Papers

K-Means is one of the most widely used clustering algorithms, but its susceptibility to initial centroid selection remains a primary bottleneck for its convergence speed and clustering accuracy. This paper proposes Sector-Mean Initialization, a deterministic initialization strategy with O(N) time complexity that partitions the two-dimensional data space into angular sectors around the global centroid and initializes centroids using sector-wise means. We evaluate the method on established two-dimensional benchmarks (SIPU, Birch) and multiple real-world datasets, comparing against random, K-Means++, and Max-Min initialization under identical Lloyd iterations. The statistical analysis of Friedman's test (p<0.05) and Nemenyi post-hoc comparison indicates that, while delivering equivalent clustering quality as K-Means++ and Max-Min, Sector-Mean offers significant computational efficiency. Experimental results show that Sector-Mean reduces the initialization time by 74.9% and 59.8% in comparison to K-Means++ and max-min, respectively. And, it yields the lowest average number of iterations, achieving approximately 5% fewer iterations than K-Means++ and 16% fewer than max-min. These results highlight that Sector-Mean initialization offers a deterministic and computationally efficient initialization strategy while preserving cluster quality.

In performative reinforcement learning the deployed policy shapes the environment that generates the learner's future data, and the natural solution concept is a performatively stable policy that is optimal in the environment it induces. Existing convergence guarantees rely on Lipschitz sensitivity assumptions on the environment map $\pi \mapsto (P_\pi, r_\pi)$, which are hard to verify and fail in settings such as multi-agent best-response dynamics. We instead study stability for mixtures of policies, and show that the resulting picture is fundamentally different from performative prediction, where randomization removes the need for any sensitivity assumption. We distinguish local mixed stability, an occupancy-weighted first-order relaxation that we show is equivalent to stationarity, from global mixed stability, which certifies against arbitrary deviating policies. Our first result is that a weighted per-state Hedge dynamic drives the local stability gap to zero at an $O(1/\sqrt{T})$ rate for an arbitrary, possibly discontinuous, environment map, both with exact and with trajectory feedback. The two notions genuinely differ: we exhibit an instance where local stability is achieved exactly but every mixture has global stability gap bounded away from zero. For global stability we introduce a bounded transition range assumption, strictly weaker than Lipschitz sensitivity, under which unweighted per-state Hedge converges up to a floor of $O(\gamma\epsilon_P/(1-\gamma)^3)$, and we prove a matching-in-$\epsilon_P$ lower bound of $\Omega(\gamma\epsilon_P/(1-\gamma))$ under trajectory feedback, so this floor is unavoidable. Finally, we extend both notions to $n$-player performative Markov games, obtaining local stability with no assumption on the joint environment map or game structure, and global stability for performative Markov potential games.

We study the cost-minimization prophet inequality problem, in which a decision-maker sequentially observes $n$ independent and identically distributed (IID) random variables. After each observation, the decision-maker must either accept the current realization and stop, or reject it and continue with the next variable. The goal is to minimize the selected value. Unlike the classical maximization setting, if none of the first $n-1$ values is accepted, the final realization must be selected. Esfandiari et al. (SIDMA 2017) showed that this problem does not admit constant-competitive online algorithms in general, which motivates subsequent work on restricted distribution classes, such as entire distributions (Livanos and Mehta, SODA 2024) and distributions with bounded extreme values (Livanos and Mehta, EC 2025). In this work, we focus on distributions with bounded support. For distributions supported on $[1,b]$, we characterize the competitive ratio of online algorithms as a function of both $b$ and $n$. We consider both distribution-aware and distribution-oblivious settings. In the distribution-aware case, we provide a nearly tight characterization of the optimal online algorithm, showing that its competitive ratio is at most $b^{(1-1/n)^n}$ for all $n\geq 2$. More significantly, we design a distribution-oblivious algorithm that achieves the same guarantee, with a sequence of predetermined thresholds that depend only on $b$ and $n$. Furthermore, we extend our analysis to the non-IID setting, where we show that a simple single-threshold algorithm attains an asymptotically optimal competitive ratio of $\Theta(\sqrt{b})$.

