Peer Revenue Returns subject to peer review

Papers

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

All of arXiv

Sunday 11 October

Optimization and Control

Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning

Yuriy Dorn, Dmitrii Vishovan, Kirill Novoselov et al. (+3 more)

We study federated learning from continuously arriving data: each client samples from its own distribution, these distributions drift over time, and the server must track the minimizer of the clients' weighted average loss. Clients are not alike as they collect data at different rates, with different noise, and change at different speeds. The main question is how much history should each one keep? A single shared window must serve every client at once, and so makes a fast-changing client carry the sampling noise of a slow, nearly stationary one. We give each client a memory of its own, sized to that client's noise, arrival rate, and drift, and refresh it by restarted accelerated method that starts from a common point. The tracking error is then bounded by \[ R\left(\sum_m w_m^{3/2}\,\sigma_m\sqrt{\gamma_m/\lambda_m}\right)^{2/3}, \] for clients with weight $w_m$, noise $\sigma_m$, arrival rate $\lambda_m$, and drift rate $\gamma_m$ on a domain of diameter $R$. This is never worse than what any common window can achieve, and strictly better whenever noise and drift are spread unevenly across clients. A lower bound that puts different groups of clients on different drift clocks shows this quantity is the right one. The two bounds agree up to a constant whenever the clients occupy boundedly many refresh scales, and in general differ only by the sixth root of the number of scales. Experiments show the gain comes from the memory rather than from the solver: it persists across accelerated, stochastic-gradient, and one-step methods, and against a separately tuned common-memory baseline.
Read the full abstract

All authors Yuriy Dorn, Dmitrii Vishovan, Kirill Novoselov, Ilya Kuruzov, Darina Dvinskikh, Alexander Gasnikov

Computation and Language

Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

Project Apertus: Yixuan Xu, Yassine Turki, Vinko Sabolčec et al. (+128 more)

Language models are becoming infrastructure, and infrastructure built in the open, by public institutions, on documented data, is the alternative to dependence on a few providers; Apertus shows this is viable at scale. Apertus 1.5 extends the fully open Apertus family from text to multimodal reasoning. Continued pretraining of the Apertus 1.0 models, on 4T additional tokens for the 8B and 2T for the 70B, adds image and audio understanding and extends the context window fourfold to 262,144 tokens; multimodality enters through the tokenizer, the language-model head remains restricted to text, and the architecture is unchanged. Supervised finetuning, long-context finetuning, reinforcement learning with verifiable rewards, and preference alignment complete the released models. Thinking is a flag of the chat template rather than a separate model, and lifts mathematical reasoning by up to 20 points on the 8B model. The released models improve over their predecessors on nearly every benchmark; among fully open models of its class, the 8B leads on knowledge, instruction following, and cultural benchmarks, and its instruction following surpasses all compared models, including open-weight ones. On image and audio understanding, a first for the family, the models are competitive with fully open multimodal models, strongest on document understanding and long-form and lower-resource speech recognition, while specialized vision and audio models remain ahead on perception and transcription of English and other high-resource languages. As in Apertus 1.0, we train only on openly available data, respect crawler opt-outs retroactively, and exclude restrictively licensed material. We release the model weights, data preparation and training recipes, and evaluation suites under permissive licenses; openness extends to values, with the Apertus charter guiding alignment stages published alongside the models.
Read the full abstract

All authors Project Apertus: Yixuan Xu, Yassine Turki, Vinko Sabolčec, Valentina Pyatkin, Tommy Chu, Sven Najem-Meyer, Sean F. Carroll, Robert Smith, Raphael Kreft, Oscar Alessandro Tazza, Oleg Lavrovsky, Nicola Irmiger, Matteo Santelmo, Marian Schneider, Juan García Giraldo, Hanna Yukhymenko, Eduard Ďurech, Davit Melikidze, Dani Tamayo, Bettina Messmer, Aryan Ahadinia, Anunay Yadav, Allen Huang, Ahmad Fraij, Alessandro Bombarda, Alex Padula, Alexander Hägele, Alexander Sternfeld, Anna Hedström, Anna Kosovskaia, Arthur Wuhrmann, Arundhati Balasubramaniam, Badr Al Mahouri, Barna Pasztor, Bartosz Szostakiewicz, Bich Ngoc Doan, Bryan Schmid, Burak Sezen, Camille Challier, Clément Charmillot, Dana Shayakhmetova, Daniel Perruchoud, David Brüggemann, David Isztl, Elia Palme, Emma Anastassova, Fabian Bösch, Faruk Zahiragić, Fawzi Roberto Mohamed, Fiona Panicali, Florian Kolly, Flynn Guerra, Francesco Monti, Frederike Lübeck, Gennaro Oliva, Haofeng Yang, Haoliang Shang, Helen El Khoury, Henrique Mendonça, Jannis Vamvas, Jérome Landolt, Jessica Lam, Jingchun Xiao, Jonathan Coles, Joshua Oyebanji, Khanh Nguyen, Konstantinos Pitas, Lasse B. Strand, Li Mi, Loïc Deslarzes, Lorenzo Baggi, Lorenzo Noci, Luca Baumann, Luca Sartori, Lukas Drescher, Marco De Negri, Marco Passerini, Mark Klein, Marko Stojanovic, Martin Majsec, Matin Ansaripour, Mattea Busato, Mauro Pellonara, Max Neuwinger, Michael Graber, Michal Tešnar, Michelle Wastl, Miguel Gila, Mikolaj Boronski, Morgane Magnin, Moritz Reihs, Mukhammadali Sayfiddinov, Nathan Ranchin, Nicolas Cuveillier, Oscar Wohlfahrt, Qianqian Zou, Rada Kamysheva, Rita Sevastjanova, Roman Machacek, Sebastian Keller, Simon Matrenok, Simon Pierre, Stefano Schuppli, Suei-Wen Chen, Szabina Horváth-Mikulas, Taliesin Perez, Thilo Spinner, Thomas Kleine Buening, Tim Robinson, Tymoteusz Kwiecinski, Vilém Zouhar, Vinzenz Thoma, Xiaozhe Yao, Yannick Metz, Yuhei Fukuhara, Yusif Askari, Zixuan Chen, Alexander Ilic, Ana Klimovic, Andreas Krause, Andrei Kucharavy, Elliott Ash, Joost VandeVondele, Martin Rajman, Mennatallah El-Assady, Thomas Schulthess, Timo Kehrer, Torsten Hoefler, Antoine Bosselut, Martin Jaggi, Imanol Schlag

