Papers

Behaviora is a preliminary conceptual architecture for representing agent and robot behavior, external and internal alike, in an addressable form. A behaving robot or agent performs a Behavior Episode composed of episode components, which can be derived from behavior taxonomies (BTax) and assigned persistent identifiers. We denote these identifiers as IoB (Internet of Behaviors) Addresses. A Behavior Episode specifies what the system does, while a Style Profile (SP) specifies how this behavior is expressed. Style can communicate characteristics of the actor and qualities such as competence and cultural manners. An Experience Profile (EP) represents behaviorally relevant internal state that modulates the execution of an Episode. Finally, a Behavior Compiler maps these behavioral representations to platform-specific actions. We use a primitive touching arm model to show these components and their relations. External Behavior is a result of addressable movements and their styles. Internal Behavior is represented through the same episodic principle and can be rendered as inner speech. Sensing, perception and complex task contexts have not been included in the present implementation, although a conceptual place is reserved for them.

KITE queries a typed behavioral kernel once per unique state, then executes populations of any size from the table with event-keyed randomness and common random numbers. An expensive flagship model is reserved for sparse paired anchors that estimate intervention effects. Measured human-model discrepancy is propagated as shared error into every conclusion. Population-experiment cost thus scales with unique states and anchors, while uncertainty is governed by evidence about people rather than Monte Carlo noise. On Epstein experiments with 9,070 participants, anchors covering 1.7% of states reduced effect error by 41% (absolute MAE reduction 0.0125). On 37 held-out SocSci210 experiments, 0.5-1.5% anchor coverage raised captured decision gain from 0.27 to 0.39. The kernel passed content-fidelity criteria in all 15 new countries of a 16-country study. Shared discrepancy yielded retrospective coverage of 93% and 96% at nominal 80% and 90%, versus 29% and 36% from human sampling uncertainty alone. A million agents executed 20 tabulated steps in 0.9 seconds on a laptop. This architecture offers a route to screening candidate interventions before human trials, multi-country content audits, and uncertainty-aware policy comparison at the cost of a few thousand kernel calls with sparse flagship anchors. Property-specific evidence records connect each use to its validation scope, correction provenance, and uncertainty, making these applications auditable.

In data-driven contextual stochastic optimization, existing approaches are predominantly frequentist: they commit to a single predictive model and treat it as ground truth, yielding prescriptions that are fragile to model uncertainty and sampling variability in small- and moderate-sample regimes. We propose Bayesian contextual optimization (BCO), a framework that maintains a Gibbs posterior over the parameter space. This decision-focused posterior weights candidate models by their empirical decision quality rather than statistical fit, thereby avoiding commitment to a potentially misspecified likelihood while encoding the full distribution of plausible models consistent with the data. A Bayesian contextual policy is then derived by minimizing the expected decision cost under the posterior predictive distribution, hedging prescriptions against model uncertainty by aggregating over the posterior. We establish three theoretical guarantees: (i) the Gibbs posterior concentrates exponentially fast around the frequentist best-in-class parameter set; (ii) BCO can strictly improve over the frequentist best-in-class policy when model uncertainty is non-negligible; and (iii) BCO attains an $O(n^{-1/2})$ excess risk rate against the oracle over all probability measures up to a misspecification term and an oracle aggregate gap. Computationally, we tailor a variational inference scheme that has the same per-iteration cost as frequentist alternatives and a gradient-free Metropolis-Hastings algorithm that handles nondifferentiable problems. Numerical experiments on two-stage shipment planning, contextual newsvendor, and return-constrained portfolio problems confirm that BCO consistently reduces out-of-sample cost and variance relative to kernel estimators and decision-focused baselines, with the most pronounced gains in small- and moderate-sample regimes under substantial model uncertainty.

