Peer Revenue Returns subject to peer review

Papers

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

All of arXiv

Tuesday 1 September

Artificial Intelligence

CacheBridge: Efficient Cross-Model KV Transfer for Multi-Model LLM Serving

Multi-model LLM serving uses routers, cascades and agent workflows to move requests across models with different costs and capabilities. Existing serving systems reuse KV caches only within one model, so every switch forces the target to re-prefill history the source already processed, adding time to first token (TTFT) that grows with history length and target size. Cross-model KV transfer can replace this prefill, yet prior methods are slower than re-prefill end to end. We present CacheBridge, the first serving system to accelerate heterogeneous multi-model workloads through cross-model KV transfer. It co-designs a compact, attention-calibrated KV mapper with systematic optimization for online multi-model serving, which makes model switch efficient on latency and memory cost. In Qwen3 14B$\rightarrow$32B agent serving on $\tau$-bench, it reduces mean TTFT by $30$ to $98\%$ versus re-prefill at $1$ to $24$ QPS with comparable task success. Across five model pairs from three families, it uses $8$ to $12\times$ less mapper memory than Closed-Form Mapper and retains on average $97.94\%$ and $102.94\%$ of re-prefill task quality on chat/reasoning and RAG workloads, respectively. The promising results have opened new opportunities for efficient multi-model LLM serving through cross-model KV reuse.
Read the full abstract

All authors Xingyu Qu, Siyuan Lu, Zhiyu Chen, Sheng Wang, Tao Lin

Information Theory

Algorithm-Hardware Co-Design of a Lightweight PCG Equalizer with a Fixed Step Size for Massive MIMO

Coarse quantization in massive multiple-input multiple-output (MIMO) systems reduces power but causes clipping distortions. The Bayesian Expectation-Maximization (BEM) algorithm can recover clipped signals, but its matrix inversion and dynamic step-size evaluation are hardware bottlenecks. We propose a hardware-friendly one-step correction that uses the initial Jacobi-preconditioned Conjugate Gradient (PCG) direction with a fixed relaxation parameter. The resulting symbol-level update has an ultra-lightweight $\mathcal{O}(U)$ feed-forward datapath and approaches high-resolution reference detectors in the evaluated massive-MIMO setting. Our finite-dimensional analysis establishes the exact one-step descent law, proves that Jacobi normalization cancels the raw multiplicative near-far scaling while confining the loaded-system dependence to bounded attenuation factors, and gives verifiable sufficient conditions for fixed-step descent in terms of normalized channel coherence. System-level results indicate projected power savings for energy-efficient massive MIMO uplinks.
Read the full abstract

All authors Junshuo Wang, Shuting Liu, Shihan Wang, Yan Tian, Jienan Chen

Combinatorics

Dominant-Degree Conditions for Ramsey–Turán Factors of Non-Directed Cycle Orientations

Let $\Cvec$ be a fixed orientation of the cycle $C_\ell$, $\ell\ge3$, which is not directed. For an oriented graph $D$, let $d_D^*(v):=\max\{d_D^+(v),d_D^-(v)\},$ and let \[ \sigore(D):=\min\bigl\{d_D^*(x)+d_D^*(y):x\ne y,\ xy,yx\notin A(D)\bigr\}, \] with $\sigore(D)=\infty$ if the underlying graph of $D$ is complete. We prove that, for every $\mu>0$, there exist $\gamma>0$ and $n_0$ such that every $n\ge n_0$ with $\ell\mid n$ and every $n$-vertex oriented graph $D$ satisfying \[ \alpha(D)\le\gamma n \text{ and } {\sigore(D)\ge\left(\frac34+\mu\right)n} \] contains a $\Cvec$-factor. {Additionally, for every fixed $s\ge2$ and every fixed real constant $C$, we construct arbitrarily large oriented graphs with $\sigore(D)\ge \frac34n+C$ that contain no $C_{2s}^{\ad}$-factor. More precisely, $C:=\frac34\alpha(D)-2$ for $s=2$ and $C:=\frac14\alpha(D)-\frac32$ for $s\ge3$.} This paper develops a weighted reduction framework adapted to dominant degree condition, proves the absorption lemma via closed-cluster merging with even-walk, and derives almost-perfect tiling structures by virtue of Farkas-lemma-based fractional decomposition.
Read the full abstract

High Energy Physics (Phenomenology)

The Type-I Seesaw as a Relativistic Fermionic Proximity Effect: Spectral Moments, EFT Consistency, and Sterile-Sector Reconstruction