Cryptography and Security

Fetch Me If You Can: A Comprehensive Analysis of Fetch Metadata

Pedro Bernardo, Alex Ploner, Marco Squarcina et al. (+2 more)

Effective server-side defenses against cross-site attacks depend on understanding the context in which browser requests are generated. However, servers often lack the information needed to distinguish legitimate requests from potentially malicious cross-site interactions. Fetch Metadata, a security mechanism introduced in 2019, addresses this limitation by adding a set of HTTP headers to outgoing browser requests. These headers provide servers with information about a request's context and provenance, enabling them to enforce request isolation policies accordingly. However, the extent of Fetch Metadata's real-world adoption and its interaction with existing security mechanisms remain largely unexplored. In this paper, we present the first large-scale measurement study of Fetch Metadata adoption. We analyze the top 1M websites in the Tranco list to detect deployments of Fetch Metadata isolation policies and identify custom policies used in the wild. We then examine how these policies address cross-site threats and assess their security coverage. Finally, we provide the first systematic comparison of Fetch Metadata with existing client-side security mechanisms, revealing security gaps that arise from differences between client-side and server-side enforcement.
Read the full abstract

All authors Pedro Bernardo, Alex Ploner, Marco Squarcina, Mauro Tempesta, Matteo Maffei

Machine Learning

Sensitivity Fidelity Reveals Physical Dependencies Beyond Forecast Accuracy in Deep-Learning Earth-System Models

Qi Chen, Peng Zhan, Hongxing Cui et al. (+2 more)

Deep-learning models increasingly rival numerical simulation in Earth-system forecasting, yet forecast error alone cannot determine whether their learned input-output dependencies are physically consistent. Here we introduce sensitivity fidelity as an additional criterion: alongside prediction error, model responses to input perturbations should be examined against a trusted reference or established physical knowledge. In an idealized Rayleigh-Bénard convection benchmark, four surrogate architectures achieved low forecast errors yet encoded markedly different sensitivities. Quantitative comparison with a matched adjoint distinguished the models far more sharply than forecast accuracy and showed that predictive skill and sensitivity fidelity need not coincide, while finite-perturbation experiments further linked these differences to the propagation of initial-condition uncertainty. We then applied this strategy to El Niño-Southern Oscillation prediction, where no adjoint reference exists and learned sensitivities showed event-wise robustness, validity under finite perturbations, and consistency with established precursors. These results identify gradient-based evaluation as a discriminating complement to forecast-error metrics, providing a practical test of whether data-driven Earth-system models learn physically credible dependencies.
Read the full abstract

All authors Qi Chen, Peng Zhan, Hongxing Cui, Wenqing Cui, Ibrahim Hoteit

Combinatorics

Tuza's Conjecture under an Edge-Count Condition

Zhen Liu and Qinghou Zeng

For a graph $G$, let $\nu(G)$ denote the maximum number of pairwise edge-disjoint triangles and let $\tau(G)$ denote the minimum number of edges meeting every triangle. Tuza's conjecture asserts that $\tau(G)\le 2\nu(G)$ for every graph $G$. We first note that Tuza's conjecture is equivalent to the following statement: for every fixed $c\ge 0$, if $G$ is a sufficiently large $n$-vertex graph with $e(G)\ge n^2/4-cn$, then $\tau(G)\le 2\nu(G)$. In this paper, we prove this statement for every $c<2$.
Read the full abstract

Soft Condensed Matter

Generalized Constraint-Controlled Rheological Model: Two Constitutive Pathways under Sinusoidal Periodic Shear Deformation

