic fidelity across model scales. Ultimately, WanPE leads all evaluated commercial offerings at 5-15 seconds and remains competitive with Seedance 2.5 at 30 seconds.
Read the full abstract

All authors Yubo Zhu, Yawen Shao, Ziyun Dai, Zixun Fang, Kai Zhu, Siyang Sun, Haolan Xue, Chuxin Wang, Tingyu Weng, Jingming Luo, Chen Shi, Lianghua Huang, Yufeng Ai, Yuzheng Wang, Wenyuan Zhang, Yu Shang, Yuxiang Bao, Zoubin Bi, Jie Xiao, Jinbo Xing, Jiaxing Zhao, Chongyang Zhong, Hengjian Chen, Chenwei Xie, Akide Liu, Zhehan Kan, Yu Liu, Wei Zhai, Sheng Zhong, Wei Tong

Optimization and Control

Riemannian Gradient Descent for Gaussian Mixture Models with unknown diagonal covariances

Romane Giard, Yohann De Castro, Roland Denis et al. (+1 more)

This paper investigates the numerical resolution of the Beurling-LASSO (BLASSO), a convex optimization framework that promotes sparsity in the space of measures. We consider its application to the estimation of Gaussian mixture models (GMMs) with an unknown number of components and unknown diagonal covariance matrices. Our approach combines the Conic Particle Gradient Descent (CPGD) principle with Riemannian gradient descent, to account for the underlying Fisher-Rao geometry of Gaussian distributions. Our contributions are twofold. First, we provide theoretical guarantees for the convergence of our algorithm. In particular, we establish exponential local convergence under a non-degeneracy condition on the solution and relate this assumption to a separation condition on the underlying statistical target. Second, we address practical implementation aspects of CPGD and present numerical experiments illustrating its performance. On the test cases considered, these experiments suggest that CPGD is more robust to overspecification of the number of components than the EM algorithm. We also investigate the impact of component separation on recovery accuracy.
Read the full abstract

All authors Romane Giard, Yohann De Castro, Roland Denis, Clément Marteau

Software Engineering

Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority

Mehmet Iscan

An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from release authority. Requirements unsupported by a deterministic parser are routed to a frozen local language model with four billion parameters. Plans are released only when both facts can be derived by an external gate under a sealed grammar. One canonical answer is requested from a gold-standard user when eligible. The protocol was evaluated once under a criterion fixed before benchmark construction, on 144 tasks written by isolated agent contexts without access to the gate, grammar, or experimental plan. Three contributions are established. First, candidate generation and release decisions were measured separately. Fabricated ready plans were committed on 21 of 22 routed unanswerable tasks, and all were rejected. The same 83 releases were reproduced without model calls. Second, no false release was observed among 83 releases. A one-sided 95% Clopper-Pearson upper bound of 0.0354 was obtained as a diagnostic under an independent-and-identically-distributed assumption, below the sealed 5% threshold. However, one false release was subsequently recorded among 146 releases outside the benchmark at seed 0. Third, protection against incorrect user answers was characterized. Both facts were bound from the original text on 13 of 96 answerable tasks. Incorrect answers were released in 169 of 431 pairings on the remaining tasks, including failures involving coordinate exclusion. A deployable questioning policy was not tested because eligibility was determined from the answer key. Gate sensitivity and real user behavior were not measured.
Read the full abstract

Machine Learning

Minimally Invasive Steering of Language Models

Taha Entesari, Jingyu Zhang, Daniel Khashabi et al. (+1 more)

Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the output distribution and degrade generation quality. We propose Minimally Invasive Steering Vector Optimization (MISVO), which penalizes interventions using the local KL geometry of the induced token distribution. The resulting Fisher quadratic measures distributional sensitivity and admits an analytic gradient computed through matrix–vector products with the frozen language-model head. We derive an exact decomposition of the sequence-level KL gradient into an analytic Fisher term and a suffix score-function term. For a fixed generation horizon, we show that the suffix term is second order in the steering magnitude and that three Fisher surrogates agree with the full KL gradient to first order. MISVO uses the frozen-reference surrogate to optimize position-specific interventions without updating model parameters. Across preference and code-generation tasks on models with approximately 1B–14B parameters, MISVO achieves the highest mean reward in six of seven model–task settings, with diversity and coherence scores close to those of Best-of-N.
Read the full abstract