Recently, Masked Pretraining (MPT) based on reconstruction pretraining tasks has risen to a promising self-supervised learning paradigm across various domains and achieves remarkable performance in multiple downstream tasks. However, the theoretical understanding of the working mechanism behind MPT is still limited. In this paper, we introduce a new theoretical framework to analyze MPT and understand the crucial role of masking in extracting meaningful representations. We establish theoretical connections between MPT and another popular self-supervised paradigm: contrastive learning. We prove that the masking technique implicitly creates positive pairs that are semantically similar and the reconstruction loss pulls them together in the feature space. Besides, as a result of the implicit alignment, we point out the dimensional collapse issue of MPT and propose a Uniformity-enhanced MPT (U-MPT) loss that can effectively address this issue and bring significant improvements in downstream tasks including linear evaluation, cross-dataset fine-tuning and out-of-distribution generalization on real-world data sets. Furthermore, we establish downstream guarantees of U-MPT and theoretically analyze the influence of masking strategies. Based on the theoretical analysis, we propose a new masking strategy which enhances the downstream performance of MPT and explains current improvements of masking strategies with our theoretical perspective.

The stochastic Landau–Lifshitz–Gilbert (sLLG) equation is a strongly nonlinear stochastic PDE with a non-convex pointwise constraint arising in the theory of micromagnetics. We analyse a fully discrete, structure-preserving finite element approximation of the sLLG equation with coloured multiplicative Stratonovich noise on a bounded interval. The method utilises continuous piecewise affine finite elements, mass lumping, and midpoint time discretisation to preserve the unit-length constraint exactly at the finite element nodes. Under suitable regularity assumptions on the initial data and the noise, we establish uniform higher-moment stability and develop an error analysis for the scheme. The analysis exploits the geometric structure of the equation and the stochastic midpoint discretisation. For every $\gamma\in(0,\frac12)$, we prove first-order spatial convergence and temporal convergence of order $\gamma$ in the natural discrete energy norm, locally in mean square on events of arbitrarily large probability and, consequently, in probability. To the best of our knowledge, this is the first convergence-rate result for a fully discrete structure-preserving finite element scheme solving the stochastic Landau–Lifshitz–Gilbert equation.

In this paper, we present a high-order, stable summation-by-parts (SBP) finite difference method for solving the Vlasov-Maxwell system in a 2D2V phase space. Central SBP operators for the advection terms are not stable when the solution becomes non-smooth and fine-scale filamentary structures develop, as is typical in high-dimensional Vlasov-Maxwell simulations. To address this issue, the method is stabilized using high-order upwind SBP operators. High-order explicit Runge-Kutta methods are employed for time integration. We prove that the fully discrete scheme exactly conserves mass and preserves momentum up to truncation error. Furthermore, we present a matrix-free implementation of the method on modern GPU architectures. A range of challenging benchmark problems is solved to demonstrate the accuracy, robustness, and performance of the proposed scheme.

Neural inertial odometry has demonstrated strong potential for motion estimation in challenging environments, yet inertial-only preintegration remains sensitive to IMU bias and uncertainty. To this end, this paper introduces PLATO:~Preintegration Learning from Accurate Trajectory Observations, a likelihood-based framework that leverages accurate trajectory observations to jointly learn IMU bias dynamics modeled by a neural ordinary differential equation~(NODE) and gyroscope and accelerometer noise covariances. Optimization exploits the sparse structure of the negative log-likelihood, with IMU noise-parameter gradients computed by forward differentiation. A tailored double-adjoint scheme couples a discrete invariant-error adjoint with a continuous-time adjoint for the bias NODE, enabling memory-efficient likelihood optimization over the nested bias-dynamics and IMU-preintegration rollouts. Validation on EuRoC shows improved performance, and underwater robot experiments demonstrate applicability under intermittent lighting failures and visual degradation.