Dario Nichetti and Alessio Zaccone

We formulate the Generalized Constraint-Controlled Rheological Model (GCCRM) for entangled linear and long-arm-branched polymer melts under sinusoidal periodic shear deformation (SPSD), spanning the linear and strongly nonlinear regimes. Molecular architecture, conformation, chain stretch, flow-active constraints, convective constraint release, dynamic tube dilation, and activated arm retraction define a common upstream molecular state. This state feeds two time-domain constitutive pathways (a configurational stress and a dissipative internal-variable stress) which are recombined before Fourier analysis. For branched polymers, the architecture is described by an entire backbone of molecular weight $M_{bb}$ and $N_a$ long arms of molecular weight $M_a$, with a compliance-weighted representative-constitutive-cell partition. The linear limit is normalized so that the configurational moduli sum to the entanglement modulus, while dynamic tube dilation and stretch drive distinct contributions to dissipative activation. Under reduced closures, GCCRM generates a smooth nonlinear elastic response with an onset of nonlinearity, an approximately logarithmic growth regime, an architecture-dependent maximum, and distinct high-deformation asymptotes. Fourier harmonics, ELR, VLR, and Lissajous curves are treated as post-processing observables of the total stress. The framework establishes a consistent constitutive architecture whose quantitative validation requires one parameter set per material across SPSD and, prospectively, transient shear histories.
Read the full abstract

Cryptography and Security

Poisoned into Action: Context Attacks on Typed Decision Workflows

Chenkai Wu, Xing Chang and Jun Yan

Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-violating state changes. Evaluating context poisoning thus requires connecting model decisions to execution outcomes while accounting for legitimate automation retained by defenses. We introduce an execution-aware protocol tracing poisoned evidence through retrieval, model choice, automated action, and persisted state. We evaluate it with 1,659 fresh calls to Jev-1.13.0 across 20 development tasks in two synthetic workflows, using three repetitions per condition. Under natural retrieval, a standalone payload reaches all 60 trials and produces five security-violating executions, while a carrier-payload pair exposes the payload in 57 trials and produces one violation. An initial source-exclusion gate blocks the pair's observed violation but also withholds ten otherwise correct attacked decisions and sixteen correct clean decisions. Correcting its empty-scope behavior restores twelve clean decisions without additional model calls. Factorial controls show that adding correct evidence reduces wrong executions from 119/120 to 55/120 in the semantic arm and from 60/120 to zero in the neutral arm, suggesting that much of the improvement reflects general evidence value rather than attack-specific protection. Three prespecified contrasts are not statistically supported after Holm correction, so the findings remain exploratory. The protocol provides an auditable framework for studying which poisoning-induced errors reach execution and how much correct automation defenses preserve. Code is available at https://github.com/WuXixiong/jev-poisoning-bench.
Read the full abstract

Cosmology and Nongalactic Astrophysics

Joint Constraints on the Hubble Constant and Cosmic Baryon Density from Localized Fast Radio Bursts and DESI DR2 Baryon Acoustic Oscillations

Ji-Guo Zhang, Tian-Nuo Li, Guo-Hong Du et al. (+3 more)

Fast radio bursts (FRBs) probe free-electron columns along cosmological sightlines through their dispersion measures (DMs), whereas baryon acoustic oscillations (BAO) constrain cosmic expansion geometry through acoustic distance ratios. In this work, we leverage their distinct physical sensitivities to simultaneously determine the Hubble constant ($H_0$) and cosmic baryon density ($\Omega_{\rm b}$) without external cosmic microwave background (CMB) or Big Bang nucleosynthesis (BBN) priors. Combining 120 localized FRBs and DESI DR2 BAO, we obtain $H_0=71.4^{+2.2}_{-2.5}\ {\rm km\ s^{-1}\ Mpc^{-1}}$ and $\Omega_{\rm b}=0.0503^{+0.0025}_{-0.0021}$ in $\Lambda$CDM, corresponding to precisions of $3.3\%$ and $4.6\%$, respectively. The inferred $H_0$ is statistically consistent with both SH0ES and CMB, and $\Omega_{\rm b}$ agrees with the joint constraint from BBN and CMB. Adopting IllustrisTNG-based DM distributions and fixing the diffuse-gas baryon fraction tightens the constraint to $H_0=68.8\pm1.0\ {\rm km\ s^{-1}\ Mpc^{-1}}$, but lowers the central value toward the CMB-inferred value, identifying extragalactic DM modeling as the dominant systematic uncertainty. These results establish FRB-BAO complementarity as a new avenue for simultaneously constraining $H_0$ and $\Omega_{\rm b}$.
Read the full abstract

All authors Ji-Guo Zhang, Tian-Nuo Li, Guo-Hong Du, Wan-Peng Sun, Jing-Fei Zhang, Xin Zhang

Combinatorics

Hull Variation in Symplectic Linear Codes

Kanat Abdukhalikov, Somi Gupta and Duy Ho

We study the variation of hull dimensions of symplectic linear codes under equivalence transformations preserving the symplectic distance. For a symplectic linear code $C$, we introduce an even-valued invariant $\Delta(C)$, which depends only on the equivalence class of $C$. This invariant can be expressed as the generic rank of an associated space of alternating matrices and, equivalently, as twice a corresponding matroid matching number. If $C$ has dimension $k$, we prove that the minimum symplectic hull dimension among all codes equivalent to $C$ is $k-\Delta(C)$. Consequently, $C$ is equivalent to a symplectic LCD code if and only if $\Delta(C)=k$. We further show that every symplectic MDS code of even dimension is monomially equivalent to a symplectic LCD code. For a symplectic self-orthogonal code $C$, we determine all attainable hull dimensions: for every integer $r$ with $0\le r\le \Delta(C)/2$, there exists a monomially equivalent code whose symplectic hull has dimension $k-2r$. We also refine a standard form for the generator matrix of a symplectic self-orthogonal code and derive the corresponding parity-check matrix and the Gram matrix of the dual code. In the self-dual case, we characterize $\Delta(C)$ through minors of an associated symmetric matrix. Furthermore, we relate hull variation to graph matchings, establish a bound for $\Delta(C)$, and give graph constructions producing symplectic self-dual MDS, optimal, and best-known codes.
Read the full abstract