All authors Taha Entesari, Jingyu Zhang, Daniel Khashabi, Mahyar Fazlyab

Cryptography and Security

Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure

David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner et al. (+3 more)

A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM agents to circumvent runtime monitoring as a means of completing ordinary tasks. We introduce EvasionBench, a benchmark of 50 diverse task-policy pairs in which completing the task requires an operation prohibited by a runtime monitor. Agents know that their tool calls are monitored and are prompted to continue working when they pause. Across our evaluations, best-of-3 evasion attempt rates reach up to 98% and success rates up to 88%, with substantial variance across models. Claude Fable 5.1 succeeds less often, but frequently makes creative attempts to circumvent the monitor. Evasion generally increases with test-time compute, with higher evasion rates at greater reasoning effort and token use. Traces show that agents encode prohibited commands, decompose operations across tool calls, and retry until relevant context leaves the monitor's history. We also find that GPT-6 Astra's low evasion rate comes with overrefusal, as it frequently abandons otherwise solvable tasks under a denial-of-service prompt injection. Our findings show that ordinary task pressure can lead to adaptive attempts to evade runtime monitors without an explicit adversarial objective. Effective oversight must therefore remain robust against repeated attempts, as the persistence that helps agents solve difficult tasks can also drive them to circumvent their guardrails.
Read the full abstract

All authors David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Anselm Paulus, Ameya Prabhu, Maksym Andriushchenko

Software Engineering

Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem

Guoming Ling, Muen Xue and Zijian Ye

Jev is a fast, low-cost decision model that answers natural-language questions with choices, binary judgments, and scores. As its public ecosystem grows rapidly, it remains unclear how Jev is used across applications and how public attention relates to project distribution. To answer these questions, we conduct a large-scale, data-driven analysis of 2,170 publicly available Jev projects collected from GitHub as of September 22, 2026. We find rapid early growth in Jev's public ecosystem, with both new projects and integration into existing repositories. Across diverse domains, projects use Jev for multiple decision purposes and combine its interfaces. Attribute judgment and scoring are widely used, while the use of action selection, content filtering, and model and tool selection varies across domains. These patterns suggest that Jev serves as a reusable decision component whose functionality varies with the surrounding workflow. Meanwhile, public attention is concentrated in routing and interface agents and does not track project counts. Our findings provide a quantitative view of Jev's emerging ecosystem and inform the design and evaluation of general-purpose decision models across diverse application contexts.
Read the full abstract

Data Structures and Algorithms

A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model

Santosh S. Vempala

We prove nearly quadratic lower bounds for randomized algorithms for linear optimization and uniform sampling over convex bodies in the membership oracle model. For linear optimization, this matches the known nearly quadratic upper bound up to a polylog factor in the dimension. For uniform sampling, this improves on the previous linear lower bound. Our construction also implies the same lower bound for volume estimation.
Read the full abstract

Robotics

Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage

Yuncong Yang, Jinlong Li, Yulong Xue et al. (+4 more)

We present Underwater C$^{3}$-JEPA (cross-view, control-conditioned, context-extended), an object-centric multi-view predictive world model for near-field heavy-load underwater ROV salvage. Without contact sensors, it predicts in latent space how the task-object state evolves through contact interaction and under the hydrodynamic lag of the vehicle, from synchronized multi-view RGB observations and vehicle control signals. C$^{3}$-JEPA encodes multi-camera observations into task-object and context tokens, fuses cross-camera evidence through held-out-view attention, and directly predicts future states conditioned on control. Weak binding anchors the target and gripper at low annotation cost, while SIGReg sharpens the geometric representation. Experiments show that the learned representation transfers substantially more task-relevant information to downstream probes than a reconstruction-free latent baseline, while keeping the predictor lightweight. The resulting predictive interface supports model-predictive-control (MPC) candidate evaluation and imagined-rollout behavior-agent training. Validation on real underwater video shows the same architecture recovering a withheld camera's object state and staying ahead of persistence, so the recipe transfers beyond simulation.
Read the full abstract