Unsupervised domain adaptation (UDA) for semantic segmentation remains challenging under adverse weather conditions because severe appearance changes enlarge the domain gap and degrade the reliability of pseudo labels in the target domain. To address this problem, we propose an Intra-Class Mixing Consistency (ICM) framework that enforces prediction consistency between an intra-class mixed image and its original counterpart. Unlike previous mixing-based consistency methods that combine regions across different images or domains and may introduce unrealistic semantic inconsistencies, ICM performs mixing within the same image and semantic class, preserving realistic semantic layout for consistency regularization. With ICM, we establish a new state-of-the-art performance for clear-to-adverse-weather unsupervised domain adaptation (UDA) in semantic segmentation. On the Cityscapes $\rightarrow$ ACDC benchmark, our method achieves 75.7% mIoU, outperforming the previous state of the art by +1.9 pp, demonstrating its effectiveness in mitigating class confusion under challenging environmental conditions. The code is provided in the supplementary material.

Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The standard recipe assigns a single outcome reward at the end and compares trajectories sampled for the same task. As a result, a group with no successful trajectory yields no training signal, failed attempts cannot be told apart by how close they came to completion, and turns that advance the task receive the same credit as turns that only query the environment. Prior work refines the unit of comparison from the trajectory to the step, or trains a reward model to supply intermediate signal: the former still derives its signal from final success alone, and the latter estimates it with a model. We observe that the acceptance checks that decide success can also be run on intermediate states, so progress is as verifiable as the outcome. We propose ProCredit, which turns this verified progress into credit: it reruns the acceptance checks after each turn, rewards the turn by its change in progress, and uses these rewards to assign credit both across attempts at the same task and across the turns within a trajectory. Starting from Qwen3.5 base models at three scales on AppWorld, ProCredit outperforms outcome-reward baselines and progress-based baselines in task completion rate at every scale on both test sets, exceeding the strongest outcome-reward baseline by 4.1 percentage points at 4B, and results in a second environment show the same direction of improvement. Ablations show that adding the final progress to the trajectory score alone does not improve performance: the gain comes from crediting progress to the turn where it occurs.

In observational time series, statistical inference for dynamic causal effects of a one-time intervention across horizons is complicated by high-dimensional observed pre-treatment information, unmeasured confounding, and serial dependence. To address these challenges, we develop a semiparametric framework for inference from a single serially dependent time series, integrating debiased machine learning with instrumental variables through buffered block cross-fitting. Under geometric beta-mixing, we derive non-asymptotic bounds on estimation error, asymptotic normality at each fixed horizon, and feasible inference that accommodates serial dependence. We further show how learner-specific prediction guarantees under temporal dependence can be used to verify the nuisance-rate conditions required for orthogonal inference. In a monetary-policy application with 468 months and 1464 lagged FRED-MD controls, we show an instrumented policy tightening lowers housing starts at medium horizons, with sensitivity analyses that support the finding.

The fate of average symmetry-protected topological (ASPT) states based on the one-dimensional cluster state is investigated by using the Choi mapping, namely, the doubled Hilbert-space formalism. By introducing two effective spins, $\tau$ and $\eta$, on each doubled rung, we obtain a transparent representation of the ASPT parent Hamiltonian and systematically identify the conserved stabilizers and the corresponding orders. We further study symmetry-preserving operations that deform the ASPT by combining qualitative effective-Hamiltonian and systematic parent-Hamiltonian analyses with numerical matrix-product-state filtering calculations. We find that although the ASPT remains robust over a broad range of decoherence strengths, strong-to-weak spontaneous symmetry breaking (SWSSB) becomes exact in the maximal-decoherence limit. In addition, we consider symmetry preserving no-click postselection, which removes the exact conservation law supporting the Rényi-2 string order of the ASPT and drives the system toward weak-symmetry spontaneous symmetry breaking (WSSB). Again, the ASPT remains robust over a broad range of postselection strengths, with WSSB becoming pronounced only near the projective limit and exact at the limit itself.