Combinatorics

A chain theorem for planar PM-compact bricks

Yaxian zhang, Qiuli Li and Fuliang Lu

A connected graph $G$ is matching covered if it contains at least one edge and every edge belongs to some perfect matching of $G$. A matching covered graph is a brick if it is 3-connected and after removing any two vertices, the resulting graph has a perfect matching. Bricks are the building blocks of matching covered graphs. A brick $G$ is extremal if the incidence vectors of all perfect matchings are linearly independent over $\mathbb{R}$. Zhou et al. [On planar extremal nonsolid bricks, J. Graph Theory, 2026] proved that for every planar extremal brick $G$, there exists a sequence of planar extremal bricks $G_0,G_1,\dots,G_n$ such that the underlying graph of $G_n$ is an odd wheel, $G_0=G$, and each $G_i$ $(0\leq i < n)$ has a triangle $T_i$ such that $G_i/T_i = G_{i+1}$, where $G_i/T_i$ means contracting the triangle $T_i$ into a single vertex. In this paper, the result of Zhou et al. is generalized to planar PM-compact bricks, a larger class of bricks including extremal bricks. We present a chain theorem for planar PM-compact bricks: for every planar PM-compact brick $G$, there exists a sequence of planar PM-compact bricks $G_0,G_1,\dots,G_n$ such that the underlying graph of $G_n$ is an odd wheel, $G_0=G$, and each $G_i$ $(0\leq i < n)$ contains a triangle $T_i$ such that $G_i/T_i = G_{i+1}$.
Read the full abstract

Computer Vision

UMAS3D: Unified Mask-Free 3D Editing with Region-Adaptive Source Preservation

Xianlin Zeng, Xiaolong Shen, Ruijie Quan et al. (+1 more)

3D editing aims to modify an existing 3D asset according to user intent while preserving geometry and appearance outside the intended edit region. Existing methods often rely on task-specific training, source-3D inversion, or external 3D masks, and lack a unified framework for diverse editing conditions and tasks. We propose UMAS3D, a unified 3D editing framework that is training-free, inversion-free, and free from external 3D masks. UMAS3D converts text, bounding boxes, reference images, and their combinations into common target-view guidance, after which addition, deletion, modification, appearance, and pose editing share the same downstream 3D generation process. Our key insight is to couple online edit-region estimation with region-aware source preservation. Mask-Free Adaptive Region Modeling (MARM) initializes an Edit/Keep prior from source-target visual differences and progressively refines it as the target structure evolves, while Source-Guided Preservation Steering (SGPS) constrains the current Keep-region states to retain source geometry and appearance without suppressing target-driven changes. Experiments show that UMAS3D supports addition, deletion, modification, appearance, and pose editing while effectively preserving unedited source content. These advances make UMAS3D a unified framework for flexible and source-preserving 3D editing across diverse editing conditions.
Read the full abstract

All authors Xianlin Zeng, Xiaolong Shen, Ruijie Quan, Yi Yang

Sound

Sleep Sound Event Detection Powered by Learnable Multi-Resolution Adaptive Line Enhancer

Chanwoo Park and Chanwoo Kim

Sleep-disordered breathing, including snoring, hypopnea, and obstructive apnea, is the hallmark of obstructive sleep apnea, whose severity is quantified by the Apnea-Hypopnea Index (AHI). As conventional polysomnography is costly and clin- ically demanding, microphone-only detection has emerged as a noninvasive alternative for screening. We propose ALE- Confidence Fusion Sound Event Detection (ACF-SED), the first framework that directly injects the per-frame confidence map of an Adaptive Line Enhancer (ALE) into Transformer atten- tion biasing and feature modulation, rather than as mere pre- processing. A Multi-Resolution ALE Bank aggregates three parallel NLMS filters at distinct decorrelation delays, while a Confidence-Guided Cross-Path block couples event and noise streams via gated cross-attention. On the Audio-Polygraphy Dataset for Sleep Apnea Analysis, ACF-SED achieves state- of-the-art detection across Event-F1, Segment-F1, and PSDS, enabling end-to-end AHI estimation.
Read the full abstract

Statistical Methodology

Identifying and Measuring Treatment-Effect Heterogeneity across Sites through Within-Site Randomization

