Soft Condensed Matter
Meso-scale modeling of cohesive cavitation in polymer networks
Saleh Assadi, Zachary T. White, Fay Salmon et al. (+6 more)
Cavitation influences the failure of elastomers and soft adhesives, but connecting its microscopic initiation to subsequent cavity growth remains challenging. Here, we develop a discrete mesoscale framework that combines finitely extensible, breakable strands with local van der Waals interactions to examine how cohesion and network heterogeneity transform distributed dilation into localized damage. In the simulations, local cohesive instability produces a network-scale precursor whose subsequent expansion is coupled to strand stretching and rupture. Cohesive strength and intrinsic defect size govern the critical hydrostatic tension, while cohesion also controls the number and spatial distribution of cavities. Under confined loading, decreasing the layer thickness promotes multiple cavities and distributed strand rupture, extending the load-bearing response and increasing the critical work density of rupture. An energetic interpretation based on the thickness dependence of the crack-driving force connects these observations to competition between additional cavity nucleation and propagation of existing damage. The results link local cohesive instability to the collective
evolution of cavities and rupture in disordered
polymer networks.
Read the full abstract ▾
All authors Saleh Assadi, Zachary T. White, Fay Salmon, Nitin Hansoge, Zhuonan Liu, Victor Crespo-Cuevas, Jason Clapper, Nikolaos Bouklas, Franck J. Vernerey
Astrophysics of Galaxies
Untangling Similarities and Differences in Star Formation Histories Across Cosmological Simulations
Alicia M. Savelli, Matthew A. Kustec, Joshua S. Speagle et al. (+5 more)
How
galaxies assemble depends on processes ranging from small-scale baryonic physics to large-scale cosmological assembly, which are difficult to disentangle with observations alone. Using $\sim$63,000 simulated
galaxies from seven cosmological simulations spanning hydrodynamical, semi-analytic, and semi-empirical models, we explore how specific
star formation histories (sSFHs) vary across modelling assumptions. Using non-linear dimensionality reduction (UMAP), we find that sSFH shape variation organizes along a few smooth axes in a 2D
embedding, broadly corresponding to (1) peak timing, (2) peak sharpness, and (3) subsequent quenching rate. We identify sSFH shapes that many simulations share ("common"), well described to first order by dark matter
halo assembly, and a few tied to individual simulations ("unique"), which likely reflect subgrid and parametrization choices such as merger-triggered burst prescriptions. A notable exception is a common population of rapidly quenched
galaxies found across most simulations, likely driven by e.g., active galactic
nucleus (AGN) feedback, that
halo assembly alone cannot reproduce. The origin of the most distinctive unique shape, an Illustris-dominated history with an early peak and slow decline, remains unclear, but we test the effects of short-term variability. With a multi-objective auto-encoder neural network, we recover the simulation that a given sSFH is drawn from with $\sim$95% out-of-sample accuracy; ablation tests indicate this information is embedded in long-timescale sSFH morphology rather than short-term variability. These results provide avenues for theoretical and observational follow-up connecting
star formation histories to subgrid physical models.
Read the full abstract ▾
All authors Alicia M. Savelli, Matthew A. Kustec, Joshua S. Speagle, Kartheik G. Iyer, Eshal Ahmed, Zehao Peng, Norman Murray, Cissy Kuang
Computation and Language
claimcheck: Measuring and Improving Specification Faithfulness
Martin Amster, One An, Holly Baker et al. (+3 more)
Formal verification proves that a program satisfies its specification, but says nothing about whether the specification captures what the author meant. As LLMs increasingly write both code and specifications, a gap between the author's natural-
language requirement and the specification becomes a live risk. A machine-checked proof of a property narrower than the one requested is worthless but passes every check. Closing this gap is solving the spec formalization problem: given a natural-
language requirement, produce a formal artifact whose meaning matches it. To measure the gap, we curate an end-to-end
benchmark for spec formalization spanning four formal
languages: Dafny contracts and Lean 4, Isabelle and Rocq
theorem statements. Each of its 3,234 rows pairs a natural-
language requirement with a formal artifact and a label established by execution, by proof, or by the
benchmark it is drawn from. A third of the rows are meaning-preserving rewrites of the artifact that keep the faithful label, so a judge cannot score by detecting that a row was edited. We introduce claimcheck, a tool that detects incorrect formalizations: the formal artifact is translated back into plain English by a model that never sees the requirement, and a separate model, the judge, decides whether the informalization and the requirement express the same guarantee. On all four
languages it gains 8.2 to 9.8 points of macro recall over a single call shown the requirement and the artifact, and 4.2 to 6.0 over that call handed the same list of meaning-preserving rewrites. Showing the judge the artifact as well costs 1.4 to 4.5 points. Across four judges that also see the artifact, the gain shrinks as the judge gets stronger, to within a point of the informed single call for the strongest.