We formulate the type-I seesaw as a relativistic fermionic proximity effect in the exact active-sector two-point kernel. Active neutrinos have no renormalizable gauge-invariant Majorana mass and couple by lepton-number-conserving Yukawa hybridization to a sterile Majorana pairing kernel. Integrating out the sterile fields gives a nonlocal Nambu-Gorkov embedding self-energy. In a sterile Takagi basis its anomalous and normal flavor responses are $\mathcal{A}(Q^2)=\sum_i M_i y_i y_i^T/(Q^2+M_i^2)$ and $\mathcal{B}(Q^2)=\sum_i y_i y_i^\dagger/(Q^2+M_i^2)$, respectively. Their low-energy expansions generate correlated lepton-number-violating and lepton-number-conserving moment towers. The leading moments reproduce the Weinberg coefficient and the dimension-six kinetic operator. Both towers share one sterile mass set; its positive normal support supplies a common annihilator, although anomalous residues can cancel at exact degeneracy. We prove normal block-Hankel positivity and positivity of a dimensionally rescaled mixed Nambu-Hankel sequence. The latter gives matrix Cauchy-Schwarz inequalities between lepton-number-conserving and lepton-number-violating data and can reveal paired directions hidden by a degenerate normal residue. Isolated nondegenerate pole residues satisfy an additional nonlinear compatibility identity. These results yield tree-level EFT consistency tests and a matrix-pencil reconstruction of visible pole and aggregate-residue data; selecting a unique ultraviolet Lagrangian requires additional information about sterile-basis multiplicities. An exact one-generation example distinguishes the static Schur-complement kernel from the physical Takagi pole mass. The proximity structure applies without a Fermi surface or condensate, and Nambu doubling introduces no new physical degrees of freedom.
Read the full abstract

Materials Science

Large Exchange Magnetostriction in a Kagome Antiferromagnet at Room Temperature

The pursuit of high-performance magnetostrictive materials is crucial for advancing technologies in sensing, actuation, and microelectromechanical systems. Although pronounced magnetostrictive effects have been observed in a few ferromagnets, a systematic exploration of magnetostriction across a broader range of antiferromagnets remains limited. Here, we report the observation of large magnetostriction in the kagome antiferromagnet YMn6Sn6. Under a magnetic field, the system undergoes a field-induced evolution from a helical magnetic ground state toward a collinear field-polarized state, accompanied by a large anisotropic lattice strain and a substantial volume magnetostriction exceeding 400 ppm at room temperature. Remarkably, the magnetostrictive response remains nearly fully reversible up to 9 T with nearly hysteresis-free behavior, effectively minimizing the energy dissipation commonly associated with domain-wall pinning. Combined experimental measurements and theoretical calculations reveal that the large, nearly hysteresis-free magnetostriction originates from the competition between intralayer ferromagnetic and interlayer exchange interactions. This exchange-driven magnetoelastic coupling further gives rise to a strongly direction-dependent lattice distortion pathway. This work establishes kagome helimagnets as a tunable platform for low-dissipation magnetoelastic functionalities and responsive magnetomechanical applications.
Read the full abstract

All authors Jie Du, Liang Yao, Hang Li, Xiaodong Zhou, Yuan Yao, Xuekui Xi, Yong-Chang Lau, Wenhong Wang

Cryptography and Security

Using LLMs to Elicit Security Requirements for Service-Oriented Cyber Ranges

Cyber ranges are complex environments comprising many interacting components and stakeholders with different security concerns. The Service-Oriented Cyber Range (SOR) is no exception, particularly when it comes to training scenarios targeting critical infrastructure. Security concerns are translated into security requirements, the elicitation of which is usually difficult and time-consuming. This work examines how large language models can assist in eliciting security requirements for a service-oriented range and help produce a useful baseline for designers and developers. The approach follows a SEBoK-guided process in which security mission objectives and stakeholder needs were first identified and then provided as a prompt context along with architectural guidelines to five LLMs: GPT-5.2, Gemini 3.1 Pro, Grok 4.1, Sonar, and Kimi K2.5. The models generated 84 security requirements in total, which were consolidated into a comprehensive set of 27 requirements and then mapped to the architectural layers of the service-oriented range. The final set was evaluated by five cybersecurity experts against the criteria of necessity, clarity, completeness, feasibility, and testability, with an additional rejection option. The results showed a high acceptance rate, specifically for necessity with 98.5%, clarity with 87.4%, completeness with 85.2%, feasibility with 78.5%, and rejection with 0.7%. Testability was lower at 44.4%, indicating a slight lack of information on how these requirements could be tested. These findings show that LLMs can support early stages of the elicitation of security requirements, although human review is still needed, especially to improve or adjust certain aspects of the requirements.
Read the full abstract

All authors Michail Takaronis, Athanasia Kollarou, Georgios Kavallieratos, Vasileios Gkioulos, Sokratis Katsikas

Artificial Intelligence

Denoising Diffusion Generative Models Secretly Calculate Attentions

Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily handled by well-known transformer architectures employing attention mechanism. Here, we show that diffusion models also inherently use an attention mechanism very similar to that of transformers. Therefore, attention emerges as a universal machine learning principle, based on a general training objective. We also show similarities in basic functional principle of auto-encoders and attention-based models. These equivalences allows us to interchange these designs based on practical requirements. As an example, we can reformulate the diffusion framework to reduce the lengthy training process and computation-intensive image generation. Using this approach, a simplified algorithm is proposed for image generation which is based on attention mechanism. Results show that the attention-based implementation achieves comparable performance with significantly less effort and computational resources.
Read the full abstract