Takahiro Hoshino

Parallel cluster-randomized trials can identify mean effects by site characteristics and risk differences between fixed predictors, while leaving residual heterogeneity and absolute prediction risk (mean squared error of site-effect predictions) unidentified. We acquire missing same-site cross-arm information by randomizing participants within selected sites. Under randomized site selection with compatible participant reference distributions and intervention versions, we characterize necessary and sufficient observation patterns for quadratic targets in a model with unrestricted joint distributions of site response means. From finite independent participant samples, we construct unbiased moments and exact covariances. Under regularity conditions, we prove consistency as informative paired site counts grow, allowing fixed within-site sample sizes. For a fixed predictor, we optimize paired-site selection and unequal cell counts using corrected risk variances, pilot error, and costs. In an International Stroke Trial information-deletion experiment, pilot allocation reduces the conditional variance of reconstructing the complete-information corrected risk estimate by 34.3% relative to uniform allocation with equal expected cost. In 40 Honduras villages, correction reduces estimated residual variation from 0.04081 to 0.00282 in squared log-consumption units for the same fixed explanatory basis; the explained share rises despite a smaller explained component, illustrating how participant sampling noise can inflate estimated residual variation.
Read the full abstract

Quantum Physics

Breakdown of thermalization in quantum spin systems with long-range interactions

Filippo Caleca, Fabio Mezzacapo and Tommaso Roscilde

Quantum thermalization of closed systems – i.e. the relaxation of local properties to their thermodynamic value along the Hamiltonian evolution – is generically expected in non-integrable systems at finite energy density. In this work we show that quantum spin systems with at least one spin component coupled through long-range ferromagnetic interactions, and a second spin component coupled to a field, cannot in general thermalize to a paramagnetic state whenever they have a finite, negative energy per spin. The long-range interactions we consider decay as a power law of the distance, $\sim r^{-\alpha}$ with $\alpha < d$, where $d$ is the number of spatial dimensions of the system. The lack of thermalization is generic to an infinite family of Hamiltonians, and it is not associated to any form of integrability. It can instead be understood by the anomalous features of the thermodynamics of the system in the paramagnetic phase, which cannot be reflected in the properties of the eigenstates. This leads to a breakdown of eigenstate typicality and of the eigenstate thermalization hypothesis. Interestingly, the non-thermal states emerging at long times in the dynamics display long-range multipartite entanglement, elevating the breakdown of thermalization to a resource.
Read the full abstract

Artificial Intelligence

Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems

Xiuming Liu, Le Gai, Zhiyuan Chang et al. (+4 more)

Agent-to-agent protocols allow LLM agents to discover peers, exchange results, and coordinate tool use. A locally successful protocol attack, however, may be rejected by a later agent or propagated into a consequential task decision. Measuring local exploitability alone leaves this difference unresolved and provides limited evidence about which participant caused the final outcome. We present Agent-Canary-Mas, an end-to-end evaluation system that follows protocol risk through long-horizon multi-agent tasks. It covers five risk classes and 13 subclasses across A2A, ANP, and BCS, with 975 matched malicious–benign task pairs in five business domains. A shared OpenClaw framework runs autonomous, tool-using agents under different underlying models while preserving the task and execution setup. Matched runs separate local protocol success from downstream consequences; retained evidence connects participant selection, message consumption, tool activity, and task-state changes. We further evaluate a protocol-context Guard that checks an object's authority at consequential handoffs. Across three model conditions, local attack success is frequently at or above 90%, while consequence conversion ranges from 7.1% to 100.0%. Cross-agent evidence raises macro-averaged Audit-F1 from 29.7% to 95.5%. On Finance tasks, the Guard lowers average ASR from 86.1% to 53.8% and PTCR from 65.5% to 31.2%, with a measurable completion tradeoff. These results show that protocol risk depends on how agents use exchanged objects throughout the task, and that evaluating this path supports more informative risk assessment, attribution, and defense.
Read the full abstract

All authors Xiuming Liu, Le Gai, Zhiyuan Chang, Peiyang Li, Bin Zhu, Shuo Wang, Chao Feng

Analysis of PDEs

A Viscoelastic Wave Equation with Nonlinear Damping and Supercritical Variable-Exponent Logarithmic Sources

Menglan Liao and Mingxue Zhang

We investigate a viscoelastic wave equation with nonlinear variable-exponent damping and a variable-exponent logarithmic source, allowing supercritical growth. The main difficulties arise from the failure of the source to map the energy space into $L^2(\Omega)$, the sign-changing logarithmic potential, and the lack of Sobolev control of the displacement for supercritical damping. Under an exponent condition linking the source and damping exponents, we prove local existence, an energy identity, and a continuation criterion. We prove finite-time blow-up for nontrivial solutions with nonpositive shifted initial energy. We also establish a blow-up criterion based on a sufficiently large initial displacement–velocity pairing, with a threshold depending on the positive part of the shifted initial energy, and derive an explicit upper bound for the lifespan. This criterion allows us to construct blow-up data at every prescribed level of the original energy. For initial data in a suitable stable region, solutions exist globally. For damping within the Sobolev range, a general relaxation condition yields energy decay estimates that include exponential and polynomial rates. Beyond this range, a time-weighted displacement estimate and a splitting of the memory integral give logarithmic decay.
Read the full abstract

Computation and Language

A Step in the Right Place: Understanding and Optimizing Timestep Placement in Continuous Diffusion Language Models

Shutian Zheng, Zhihong Yu, Linye Wei et al. (+2 more)