Read the full abstract ▾
All authors Martin Amster, One An, Holly Baker, Fernanda Graciolli, Simon Henniger, Nada Amin
Rings and Algebras
A Gordon–Green-type result for Gorenstein-projective modules
A. M. Bouhada and M. Laaraj
Let \(\Lambda\) be a \(\Z\)-graded Artin
algebra which is Iwanaga–Gorenstein. We prove that \(\Lambda\) is CM-finite if and only if the category of gradable Gorenstein-projective modules has finite type, and if and only if the lengths of the indecomposable gradable Gorenstein-projective modules are bounded. Moreover, if \(\Lambda\) is CM-finite, then every Gorenstein-projective \(\Lambda\)-module is gradable. These results provide Gorenstein-projective analogues of the corresponding
theorems of Gordon–Green for graded Artin
algebras of finite representation type.
Read the full abstract ▾
Computer Vision
Brain2Face: A Study on the Relation of EEG Signals and Spatio-temporal Head Avatars
Camilo Andrés Martínez Martínez, Olaf Dünkel, Kartik Teotia et al. (+3 more)
Driving digital head avatars is classically done by hand-crafted artist design or by image-based facial performance capture. In this work, we ask whether spatio-temporal tracking of the humans's head geometry and appearance can be performed solely from
brain signals, i.e., Electroencephalography (
EEG). Since prior work mostly focused on activity and emotion recognition, this task is relatively unexplored without even having publicly available high-quality
datasets and
benchmarks. Thus, we contribute a
dataset featuring paired
EEG and human head geometry as well as appearance annotations. We synchronize 64-channel
EEG with per-frame expression latent codes of a personalized Gaussian head avatar. Second, we introduce a baseline to the task of expression recovery of a head avatar from
EEG signals. To this end, we propose a dedicated
EEG-to-expression model that takes a temporal sequence of
EEG signals as input and regresses the latent expression parameters of the 3D Gaussian head avatar. Lastly, we validate our capture and algorithmic design choices through a
benchmark protocol that we introduce to this task. We believe this work paves the way towards better understanding of the relation between
EEG signals and facial surface as well as appearance changes.
Read the full abstract ▾
All authors Camilo Andrés Martínez Martínez, Olaf Dünkel, Kartik Teotia, Maurice Rekrut, Christian Theobalt, Marc Habermann
Computer Vision
WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs
Ameen Ali, Tamim Zoabi, Lior Wolf et al. (+1 more)
Video language models represent a
video as a long sequence of visual
embeddings in a decoder's input. Every visual
embedding is processed by every decoder layer during prefill, stored in the key value cache, and attended by every generated
token, so a long
video raises prefill,
memory, and generation cost at once. We present WIRE (Weight Space Implicit Representation Encoding), which reduces this recurring cost by moving part of the
video conditioned computation of a frozen
video language model from its input activations into a temporary low rank update of its weights. WIRE keeps a short explicit visual context, so the update acts as a correction rather than a replacement of the
video. WIRE first compresses the full resolution
embeddings of each frame into a small set of carrier
tokens using a question conditioned bidirectional selective scan, and physically contracts the decoder input so every decoder layer, cache entry, and decoding step operates on the shorter sequence. Hypernetworks at selected decoder layers read the compressed forward pass together with a readout of the full resolution features removed by contraction and generate LoRA updates to the
attention and feedforward projections. The updates are merged after prefill, so autoregressive decoding runs the unmodified frozen backbone. On Qwen3-VL-8B, WIRE with 16 carrier
tokens per frame contracts the visual stream by $3.5\times$, reduces decoder prefill time by $3.35\times$ at 256 frames and $4.14\times$ at 1024 frames, shrinks the key value cache proportionally, and keeps per
token decoding latency approximately constant. Across nine
benchmark settings at 256 frames, it obtains the highest average accuracy among efficient
video language models we evaluate under a common 256 frame budget.
Read the full abstract ▾
All authors Ameen Ali, Tamim Zoabi, Lior Wolf, Chaim Baskin
Computer Vision
MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation
Vincenzo Marcianò, Xiaoming Zhang, Gianluca Guglielmo et al. (+3 more)
Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, which require each prediction to be paired with a ground-truth mask. Yet two limitations arise in practice: they are inapplicable when predictions are made on unlabeled data; and even when annotations are available, they cannot assess whether a collection of predictions matches the distributional structure of the ground-truth population. We introduce MID (Mask-Image Distributional Divergence), a distribution-level evaluation metric for medical image segmentation. MID builds upon the observation that segmentation quality is a property of the joint image-mask distribution: a mask may be anatomically plausible in isolation yet incorrect for the image it accompanies. MID compares the joint distribution of images and masks between a reference set and a set of predictions, without requiring sample-wise correspondence. This captures both mask realism and image-mask consistency. We evaluate MID across 13 publicly available
datasets spanning CT, MRI, and MRA. Under anatomically realistic corruptions across 56 organ groups, MID tracks mean Dice and Hausdorff distance without per-sample ground-truth pairing. MID also detects distributional shifts across modalities and anatomies, identifies image-mask misalignment through controlled shuffling experiments, and produces reliable model rankings across real segmentation models. Official implementation available at github.com/erc-caravel/pytorch-mid
Read the full abstract ▾
All authors Vincenzo Marcianò, Xiaoming Zhang, Gianluca Guglielmo, Michela Antonelli, Sebastien Ourselin, Maria A. Zuluaga
Fluid Dynamics
Preferential concentration in a periodically forced particle-laden turbulent planar jet
Mohammad Ahmad, Pierre Bragança, Christophe Cuvier et al. (+1 more)
Periodic forcing is common in particle-laden jets, yet its influence on
turbulence and inertial-particle clustering remains poorly understood. We investigate a turbulent planar jet at two Reynolds numbers, approximately 4950 and 9900 based on nozzle height, subjected to sinusoidal forcing at a frequency three orders of magnitude below the preferred jet instability. Hot-wire anemometry and high-speed particle imaging characterise the carrier
turbulence, while Voronoi tessellations quantify preferential concentration of dilute inertial droplets. Despite its low frequency and moderate amplitude, forcing substantially modifies
turbulence while leaving the mean-flow development nearly unchanged. The integral scale decreases by up to $40\%$, while forced and unforced jets retain the same time-averaged relationship between the dimensionless dissipation coefficient and Taylor-scale Reynolds number. Within the forcing cycle, velocity fluctuations and the Taylor microscale vary approximately in opposite phase, keeping the Taylor-scale Reynolds number within $\pm10\%$ of its cycle mean despite substantial variations in dissipation and Kolmogorov time scale. Particle clustering is even more sensitive, with forcing increasing mean preferential concentration and producing phase-dependent variations of $21$–$49\%$ of the cycle mean. Clustering peaks when the Kolmogorov time scale is largest, corresponding to the smallest particle Stokes number. Thus, markedly different clustering states occur at similar instantaneous Taylor-scale Reynolds numbers. These findings demonstrate that weak temporal modulation can control particle organisation without substantially altering the mean transporting flow.