Fast Fourier transforms on parallel machines incur two forms of data movement: processor-local transfers through the memory hierarchy and global redistribution between processors. Four-step FFT organizations switch the active transform dimension with one global transpose-like exchange, but this alone does not yield cache-efficient local computation. Cache-oblivious FFTs achieve asymptotically optimal local memory traffic through recursive layout transformations, whose direct materialization can require extra data-rearrangement passes and global exchanges. We present PACO, a fully cache-oblivious parallel FFT framework that reconciles these objectives. PACO executes LocalFFT -> OneGlobalPermutation -> LocalFFT. Its local stages recursively partition both transform and batch dimensions without knowledge of the cache parameters. Rather than materializing the transpose-like layouts induced by this recursion, PACO defers them, showing that they compose into a base-b digit-reversal permutation that is fused with the redistribution already required to change the local transform dimension. The resulting middle stage is a perfectly balanced parallel cache-oblivious digit-reversal permutation in which each source-destination processor pair exchanges exactly $N/p^2$ elements. Under an exact base-b slab decomposition in a hybrid ideal-cache/BSP model, PACO computes an N-point DFT exactly with maximum per-processor work $\Theta((N/p) \log N)$ and maximum per-processor cache complexity $\Theta((N/(pB))(1 + \log_M N))$, using exactly one global redistribution round. PACO returns canonical logical DFT coefficients under a factor-swapped target slab ownership. The single redistribution is necessary under the stated no-replication ownership model, while its communication volume is optimal for the prescribed fused permutation and source-target slab distributions.

Randomized benchmarking can hide classical temporal correlations because its Clifford-twirled response is even in the noise phase. For a stationary symmetric telegraph fluctuator, we show that continuous evolution and independent stationary resets at slot boundaries yield identical mean responses for arbitrary fixed idle modulations. We construct an eight-setting phase-cycle measurement of the connected sine-phase covariance under ideal Clifford twirling and classical idle dephasing. This observable vanishes for independent slot noise and fixed detuning without a weak-phase or Gaussian approximation. A closed telegraph response, independent circuit calculations and 800 simulation trials validate the construction and quantify the empirical coverage of a paired bootstrap estimator. A separate conservative confidence set states its finite-sample assumptions. Two acquisitions on an IBM processor compare engineered shared-sign and independently reset phases with identical marginals. Their primary contrasts are 0.254 and 0.211, with empirical 95% intervals [0.177, 0.331] and [0.136, 0.285], respectively; all negative-control intervals include zero. At equal shot and sensingwindow budgets, an ideal Ramsey/echo estimator is more precise in every tested class. The result supplies an explicit connection between a benchmarking identifiability limitation and a controlled correlation measurement. No native or quantum-memory detection is claimed.

A provider of a high-risk AI system must keep records that make a decision traceable, and for agentic systems it has not been established what those records must contain for post-hoc causal attribution to be possible. We give the estimator framework and then the conditions under which it fails. We separate the marginal total effect that prior work measures from a common-random-numbers total effect that isolates a step's own contribution, add the natural direct effect under a pinned downstream, and check the estimators against hand derivations. Both estimands then fail, in the same direction. Under the marginal estimand a causally inert step has the identical total effect to the decisive one on every run of our planted chain, an algebraic identity and not a coincidence at one draw. Under common random numbers the decisive step returns exactly zero on the runs where the executing step flips, about one in ten, while its direct effect there is 0.25 and it demonstrably acts; an exact zero does not certify that a step did nothing, and we put that here rather than in the limitations. We derive the coupling that keeps the direct effect estimable once contexts diverge, with a closed form for its degradation, and show that the mediated share on which a natural ranking is built is not a share under suppression: where the direct and mediated paths oppose, it exceeds one and ranks a suppressed component above a pure mediator. We publish the discrepancy experiment's pre-registration rather than a result, because the live pipeline it requires was not available in the study window. We contribute the traceability specification such a filing would need, against a gap the Act's calendar opens: Article 86's right to an explanation has applied since 2 August 2026, while the Article 12 logging and Annex IV documentation that could evidence one were deferred to 2 December 2027 by Regulation (EU) 2026/1744.