All authors Yuncong Yang, Jinlong Li, Yulong Xue, Feng Wu, Chunwen Zhang, Lei Qiao, Xuyang Wang

Robotics

ReVAMP: Vector-Accelerated Motion Planning for Kinematically-Constrained Systems via Reparameterization

Shrutheesh R. Iyer, Thomas Cohn and Zachary Kingston

Robots often must satisfy one or more constraints during motion planning for real-world tasks. When such constraints reduce the valid configuration space to a measure-zero subset, sampling based planning algorithms require modifications to draw feasible samples. For many common end-effector constraints, parameterizations built on inverse kinematics (IK) provide an alternate formulation where the constraints are satisfied by construction, allowing directly sampling the feasible set. Despite their elegant approach, parameterized planners have remained slower than vector-accelerated implementations of projection-based approaches, leaving their performance ceiling an open question. We explore a new axis of vectorization built upon reparameterizing the planning space through analytic IK. This approach addresses existing inefficiencies in vectorized projection-based planners and exposes new opportunities for parallelism within the planner. We show that the planner can synthesize plans in microseconds to milliseconds for high dimensional systems (up to 20 dimensions), with complex constraints, up to 10x faster than the current state-of-the-art. Furthermore, we demonstrate how such planning speeds open up avenues for restructuring sequential manipulation pipelines.
Read the full abstract

Optimization and Control

Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems

Ruichen Jiang and TaeHo Yoon

We characterize, up to logarithmic factors, the optimal higher-order oracle complexity of finding approximate solutions to composite monotone inclusion problems, formed by the sum of a smooth single-valued monotone operator and a maximal monotone set-valued operator. We introduce the Anchored Extra-Proximal (AEP) framework, which combines an anchored extrapolation step with an inexact anchored proximal update satisfying a relative-error condition. This framework recovers the composite Fast Extragradient method in the first-order setting and yields natural higher-order extensions through Taylor approximations of the smooth operator at the extrapolated point. For every $p\geq 2$, assuming that the $(p-1)$th derivative of the single-valued operator is $L_p$-Lipschitz continuous and the initial distance to a solution is at most $R$, we combine AEP with a bisection line search to obtain a $p$th-order method that attains a tangent residual of at most $\varepsilon$ in $\widetilde{O}((L_p R^{p}/\varepsilon)^{\frac{2}{3p-1}})$ oracle calls. We complement this result with a worst-case lower bound of $\Omega((L_p R^p/\varepsilon)^{\frac{2}{3p-1}})$ for every deterministic algorithm in the $p$th-order oracle model, without imposing any prescribed update structure. For the subclass of smooth nonexpansive fixed-point problems, we further establish a lower bound of $\Omega(\min\{R/\varepsilon, {(L_p R^{p}/\varepsilon)}^{\frac{2}{3p-1}}\})$. By choosing between AEP and Halpern iteration, we match this lower bound up to logarithmic factors, thereby also settling the deterministic oracle complexity of smooth nonexpansive fixed-point problems.
Read the full abstract

Operator Algebras

The Dynamical Radius of Comparison for C*-Dynamical Systems

M. Ali Asadi-Vasfi and N. Christopher Phillips

We introduce a dynamical version $\operatorname{rc} (A, \alpha)$ of the radius of comparison $\operatorname{rc} (A)$ of a unital C*-algebra, based on the dynamical Cuntz semigroup. We also give an intrinsic ordered semigroup definition, which agrees with $\operatorname{rc} (A, \alpha)$ when $A$ is residually stably finite, and is lower semicontinuous for equivariant direct limits with injective unital maps. We construct actions $\alpha$ of $G = \mathbb{Z} / 2 \mathbb{Z}$ on simple unital AH~algebras for which $\operatorname{rc} (A, \alpha)$ lies strictly between $\operatorname{rc} (A)$ and $\operatorname{rc} (A) / \operatorname{card} (G)$, and actions $\alpha$ of a finite group $G$ on unital C*-algebras for which $\operatorname{rc} (A, \alpha)$ lies strictly between $\operatorname{rc} (A)$ and $\operatorname{rc} (C^* (G, A, \alpha))$. For a minimal action of a countable discrete group $G$ on a zero dimensional compact metrizable space $X$, we prove that $\operatorname{rc} (C (X), \alpha) = 0$ if and only if the action has dynamical comparison as defined by Kerr. For finite group actions on simple unital stably finite C*-algebras, assuming the weak tracial Rokhlin property, we get $\operatorname{rc} (A, \alpha) \leq \operatorname{rc} (A) / \operatorname{card} (G)$, and assuming weak tracial strict approximate innerness, we get $\operatorname{rc} (A, \alpha) = \operatorname{rc} (A)$.
Read the full abstract