All authors Farzan Haddadi, Leila Monfared, Ebrahim Rezaii, Mohammadreza Malek-Mohammadi, Pejman Zakalvand, Narges Mokhtari

Logic

The weakness of typicality

Many statements studied in reverse mathematics can be seen as mathematical problems, formulated in terms of instances and solutions. We develop a framework of typicality encompassing measure and genericity, and we classify the reverse mathematics zoo in terms of which problems admit typical solutions. It turns out that even very weak problems do not admit typical solutions.
Read the full abstract

All authors Eric P. Astor, Laurent Bienvenu, Damir Dzhafarov, Ludovic Patey, Paul Shafer, Reed Solomon, Linda Westrick

Machine Learning

iPINN for Broadband CARS Phase Retrieval: A Framework for Function Approximation and Inverse Modeling Problems in Nonlinear Spectroscopy

Broadband coherent anti-Stokes Raman scattering (BCARS) records chemically specific vibrational spectra, but the measured signal mixes the resonant, Raman-like response of the sample with a non-resonant background that changes from one measurement to the next. Recovering the resonant response, known as phase retrieval, is an ill-posed inverse problem. We present iPINN, an inverse physics-informed neural network that predicts the positions, amplitudes, and widths of Lorentzian vibrational bands directly from a BCARS spectrum. A transformer network estimates these band parameters, and a differentiable analytical model of the resonant susceptibility rebuilds the Raman-like spectrum from them as a sum of physically defined bands. We train the network on simulated spectra in which the bands of each reference compound stay fixed while the shape and strength of the background and the noise vary. Training also encourages similar band predictions for the same compound across these variations. On a public benchmark of toluene and dimethyl sulfoxide spectra, the network reached a mean absolute error about one third of that of the best of five deep-learning baselines. Its error for dimethyl sulfoxide stayed nearly constant across three noise levels. We also used 28 spectra of seven solvents, recorded at four focal depths with different background strengths. For five of the seven solvents, the mean absolute error changed little with depth, while it varied more for the other two. These results indicate that this approach keeps phase retrieval stable for most of the tested solvents when the background changes.
Read the full abstract

All authors Ravi Teja Vulchi, Carl Messerschmidt, Mohammadsadegh Vafaeinezhad, Rajendhar Junjuri, Tobias Meyer-Zedler, Juergen Popp, Thomas Bocklitz

General Relativity and Quantum Cosmology

Reissner-Nordstrom in the Bertotti-Robinson-Bonnor-Melvin electromagnetic field

The magnetic Reissner-Nordstrom black hole embedded into the Bertotti-Robinson magnetic field is presented. Then it is used, as a seed, to generate, through the Harrison transformation of the Ersnt's equations, the Reissner-Nordstrom metric in the Bertotti-Robinson-Bonnor-Melvin magnetic field. Special cases generalising, the vacuum hairy type I Schwarzschild solution is discussed. The local equivalence between various forms of the Schwarzschild-Bertotti-Robinson is shown by exhibiting the explicit diffeomorphism.
Read the full abstract

Quantum Physics

Towards Natural Gas Contract Selection via Quantum-Guided Independent Set Reduction

Selecting mutually compatible natural gas transportation contracts is a practically important optimization task in which operators must choose from many candidate agreements subject to temporal, infrastructural, and flow-related constraints. As the number of candidates grows, the resulting search space becomes difficult to explore exhaustively. We study a pairwise abstraction of this task, formulated as a Maximum Clique problem on a contract-compatibility graph, or equivalently as a Maximum Independent Set (MIS) problem on the complement graph. Building on recent work, this paper studies a quantum-classical framework for solving large-scale MIS instances within the limitations of noisy quantum hardware. The approach combines iterative classical graph reduction with quantum-guided optimization to progressively simplify the search space while maintaining high solution quality. This enables large candidate spaces to be reduced to smaller subproblems that are more suitable for execution on current quantum computers. We evaluate the approach on fifteen benchmark instances from the Quantum Optimization Benchmarking Library (QOBLIB), obtaining an average approximation ratio of 0.996 and recovering optimal solutions for fourteen instances, including graphs with up to 186 vertices. We further evaluate the algorithm on six synthetic pairwise contract-compatibility graphs containing up to 900 contracts, where the proposed method achieves an average approximation ratio of 0.989 and obtains optimal solutions in four cases. These experiments demonstrate the ability of the hybrid MIS solver to reduce industrially motivated graphs. The pairwise abstraction serves as the first step of a two-stage screening procedure that narrows the candidate contracts to a smaller set of mutually compatible ones, which can then be verified against pipeline-capacity constraints.
Read the full abstract

All authors Vivek Dixit, Vaibhaw Kumar, Kentaro Ohno, Alberto Maldonado Romo, Larry Bowden

Optimization and Control

Partially Observed Mean Field Games Without Perfect Recall: Optimality Conditions and Equilibria