Read the full abstract ▾
All authors Mohammad Ahmad, Pierre Bragança, Christophe Cuvier, Martin Obligado
Materials Science
Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides
Vladislav Korostelev, Pjotrs Žguns and Konstantin Klyukin
Small polarons, formed when excess electrons become localized through
lattice distortions, play a critical role in charge transport, catalysis, and degradation processes in transition-metal (TM) oxides. Whether universal machine-learning interatomic potentials (uMLIPs), which lack explicit electronic degrees of freedom, can describe them remains unclear. Here, we investigate H-induced electron localization across a range of TM oxides using a
geometric descriptor based on TM-O bond-length expansion (Z-score) to identify polaronic distortions. We find that uMLIPs exhibit varying degrees of electron localization, from delocalized states to metastable small polarons, with their behavior strongly dependent on the training data and treatment of electronic correlations. In particular, the absence of Hubbard U corrections for specific TM cations in the training data leads to electron delocalization, in contrast to DFT+U predictions. Although some uMLIPs reproduce polaron hopping barriers during coupled
proton-polaron transfer, all of them fail to stabilize spatially separated polaron-donor configurations, instead favoring localization near the H dopant.
Read the full abstract ▾
High Energy Physics (Phenomenology)
Pallavi Bhardwaj and Michael Spannowsky
Lorentz
symmetry and the three-prong structure of hadronic top decays provide physical guidance for designing compact
quantum jet taggers. We introduce QGrAT (
Quantum Grade-Aware
Transformer), a
quantum transformer that incorporates these structures into its interactions between constituent
qubits.
Geometric features constructed from the constituent four-momenta are organised by the grades of the spacetime Clifford
algebra $C\ell(1,3)$, and their grade-specific inner products determine the pairwise
attention couplings. For fixed constituents and co-transforming reference vectors, these couplings are Lorentz invariant, although the component-wise input encoding makes the complete classifier frame dependent. An auxiliary
qubit introduces an explicit three-particle interaction through products of pairwise Minkowski inner products, while a trainable in-
circuit readout converts the resulting
quantum state into a classification score. We evaluate the architecture in state-vector simulation on the Top Tagging
benchmarks. With ten constituents per jet, the configuration using grades $0\text{-}3$ and the three-particle ancilla requires twelve
qubits and $144$ trainable parameters, reaching AUC $0.944 \pm 0.002$ and background rejection $1/\varepsilon_B = 35.7 \pm 2.4\ (96.8 \pm 7.7)$ at signal efficiency $\varepsilon_S = 0.50\ (0.30)$. This performance is competitive with the L-GATr-Slim baseline at matched constituent and parameter budgets. Adding the three-particle ancilla raises background rejection at $50\%$ signal efficiency from $19.9$ to $35.7$, whereas extending the representation to the tested grade-$4$ feature gives no consistent improvement. The study establishes a framework for incorporating spacetime geometry into
quantum attention and identifies explicit three-particle correlations as the principal source of improved background rejection among the architectural variations tested.
Read the full abstract ▾
Robotics
Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?
Jack B. Jedlicki, Amish Sethi and Heng Yang
We use a frozen frontier
vision-
language model, GPT-6-Astra, directly as the
robot policy on RoboMME, a
benchmark of 16
memory-dependent manipulation tasks spanning temporal, spatial, object, and procedural
memory. The model keeps the whole episode in context and outputs every end-effector waypoint and gripper command, with no RoboMME-specific training. On the 800 test episodes it succeeds in 92.1%, above the previously reported human score of 90.5%, which was obtained with an oracle skill interface, and far ahead of the best leaderboard entry (60.8%) and of a hierarchical system that pairs the same model with a RoboMME-trained policy (79.1%). It matches or exceeds the human score on 13 of the 16 tasks. Its 63 failures concentrate in two tasks and are mostly premature completions and mistimed or unintended button presses. These results blur the usual division between long-horizon planning,
memory and end-effector control, and raise the question of how much of this stack a single general-purpose model can take over in embodied systems. Project website: https://embodied-astra.github.io. Code,
prompts and all episode logs: https://github.com/jackbjed/embodied-astra-robomme.