An LLM judge evaluates outputs at scale. Experts should label only where it is least sure. Its natural escalation signal conflates two uncertainties: aleatoric, real disagreement in the expert pool, which labels cannot reduce, and epistemic, the judge's ignorance, which labels do reduce. A small Bayesian model separates them: a regression on labels already collected learns how far to trust a black-box judge's prediction. Both components follow as simple formulas, with no sampling or further judge calls. The components isolate on a real LLM judge against exactly known truth, and stated confidence is no guide to its actual error. On real human disagreement (ChaosNLI) the epistemic ranking removes 83% more error than total uncertainty for the same expert labels, though simply escalating the least-labelled items does as well there. We demonstrate we can estimate where a judge is ignorant rather than where experts genuinely disagree, and propose using this to direct expert labelling. Code and data are available at https://github.com/composo-ai/judge-uncertainty-decomposition.

Control operators, such as exceptions and effect handlers, provide a means of representing computational effects in programs abstractly and modularly. While most theoretical studies have focused on multi-shot control operators, one-shot control operators—which restrict the use of captured continuations to at most once—are gaining attention for their balance between expressiveness and efficiency. This study aims to fill the gap. We present a mathematically rigorous comparison of the expressive power among one-shot control operators, including effect handlers, delimited continuations, and even asymmetric coroutines. Following previous studies on multi-shot control operators, we adopt Felleisen's macro-expressiveness as our measure of expressiveness. We verify the folklore that one-shot effect handlers and one-shot delimited-control operators can be macro-expressed by asymmetric coroutines, but not vice versa. We explain why a previous informal argument fails, and how to revise it to make a valid macro-translation.

In this paper, we study the performance of algebraic geometry (AG) codes against adversarial insertion-deletion (insdel) errors. The half-Singleton bound states that an $[n,k]_q$ linear code can correct at most $n-2k+1$ insdel errors. It was recently proven that random Reed-Solomon codes approach this bound. However, these constructions require the field size $q$ to grow linearly with the code length $n$. We overcome this barrier by extending the probabilistic analysis of general linear insdel codes to AG codes. We demonstrate that curves with many rational points allow for nearly optimal codes over significantly smaller alphabets. We prove the following main asymptotic results: (1) For general smooth complete curves of fixed genus, random AG codes are nearly optimal, that is, they can correct $(1-\varepsilon)n-2k$ insdel errors with high probability over linear-sized fields ($q=\Theta(n)$). (2) By utilizing Hermitian curves, we achieve this optimality over sublinear fields of size $q=\Theta(n^{2/3})$, breaking the linear field size barrier. (3) Using asymptotically optimal García-Stichtenoth towers, we prove the existence of random AG codes that approach the half-Singleton bound with high probability over fields of size $q=2^{O_R(1/\varepsilon^2)}$, independent of $n$.

Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-stage visualization prompting pipeline (Explore–Focus–Test–Present) that emulates expert analytical workflows, together with VG-COPRO, a vision-guided automatic prompt optimization (APO) method adapted to jointly optimize such multi-stage, executable pipelines. To address the evaluation gap for complex data visualization, we introduce the Insight Progression Metric (IPM), a rubric combining four text-based dimensions with a vision-based dimension. We assess IPM through a 100-chain human pilot and an expanded 300-chain agent-based evaluation spanning all ten domains. Experiments on public datasets show that InsightChain consistently outperforms competing prompting baselines. Existing APO methods fail to yield consistent gains on this multi-stage task, whereas VG-COPRO improves performance in both in-domain and cross-domain settings.

Diffusion-weighted imaging (DWI) is widely used in clinical settings but remains vulnerable to geometric distortion. Conventional correction methods often require additional acquisitions or vendor-specific solutions, limiting their feasibility in high-throughput, resource-constrained settings. This study investigates whether large-scale pretraining strategies can improve deep learning-based distortion correction for single-phase-encoding DWI. We formulate the task as image reconstruction, and compare a non-pretrained baseline against a self-supervised and a generative pretrained model, evaluated using both quantitative image-similarity metrics and qualitative expert assessment. The best-performing model was further tested for transferability on data collected in an LMIC setting with acquisition shift. Pretrained models outperformed the non-pretrained baseline, with cWDM achieving the strongest results across both quantitative and qualitative evaluation. However, application to LMIC data revealed transferability challenges, including contrast alteration and over-reliance on T1-weighted anatomical structure. Registering images to a common standard space improved predictions, suggesting that harmonized preprocessing may enhance cross-domain deployment.