This paper studies partially observed mean field games without perfect recall (WPR). The representative agent observes a noisy signal, but the control at time \(t\) uses only \(\mathcal G_t^I=\sigma(y_t)\), a generally non-nested information family. The conditional population law instead uses the observation filtration \(\mathbb F^Y\). These coupled levels rely on different information scales and are difficult to close within one construction. We parameterize the environment by a deterministic compatible joint law of state, driving variables, and random mean field term, thereby preserving its dependence structure without enlarging the agent's control information. For a fixed law, a reference measure and Girsanov's theorem yield a WPR stochastic maximum principle; the selected response is represented by the conditional Hamiltonian and WPR belief measure. The joint path posterior of hidden state and mean field term gives a weak Kushner-Stratonovich representation of the conditional population law. A recursive response map is continuous on a compact convex set of compatible laws, so Schauder-Tychonoff yields a weak WPR equilibrium. For a fixed equilibrium law and feedback, a compatible Yamada-Watanabe theorem lifts pathwise uniqueness to a strong realization. Finally, a linear-quadratic interbank lending example compares perfect recall (PR) with WPR. The PR response follows the Kalman-Bucy feedback, whereas the WPR response solves a Fredholm-Volterra equation and is affine in the current observation under Gaussianity. The numerical experiment illustrates how equilibrium behavior differs between PR and WPR.
Read the full abstract

Artificial Intelligence

Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning

Reliable disaster damage assessment requires models that provide both accurate predictions and transparent explanations. However, existing multimodal approaches are limited by scarce annotated data and insufficient evaluation of reasoning quality. This study proposes a two-stage training framework that integrates Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) within a unified data construction pipeline. From a single Human-in-the-Loop (HITL) annotation workflow, two complementary datasets are derived, namely ReasoningSet, which contains validated rationales for SFT, and PreferenceSet, which comprises paired rationales for DPO-based alignment. The framework evaluates both classification performance and explanation quality using automatic metrics, model-based scoring, and human ranking. Experimental results show that SFT improves accuracy from 73.64% to 78.29% and increases Macro-F1 by 29% compared to the baseline, while explanation quality improves by approximately 25%. Subsequent DPO alignment further enhances interpretability on the PreferenceSet. Cross-model validation on InternVL-3-8B and LLaVA-1.5-7B demonstrates the robustness and generalizability of the approach. The proposed framework improves detection of underrepresented mild damage cases, reduces high-risk misclassifications, and strengthens alignment between model reasoning and human judgment. Overall, it provides a reproducible pathway to develop reliable multimodal systems that deliver auditable, actionable disaster insights for emergency management.
Read the full abstract

All authors Yuanjun Zhang, Fuzel Ahamed Shaik, Suvojit Acharjee, Fahad Khalid, Mourad Oussalah

Optimization and Control

DOFFO_TR: a Decentralized Objective Function-Free Optimization method with Trust-Region

In this paper, we propose a novel objective function-free trust-region method designed to solve optimization problems over decentralized networks. Unlike traditional approaches that often rely on stepsize tuning, our framework employs a function-free trust-region procedure that enables adaptive selection of the step length. Our approach accommodates first- and second-order models and eliminates the need to share local function values and gradients among agents, thereby enhancing privacy and computational efficiency. On the theoretical side, we establish provable iteration complexity guarantees that, for some variants, match those established for classical centralized trust-region methods. Numerical evaluations demonstrate that our approach achieves a favorable trade-off between performance and efficiency, requiring only moderate communication overhead compared to state-of-the-art methods in the literature.
Read the full abstract

Distributed Computing

Prediction-Robust Service Deployment with Capacity-Aware Edge Admission

Edge platforms instantiate executable services close to users to reduce request-serving cost, but each instance incurs a one-time deployment cost and remains useful only for a finite time-to-live (TTL). The resulting online decision is both prediction-sensitive and capacity-coupled: an optimistic forecast can waste deployment cost, whereas a delayed decision misses the burst it is intended to serve. We study this problem under a common TTL cost model and propose CAPSUM, a capacity-aware admission policy with an elastic specialization, CAPSUM-E. In the local elastic setting, every node-service trace is exactly a variable-price Bahncard instance. This reduction lets CAPSUM-E inherit PFSUM's tight prediction-error-dependent ratio, including $2/(1+\beta)$ consistency and $1/\beta$ robustness for $\beta>0$. A redirect-aware variant preserves the same local deployment schedule. For finite-capacity nodes, CAPSUM combines size-scaled break-even tests, a utilization-dependent shadow price, and evidence-density eviction; we prove capacity feasibility, scale invariance, and exact agreement with CAPSUM-E under an elastic configuration. We implement an exact local offline dynamic program and compare against direct common-model baselines and documented source-derived adapters for EDP-A, OREO, and uEDC-L. Experiments cover controlled prediction error, three synthetic demand regimes, a causal predictor on a public Globus Compute trace, and joint scaling to 1,024 nodes and 10,000 services. Under the common model, CAPSUM reduces normalized cost by 33.7-42.9% relative to the best source-derived adapter across the synthetic regimes and by 45.5% on the sampled trace.
Read the full abstract