Read the full abstract ▾
Number Theory
Higher derivatives of the Gram function
Marius Dundulis, Ramūnas Garunkštis, Antanas Laurinčikas et al. (+1 more)
We study the nonlinear phenomenon of the asymptotics of higher-order derivatives of the Gram function $t_u$. We also prove the uniform distribution and continuous uniform distribution modulo one of $t^n_u$ for $n = 1, 2, \dots$. We use AI to formalize our proofs in Lean.
Read the full abstract ▾
All authors Marius Dundulis, Ramūnas Garunkštis, Antanas Laurinčikas, Raivydas Šimėnas
Computer Vision
HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion
Yating Wang, Kui Wu, Ran Yi et al. (+5 more)
Modeling 3D hair strands is challenging due to complex hairstyle geometry, scarce high-quality training data, and incomplete or noisy input observations. Foundation models offer broader hairstyle priors, but their outputs are not directly usable for strand-based rendering and simulation. Existing approaches require costly per-instance optimization to fit hair priors to meshes from foundation models and 2D orientations from specialized predictors trained on limited hair data, restricting efficiency and generalization. We present HairFlow, a
multimodal conditioned
diffusion framework for efficient and controllable hair strands modeling. HairFlow conditions strand generation on two complementary representations: a coarse mesh that constrains global shape and multi-view sketches that specify local strand flow. HairFlow combines an Orientation VAE with a conditioned
diffusion transformer to generate volumetric fields that are traced into explicit strands. To overcome the lack of paired sketch-strand training data, we introduce an automatic synthesis pipeline that generates geometrically aligned multi-view sketches with diverse styles representative of inference-time inputs. Experiments show that HairFlow generates plausible 3D strands that faithfully follow the input conditions across diverse hairstyles, substantially reduces inference time, and supports flexible
multimodal control.
Read the full abstract ▾
All authors Yating Wang, Kui Wu, Ran Yi, Zixuan Lu, Tongtong Wang, Zhongtian Zheng, Lizhuang Ma, Yuefan Shen
Machine Learning
On the Statistical Mechanics of Attention
Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su et al. (+1 more)
We revisit the statistical mechanics of
Transformer attention via modern Hopfield models. We present a free-energy formalism to characterize parameter regimes and critical thresholds for robust
attention inference. The resulting free-energy landscape incorporates randomness in query states and
attention weights.
Attention then emerges as the equation of motion of the corresponding statistical-mechanical system (i.e., modern Hopfield model) through the standard free-energy minimization principle. This allows us to identify first-order phase transitions in
attention between glassy and robust-inference phases. We further extend to attentions with
stochastic queries and keys. Together, our results provide a rigorous statistical-mechanics framework for characterizing phase structure and inference reliability across a family of
Transformer attention mechanisms.
Read the full abstract ▾
All authors Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su, Han Liu
High Energy Physics (Phenomenology)
Non-accumulation of background-enhanced neutrino forces in proto-neutron stars
Himanshu Bora, Anupam Deka and Debajyoti Dutta
In a
neutrino background, the
vacuum two-
neutrino exchange potential $V \propto G_F^2 /r^5$ acts as a much longer-ranged interaction, scaling as $V\sim1/r$ for a directional background. A proto-
neutron star (PNS) hosts one of the densest astrophysical
neutrino environments known, and naturally provides a setting in which to test whether this pairwise enhancement produces a macroscopic Hartree contribution. We show that this does not happen. In the
spin-independent sector, averaging over pair orientations projects the background onto its angular monopole. The bulk Hartree contribution then saturates instead of growing with system size. We also find that the
spin-dependent parity-conserving and parity-violating terms do not generate macroscopic growth under the PNS mean-field conditions considered here. Thus, although the pair potential can be strongly enhanced, the resulting bulk interaction remains very small. The suppression comes from the angular and oscillatory structure of the kernel, not from screening. Within the Standard Model mechanism considered here, the effect is not important for the PNS equation of state or for events like
pulsar kicks.
Read the full abstract ▾
Optimization and Control
Vanishing Events and Regularity-Conditioned Reachability in Linear Stieltjes Systems
Francisco J. Fernández
We study linear Stieltjes control systems in which actuation is concentrated at finitely many temporal events, and we ask what happens when one of those events progressively loses its atomic weight in the associated Stieltjes measure. For constant coefficients, ordinary finite-atomic reachability is governed by a truncated Krylov space and is therefore insensitive to the positive values of the event weights. A different picture emerges once trajectory regularity is imposed. In the supercritical super-$g$-Hölder regime, we minimize the largest event-normalized state jump and characterize exactly the terminal directions for which this cost remains uniformly bounded as a prescribed event weight tends to zero. The characterization combines what can be reached before the vulnerable event, a drift-cancellability condition at that event, and the directions that remain available afterwards. Ordinary reachability of the deleted-event system can therefore be strictly larger than bounded-cost reachability in the singular limit. We also separate two mechanisms of divergence: loss of ordinary reachability after deletion and failure of the intermediate compatibility condition. For compatible targets, the minimum cost converges to a constrained deleted-event problem. A dimensionless position–velocity
benchmark motivated by pulsed proximity maneuvers shows the distinction explicitly.