Continuous diffusion language models represent an emerging paradigm for language modeling. They generate text in parallel by iteratively refining continuous representations and mapping them back to tokens through a decoder. However, realizing the efficiency advantage of parallel generation requires maintaining generation quality with only a few denoising steps. Even when the number of steps is fixed, their placement along the denoising trajectory remains flexible. In this paper, we demonstrate that changing timestep placement alone can substantially alter the final latent representations and thereby affect the decoded token distributions. Building on these findings, we introduce StepTune, an algorithm that searches for timestep placements that improve generation quality. The search is conducted on a small calibration set and guided by a language-aware objective, with the model and sampling budget fixed. Once calibrated, the timestep placement is fixed and reused across inputs. Experiments demonstrate consistent improvements in unconditional generation perplexity and conditional task metrics across all evaluated sampling budgets. In particular, StepTune enables 16-step sampling with a frozen model to outperform its native 64-step baseline on both XSum summarization and WMT14 translation and reduces end-to-end latency by approximately $3.8\times$. These results establish timestep placement as a practical means of improving the quality-efficiency trade-off in continuous diffusion language models.
Read the full abstract

All authors Shutian Zheng, Zhihong Yu, Linye Wei, Zeyang Zhang, Meng Li

High Energy Physics (Phenomenology)

Quantum circuit representation and incomplete Bell measurements in Compton scattering

Wei Xie, Yu-Chen Guo, Shuang Li et al. (+1 more)

We formulate massless tree-level Compton scattering as an effective two-qubit operation on electron and photon helicities. In the Bell basis, the scattering map separates into two parity sectors and admits a simple quantum circuit representation with one nonunitary filter. After Kraus normalization, this filter defines an unsharp incomplete Bell measurement that distinguishes the two Bell-parity sectors but not the relative Bell label within each sector. We further show that the incomplete measurement alone does not surpass the classical teleportation threshold, whereas a subsequent complete Bell-basis readout enables unit conditional teleportation fidelity.
Read the full abstract

All authors Wei Xie, Yu-Chen Guo, Shuang Li, Ji-Chong Yang

Number Theory

A linear independence criterion for $p$-adic Hurwitz zeta values at odd integers

Makoto Kawashima and Anthony Poëls

In this article, a new criterion is established to obtain the linear independence of some values of the $p$-adic Hurwitz zeta function at odd integers $s\geq 3$. We generalize a theorem of F.~Beukers, who gave, among others, an alternative proof—using Padé approximation theory—of a result originally due to F.~Calegari on the irrationality of the $p$-adic Riemann zeta value $\zeta_p(3)$ for $p = 2, 3$. To prove our main theorem, we work in a general setting, where we construct and study new Padé approximants of Laurent series satisfying the functional equation $f(z) = f(1-z)$. This complements our previous work on the linear independence of $p$-adic polygamma values.
Read the full abstract

Medical Physics

BOLD PSF: Impact of k-space trajectories and timing on the depiction of T2* contrast

Maria Engel, Lars Kasper and Klaas P Pruessmann

The timing of BOLD-fMRI is typically chosen such that TE matches T2*. This assumes contrast being exclusively elicited by signal differences at TE. While sensible for short or TE-symmetric readouts, such as EPIs, it oversimplifies contrast generation for longer or TE-asymmetric trajectories, such as spirals. We propose the concept of a BOLD PSF for a more comprehensive perspective on the imaging characteristics of a functional experiment. Our findings indicate that TE can be reduced for spiral-out without sacrificing BOLD-sensitivity when compared to EPI. Furthermore, we characterize the intrinsic trade-off between specificity and resolution of the BOLD response under varying TE.
Read the full abstract

Information Retrieval

Rethinking Evidence Modeling: Context-Coupled Graph Learning for Multimodal Recommendation

Mingqiao Zhang, Qiyao Peng, Yumeng Wang et al. (+3 more)

Multimodal graph recommendation integrates observed interactions with item images and text to learn user preferences. These inputs constitute Semantic-Behavioral Evidence (SBE). Many existing graph methods incorporate collaborative and multimodal semantic relations, yet their aggregation and state updates remain context-separated, limiting the continuous composition of preference evidence across layers and the joint use of multiple sources. To address this limitation, we propose CC-MGRec, a context-coupled graph learning method that organizes SBE within a common graph learning context for cross-relation modeling and compositional propagation. Its context-coupled multimodal graph integrates user-item collaborative relations and item-item semantic relations, coordinating their message scales through joint normalization. Recommendation-grounded semantic calibration uses training behavior to adjust semantic neighbor weights while preserving normalized collaborative propagation coefficients. Collaborative-semantic compositional propagation updates shared node states layer by layer to continuously compose collaborative and multimodal semantic evidence, implicitly forming Preference Evidence Chains (PECs), including collaborative-semantic and visual-textual PECs. Joint execution of relation messages on the same shared node states within each layer preserves propagation outputs while reducing intermediate output processing and fusion overhead. We provide theoretical analysis of the proposed mechanisms. Experiments on three Amazon datasets demonstrate improved recommendation quality and faster inference during graph propagation.
Read the full abstract

All authors Mingqiao Zhang, Qiyao Peng, Yumeng Wang, Wenzhe Dong, Hongtao Liu, Jian Yang

Robotics

GNFormer: Gaussian Neural Field Transformer for Efficient Camera-based Occupancy Prediction