All authors Hailiang Zhao, Ziqi Wang, Yifei Zhang, Mingyi Liu, Xinkui Zhao, Kingsum Chow, Shuiguang Deng

Mathematical Physics

A general improbability result for non-collision singularities as subsystems with at most four particles

Non-collision singularities of the $n$-body problem are initial conditions for which no global solution exists and which, however, do not lead to a collision in the limit; i.e., the moment of inertia of the system diverges. The question of whether the set of initial conditions leading to non-collision singularities in the $n$-body problem is improbable is open and is the first on Barry Simon's list of fifteen problems in mathematical physics from the year 1984. So far, this question has only been answered positively in the case $n=4$. Using a final cluster decomposition into subsystems whose particles interact strongly with each other and exert only small forces on particles from different subsystems, we can prove the improbability of the set of all singular orbits with the following conditions: -There may be arbitrarily many subsystems undergoing total collision at their center of mass. - There may be subsystems exhibiting a non-collision singularity, i.e. the respective moment of inertia of the subsystem diverges. These subsystems consist of exactly four particles each and the asymptotic directions of these subsystems have to differ (which is only a mild condition). This result includes all known statements and indicates a way how the general problem could be solved.
Read the full abstract

Artificial Intelligence

FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study

Satellite mega-constellations are emerging as large-scale sensing, communication, and computation fabrics, yet their learning architectures remain largely inherited from terrestrial federated learning and ground-centric mission operations— ill-suited to satellites that differ by orders of magnitude in Size, Weight, Power, and Cost (SWAP-C), radiation tolerance, link availability, and propagation delay. We propose a heterogeneous federated learning method based on the FractalNet architecture for orbital edge intelligence. We formalize contact-window-constrained, depth-heterogeneous federated optimization and introduce a distributed path scheduler that assigns model depth as a function of SWAP-C constraints, predicted inter-satellite contacts, and training statistics. To reduce message overhead and energy consumption, each tier pools updates periodically rather than at every contact opportunity, and a three-tier agentic control plane governs in-space scheduling, anomaly escalation, and policy-governed autonomy. As a case study, we apply the framework to wildfire detection, where each orbital shell naturally learns a different semantic level of situational awareness: pixel-scale thermal anomalies at low Earth orbit (LEO), regional fire-front dynamics at medium Earth orbit (MEO), and larger-scale risk propagation at geostationary or high Earth orbit (GEO/HEO). Experiments on simulated mega-constellations validate the approach across convergence, communication efficiency, energy adaptation, scheduled-pooling savings, robustness, and latency.
Read the full abstract

Artificial Intelligence

A Score Is Not a Policy: Measuring the Value of Adaptive Revision

As agentic systems become compound systems, increasingly important decisions move above task execution itself: when should a higher-level controller preserve the strategy guiding another process, and when should it revise it? We study this meta-level control problem in a hierarchical latent reasoner whose manager can retain or replace a commitment governing lower-level computation. Across three precommitted training seeds, learned revision timing produces qualitatively different policies, ranging from an almost deterministic early clock to substantially more state conditioned schedule distributions, yet none outperforms the best forced timing policy evaluated on the same frozen checkpoint. This separates state dependence from decision value: a controller can vary its actions with internal state without turning that variation into a reproducible task-performance benefit. A deeper intervention study on the original checkpoint shows that timing itself is consequential and order-sensitive, while exhaustive enumeration reveals that a strong fixed schedule captures most of the measurable value available from timing at this decision budget. Counterfactual PERSIST/REPLAN diagnostics further show why score-level evidence can be misleading when predictability is dominated by decision position rather than within-position discrimination. Together, these results argue that learned meta-level control should be evaluated along three separate axes: whether its score depends on state, whether that dependence changes realized behavior, and whether those changes capture outcome value beyond a strong non-adaptive policy.
Read the full abstract

Computation and Language

Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive LMs, offering advantages such as parallel generation and bidirectional context modeling. Despite growing interest in their generative capabilities, the privacy risks of DLMs remain underexplored. We identify a phenomenon termed token-level memorization asymmetry through theoretical analysis of diffusion training dynamics. Building on this finding, we propose Q-Skew, a quantile-weighted skewness-based indicator for membership inference on finetuned DLMs. Experiments across multiple fine-tuning datasets and models show that our method outperforms existing baselines. Moreover, we show that Q-Skew can also facilitate other privacy violations, such as PII extraction. Our findings reveal a previously underexplored privacy attack surface and highlight the need for systematic privacy evaluation of DLMs.
Read the full abstract

All authors Shengfang Zhai, Leo Marchyok, Yuling Shi, Huanran Chen, Yinpeng Dong, Jiaheng Zhang, Sanghyun Hong