Read the full abstract ▾
Soft Condensed Matter
Machine-learned topological transport of magnetic colloids
Sebastian Wohlrab, Aneena Rinu Perayil, Piotr Kuświk et al. (+6 more)
By modulating the orientation of a uniform
magnetic field it is possible to transport
magnetic microparticles above
magnetic patterns. In periodic patterns, driving control loops that wind around special orientations, which are dictated by the
symmetry of the pattern, induce transport by one unit
cell. The transport is topologically protected with trajectories controlled by the winding numbers of the control loop around the special orientations. In non-periodic patterns, the special orientations are position dependent, precluding a global characterization of the transport using a small set of winding numbers. We use here a reinforcement learning
agent trained with Brownian dynamics simulation data that uses the local environment of the
magnetic pattern to decide an action over the control loop. The
agent autonomously discovers topological transport protocols directly from the particle response without prior characterization of the
magnetic potential landscape. An
agent trained solely on a complex non-periodic pattern directly generalizes to completely unseen periodic, quasicrystalline, and disordered substrates. Moreover, the
agent dynamically adjusts the control loop to transport particles across
lattice defects and to counterbalance external drift forces that would cause static topological loops to fail. By adding a pathfinding
algorithm to the model, we additionally achieve simultaneous, independent transport of multiple identical colloids along different on demand trajectories. We demonstrate that the control loops can be directly transferred to an experimental setup to successfully drive
magnetic microparticles across a non-uniform
magnetic thin film.
Read the full abstract ▾
All authors Sebastian Wohlrab, Aneena Rinu Perayil, Piotr Kuświk, Maciej Urbaniak, Feliks Stobiecki, Arne J. Vereijken, Arno Ehresmann, Thomas M. Fischer, Daniel de las Heras
Machine Learning (Statistics)
Monitoring for Shifts at Unknown Times: Parameter-Free Conditional Conformal Martingales
Tuo Liu, Drew Prinster and Francesco Orabona
Conditional conformal test martingales provide sequential tests for detecting distribution shifts, using a fixed reference
dataset to avoid contamination from test-time samples. Prior work used a penalized betting function via online optimization with smoothing, clipping, and other hyperparameters, which can adapt slowly when a shift occurs after a long stationary period. In this work, we introduce an approach that requires no hyperparameters and provably adapts quickly to shifts occurring at unknown times. Our key idea is to frame the penalized betting problem as portfolio selection in a three-asset
market. Then, we use a restarting universal portfolio, with a heavy-tailed wealth allocation over time. We establish anytime false-alarm control and derive optimal finite-sample bounds on detection delay under detectable alternatives. We also develop an FFT-based implementation that computes the portfolio sequence over $T$ rounds in $\mathcal{O}(T^2\ln T)$ time, instead of $\mathcal{O}(T^3)$ of the naive implementation. Synthetic and real-world experiments suggest that the proposed approach adapts rapidly after long periods of null samples, with detection delays depending substantially less on shift time than prior baselines.
Read the full abstract ▾
Astrophysics of Galaxies
Intermittency in the Multiphase ISM — I. Extreme Density, Velocity, and Magnetic Fluctuations
Yue Hu
Intermittency is a fundamental property of astrophysical
turbulence because it concentrates strong gradients, dissipation, and transport into rare, localized structures. In the multiphase interstellar medium (ISM), turbulent driving is especially important because the balance between compressive and solenoidal motions can regulate how extreme fluctuations are distributed among thermal phases. Yet conventional increment statistics quantify intermittency without identifying the structures that host it. We analyze three matched ideal-MHD simulations of a thermally multiphase neutral medium that differ only in the compressive fraction of the driving. Density, velocity, and
magnetic-field increments are non-Gaussian in every thermal phase. Increasing compressive driving redistributes density and
magnetic fluctuations preferentially into the cold gas rather than uniformly enhancing them across phases. We identify the structures associated with extreme increments using local, scale-matched diagnostics of compression, thermal gradients, vorticity, strain,
magnetic curl, and
magnetic tension. Extreme
magnetic increments preferentially occur where
magnetic curl and
magnetic tension are simultaneously enhanced, more strongly than extreme velocity increments are associated with their kinematic hosts. Extreme velocity increments show comparable enrichment in vorticity and strain, whereas extreme density increments preferentially trace converging flows and thermal gradients only in the unstable medium. These associations weaken beyond a phase-dependent coherence scale. Our results show that turbulent driving controls how intermittency is partitioned among thermal phases, while distinct physical structures host extreme density, velocity, and
magnetic fluctuations.