Guangcheng Chen, Li He and Hong Zhang

Camera-based occupancy prediction provides geometric and semantic scene understanding for robot perception and has been adopted in autonomous vehicle and UAV perception systems. Gaussian primitives offer a promising alternative by potentially representing only occupied regions, thereby concentrating computation and representational capacity where needed and reducing wasted computation and memory in empty space. However, existing Gaussian-based methods suffer from poor primitive utilization, as ineffective training objectives leave some Gaussians in empty space, while the limited expressiveness of Gaussian functions restricts their ability to model complex shapes. To address these limitations, we propose a novel 3D representation, Gaussian Neural Field (GNF), which can accurately map voxel positions to semantic occupancies. In GNF, Gaussians and a neural network jointly parameterize the field, where the Gaussians define its spatial support and provide features for neural decoding, while the neural network enables more expressive occupancy modeling than Gaussian functions alone. We further develop the Gaussian Neural Field Transformer (GNFormer), a streamlined and flexible method that predicts GNFs for camera-based occupancy prediction. Across Occ-ScanNet, SSCBench-KITTI-360, and nuScenes-SurroundOcc benchmarks, GNFormer achieves the highest IoU and mIoU and the fastest inference among the compared single-frame methods. In the experiments, GNFormer can represent indoor and outdoor scenes with only 256 and 1024 Gaussians, respectively, substantially fewer primitives than prior Gaussian-based methods. The code will be released.
Read the full abstract

Algebraic Geometry

Crystals and the parabolicity conjecture

Marco D'Addezio

These notes introduce crystals and crystalline Dieudonné theory through the example of abelian varieties. After discussing $p$-divisible groups, $F$-isocrystals, slope filtrations, and overconvergence, we explain the parabolicity theorem for $F$-isocrystals and some of its applications to monodromy and Hecke orbits. Two appendices formulate research projects on isocrystals over formal schemes and on monodromy beyond the constant-slope setting. The exposition is intended for readers familiar with basic algebraic geometry and the étale and fppf topologies; prior knowledge of Witt vectors is helpful but not required.
Read the full abstract

Game Theory

Improving the Bounds on Approximating Weighted Maximin Share for Chores

Trung Thanh Nguyen, Khaled Elbassioni and Jörg Rothe

We investigate the problem of allocating indivisible chores among agents with arbitrary positive weights and additive nonnegative cost functions. An allocation is said to be $\alpha$-weighted-maximin-share (WMMS) fair if the cost incurred by each agent is at most $\alpha$ times her weighted maximin share. We establish that every instance admits a $4.124234528$-WMMS allocation. Moreover, for instances in which all weights and costs are rational numbers represented in binary, we give an algorithm that computes a $4.12424$-WMMS allocation in time polynomial in the number of agents, the number of chores, and the total binary encoding length of the input. Complementing these upper bounds, we construct a family of instances with strictly positive, identically ordered costs for which the optimal WMMS approximation factors converge to $e$. Together, our results substantially narrow the previously best-known gap of $[2,12]$ established by Li et al.~\cite{LWX26} to $[e,4.12424]$.
Read the full abstract

Optics

From Microresonator to Packaged Microcomb System: Fiber-Coupled Module and System Integration

Yudai Matsumura, Yoshihiro Makimoto, Tsutomu Mizuguchi et al. (+4 more)

We demonstrate a compact and robust soliton microcomb source designed for field-deployable operation. A directly fiber-coupled SiN microresonator was integrated with precise thermal control into a palm-sized module, reducing the footprint and volume by 16- and 81-fold, respectively. The module, together with the laser sources and optical amplifiers required for microcomb generation, was further integrated into a 19-inch rack-mounted enclosure, achieving system-level footprint and volume reductions of 2.3- and 3.7-fold, respectively. The packaged system achieved a 90% manual startup success rate and maintained continuous soliton operation for 18.8 days, while remaining operational under substantial temperature variations. A state-based automated startup scheme using discrete microcomb-state evaluation achieved single-soliton generation without manual intervention with success rates of 50% within 2 min and 60% within 3 min. Moreover, automated soliton initiation and sustained operation were demonstrated while the packaged microresonator module was directly subjected to random mechanical vibration. These results provide a practical platform for compact, robust, and field-deployable microcomb sources.
Read the full abstract

All authors Yudai Matsumura, Yoshihiro Makimoto, Tsutomu Mizuguchi, Masayuki Higaki, Yu Tokizane, Naoya Kuse, Takeshi Yasui

Machine Learning

OceanFlow: Coherent Flow Matching for Probabilistic Ocean Modeling

Yuan Gao, Fan Xu, Hao Wu et al. (+1 more)

Probabilistic ocean modeling is essential for risk-aware marine operations, climate analysis, and scientific decision-making, where downstream decisions depend on the conditional distribution of future ocean states rather than a single deterministic trajectory. Recent data-driven ocean models have made deterministic global ocean modeling increasingly accurate and efficient, but probabilistic ocean modeling remains underdeveloped. Specifically, perturbation-driven ensembles can create spread without explicitly optimizing the joint distribution of their members, often yielding poor calibration and physical inconsistency. To address these issues, we propose OceanFlow, a coherent flow matching framework for probabilistic global ocean modeling. OceanFlow first establishes a sharp, stable mean anchor for the conditional ensemble. Flow matching then learns a coherent state-conditioned pathwise law that jointly reshapes the residual distribution around this anchor at each transition, preserving the predictive center while refining state-dependent uncertainty. We further introduce a Factorized Dynamics Operator (FDO), which combines factorized transitions with a learned state-conditioned response to parameterize the mean anchor and residual-flow velocity. Extensive experiments show that OceanFlow improves ensemble-mean accuracy, probabilistic reliability, and physical-consistency diagnostics over competitive baselines, supporting coherent flow matching as an effective route toward data-driven probabilistic ocean modeling. Code is available at https://github.com/YuanGao-YG/OceanFlow.
Read the full abstract