We investigate quark stars (QSs) described by three quark matter (QM)equations of state (EoSs) and analyse their radial and quasiradial oscillation modes within the slowly rotating relativistic approximation. The considered EoSs describe massless quarks, massive quarks, and massive quarks with a temperature-dependent gluon mass. Our analysis of radial modes shows that the mode separation depends on the stellar mass and radius for a given compactness, as well as on the stellar temperature. The considered QS models satisfy the slowly rotating relativistic condition of Hartle, Thorne and Chitre formalism, allowing rotation to be treated as a small perturbation of the non-rotating configuration. We find that, although more massive and larger stars can exhibit greater surface eccentricity and quadrupole deformation, their stronger self-gravity results in a lower tendency to deform than less massive and smaller stars. For all models, the variation in mass distribution increases towards the stellar surface, while the variations in pressure, energy density, and number density remain small near the center and become more pronounced towards the surface. More compact stars exhibit stronger twisting of the local inertial frame but weaker frame dragging for a given angular velocity. Rotation shifts the oscillation modes from their non-rotating values and leads to different vibrational decay times at different angular velocities. The fundamental modes considered here exhibit frequencies below $2$ kHz and show non-continuous behaviour across the investigated rotational configurations.

Traffic Signal Control (TSC) is a safety-critical cyber-physical system that relies on real-time sensing. Corrupted observations caused by adversarial perturbations or sensor failures can propagate from the sensing layer into the controller and degrade traffic efficiency. Existing robust Reinforcement Learning (RL)-based TSC methods often suffer from limited cross-city generalization, high inference latency, and weak recovery under partial observability. We present MDRC (Meta-Diffusion-based framework for Resilient traffic signal Control against adversarial attacks and sensor failures), a post-detection state-recovery defense inserted between sensing and control. MDRC reconstructs trustworthy traffic states before they are consumed by the controller. It combines Denoising Diffusion Implicit Models (DDIM) for efficient state recovery with Reptile meta-learning for a transferable initialization across cities. We provide an optimization-based view of the DDIM recovery dynamics and establish a recovery-error bound that separates score approximation, numerical discretization, and initialization mismatch. Across seven real-world-derived CityFlow benchmarks, MDRC reduces Average Travel Time by 6.77% under stochastic and policy-aware attacks and by 12.75% under structured sensor loss, while improving state-recovery fidelity. We further evaluate 3,600 seconds of real roadside measurements with 50% of detector channels disabled and integrate MDRC into a hardware-in-the-loop traffic-signal stack. Over a 9.16-hour run with 32,389 sensing/control cycles, the system achieves 99.79% decision availability, produces no out-of-plan recommendations, and requires approximately 38 ms of component-wise processing per one-second control interval.

In upcoming integrated sensing and communications (ISAC) systems, security depends on whether an eavesdropper (Eve) can recover data symbols or infer sensing information from a common observation with a legitimate receiver. However, existing information and estimation measures do not quantify this dual risk under finite observation records. This letter introduces the novel metric of operational leakage, which signifies Eve's optimal probability, in the Bayesian sense, of reconstructing communication symbols or estimating a sensing parameter within prescribed distortions. By showing that prior adversarial success probability separates the effect of side information from that of the observation, we propose a conditional Laplace approximation for efficiently evaluating the proposed metric and jointly quantifying the eavesdropping risk to the sensing and communication functionalities. Numerical results showcase that the risk enabled by adversarial observation increases with Eve's signal-to-noise ratio (SNR), conventional metrics do not uniquely determine finite-record adversarial success probability, and that the proposed conditional Gaussian approximation closely follows numerical Bayes evaluation.

Long-horizon navigation requires an agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, while compact summaries may omit details needed to reconsider earlier decisions. We introduce NavProbe, a hierarchical zero-shot navigation agent that couples a dynamic subgoal agenda with active evidence retrieval. A compact index links summaries of visited places, transitions, and landmarks to their visual and geometric records. When the current context is insufficient, a task executive retrieves targeted evidence to generate, revise, or resolve subgoals. Reusable conclusions are used to update the index, and a skill policy converts the revised task state into parameterized navigation actions. NavProbe achieves 71.7% SR and 55.8% SPL on R2R-CE and 55.3% SR and 38.6% SPL on RxR-CE, outperforming strong zero-shot baselines. It also achieves 79.3% SR on HM3D-v2 ObjectNav, with qualitative real-robot demonstrations illustrating physical deployment. Code is available at https://github.com/liujy25/NavProbe.