Read the full abstract ▾
Applied Physics
Progress in Cavitated Front Gridline Ag Paste for PERC Solar Cell Architecture
Donald Intal, Sandra Huneycutt, Abasifreke Ebong et al. (+2 more)
This paper reports on the progress made with the cavitated silver paste on passivated emitter rear contact
cells (PERC) to reduce the series resistance. Thus, electrical and microscopy characterizations are used to examine these resistive losses. Fifteen 252 cm2 PERC
cells were fabricated for this assessment. Under standard test conditions, these
cells achieved a mean conversion efficiency of 21.87% and a maximum of 22.07%. The mean measured fill factor was 79.98%, compared with a pseudo-fill factor of 83.60%, giving a mean deficit of 3.62 percentage points. Fill factor decreased with increasing area-normalized series resistance, which ranged from 0.53 to 0.83 ohm-cm2, while open-
circuit voltage and short-
circuit current remained unvaried. These electrical trends support resistive current extraction as the principal contributor to fill-factor variation. Electroluminescence imaging revealed localized emission nonuniformity. Cross-sectional scanning transmission electron microscopy showed variation in the glass interfacial layer, while scanning electron microscopy identified micrometer and sub micrometer silver particles. Conductive atomic force microscopy after sequential removal of the bulk metal and glass revealed spatially heterogeneous current response. These observations are consistent with nonuniform electrical access at the contact, where restricted conducting pathways may concentrate on current and increase local voltage drops. The combined characterization identifies interfacial heterogeneity and the connectivity of conducting pathways as priorities for understanding and reducing extraction losses in cavitated silver metallization.
Read the full abstract ▾
All authors Donald Intal, Sandra Huneycutt, Abasifreke Ebong, Dana Hankey, Marshall Tibbetts
Statistical Methodology
Frequentist and Bayesian population pharmacometrics: similarities, differences, and practical implications
Jodie A. Cochrane, Haini Wen, Liang Yang et al. (+2 more)
Although the frequentist versus
Bayesian debate has a long-standing history, and both are well-established approaches for inference, they are often considered separately in pharmacometric literature, with their theoretical and practical differences receiving limited direct comparison. We address this gap by providing a conceptual background and comparative evaluation of frequentist and
Bayesian methods for parameter inference in pharmacometrics. First, we highlight the theoretical and algorithmic differences between approaches within a general and pharmacometric context. We then apply both to classical compartmental pharmacokinetic models using simulated and real data; initially through evaluating four inference methods (two frequentist, two
Bayesian) across a range of simulated data conditions, followed by investigating each inference approach in the practical setting. The simulation studies facilitate evaluation of the sensitivity of the methods to sample size, number of observations, residual noise and inter-individual variability, comparing the performance with respect to relative error, confidence/credible interval coverage and bias in the estimated variability. The real-world data analysis further highlights how each approach quantifies and presents uncertainty estimates by examining this for both the parameter estimates and system dynamics. By providing a theoretical and practical comparison that highlights the similarities and differences between approaches, this work aims to lower the barrier to understanding and implementing
Bayesian and frequentist inference in pharmacometrics.
Read the full abstract ▾
All authors Jodie A. Cochrane, Haini Wen, Liang Yang, Tyler Cassidy, Sara Hamis
Human-Computer Interaction
Human Situational Awareness and Workload during Heterogeneous Autonomous Vehicle Hazard Monitoring: A Cross-Platform Study
Ziyue Wang, Yang Xing, Argyrios Zolotas et al. (+3 more)
As autonomous ground and aerial vehicles become increasingly capable, human operators are transitioning from direct control to supervisory monitoring roles. Maintaining Situational Awareness (SA) during rare but safety critical hazard events remains a fundamental challenge, particularly when operators must monitor heterogeneous autonomous platforms with different spatial and cognitive demands. This study develops a unified experimental framework for investigating human SA and workload during supervisory monitoring of autonomous ground and aerial vehicles under hazard conditions. Eighteen participants completed six within-subject conditions combining three interface modalities, namely, visual-only, haptic-only, and visual-haptic, with two platform types, ground vehicle and aerial drone. SA was measured using Situation Awareness Rating Technique (SART), while workload was assessed using the NASA Task Load Index (NASA-TLX). The key findings are: 1) Aerial monitoring produced significantly lower overall SA, higher situational demand, and greater workload than ground monitoring, driven by elevated Demand and reduced Understanding rather than diminished Supply. 2) Workload was consistently coupled with situational demand across all conditions, suggesting a stable SA-workload mechanism. 3) Both haptic-only and visual-haptic significantly improved overall SA relative to visual-only without increasing workload, demonstrating that interface design can enhance awareness within the existing workload envelope. These findings establish a cross-platform behavioural baseline for designing
multimodal interfaces that enhance operator SA without elevating workload in heterogeneous autonomous vehicle systems.
Read the full abstract ▾
All authors Ziyue Wang, Yang Xing, Argyrios Zolotas, Adolfo Perrusquia, Weisi Guo, Antonios Tsourdos
Artificial Intelligence
Budgeted KV-Cache Repair for Evolving Contexts
Han Yu, Wenhui Zhu, Jincheng Cao et al. (+15 more)
Language-model
agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation. Later key-value (KV) states remain conditioned on the deleted content, while recomputing the entire retained suffix can be costly. We introduce budgeted KV-cache repair: recovering task performance by recomputing a user-chosen fraction of the retained suffix. Comparing repair allocations under identical relevance scores and
token budgets, we find that refreshing coherent regions can substantially outperform refreshing isolated
tokens. This finding motivates Semantic-Unit Refresh (SUR), which allocates the budget to query-relevant text regions using inexpensive
embedding scores, without training or an auxiliary
transformer forward. To execute these repairs efficiently, a layer-packed executor processes selected states together at each layer while preserving full causal cache access. Across five models, SUR achieves strong recovery in controlled deletion tasks while recomputing only 2-5% of the suffix. On four natural multi-hop QA
datasets, it achieves near-full-recompute exact match at a 5% budget with lower post-edit latency. The executor accelerates fragmented refresh by up to 16.1x over interval-wise execution.