Computer Vision

The Alignment Illusion in Multimodal Large Language Models

Hong-Han Wang, Yuntao Wang and Hu Ding

Layer-wise visual-text similarity in Multimodal Large Language Models (MLLMs) is widely interpreted as evidence that the language model progressively integrates visual content into a shared representation space. This reading rests on the assumption that scalar alignment scores reflect content-level cross-modal interaction. To test this assumption, we apply controlled interventions to the visual stream. Across 13 MLLMs from five families spanning 0.5B to 72B parameters, replacing projector-output visual tokens with Gaussian noise sharply reduces task accuracy, yet four standard scalar measures (CKA, SVCCA, MIR, and the leading principal-angle cosine) fail to consistently separate the corrupted stream from the original. We call this failure the alignment illusion and trace it to the shared language-model pathway: anisotropic MLP down-projections pull visual and text tokens toward common output directions, producing weight-induced alignment. Because this component is essentially one-dimensional, we introduce the principal-angle gap (PA gap), defined as the difference between the top two principal-angle cosines, which separates weight-induced similarity from multi-directional visual structure. Under graded visual corruption, the PA gap tracks task accuracy more consistently than the scalar scores we consider; under a structured but irrelevant image, it further exposes regimes in which internal geometry and task accuracy come apart. Internal visual-text alignment in MLLMs is therefore best read as a geometric diagnostic of the visual stream inside the language model rather than a direct proxy for content-level cross-modal interaction, and is most informative when calibrated by controlled task evidence.
Read the full abstract

Mathematical Physics

Localization near the edge for the lattice Anderson-Bernoulli model on general dimension

Linjun Li, Shihe Liu and Lingfu Zhang

The Anderson tight-binding model is a fundamental model of quantum transport and localization in disordered media. Solving a problem left open by Bourgain and Kenig, this paper proves Anderson localization near the bottom of the spectrum for the lattice Anderson model with Bernoulli potential, in any dimension $d\ge 2$. The proof uses the multiscale framework of Fröhlich-Spencer and Bourgain-Kenig, and the main new ingredient is a probabilistic discrete unique continuation principle (PDUC) for the discrete Schrödinger equation. This PDUC is established via a bootstrap argument and a key probabilistic lemma proved by adaptively revealing the random potential.
Read the full abstract

Computational Engineering

Voxel-based block variational quantum linear solver: a hybrid quantum-classical method for static analysis of solids

Feng Wu, Chen Li, Li Zhu et al. (+2 more)

In solid mechanics, finite element discretization of large-scale static problems produces large sparse linear systems whose solution requires substantial computation time and memory. The variational quantum linear solver (VQLS) offers a hybrid quantum-classical route, but its use in quantum finite element analysis is limited by the decomposition of nonunitary matrices, barren plateaus, and the measurement cost of expectation values. We propose a voxel-based block variational quantum linear solver (Voxel-BVQLS) that combines structured matrix decomposition, the principle of minimum potential energy, and batched quantum tests. First, we construct an LCU decomposition of the stiffness matrix from the recursive block-banded structure of voxel-grid finite element matrices, with the number of unitary terms bounded independently of the problem size. Second, we optimize the ansatz parameters using a minimum-potential-energy objective in place of a conventional VQLS loss function, thereby mitigating barren plateaus in the studied problems. Third, we introduce a block-Hadamard test whose circuit directly estimates weighted sums of multiple inner products, reducing the number of circuit configurations required per iteration. We assessed the proposed method in noiseless classical simulations using three examples. These examples show that the method reduces both the number of unitary terms in the LCU decomposition and the number of iterations required to converge, while still yielding solutions of finite accuracy. Voxel-BVQLS thus provides a structured hybrid quantum-classical framework for quantum finite element analysis on regular grids.
Read the full abstract