High-resolution 3D asset generation is vital in various 3D applications. Existing state-of-the-art diffusion-based models remain constrained by fixed resolutions, limiting their ability to produce details. In this paper, we tackle the challenge of generating more detailed, higher-resolution 3D objects by introducing a 3D super-resolution (SR) framework built on existing 3D generative foundation models. To this end, we design PLSR, a progressive and localized super-resolution solution to achieve this goal effectively and memory efficiently. Technically, given a coarse geometry from a pretrained 3D generator, we decompose the global SR task into localized sub-tasks via an associative input decomposition scheme, adapt a flow-based 3D generator into a localized super-resolution model through low-cost finetuning, and unify them in an iterative patch-wise denoising pipeline for seamless high-resolution output. Experiments on challenging objects show that our approach is able to generate 3D details with new strong fine-detail fidelity while significantly reducing the computational cost, offering a new and practical solution for high-resolution 3D asset generation.

Can people distinguish between human and AI agency in humanoid teleoperation? To explore this question, we developed Ghost-in-the-Loop, a teleoperation framework that supports both human-operated and AI-generated control of a robot's voice, facial expressions, and gestures while maintaining a consistent embodiment. We conducted a preliminary online study ($N=50$) in which participants viewed short interaction clips generated by either a Human Operator or an AI Control and judged the perceived source of control. Results suggest that participants often struggled to distinguish between the two conditions in brief interactions. Qualitative responses indicate that judgments were primarily influenced by perceived naturalness, temporal coordination, and consistency across speech, facial expression, and gesture. These findings provide initial insights into agency perception in embodied human–AI communication and motivate future investigations of blended human–AI telepresence systems.

The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles. Prior approaches typically perturb the trajectories of existing agents in a traffic scenario using simplified adversarial objectives to induce safety-critical interactions, which can limit the plausibility and diversity of the generated scenarios. Although inserting new adversarial vehicles can alleviate this limitation, determining when and where to introduce them in a scenario-specific manner remains challenging. In this work, we introduce \underline{CO}llision \underline{S}napshot guided \underline{T}im\underline{E}-\underline{R}eversed safety-critical scenario generation (COSTER), a framework that leverages learned traffic priors to determine plausible collision times and locations. COSTER first constructs a collision snapshot by inserting a new vehicle in contact with the target vehicle at the identified collision state within a traffic scenario. Starting from this collision snapshot, a conditional variational autoencoder is used to perform a time-reversed rollout, reconstructing the trajectory of the inserted vehicle backward toward earlier timesteps. Experiments show that COSTER outperforms existing methods in plausibility, diversity, and data efficiency. Moreover, agents trained on COSTER-generated scenarios reduce collision rates by 31% on safety-critical scenarios from the Waymo Open Motion Dataset while also improving ego task completion. The project website is available at https://anonym-121.github.io/COSTER/.

We study the Tsallis-to-Kullback–Leibler (KL) limit for entropy-regularized optimal transport with nonnegative bounded continuous costs. Fixing the regularization parameter $\varepsilon > 0$, we first derive an exact variational reformulation of Tsallis-regularized optimal transport in terms of the Tsallis information projection onto the set of couplings. The formula isolates an explicit correction term and thereby explains why, unlike in the KL case, the regularized transport problem and the corresponding information projection problem do not coincide exactly. We also establish existence and uniqueness for the Tsallis information projection. We then prove, with respect to the narrow topology, the $\Gamma$-convergence of the Tsallis-regularized functionals to the KL-regularized functional as $q\downarrow1$, together with narrow convergence of their unique minimizers. Finally, we obtain explicit error estimates of order $O(q-1)$ for both the regularized optimal transport values and the associated information projection values. These results quantify the passage from Tsallis regularization to the classical KL setting and clarify the relation between entropic regularization and information projection for $1 < q \leq 2$.