All authors Yuan Gao, Fan Xu, Hao Wu, Xiaomeng Huang

Representation Theory

On a derived equivalence classification of weakly symmetric algebras of Euclidean type

Hideto Asashiba, Ayako Itaba and Manuel Saorin

We consider a family $(\Lambda_\lambda)_{\lambda \in \Bbbk^\times}$ of weakly symmetric algebras of Euclidean type over an algebraically closed field $\Bbbk$, where $\Bbbk^\times:= \Bbbk\setminus \{0\}$, and for each $\lambda \in \Bbbk^\times$, $\Lambda_\lambda$ is socle equivalent to $\Lambda_1$, which is the trivial extension of a hereditary algebra of type $\tilde{A}$. We compute their Hochschild cohomologies, which shows that $\Lambda_\lambda$ is not derived equivalent to $\Lambda_1$ if $\lambda \neq 1$. This means that a derived equivalence classification of weakly symmetric algebras of Euclidean type given by Bocian–Holm–Skowroński is not complete.
Read the full abstract

Game Theory

Robust Proportionality Axioms for Additive Utilities

Piotr Skowron

We study the model of participatory budgeting, in which a subset of candidates is selected subject to a budget constraint. Voters express their preferences by assigning a numerical utility to each candidate. Our focus is on formal analysis of proportionality, a central notion of fairness in multi-winner elections. Intuitively, proportionality means that each group of voters should influence the election outcome roughly in proportion to its size. Recent "plus" axioms of proportionality are particularly appealing notions: they are verifiable in polynomial time, and they provide strong representation guarantees without requiring groups of voters to have cohesive preferences. However, their existing formulations are restricted to approval-based preferences. We generalise extended justified representation plus (EJR+), and Core plus (Core+) to general additive utilities. Our approach builds on a payment-based interpretation of proportionality: candidates' costs are shared among their supporters, with the aim of balancing voters' total payments.
Read the full abstract

Computer Vision

Semantically Steerable Image Tokenization

Danilo de Goede, Mohammad Mahdi Derakhshani, Yuki M. Asano et al. (+1 more)

Adaptive image tokenizers compress an image into a variable number of tokens matched to its complexity, and recent work makes this allocation controllable: conditioned on a target reconstruction error, the tokenizer itself decides how many tokens an image needs. However, the fidelity measure guiding this allocation shapes which aspects of the image are preserved under compression. The pixel-wise error used in prior work is blind to the spatial structure that carries an image's meaning, and under heavy compression such tokenizers are prone to abruptly discarding tokens that encode essential content. We introduce GIST (Guided Image Semantic Tokenizer), an adaptive tokenizer that can be steered toward a requested semantic fidelity. Its token allocation is jointly controlled by pixel-level and semantic target errors, with semantic error measured in the feature space of a frozen DINOv3 encoder. This joint control enables semantic protection: with the semantic target fixed at zero, the reconstruction target can be relaxed to discard pixel detail while preserving what the image depicts. In a controlled comparison on ImageNet-100, GIST outperforms its pixel-controlled counterpart KARL at every token count, with up to $30\%$ lower LPIPS and $37\%$ lower DreamSim. On average, lowering its semantic target reduces LPIPS $2\times$ faster per token than lowering the reconstruction target, and up to $5\times$ in the low-token regime. Semantic fidelity is thus an effective control signal for adaptive tokenization: it lets a tokenizer see, and so preserve, what an image depicts.
Read the full abstract

All authors Danilo de Goede, Mohammad Mahdi Derakhshani, Yuki M. Asano, Cees G. M. Snoek

Machine Learning

SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning

Sankar Behera, Dhruv Singh, Satyadev Ahlawat et al. (+1 more)

Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardware-agnostic speedup. Existing post-training methods couple neuron selection and weight reconstruction through a shared calibration dataset, introducing domain bias and out-of-memory failures at high sparsity. We propose SARATHI, a framework that decouples these two stages. A data-free NMF Residual Subspace Probe scores neurons using intrinsic weight geometry, without accessing any calibration data, and carries a formal connection to Robust PCA. Adaptive OBS then reconstructs the pruned weights with a localized calibration batch, operating in $\mathcal{O}(d^2)$ peak memory per layer and eliminating the global memory bottleneck of coupled methods. A Bias Shift Compensation step corrects systematic activation drift in post-LayerNorm architectures that would otherwise cause perplexity collapse at high sparsity. Experiments across six models from two architecture families (gated and non-gated FFN) at 15–40% sparsity show that SARATHI achieves competitive perplexity and matches or exceeds existing structured pruning baselines on zero-shot accuracy.
Read the full abstract

All authors Sankar Behera, Dhruv Singh, Satyadev Ahlawat, Yamuna Prasad