Read the full abstract ▾
All authors Han Yu, Wenhui Zhu, Jincheng Cao, Rui Cai, Yuanda Xu, Zhengze Zhou, Xiwen Chen, Hao Wang, Xuanzhao Dong, Han Shi, Menglin Zhou, Shayan Mohajer Hamidi, Lin Su, Mina Razghandi, Sayan Ghosh, Qing Lan, Rohit Jain, Alborz Geramifard
Systems and Control
Filtering for Liveness: Recurrence via Backup Reachability Control Barrier Functions
David E. J. van Wijk, Pio Ong, Aaron D. Ames et al. (+1 more)
Liveness requires a dynamical system to repeatedly accomplish a desired objective over time. In this work, we consider a particular form of liveness known as recurrence, which requires the closed-loop trajectory to regularly revisit a prescribed set, with no more than a specified amount of time between visits. Inspired by the control barrier function (CBF) safety-filter paradigm, we develop a controller-filtering framework that makes adjustments to a nominal controller only when necessary to guarantee recurrence. Unlike conventional CBF methods, which enforce set forward invariance, our framework allows the trajectory to leave the set while guaranteeing its timely return. To achieve this, our framework combines two components: a backup reachability CBF that preserves the ability to return to the prescribed set within the allowable time, and a timing-based mechanism that invokes a reaching controller only when the nominal behavior would otherwise fail to meet the return-time requirement. The resulting framework guarantees recurrence while preserving the nominal behavior when possible, enabling control objectives that require temporary excursions from the set, such as traversal between disjoint regions. Our method is successfully utilized in a drone racing example with a recurrence constraint on beacon visibility.
Read the full abstract ▾
All authors David E. J. van Wijk, Pio Ong, Aaron D. Ames, Joel W. Burdick
Game Theory
An Introduction to Contract Theory for Computer Scientists
Paul Duetting, Michal Feldman and Inbal Talgam-Cohen
This survey introduces contract design to computer scientists: using outcome-based payments to incentivize effort. We discuss applications that motivate a computational approach to contract design, ranging from online labor
markets, to incentive-aware algorithmic classification, to emerging ecosystems of AI
agents. We present the classic principal-
agent model and introduce basic concepts. We show how optimal contracts are computable via linear programming, and why they can be opaque and brittle. Motivated by this we turn to simpler contract formats, specifically linear contracts. We discuss approximation guarantees, and robust (max-min) optimality of such contracts. We then move beyond the single-
agent setting to combinatorial contract settings with multiple
agents, mapping the algorithmic landscape of tractability and approximation. Finally, we discuss partial information settings through the lens of learning
algorithms, and outline open directions. The goal is a concise, accessible entry point that connects economic foundations with algorithmic tools and highlights opportunities for new theory and applications.
Read the full abstract ▾
Complex Variables
On the rank-one limit sets for maps in the constant-Jacobian shear group of $\mathbb{C}^2$
Luka Boc Thaler
Let $\mathcal{S}_c$ be the subgroup of $Aut(\mathbb{C}^2)$ generated by affine maps and shear automorphisms with constant Jacobian. We determine the possible conformal types of the rank-one limit set of an invariant recurrent Fatou component when the induced dynamics has infinite order. In particular we show that, under this infinite-order hypothesis, the limit set of a finite composition of Hénon maps (
polynomial or transcendental), can only be conformally equivalent to a disk or an annulus. Thus we exclude the remaining three conformal types, i.e. $\mathbb{D}^*$, $\mathbb{C}^*$ and $\mathbb{C}$, from the classification result by Arosio, Benini, Fornæss and Peters. We also prove that the set of fixed points of a finite composition of Hénon maps (
polynomial or transcendental) contains no entire curves.
Read the full abstract ▾
Quantum Physics
Generating Superposition of Transverse Ising Ground States by Quantum Interaction
Koushik Das, Sayan Mondal and Ujjwal Sen
We investigate superpositions of
quantum Ising ground states generated through a
quantum interaction, in which the nearest-neighbor coupling strength is promoted to an operator acting on a central auxiliary
spin. We prepare the central
spin in a superposition, which allows the chain to evolve coherently under different effective interaction strengths. The states are prepared by adiabatic
evolution of the joint system comprising the central
spin and the many-body
spin chain, followed by a measurement on the central
spin and post-selection of a specific outcome. It is possible to prepare superpositions of transverse-field
quantum Ising ground states belonging to the three
magnetic phases, namely, the paramagnetic, ferromagnetic, and anti-ferromagnetic phases. For a
spin-1/2 central system, it is possible to prepare superpositions of ground states belonging to any two phases, while for the
spin-1 case, the superpositions may contain three ground states, each belonging to one of the three phases. We analytically derive expressions for the magnetization,
spin correlations, and
entanglement of such states. The magnetization and
spin correlations show distinct features in different superposition sectors. The nearest-neighbor
entanglement is largest where the transverse field and Ising interaction compete, and its behavior differs from that of the
magnetic observables. We also derive the
quantum Fisher information relevant to estimating the Ising interaction strength. And it exhibits multiple peaks near the critical points of the constituent ground states, with the maximum value showing Heisenberg scaling, for the parameters and system sizes examined.