Analysis of PDEs

Sharp Mixed Spectral Barron Regularity of Coulombic Many-Electron Wave Functions

We establish sharp mixed spectral Barron regularity for eigenfunctions of molecular Coulomb Hamiltonians. The mixed norm is a Fourier $L^1$ norm with one isotropic weight and coordinate-product weights, and therefore detects regularity invisible to the isotropic Barron scale. For a nonempty set $I$ of electron indices on which the wave function is antisymmetric, we derive an explicit admissible region for the isotropic order $s$ and the coordinate orders $\alpha,\beta$. This region is optimal as a uniform statement over the class of clamped-nuclei Coulomb Hamiltonians. For fixed-spin components with two occupied spin blocks, it reduces to $s+\alpha+\beta<1$; in the fully spin-polarized class it reduces to $s+\alpha<1$. In particular, if $\mathcal I_\sigma$ denotes the family of occupied same-spin blocks determined by $\sigma$, then every fixed-spin spatial component $\psi_\sigma$ satisfies, for every $0\leq\alpha<1$, \[ \left(\sum_{I\in\mathcal I_\sigma}\prod_{i\in I}\langle\xi_i\rangle^\alpha\right)\widehat{\psi_\sigma}\in L^1(\mathbb{R}^{3N}). \] For a fully spin-polarized state, $\mathcal I_\sigma=\{\{1,\ldots,N\}\}$.
Read the full abstract

Formal Languages and Automata

Construction of a DFA for Computing Grundy Numbers in the Successful Derivation Games on Right-Linear Grammars

Inoue et al. have introduced the successful derivation game (SDG) on context-free grammars (CFGs), which is a generalization of classic heap-based games including subtraction games and Keyles, and shown that the least upper bound of the Grundy numbers in the SDG on a given CFG G is undecidable in general even when we restrict G to be a linear CFG. This paper shows that for the SDG on a right-linear grammar (RLG), we can construct a DFA for computing the Grundy number of a given position. In other words, for the SDG on an RLG, the set of positions with a given Grundy number c is regular. As a corollary, the least upper bound of the Grundy numbers in the SDG on a given RLG is decidable. We also investigate the complexity of computing the least upper bound of the Grundy numbers in the SDG on a given RLG, and it is shown to be PSPACE-complete.
Read the full abstract

Optimization and Control

Stochastic Optimization of Tree Tensor Networks

Tensor networks, originally developed for quantum many-body physics, are promising models for machine learning. We derive stochastic Riemannian optimizers for tree tensor networks (TTNs) on both their parameter and quotient manifolds, including adaptive and learning-rate-free schemes suitable for minibatch training. Using a hybrid CNN-TTN architecture, we evaluate the methods on Fashion-MNIST, CIFAR10, and Imagenette. The proposed optimizers achieve predictive performance comparable to unconstrained optimization while enabling numerically stable downstream compression.
Read the full abstract

All authors Marius Willner, Maximilian Scharf, André Uschmajew, Timo Felser, Marco Trenti

High Energy Physics (Phenomenology)

Understanding IR singularities in the Loop-Tree Duality

One of the main advantages of the Loop-Tree Duality representation of scattering amplitudes is that it makes the origin of infrared and threshold singularities particularly transparent. This talk reviews recent progress in describing how singularities emerge and cancel at the level of scattering and vacuum amplitudes, discusses a novel strategy to efficiently construct finite integrals, and presents a complementary perspective based on encoding the underlying causal and singular structure in terms of qubits and quantum circuits.
Read the full abstract

All authors Germán Rodrigo, Leandro Cieri, Prasanna K. Dhani, Roger J. Hernández-Pinto, Jorge J. Martínez de Lejarza, Salvador A. Ochoa-Oregon, Konstantinos Pyretzidis, Selomit Ramírez-Uribe, David F. Rentería-Estrada, Andrés E. Rentería-Olivo, José Ríos-Sánchez, German F.R. Sborlini, Surabhi Tiwari, Juan P. Uribe-Ramírez

Computer Vision

The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence

Vision-language models are evaluated by aggregate accuracy on multimodal benchmarks, a practice that implicitly assumes the model uses its visual input. We show this assumption fails on 40%–97% of samples across six VLMs and three perceptual benchmarks: blurring the question-relevant visual region leaves the next-token distribution nearly unchanged. We name this phenomenon the Visual Insensitivity Gap and quantify it with a per-sample Visual Sensitivity Index (VSI). The gap is a property of samples, not of models: VSI ranks correlate across models (grand-mean Spearman rho=+0.40, permutation p<10^-3), so the same samples are flagged insensitive by VLMs sharing no architectural detail beyond a contrastively pretrained vision tower. The mechanism is concrete: on the insensitive samples, a linear probe on each model's own vision tower distinguishes perturbed from clean images at 0.72–0.79 accuracy, yet the model's argmax token changes on only 2%–11% of the same samples, an encoder–LLM gap above 0.65 on every model. Mapping VSI's diagnostic utility cell by cell surfaces a strong regime (multi-choice reasoning on capable VLMs: AUROC=0.85–0.87) and a weak regime (well-calibrated factuality, where softmax confidence already leads). VSI is not a universal best abstention signal; it is a sample-intrinsic indicator of vision-ignoring failure, best used as a conditional ensemble component.
Read the full abstract