Symmetry-protected bound states in the continuum (SP-BICs) offer exceptional optical confinement but remain nonradiative. Here, we demonstrate that magnetically lifting their protecting symmetry enables nonreciprocal beam steering with intrinsic angular information encoding. In a magneto-optical photonic crystal slab, an in-plane magnetic field converts an SP-BIC into a radiative quasi-BIC and, together with vertical dielectric asymmetry, continuously displaces the associated band extremum away from the Gamma point. The steered beam exhibits two independent locking relations: its wavelength is locked to the elevation angle, while its polarization orientation is locked to the azimuthal angle. These relations embed complementary spectral and polarization information into the scanning beam, providing additional sensing channels for multidimensional LiDAR. Moreover, the nonreciprocal dispersion gives different resonance frequencies at opposite wave vectors, supporting resonant emission at +k while back-reflected light at the same frequency is off resonance at -k, opening a route to intrinsic self-isolation and reduced optical feedback. These findings establish a unified framework connecting magnetic beam steering, angular information encoding, and nonreciprocal feedback suppression, with prospects for compact reconfigurable light sources and integrated optical engines.

The Tutte polynomial is a bivariate polynomial that has been extensively studied in graph and matroid theory. Gordon was the first to study the Tutte polynomial $T(P;x,y)$ of the greedoid induced by a poset $P$, including the special case of series-parallel posets. In particular, Gordon and McMahon conjectured that, for any two series-parallel posets $P$ and $Q$, the equality $T(P;x,y)=T(Q;x,y)$ holds if and only if $P\cong Q$. In studying this conjecture, Gordon introduced a subclass $\mathcal{P}$ of series-parallel posets and proved that this equivalence holds for all $P,Q\in\mathcal{P}$. In this paper, we introduce a new subclass $\mathrm H$ of series-parallel posets and prove that $\mathcal P\subseteq\mathrm H$. Moreover, we show that, for every $P\in\mathrm H$ and every $Q\in\mathrm{SP}$, the equality $T(P;x,y)=T(Q;x,y)$ holds if and only if $P\cong Q$, thereby extending Gordon's result.

Breast image classification requires local detail and global tissue context, yet these cues can weaken as representations deepen. We present M3D-Net, a mammography encoder that hierarchically coordinates multi-scale coordinate attention, bounded dynamic feature reuse, and differential attention through resolution-aware operator placement. Within-stage retrieval preserves access to earlier features, coordinate-aware aggregation integrates local and global context, and differential attention operates at coarse resolutions. We evaluate image-only classification on AISSLab mammography and an adapted image–clinical model on BrEaST ultrasound. Against EdgeNeXt, RepViT, and TransXNet, the proposed implementations achieve the highest recorded validation accuracy and late-training accuracy, with the lowest endpoint cross-entropy loss. Validation accuracies reach 97.78% and 80.39%, respectively. These results support further evaluation of hierarchical coordination across breast imaging settings; repeated-seed, component-controlled, and independent evaluations remain necessary.

kicad-pycbnew is an open-source Python library for the automated, script-based generation of KiCad PCB designs, tailored to the precise geometric and impedance constraints of particle detector readout electronics. By enabling the programmatic definition of copper traces, zones, vias, and footprints — without a graphical interface — it addresses the challenges of designing large-scale, repetitive, or parameterized layouts (e.g., Resistive Plate Chamber (RPC) strips or controlled-impedance signal paths). Key features include constraint-driven routing, parallel track arrays with rounded corners, via grids with exclusion zones, and full compatibility with KiCad's native file format. Standalone operation (no KiCad runtime required) facilitates integration into CI/CD pipelines and ensures reproducibility. The library, released under the MIT License, includes validated examples such as trapezoidal RPC readout boards and extension boards for the COMET experiment, alongside comprehensive tests and documentation.