Read the full abstract ▾
Machine Learning (Statistics)
Accounting for model error in ensemble variational data assimilation through learned generative dynamics
Marc Bocquet, Tobias S. Finn and Sibo Cheng
Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models. Here, we focus on combining advanced sequential data assimilation schemes with a generative forecasting model which accounts for complex model errors. This generative model provides a
stochastic approximation of the conditional distribution of the successor state given the current state. The proposed variational formulation is a novel one-step weak-constraint 4D-Var scheme in which a learned conditional
stochastic forecast replaces the prescribed additive Gaussian model error representation. We derive and implement this formulation as an ensemble variational
algorithm, the generative iterative ensemble Kalman filter (IEnKF-G), which generalises the iterative ensemble Kalman filter with additive Gaussian model error (IEnKF-Q). We extend the method to a smoother with an assimilation window spanning multiple time steps and propose a simplified variant. The IEnKF-G is evaluated on a
stochastic variant of the Lorenz 1963 model to assess its robustness. It is then tested on a multi-scale variant of the one-dimensional Lorenz 1996 model, in which the resolved variables are affected by model error originating from the hidden small-scale variables. The
algorithm is then compared to an ensemble Kalman filter that adaptively mitigates model and sampling errors, and to the IEnKF-Q. The IEnKF-G is generally more accurate in the tested configurations, with substantial gains under partial observations and significant model error. This demonstrates the potential of generative data-driven models when paired with classical data assimilation methods, particularly when model error is substantial.
Read the full abstract ▾
Machine Learning
COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration
Damien Lo, Hong Kyu Lee, Ruixuan Liu et al. (+1 more)
Vision large
language models (VLLMs) are deployed in
privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership inference attacks (MIAs) commonly rely on
entropy statistics or generated descriptions, requiring costly generation with limited membership separation. Perturbation-based methods instead measure response changes but focus on large perturbations, leaving VLLM membership behavior under smaller perturbations poorly understood. We systematically characterize VLLM membership behavior under controlled Gaussian perturbations across noise levels at fine resolution. We find that optimal perturbation magnitude and membership-signal direction vary across model-
dataset pairs. In many settings, a previously unstudied low-noise regime yields stronger separation than large perturbations, with members exhibiting lower divergence than non-members, reversing the conventional score direction. Other settings retain the conventional direction, demonstrating that neither a fixed perturbation magnitude nor a predetermined score orientation is universally reliable. We propose COMPASS, an adaptive gray-box MIA that calibrates both the perturbation magnitude and membership-score direction using a loosely distribution-matched, known non-member reference set. We instantiate COMPASS using Renyi-normalized KL divergence and Renyi divergence, with max-k aggregation over the most informative image-logit positions. Across LLaVA v1.5-7B, MiniGPT-4, and HuluMed-32B, spanning pretraining, instruction-tuning, and medical-image
datasets, COMPASS outperforms baselines. On general-domain data, COMPASS achieves AUCs up to 0.88. On the distribution-matched medical evaluation, it reaches 0.64 AUC, while the strongest baseline remains at chance level. These results establish full-range adaptive perturbation analysis as an effective approach to VLLM membership inference.
Read the full abstract ▾
All authors Damien Lo, Hong Kyu Lee, Ruixuan Liu, Li Xiong
Artificial Intelligence
Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean
Tomas Ortega, Simon Park, Ayush Khaitan et al. (+3 more)
General-purpose coding
agents use standard shell and file interactions, yet formal
theorem-proving
agents often rely on specialized, ad-hoc tooling. This makes it difficult to determine which components of
theorem-proving
agents provide
benchmark gains: an improved base model, a specialized harness, a specific tool, or a combination of any of them. We introduce mini-Lean-
agent, a deliberately minimal
agent for Lean tasks whose only model-visible tool is bash. The model must use bash to inspect and edit the repository, search local libraries, invoke Lean, and manage its own intermediate work, while a separate trusted evaluator verifies the final artifact. We compare mini-Lean-
agent against AxProverBase and Numina-Lean-
Agent on the Putnam 2025
benchmark. Experiments with Gemini 3.8 Flash as the base model show that mini-Lean-
agent solves 7/12 problems at \$2 per problem limit, compared with AxProverBase's 4/12. With Astra as the base model, mini-Lean-agent solves 12/12 problems at an average cost of \$1.28 per problem. This suggests that a generic coding
agent with a minimal harness can already achieve strong performance on Lean
benchmarks. Our results motivate using mini-Lean-
agent as a standard baseline when evaluating
theorem-proving infrastructure.
Read the full abstract ▾
All authors Tomas Ortega, Simon Park, Ayush Khaitan, Liam Fowl, Alex Kontorovich, Sanjeev Arora