All authors Feng Wu, Chen Li, Li Zhu, Yuxiang Yang, Xu Guo

Number Theory

Diophantine approximation by primes and Landau–Siegel zeros

Sun-Kai Leung and Stelios Sachpazis

Let $\alpha>0$ be an irrational number of finite type and let $\beta\in\mathbb{R}$. Assuming the infinitude of Siegel zeros (respectively, sufficiently strong Siegel zeros), we show that for every sufficiently small $\varepsilon>0$, there exist infinitely many primes $p$ such that \begin{gather*} \|\alpha p+\beta\|\leq p^{-1/3+\varepsilon} \qquad\text{(respectively, }\|\alpha p+\beta\|\leq p^{-1/3-1/20}\text{)}. \end{gather*}
Read the full abstract

General Relativity and Quantum Cosmology

Topological black holes of Einsteinian cubic gravity and Born-Infeld-type electrodynamics

Askar Ali

In this paper, we examine the new black holes of Einsteinian cubic gravity within the framework of Born-Infeld-type electrodynamics. Initially, we establish the differential equations of motion that characterize an innovative collection of charged black hole solutions in Einsteinian cubic theory. Next, we compute the thermodynamic quantities of these black holes for the case of vanishing bare cosmological constant. We consider this situation because the model is unitary only for the asymptotically flat solutions that allow horizons with spherical topology. We also present that the first law of thermodynamics is fulfilled for these objects. Finally, we examine how the nonlinearity of electric field, electric charge and cubic coupling parameter can impact the local thermal stability of our simulated black holes in both canonical and grand canonical ensembles.
Read the full abstract

Artificial Intelligence

A Living Benchmark for Information Retrieval from Electronic Health Records

Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani et al. (+23 more)

Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safety and utility depend on rigorous evaluation, yet existing benchmarks are manually curated, costly to update, and rapidly become obsolete with evolving technological advancements. We present a scalable framework that automatically generates question–answer pairs from longitudinal EHR notes. Nineteen clinicians validate the benchmark generator, producing the Benchmark for Retrieving Information in EHRs (BRIE), a continuously maintainable evaluation dataset. Across nine LLMs and five inference strategies, state-of-the-art systems frequently omit clinically important information, particularly for questions requiring synthesis across multiple documents and encounters. Because the generator itself is validated, BRIE supports evaluations that static benchmarks cannot, including the generation of multiple answers that reflect variation in clinician reasoning for robust performance assessment and continuously refreshing benchmark content to guard against leakage. Our results demonstrate that scalable benchmark generation enables rigorous, up-to-date evaluation of clinical LLMs as they are deployed in rapidly evolving healthcare settings.
Read the full abstract

All authors Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani, Philip Chung, Kevin R Keet, Kameron C. Black, Andrea T. Fisher, Sarita Khemani, Jerry Liu, Stephen Ma, Saloni K. Maharaj, Rita M. Pandya, Eduardo Perez-Guerrero, Priyanka Pillai, Lisa Shieh, David J.H. Wu, James Xie, James C. McAvoy, Teresa Nguyen, Jessica Tran, Lucy Yin, Bridget Lin, Alison Callahan, Jason A. Fries, Nigam H. Shah, Emily Alsentzer

Dynamical Systems

Equidistribution of saddle periodic points for automorphisms on compact Kähler manifolds

Muhan Luo and Qi Zhou

Let $f$ be a holomorphic automorphism of a compact Kähler manifold $X$ with simple cohomological action. We prove that the saddle periodic points of $f$ equidistribute with respect to the equilibrium measure. In particular, our result applies to every holomorphic automorphism of a compact Kähler surface with positive topological entropy.
Read the full abstract