Probability

Uniform Partition-Function Estimates for Coulomb Modulated Energy at All Positive Temperatures

We prove uniform-in-$N$ partition-function estimates at all positive temperatures for the centered modulated energy of logarithmic, Riesz, and Bessel–Riesz kernels on $\mathbb R^d$ in the locally square-integrable range $0\le s<d/2$. They yield finite-particle exponential integrability, quadratic behavior at small parameter, explicit kernel-dependent growth at large parameter, and uniform entropy control of the associated Gibbs measures. As applications, we obtain uniform Rényi-divergence and relative-entropy bounds for interacting Gibbs equilibria and entropic mean-field convergence near thermal equilibrium; the optimal $N^{-1}$ normalized relative-entropy rate for the three-dimensional Coulomb flow; and an $N^{-1/2}$ Gaussian approximation for fixed-time finite-dimensional fluctuations. Finally, the modulated energy converges to a random variable in the second Wiener chaos, and for every positive parameter the partition functions converge to its Laplace transform, represented by a Carleman–Fredholm determinant. This formula identifies the sharp small-parameter behavior and, when the reference density is bounded below on a ball, the sharp large-parameter growth.
Read the full abstract

Computer Vision

Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generation

The rapid advancement of vision-language models (VLMs) has accelerated progress in computational pathology; however, whole-slide image (WSI)-based pathology report generation remains limited by the scarcity of large-scale WSI–report datasets and the complexity of mapping spatially distributed visual patterns to structured clinical text. To address this, we introduce a clinically curated Pan-Asia WSI–report dataset of approximately 10,500 pairs from five institutions and establish the REG 2025 benchmark through a MICCAI challenge for systematic evaluation of multimodal models. We analyze submitted methods spanning pretrained VLMs, multiple-instance learning frameworks, hierarchical expert models, retrieval-augmented generation, and cross-modal Transformers. Rather than indicating that VLM use alone was sufficient for superior performance, the results suggest that top-performing methods benefited from structured report representations, hierarchical diagnostic decomposition, and effective multimodal grounding. We identify key limitations, including instability in quantitative attribute estimation (e.g., numeric hallucination) and a tendency toward diagnostic overspecification, with some errors resembling known diagnostic pitfalls in routine pathology. These findings establish REG 2025 as a benchmark for evaluating WSI-based structured report generation and vision-language understanding in computational pathology, providing insights for the design of clinically grounded multimodal pathology models.
Read the full abstract

All authors Yumi Lee, Harim Oh, Hyoryung Kim, Minji Kim, Eunsu Kim, Hyeseong Lee, Junya Fukuoka, Andrey Bychkov, Jijgee Munkhdelger, Rajiv Kumar Kaushal, Ayushi Sahay, Rajni Yadav, Bharathi Prabakaran, Sulen Sarioglu, Serdar Balc{\i}, Ilknur Turkmen, Yuri Tolkach, Christian Harder, Julian Westerdorf, Reinhard Buettner, Audun Ljone Henriksen, Sepp De Raedt, Byung Hyun Lee, Sungjin Lim, Joohoon Lee, Gwanghyun Kim, Se Young Chun, Suryakant Singh, Saarthak Kapse, Prateek Prasanna, Kyung A Kim, Yousun Kang, Sehwan Yoo, Sungman Hong, Shubham Innani, Michael Feldman, Spyridon Bakas, Ujjwal Baid, Prasad Dutande, Suhas Gajare, Bhakti Baheti, Serkan Sökmen, Ece Tuğba Cebeci, Ahmet Hal{\i}c{\i}, Musa Balc{\i}, Kardelen Peçenek, Srividhya Sainath, Kyongseok Jang, Messi H.J. Lee, Noorul Wahab, Bodong Du, Jiaming Zhang, Qixiang Zhang, Jang-Hwan Choi, Sangjeong Ahn

Machine Learning

MemoryWalker: Stop Training Agents on Contexts They Never Saw

Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning problem: every eviction branches the effective history, so the learning object is a tree rather than a sequence. Existing linearizations either retain the rightmost path, causing time-travel leakage, or replay a depth-first traversal, causing train-inference mismatch. We introduce two exact, gradient-equivalent corrections: LogitTree, a segmented K-forward traversal, and a packed 4D attention mask. LogitTree requires K+1 backward passes; the 4D mask requires a custom kernel and white-box eviction records. We also propose SDCC (Self-Distillation for Conditioning Consistency), a single-backward-pass variational relaxation. At each eviction, it minimizes forward KL between the compressed student and a stop-gradient teacher on the reconstructed pre-eviction prefix. A residual per-junction KL of epsilon_KL gives an O(sqrt(epsilon_KL)) bound on the train-deployment total-variation gap. SDCC also applies to black-box harnesses. On seven web-search benchmarks with TC-RAG, AgentFold, MemexRL, Claude Code, and OpenCode, naive training inflates the train-rollout log-probability gap, especially on eviction-heavy batches. The exact methods stay at the no-compression floor, and SDCC substantially closes the gap, with lower logit drift and higher rollout rewards.
Read the full abstract