We study the identity straight-through estimator (STE) for training a two-layer binary-activation network with hinge loss from the perspective of Statistical Learning Theory (SLT). Our central question is whether algorithmic stability can explain the statistical generalization of the estimator produced by the discontinuous STE training rule. In the saturated-output regime, the zero-initialized samplewise STE recursion is exactly the stochastic subgradient descent on the convex latent loss $(-yu^\top x)_+$. This representation makes a stability analysis possible. We derive an exact distance identity for two coupled updates and prove approximate non-expansiveness of the common-example map, with a quadratic defect only when the two latent margins straddle zero. We then obtain explicit $\ell_2$ on-average model-stability and generalization bounds, transferring stability isometrically from the latent vector to the full first-layer matrix. Combining stability with a standard optimization bound yields an explicit excess induced-risk guarantee and the rate $O(n^{-1/2})$ when $T=n^2$. Under margin separability, a complementary argument gives the optimal-order $O(R^2/(\gamma^2n))$ expected excess misclassification error for a randomized one-pass STE iterate and a corresponding majority-vote bound.

This paper introduces LQ8, an open-source weak-signal digital mode for amateur radio that completes structured two-way contacts in 4 transmissions (60 s), achieving a 1.50x speedup over canonical 6-transmission exchanges (90 s) and 1.25x over 5-transmission RR73 exchanges (75 s) while preserving complete bidirectional exchange of Maidenhead grid locators, signal reports, and mutual acknowledgments. By replacing fixed-width message-type headers with variable-length prefix codes matched to physical-layer bit budgets, LQ8 packs the answering station's grid locator and measured signal report into a single 77-bit reply. In multi-station pileup operations, LQ8 confirms up to two answering stations simultaneously within a single-carrier 50.0 Hz transmission with a 0.0 dB RF power-splitting penalty, achieving a peak rate of 240 QSOs/h in continuous pileup (4x over single-carrier FT8; 480 QSOs/h dual-carrier) while retaining -21.0 dB SNR sensitivity. The protocol family also defines three extended profiles (LQ16, LQ4, and LQ2) tailored for extreme sensitivity, VHF/UHF contesting, and fast-burst channels.

Small additive ensembles of symbolic rules offer interpretable prediction models. Traditionally, these ensembles use rule conditions based on conjunctions of simple threshold propositions $x \geq t$ on a single input variable $x$ and threshold $t$, resulting geometrically in axis-parallel polytopes as decision regions. While this form ensures a high degree of interpretability for individual rules and can be learned efficiently using the gradient boosting approach, it relies on having access to a curated set of expressive input features so that a small ensemble of axis-parallel regions can describe the target variable well. Absent such features, reaching sufficient accuracy requires increasing the number and complexity of individual rules, which diminishes the interpretability of the model. Here, we extend classical rule ensembles by introducing logical propositions with learnable sparse linear transformations of input variables, i.e., propositions of the form $\mathbf{x}^T\mathbf{w} \geq t$, where $\mathbf{w}$ is a learnable sparse weight vector, enabling decision regions as general polyhedrons with oblique faces. We propose a learning method using gradient boosting based on a weighted logistic regression. Empirical results across 14 regression and classification tasks demonstrate that the proposed method achieves lower model complexity than competitive baselines while maintaining similar or better predictive accuracy. Hence, the approach provides a favorable trade-off between interpretability and accuracy and reduces the reliance on manual feature engineering.

Homes change between a robot's visits. Navigation benchmarks pose their goals in the world the agent currently sees, and the two-visit benchmarks that exist score recall or rearrangement rather than navigation. None of them can express go to the chair that was moved or go to where the vase used to be. OVMAN is a task in which an agent tours a scene, returns after a scripted change, and must navigate to a goal specified by the change itself. Two of its six change relations answer with a place an object has left, where nothing remains to be detected. We release 219 two-visit episodes, each certified solvable by an oracle agent that completes it three times. Two released systems fail as predicted. A zero-shot object-goal navigator reaches the change-defined target in 12.3% of episodes and almost never reaches a vacated location, 0.026 on former and 0.050 on removed. When a self-maintaining open-vocabulary map is read as two visits rather than as one maintained map, overall success rises (0.396 to 0.479 on our mapping) but the past-position relations specifically do not recover, on our maps or on a released self-maintaining one; keeping a map current is therefore not the whole obstacle. A simple two-visit reference agent reaches 45.2% when navigating, against an embodied oracle of 99.5%. An error decomposition places the remaining difficulty in carrying an instance identity across visits rather than in naming it or in selecting the answer once positions are known.