Combinatorics

On the Binary Rank of Matrices with Constant Real Rank

Michal Parnas

We study the problem of determining upper bounds on the maximal binary rank, $b_d$, of a $0,1$ matrix with real rank $d$, for small constant $d$. We prove a general upper bound of $b_d \leq \left\lfloor \sqrt{d2^d + 2d}\right\rfloor -1$. We also develop a general dimension reduction technique of bounding $b_d$ using known upper bounds on $b_{d-1}$ and $b_{d-2}$, as well as prove interesting general structural results on extremal matrices with binary rank $b_d$. This allows us to get improved non-trivial upper bounds on $b_d$ for constant values of $d$, which imply tight bounds on $b_d$ for $3 \leq d \leq 5$. Our results also imply bounds on the equivalent problem of finding the minimum number of bicliques needed to partition the edges of a bipartite graph whose reduced adjacency matrix has real rank at most $d$.
Read the full abstract

Mesoscale and Nanoscale Physics

Incipient superconductivity and tunable Chern insulators in twisted bilayer-trilayer graphene

Derek Waleffe, Aryana Bhattacharyya, Manish Kumar et al. (+7 more)

Moiré superlattices assembled by twisting Bernal and rhombohedral multilayer graphene host a rich set of interaction-driven magnetic and topological states, yet superconductivity has not been observed in these systems except in proximity to a transition-metal dichalcogenide. Here we report incipient superconductivity and tunable Chern insulators in twisted bilayer-trilayer graphene encapsulated by hexagonal boron nitride. Across twist angles from $\theta = 1.05^\circ$ to $1.50^\circ$, Chern insulators form at integer and fractional moiré fillings for electron doping, with Chern numbers up to |C| = 3 set by twist angle and tuned by doping. At $\theta = 1.18^\circ$, a symmetry-broken metallic region forms for hole doping and hosts a trivial insulator at band filling $\nu = -2$. Displacement field alone drives this insulator into a pocket of incipient superconductivity with a sharp transition, a well-defined critical current, and a critical temperature that peaks near the insulating boundary, although the resistance does not fall to zero. In-plane magnetic field expands the pocket, which persists to more than four times the weak-coupling Pauli limit, and stabilizes a second pocket in which Fraunhofer-like modulation of the critical current signals phase-coherent pairing. Twisted bilayer-trilayer graphene thus offers a single gate-tunable system in which pairing can be interfaced with Chern insulators whose topology is itself an adjustable parameter.
Read the full abstract

All authors Derek Waleffe, Aryana Bhattacharyya, Manish Kumar, Eric Maginnis, Anna Okounkova, Tobias Faehndrich, Kenji Watanabe, Takashi Taniguchi, Joshua Folk, Matthew Yankowitz

Combinatorics

An extremal theorem for non-isomorphic spanning trees

Zhifei Yan and Lu-Ming Zhang

For a graph $G$, let $\tau_{\mathrm{iso}}(G)$ denote the number of isomorphism classes of its spanning trees. For every fixed $d\ge3$ and all sufficiently large $n$, we prove that every connected $n$-vertex graph $G$ with $\delta(G)\ge d$ satisfies \[\tau_{\mathrm{iso}}(G)\ge \tau_{\mathrm{iso}}(K_{d,n-d})=A_dn^{d-1}+O_d(n^{d-2}),\] for an explicit constant $A_d>0$, and $K_{d,n-d}$ is the unique minimizer. This confirms a conjecture of Bitonti, Michel and Scott and extends it to every $d\ge3$. We also show that any such graph with $O(n^{d-1})$ spanning-tree types has all but a bounded number of vertices with the same $d$ neighbours.
Read the full abstract

Group Theory

High Rank and Multiplicity in Random and Perfect Profinite Groups

Carlo Pagano and Mark Shusterman

We prove that almost sure topological finite generation holds for a general class of random models of profinite groups. We deduce that in the models introduced by Liu–Wood and Sawin–Wood, one has that finite presentation holds almost surely, with almost sure control of the deficiency in the presentation. In particular this settles questions raised in work of Liu–Wood and Sawin–Wood. Using the same underlying principle, we show that there exists a unique universal d-generated perfect profinite group: its finite quotients are precisely the finite d-generated perfect groups. This settles a conjecture of Nikolov. We show in addition that this group is projective and admits a profinite presentation with $d$ generators and $d$ relations, and with no fewer relations on $d$ generators. The main underlying theme is to bring in an insight from crown theory: groups with high rank are always witnessed by a crown with large multiplicity. This approach was discovered independently by ChatGPT5.5 pro and Aletheia, an internal agent at Google DeepMind.
Read the full abstract