Coronal mass ejections (CMEs) are driven by the eruption of magnetic flux ropes (MFRs) whose footpoints are often observed indirectly as coronal dimming regions. However, the relationship between observed dimmings and true MFR footpoint locations remains uncertain due to limitations in both detection methods and coronal magnetic field modelling caused by the complexity of eruptive events. We aim to investigate the M4 flare and CME event on 28 March 2022 in AR 12975 to determine how well observed coronal dimmings trace the footpoints of an erupting MFR. We also assess how these signatures compare with the MFR evolution from a data-driven magnetofrictional simulation. We combined multiwavelength SDO/AIA observations with a time-dependent data-driven magnetofrictional simulation of the AR. We identified coronal dimmings using intensity-thresholding and minimum-intensity maps. For challenging regions we used a tailored region growth algorithm from strong gradients. We extracted MFR structures in the simulation using a combined twist and squashing factor metric. We compared the location of the footpoints and derived magnetic fluxes from both dimmings and the modelled MFR. The simulation reproduces the formation, evolution, and eruption of the observed MFR whose footpoints migrate during the eruption. The footpoints match well with the dimming location. The southern dimming shows characteristics of a moving flux rope dimming, while the northern dimming behaves as a shrinking flux rope dimming that is rapidly closed by the flare ribbons. Quantitative comparisons of area and magnetic flux show good overall agreement between simulated footpoints and observed dimmings, with discrepancies mainly arising from detection limitations and event complexity. The dimmings at the northern footpoint region is particularly challenging in observations due to pre-existing low intensities and its fast shrinkage.

We analyze two fixed-point iterations for computing the principal square root of an M-matrix $A$. Although these iterations, with customary initialization, converge sublinearly when $A$ is a singular M-matrix, we show that, under suitable mild conditions on the initial approximation, the convergence is linear. Moreover, we provide component-wise accurate versions of these iterations, which allow us to approximate the principal square root with a component-wise relative error uniformly bounded by a small multiple of the machine precision. Numerical experiments demonstrating the effectiveness of the proposed algorithms for certain classes of problems are presented.

Block error rate is a standard metric in finite blocklength (FBL) communication, yet it conflates two qualitatively different failure modes: block confusions, where the decoder selects a wrong codeword, and block erasures, where it declares a loss. Higher-layer protocols treat physical-layer failures as erasures, but this cross-layer assumption lacks FBL justification. We derive a rigorous upper bound and a companion lower-side estimate on the block confusion probability (BLCP) and block erasure probability (BLEP) for bounded-distance decoders over additive white Gaussian noise (AWGN) channels at finite blocklength, recasting the coding problem as a geometric sphere packing one. We analyze the sensitivity of these bounds to blocklength and signalto-noise ratio, characterize the envelope of the upper bound, and derive closed-form Chernoff approximations. Extending the model to idle transmission blocks, we bound the false alarm probability (FAP) and show that a block z-channel abstraction emerges from the bounded-decoding geometry. Numerical results confirm that confusion and false alarm probabilities lie far below the error rate constraint, providing quantitative physicallayer support for the block erasure channel and block z-channel abstractions assumed in protocol design.

We characterise C*-irreducible regular C*-inclusions using a number of different conditions considered by different authors. In particular, we show that all C*-irreducible regular inclusions $A\subseteq B$ are modelled by outer Fell bundles $(B_{g})_{g\in G}$ over discrete groups with a simple unit fibre $A=B_1$. In this case, we prove a bijection between intermediate C*-algebras $A\subseteq C \subseteq B$ and subgroups $H$ of $G$. This extends the Galois correspondence for reduced crossed products by discrete group actions established by Cameron-Smith. We relate it to the Galois correspondences of Izumi and Mukohara for fixed-point algebras of actions of compact abelian groups, and the mixed inclusion of a fixed-point algebra in a reduced crossed product considered by Echterhoff-Rørdam. In addition, using a recent result of Geffen-Ursu, we show that the inclusion of a fixed-point subalgebra $A\subseteq B$ of an action of $\mathbb{T}$ or $\mathbb{Z}/p$ for a square-free number $p>0$ is aperiodic if and only if $A$ detects ideals in $B$. We apply this to give examples of C*-irreducible inclusions coming from Cuntz-Pimsner algebras, including crossed products by endomorphisms or transfer operators. In particular, we characterise when a core subalgebra of a graph C*-algebra is C*-irreducible. Lastly, we show that a general regular topologically graded C*-inclusion $A\subseteq B$ is aperiodic and has a unique pseudo-expectation provided $A$ detects ideals in all intermediate C*-algebras of $B$. This partially answers a question by Pitts-Zarikian.

Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical reasoning, the intended interpretation depends on the reading in force – open- versus closed-world, two- versus three-valued, and credulous versus skeptical. We study which reading of negation large language models adopt by default and whether they can override that preference when a different reading is explicitly specified. To this end, we introduce NAFBench, a procedural generator of solver-certified instances spanning four semantic viewpoints: SLDNF, well-founded semantics (WFS), and credulous and skeptical reasoning under stable-model semantics. The generator emits ground normal logic programs with controlled depth, width, and cycle structure. Each program is solved under all four viewpoints using SWI-Prolog, a well-founded semantics solver, and clingo, yielding up to four divergent labels. The programs are then verbalized into natural language under multiple framings and rule orderings that leave the answer invariant. The results expose a consistent gap. Across open-source models, following a specified negation semantics remains unsolved: the strongest models score 59–74% across the four semantic viewpoints, while the weakest score 31–67%. All models are order-sensitive on more than half of logically identical rule shufflings, while the two weaker models frequently overcommit on well-founded "undefined." Two frontier models reach 100% on the main fixed-complexity evaluation set, and a third, o4-mini, is near-perfect, falling only to 81% on well-founded "undefined." Delegating reasoning to a solver, fine-tuning on certified traces, or forcing an explicit three-valued verdict each partly closes the gap.

We prove that every minimizing $p$-harmonic map from $B^3$ into $\mathbb S^3$ is locally $C^{1,\alpha}$ for some $\alpha\in(0,1)$, for every $p>p_0$, where $p_0=\frac{7-\sqrt{17}}{2}\approx 1.44$. This closes the gap between the previously established regularity ranges $[2,2.642]\cup[2.961,3]$ and, in particular, yields full interior regularity for all $p\ge2$. The result also extends regularity to the subquadratic range $p_0<p<2$.

Existing general-relativistic magnetohydrodynamics (GRMHD) codes offer complementary capabilities, but these capabilities remain distributed across different frameworks. To unify them, we introduce PANGU–Parthenon-Based Astrophysics for Numerical Relativity and GRMHD in a Unified Framework–a modular computational framework that integrates a shared solver across physical regimes, flexible spacetime geometry, and extensible computational infrastructure within a single architecture. In the first paper of this series, we present and validate the fixed-spacetime GRMHD component of PANGU. The shared solver combines finite-volume Godunov methods with constrained transport on uniform and block-structured, statically refined meshes, and covers hydrodynamics and magnetohydrodynamics in Newtonian, special-relativistic, and general-relativistic regimes. PANGU provides a flexible geometry interface supporting coordinate selection and either on-the-fly or precomputed evaluation of prescribed stationary spacetimes, demonstrated here in Kerr spacetime with Cartesian Kerr-Schild and modified Kerr-Schild coordinates; additional components can be incorporated without restructuring the core solver. Verification covers all three regimes on uniform and statically refined meshes: smooth Newtonian and special-relativistic problems approach second order against their analytic solutions, with deliberately matched double-precision trajectories agreeing with AthenaK to roundoff; in fixed-spacetime GRMHD, the stationary analytic solutions are preserved to second order, and the turbulent accretion reproduces the same flow and flux scales as BHAC. Together, these results establish the fixed-spacetime matter-sector foundation for the broader PANGU framework. Numerical-relativity and coupled dynamical-spacetime GRMHD capabilities will be presented in subsequent work.