Batch normalization (BN) substantially improves sample efficiency in continuous-control actor-critic methods such as CrossQ, yet recent studies report performance degradation in discrete-action value learning on Atari. These failures are surprising because discrete Q-networks lack the action-input distribution mismatch identified by CrossQ. We show for target-based C51 and target-free PQN that the simple choice between running and batch statistics at specific forward passes can reverse this degradation. In C51, switching the BN bootstrap forward to batch-statistic mode significantly improves performance over unnormalized and LayerNorm baselines and scales stably with update-to-data ratios up to 12. In PQN, using batch-statistics for both action selection and bootstrapping recovers performance from the failing running-statistic configuration. Across 26 Atari games at 400M frames, this configuration achieves a higher final aggregate score than PQN with LayerNorm. Our results show that carefully configured BN can substantially improve discrete-action value learning, and that its forward protocols are an essential part of the algorithm specification.

Medical vision-language models (VLMs) require confidence that reflects both answer correctness and patient-specific visual evidence. Recent GRPO-based methods optimize verbalized confidence together with answer generation. However, this joint optimization may interfere with answer learning and drive confidence toward near-binary values. Verbalized confidence also provides no explicit assessment of visual support. We therefore separate capability learning from confidence estimation and propose DualRead. DualRead builds on the insight that reliability can be read from the actor's internal states at critical moments in the answering process. It freezes the GRPO-trained actor and combines pre-answer solvability with a post-answer assessment of the generated answer and its visual support. To further assess whether confidence reflects visual grounding, we introduce Counterfactual Confidence Grounding AUC (CCG-AUC). It measures whether confidence decreases when real-image substitution changes the actor from correct to incorrect. Across two VLM backbones and both in- and out-of-distribution medical VQA benchmarks, DualRead improves correctness discrimination and calibration over verbalized confidence while preserving answer accuracy. CCG-AUC reveals whether confidence responds to answer-relevant visual evidence rather than primarily to non-visual cues.

Let $\mathbb D$ be the normalized ridge dictionary generated by $\operatorname{ReLU}^k$ on a bounded Lipschitz domain $\Omega\subset\mathbb R^d$. We determine the sharp algebraic rate of finite $n$-term approximation from $\mathbb D$ when the outer $\ell^1$ coefficient budget is independent of $n$. More precisely, let $d\ge3$, $k\in\mathbb N_+$, $0\le m\le k$, $0<p<1$, and $0<q\le1$. For the unit ball of the critical Besov space $B_{p,q}^{k+d/p}(\Omega)$, measured in $H^m(\Omega)$, the optimal algebraic exponent is \[ \min\left\{\frac{k-m+d/2}{d-1}, \frac{k-m+d/2+1/p-1/2}{d}\right\}. \] We prove two-sided estimates in the three regimes determined by the two branches of this minimum and give the corresponding logarithmic factors at and beyond the transition. The estimates coincide without logarithmic loss in the strict angular regime and at the transition when $q\le[1/2+(k-m+d/2)/(d-1)]^{-1}$. The upper estimate combines critical wavelet sparsity, localized Fourier–Radon representations, and a stable allocation of directions and biases. The lower estimates arise from two distinct obstructions, namely radial ridge approximation on the direction sphere and Gevrey localization in the joint direction–bias space. The critical smoothness is exactly the endpoint at which Besov regularity provides a uniform shallow-network variation bound without additional scale decay. The resulting representation exponent is strictly larger than the degree-limited exponent for fixed-degree isotropic finite elements under a parameter-count comparison. This last statement concerns best approximation, not training or computational complexity.

Encrypted quantum cloning enables the creation of multiple encrypted clones of an unknown quantum state while allowing only one effective decryption, with the decryption resource being intrinsically consumed in the process. In this paper, we argue that this property supports a distinctive custodial security primitive for post-compromise response. We consider a threat model in which an adversary steals an encrypted quantum clone but does not yet possess the corresponding decryption key. In such a scenario, a legitimate custodian may unseal a different trusted clone, thereby exhausting the sole available unsealing opportunity and rendering the stolen clone permanently useless. We argue that this mechanism is not adequately described as mere revocation. Rather, it realizes a stronger form of post-theft response, which we call neutralization. We formalize this distinction, locate it within a broader post-theft response space, and introduce a temporal threat model. We compare the mechanism with its closest classical analogue, showing that the classical case can reproduce the policy outcome only through external procedural composition. We finally interpret encrypted quantum cloning as a primitive for post-compromise quantum custody in distributed preservation settings, with prospective relevance for Cyber-Humanities-oriented preservation architectures.