All authors Zinco J, Xunjie Zhu, Shen Huang, Zhenyi Wang, Pengjun Xie, Jieping Ye

Materials Science

Independent Tuning of Surface Acoustic-Waves and Spin-Waves via Buffer-Layer Engineering in Co2FeGe Heusler Thin Films

Understanding and controlling acoustic and spin-wave excitations in magnetic thin films is critical for the development of magnonic and spin-acoustic devices. We report on the use of Cr and W buffer layers to independently modify the acoustic and magnetic excitations in Co2FeGe full-Heusler thin films grown on MgO(001). Using Brillouin light scattering (BLS) spectroscopy and ferromagnetic resonance (FMR), we probed Rayleigh and Sezawa surface acoustic waves (SAWs) alongside Damon-Eshbach and perpendicular standing spin-wave (PSSW) modes. Our results show that acoustic dispersion depends strongly on the buffer material; W-buffered films exhibit a pronounced 16% reduction in Rayleigh SAW frequency compared to buffer-free films, primarily due to mass loading and acoustic impedance shifts. While the buffer layers significantly shift acoustic frequencies, they simultaneously modify the dynamic magnetic response (increasing spin-wave group velocity by ~34%) through different physical mechanisms. Finite-element simulations show excellent agreement with the experimental acoustic data. These findings demonstrate that buffer-layer engineering is an effective strategy for the independent tailoring of elastic and magnetic excitations, providing a versatile platform for hybrid spin-acoustic technologies.
Read the full abstract

All authors A. V. Achuthan, A. Vovk, S. Bunyaev, B. Postolnyi, P. Štrichovanec, P. A. Algarabel, K. Załęski, J. P. Araujo, G. N. Kakazei, A. Trzaskowska

Machine Learning

Conditional Flow Matching for ML-Based Inverse Design Problems

Engineering inverse design is often limited by the high computational cost of iterative solvers for optimization problems constrained by partial differential equations (PDEs) and by their sensitivity to initialization. Deep generative models can produce candidate designs without rerunning the simulator at inference time. Generative adversarial networks (GANs) sample in one forward pass, whereas diffusion models require iterative reverse-time integration. In this work, we add conditional flow matching (CFM) to EngiOpt and compare it with a conditional diffusion model and a conditional generative adversarial network (cGAN) on structural (beams2d) and thermal (heatconduction2d) benchmarks from EngiBench using the same downstream optimization protocol. We use cumulative optimality gap (COG) and final optimality gap (FOG) as the primary metrics for evaluating the generated designs as warm starts for gradient-based refinement. On the evaluated EngiOpt implementations and two EngiBench tasks, CFM achieves the lowest measured COG, FOG, maximum mean discrepancy (MMD), and volume-fraction deviation on both tasks. CFM has mean volume-fraction deviations of 0.4% and 1.0% on beams2d and heatconduction2d, respectively, compared with 3.8% and 11.2% for diffusion. At Euler s = 16, CFM achieves 53.2 samples/s on beams2d, about 66 times the measured throughput of the evaluated diffusion baseline using 1000 network evaluations under the same timing protocol, with COG 1.182 +/- 3.126, compared with 1.173 +/- 3.100 for Euler s = 32. Across the two tasks, CFM produces warm starts with lower measured COG than both baselines and uses fewer network evaluations than diffusion.
Read the full abstract

All authors Juliana Felder, Milad Habibi, Soheyl Massoudi, Mark Fuge

Computer Vision

Training-Free Inpainting Across Domains with a Frozen Text-to-Image Diffusion Model

We show that a frozen generic text-to-image diffusion model can perform conditional inpainting across three evaluated natural-image domains with one fixed controller configuration, without inpainting-specific weight training, dataset-specific weight adaptation, or learned inpainting-specific conditioning channels. Step-PI augments known-region projection with boundary-interior latent feedback, persistent PI state, and a predefined four-field release schedule that modulates controller signals along the reverse trajectory. Developed only on Main35-disjoint CelebA-HQ pilots, the controller transfers unchanged to AFHQ and Places2. Across two field-identical comparisons on the same 3,500 cases, adding persistent state and replacing uniform release with the predefined schedule each improve all 15 dataset-metric cells; 95% bootstrap intervals exclude zero for all five metrics in both comparisons. In descriptive native-route comparisons, Step-PI leads LanPaint and PILOT (the closest evaluated training-free baselines using vanilla SD1.5) on all five equal-dataset macro metrics. Inpainting-trained systems retain the absolute metric leads but rely on substantial inpainting-specific offline optimization. Our method provides a complementary approach for repurposing a frozen generic text-to-image model for cross-domain inpainting through test-time latent control.
Read the full abstract