This paper summarizes the Interspeech2026 second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge, which aims to advance the development of effective multilingual conversational speech language models. We describe the two challenge tasks: multilingual conversational speech diarization and recognition, and multilingual conversational speech understanding, together with the released real-world conversational speech dataset, evaluation protocols, and baseline systems. The challenge attracted 91 teams worldwide, with 704 valid leaderboard results and 14 technical reports across the two tasks. Based on the participating systems, we summarize representative approaches and distill practical insights into multilingual conversational speech recognition and understanding to support future research in the community.

Autoregressive robot policies learn continuous control by predicting discrete action tokens from observations. Different tasks often share local motions, yet behavioral correspondence across demonstrations receives limited explicit supervision in existing tokenizers. Motions with different timing can therefore lack a shared representation despite following similar patterns. We propose Behavior-Aligned Action Tokenization (BAAT), which uses soft dynamic time warping (Soft-DTW) to select corresponding action chunks and aligns their quantized coordinates jointly with reconstruction. This objective encourages similar motions across tasks to occupy nearby quantized representations while retaining executable action detail. A history-conditioned diffusion decoder reconstructs continuous action chunks from these tokens, and a downstream autoregressive policy learns to predict them. We evaluate BAAT on selected tasks from three simulation benchmarks and two real robot tasks. BAAT achieves a mean simulation success rate of approximately 45.2%, exceeding OAT by approximately 7.2 percentage points. In the controlled LIBERO-All alignment ablation, policy success rises from 70.2% to 79.0% while trajectory replay success decreases. These results support behavioral correspondence as supervision for organizing shared motion structure in action tokenizers and improving downstream robot policy learning.

We investigate the fast-advection limit ($\varepsilon \to 0$) of the stochastically forced two-dimensional incompressible Navier-Stokes equations on the torus. Numerical simulations are performed at resolution $N = 128$ for four different forcing shells on both the square torus and a thin torus, with the advection parameter $\varepsilon$ varied over approximately one decade. We find that the stationary distributions become increasingly concentrated on the lowest Fourier modes as $\varepsilon \to 0$, with the energy-to-enstrophy ratio $E/\Omega$ and the fraction $R$ of enstrophy in the lowest modes both increasing monotonically. At finite $\varepsilon$ the degree of concentration depends on the forcing shell through the effective spectral value $B_1/B_0$, in agreement with the condensation bound of Sznitman and Widmayer. Linear extrapolation to $\varepsilon = 0$ suggests that the limiting values may be forcing-independent, with $B_1/B_0$ governing only the rate of convergence. The same qualitative behaviour persists on the thin torus.

We present NV-Reason-CT, a generative vision–language model for chest and abdominal CT combining native 3D visual encoding with radiologist-guided reasoning. The model couples a native 3D vision transformer with a language model, passing all visual tokens and their explicit 3D coordinates into language decoding without further spatial token merging. This retains volumetric spatial information within the vision encoder and through the language model's positional encoding during joint processing with text. We train on a curated corpus of approximately 550,000 multimodal instruction examples from 70,111 unique CT image inputs, combining standardized reports, abnormality-focused and anatomy-specific questions, multi-turn interactions, and radiologist-authored reasoning from recorded and transcribed expert CT interpretations. Expert annotations provide direct supervision and guide additional report-grounded synthetic reasoning. End-to-end supervised fine-tuning (SFT) is followed by Group Relative Policy Optimization (GRPO), with verifiable rewards over chest and abdominal abnormality sets. The model supports abnormality classification, report generation, and interactive reasoning with reviewable observations, differential diagnoses, and uncertainty. Evaluation spans public CT benchmarks and a held-out NIH cohort. On CT-RATE, NV-Reason-CT achieves a macro-F1 of 0.614 and macro-AUROC of 0.871 without a task-specific classification head; generated reports achieve a report-derived macro-F1 of 0.592. In a preliminary study with expert radiologists, AI-assisted review received favorable confidence ratings and was associated with a 50% reduction in average reported interpretation and reporting time. We release the model and training code to support reproducible research on explainable AI for volumetric medical imaging.

Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and undermining the reliability of evaluation results. Reliable evaluation is particularly challenging for base models, whose limited instruction-following ability complicates task-based assessment. We introduce Uncheatable Eval, a dynamic benchmark that regularly collects newly published text to evaluate base language models and reduce the risk of data contamination. Drawing on the relationship between a model's predictive ability and its ability to compress data losslessly, we use compression rate to evaluate how well models predict new text. We evaluate 80 models across 14 text categories, study how compression changes with context length, and examine the correlation between compression rate and zero-shot MMLU accuracy. Our results yield three main findings: (1) compression performance follows a consistent scaling trend with model size; (2) attention-based, hybrid, and recurrent models differ in how their compression performance changes as more context becomes available; and (3) lower compression rates are strongly associated with higher zero-shot MMLU accuracy. Code is available at https://github.com/Jellyfish042/uncheatable_eval.

Stereo visual SLAM systems built on local descriptors suffer from semantic ambiguity, instance-level confusion, and independently moving objects, each corrupting data association and accumulating as trajectory drift. Prevailing semantic and dynamic SLAM methods address this through binary feature rejection, sacrificing correspondence density for outlier suppression. We contend that contextual implausibility is better expressed as a graded quantity than an exclusion criterion. We present Know-Your-Scene (KYS)-SLAM, a modular extension of ORB-SLAM3 that supplants feature rejection with continuous correspondence modulation. The contribution is the reframing of contextual evidence as correspondence cost, applied within feature matching and leaving the geometric backend unmodified. Each keypoint is augmented with semantic, panoptic, and motion priors fused through a hierarchical compatibility formulation, in which semantic class and instance identity enforce structural plausibility while a zero-shot motion score down-weights features on independently moving objects. That score comes from a training-free module fitting a depth-aware ego-motion model to background optical flow and classifying panoptic segments via self-calibrating, coverage-aware thresholds, so only segments with sufficient motion evidence are penalized and static structure is left unpenalized. Penalizing correspondences rather than discarding them preserves the geometric support bundle adjustment depends on. Under one fixed configuration, no coefficient retuned per sequence or dataset, KYS-SLAM reduces per-sequence ATE RMSE by 17.4% on outdoor KITTI and 27.7% on indoor EuRoC across 21 stereo sequences with no regressions, and by 6.6% on dynamic subsets of KITTI Tracking and 17.8%, up to 31.2%, on Virtual KITTI 2 – cross-domain transfer across outdoor driving, indoor flight, and synthetic imagery under one set of constants.

We revisit the classic 1959 paper of L. D. Landau on possible singularities of the integral associated to a Feynman graph. Focusing on the real setup, we relate it to convex geometry by representing a collection $p$ of incoming momenta as the weighted normals of a convex polytope $Q$ via the Minkowski problem. Then, a regular polyhedral subdivision $\mathcal{P}$ of $Q$ exhibits $p$ as a Landau singularity labelled by the dual graph of $\mathcal{P}$ with masses being the areas of the faces. Positivity of the Landau/Feynman/Schwinger multipliers is interpreted as strict convexity of a PL-function. This gives an interesting class of “polyhedral” Landau singularities. In the planar case going back to the original 1959 paper, Landau graphs can also be identified with plane webs of Gaiotto-Moore-Witten that provide a language dual to that of regular polygonal subdivisions.

Following the work [27], we further study spacetime observability for the wave equation on a one-dimensional interval. The main task is to characterize the observable symmetry condition (OSC) under both Dirichlet and Neumann boundary conditions, which is more complex than the torus setting due to boundary reflection, and to discuss the relation between OSC under different settings. We prove that OSC, together with the geometric control condition (GCC), is necessary and sufficient for observability. We also provide a necessary and sufficient condition for the related unique continuation property.