Hardware for lattice-based post-quantum cryptography spends a large share of its area on the number-theoretic transform (NTT), dominated by modular multipliers and twiddle storage. FoldNTT is a redesign of the released radix-2 CFNTT accelerator (TCHES 2022) for the Falcon / FN-DSA prime q = 12289 with one hardware multiplier per butterfly instead of three and about half the stored twiddle constants. The Proth shape q = 3*2^12 + 1 turns modular reduction into shift-and-add K-RED folds, and the bit-reversed twiddle table obeys w[N/2+j] = psi*w[j], so half the table is derived without a multiplier. Checking the released RTL against the mathematics also exposed a bug: its inverse transform omits a per-stage halving and returns 2^10*x, which the retrofit corrects. Every arithmetic block is proven by exact-width SMT and compositional SymbiYosys proofs, control-safety invariants by k-induction; the proofs are mutation-tested and the composed transform is validated by simulation, all rerun by CI. On Artix-7 in a fully open flow, the retrofit costs 3->1 DSP48 per butterfly and -50% stored twiddle bits at a whole-core Fmax cost of about 4% (best of three seeds; within the seed-to-seed spread), measured on the released datapath driven by a controller we reconstructed (the reference FSM was never released) and validated by full-core simulation; a sequential core with our own controller builds to a timing-gated Basys-3 bitstream.

Existing approaches to visual attribute value extraction (AVE) primarily rely on static product images, failing to capture temporal cues, multi-angle views and fine-grained visual details. Directly applying video vision-language models (VLMs) to product AVE results in limited performance due to the lack of domain knowledge, and fine-tuning them requires extensive high-quality data and substantial computational resources. Thus, we propose visual search augmented chain-of-thought reasoning (ViS-CoT), a training-free, plug-and-play pipeline that can be easily applied to any open-source video VLM for video-to-text AVE in e-Commerce. Specifically, ViS-CoT employs visual clustering to identify representative frames, followed by visual search to retrieve semantically similar product knowledge that can enrich attribute cues. Next, an interleaved CoT reasoning module iteratively refines reasoning through visually-aligned auxiliary texts derived from captioning and automatic speech recognition. Finally, the integrated information guides the model toward accurate and fine-grained attribute predictions. Extensive experiments across 14 product categories on the VideoAVE dataset show that ViS-CoT consistently enhances multiple state-of-the-art video VLMs, achieving an average improvement of 17.91 percentage points in micro-F1.

Research on 3D integrated circuits (3D-ICs) physical design has expanded rapidly in recent years, driven by the increasing adoption of hybrid bonding and the demand for higher integration density. Continued scaling of hybrid-bonding pitch supports higher vertical interconnect density and finer-grained circuit partitioning in 3D-ICs. Hybrid bonding-enabled 3D-ICs offer substantial benefits in interconnect scaling and system integration, yet tier assignment remains challenging because it jointly determines 3D wirelength and hybrid bonding terminal (HBT) assignment. This paper presents a differentiable partitioning framework that directly optimizes placement-aware tier assignment for 3D-ICs through gradient-based optimization. Discrete tier assignment is relaxed to continuous probabilities, and a Dual-Max 3D wirelength model is introduced as a placement-aware surrogate for tier-specific half-perimeter wirelength (HPWL). In addition, a terminal-aware cutsize penalty gives higher weights to cross-die nets with predicted HBT overlaps, and a local balance penalty discourages regional area overflow on each tier. On ten OpenROAD benchmarks, our method reduces final die-to-die (D2D) HPWL by 8.05% and 14.81% on average relative to hMETIS and TritonPart, respectively. On the seven benchmarks with available CoPlace results, the average HPWL reduction is 10.33%. The source code for the differentiable partitioner and the integrated 3D placement flow is publicly available to support reproducibility.