Papers

While Wikipedia promotes a neutral point of view on historical conflicts, its language editions are written by editors from distinct linguistic and cultural communities. In this study, we analyze 158 wars since 1900 to examine how the descriptions of combatants vary across 20 Wikipedia language editions. Using connotation frames—which assess power, agency, and sentiment toward an entity—we examine how each language portrays the parties involved in the conflict. We find systematic differences when language editions describe wars involving their own communities, although the direction of these asymmetries varies across languages. However, when language editions describe conflicts that do not involve their own linguistic communities, their narrative structures exhibit high cross-linguistic similarity. These findings show how linguistic communities influence war narratives on Wikipedia, revealing that shared historical accounts remain shaped by the perspectives of the language communities that produce them.

Large language models (LLMs) can fluently verbalize statistical evidence, yet statistical reports can still drift numerical values, invert effect directions, or restate thresholded contrasts as categorical effects. We frame these failures as a control problem: the evidence-bearing content of a scientific report should be fixed by structured statistical results rather than sampled during prose generation. We therefore use cross-run reproducibility to stress-test whether report-visible numbers and claims are bound before prose generation. Existing controls operate at the text or slot level; a deterministic hybrid template reproduces only 61.1% of report-visible numerical content across seeds because the LLM still selects which findings and numbers the template renders. We propose claim-locked reporting, a provenance-before-prose protocol that fixes the evidence source, numbers, direction, and allowed language strength of each reportable claim before the LLM writes only connective prose. Across fMRI functional-connectivity reporting and randomized controlled trial reporting on Evidence Inference 2.0, claim-locked reporting improves reproducibility over the hybrid template by 37.4 and 20.5 points, respectively. Blinded human audits support the observed direction-preservation and governance trends. In an fMRI cost analysis with DeepSeek, claim-locked reporting also yields the lowest observed token use and median generation latency.

Diffusion-based real-world image super-resolution (SR) achieves impressive perceptual quality but inherently suffers from severe texture hallucination. To overcome this limitation, we propose GraftSR, a texture-reference-guided generative SR framework that leverages reference images of the identical instance to anchor the restoration of authentic textures. However, severe spatial misalignment between low-quality inputs and their references poses significant challenges, often leading to ambiguous transfer targets and background feature leakage. To address these issues, GraftSR employs a novel dual-mask reference guidance mechanism that systematically decouples the cross-view texture injection process. By explicitly isolating what authentic textures to extract from the reference and precisely localizing where to apply them within the target, GraftSR achieves robust texture transfer without relying on brittle spatial alignment. Furthermore, to bridge the critical gap in appropriate training data, we construct TexRefSR-141K, the first large-scale dataset providing high-quality reference tuples equipped with complementary spatial masks. Extensive experiments on our newly established benchmark, TexRefSR-Eval, demonstrate that GraftSR sets a new state-of-the-art. Notably, it reduces LPIPS by 20.2% over top-performing baselines, achieving superior reference-faithful restoration.

Vision-Language Models (VLMs) have exhibited impressive performance across diverse visual scenarios. However, this success comes at the cost of explosive growth in visual tokens, which imposes substantial memory and computational overhead during inference, ultimately increasing latency. To improve VLM inference efficiency, a typical class of visual token pruning methods estimates token importance by aggregating attention scores across all heads in the pruning layer of the Large Language Model (LLM) backbone and prunes tokens based on aggregated scores. However, in this paper, we reveal a compelling phenomenon: the capability to pinpoint critical visual tokens is concentrated within a small fraction of heads. Aggregation exclusively on these heads can improve task performance. Inspired by this observation, we propose ProViP, a training-free progressive visual token pruning framework. ProViP first removes redundant visual tokens based on the embedding similarity of input tokens before reasoning of the LLM backbone, and then further prunes tokens during reasoning via head-aware pruning. Experiments demonstrate that ProViP delivers outstanding task performance and inference efficiency. For instance, when applied to LLaVA-1.5-7B, ProViP retains 95.9% of the original performance and achieves 1.62x inference speedup under an 88.9% pruning ratio.

Memory-augmented agents maintain compact user profiles throughout extended conversations, enabling personalized and consistent responses without the need to process the entire dialogue history. The quality of these user profiles relies on the underlying memory management strategy: at each step, the agent must determine what to retain, compress, or discard. However, existing methods typically employ a static, one-size-fits-all strategy established before training. In practice, the optimal memory decision is inherently user-specific and dynamically evolves alongside policy optimization. To address this, we propose HiPS (Hierarchical Personalized Strategy), a framework that decouples memory management into a globally shared foundation and a user-specific adaptive tier. Specifically, HiPS employs Universal Strategy to extract shared principles from cross-persona trajectories, alongside Persona Delta Distillation to generate tailored rules for users whose behaviors diverge from general patterns. Cross-Level Rule Flow dynamically calibrates their boundary by promoting broadly validated personal rules and demoting contradicted global ones. The architecture establishes a co-evolution loop where a mechanism guarantees that all strategy refinements are anchored to task outcomes. Extensive experiments demonstrate consistent improvements over memory-augmented baselines.

Cryogenic parametric amplifiers are used to amplify radio-frequency signals for a range of applications in basic and applied science. Both Josephson Parametric Amplifiers and Josephson Traveling-Wave Parametric Amplifiers have been used as first-stage amplifiers enabling readout chains operating within a few quanta of the quantum limit. However, these devices are highly sensitive to magnetic fields, having critical current suppressed by the Fraunhofer effect, requiring substantial field-free zones. In a dark matter axion search experiment, axions convert to detectable microwave photons in the presence of a strong magnetic field, necessitating amplifiers that can reliably operate close to these environments. Kinetic-inductance Traveling-Wave Parametric Amplifiers (KTWPAs) may be the ideal candidate for this type of application having high critical magnetic field of the materials used throughout their construction. In this letter we demonstrate that KTWPAs can provide high gain (>20dB) over a multi-GHz bandwidth in spite of from multiple exposures to multi-Tesla fields. Further, we explore operational characteristics of these devices under harsh conditions as a function of overall field strength, device orientation within the field, applied bias current, and pump power & frequency. In so doing, we find KTWPA gain vanishes in devices oriented perpendicularly to a field of 0.02T, but gain values >10dB are achievable in fields over 1T when oriented near~parallel to the device plane, with peak gain achieved with an applied 0.25T to 0.5T field. It is our expectation that KTWPAs will expand the accessibility of quantum-limited RF measurements in the presence of Tesla-scale fields.

Physics-Informed Neural Networks (PINNs) frequently fail on stiff or advection-dominated PDEs, and two recent accounts offer competing remedies: switching from FP32 to FP64 to repair an L-BFGS stopping artifact, or replacing the MLP with a state-space-model (SSM) backbone plus sub-sequence alignment to counter architectural simplicity bias. We test both under matched, seed-paired controls in a pre-registered 144-run study spanning convection, reaction, and wave, plus an independent 85-run convection/wave study; success is relative $\ell_2$ error below $0.05$. The two remedies act on disjoint regime-and-seed slices: neither substitutes for the other. On hard convection ($\beta{=}50$), alignment recovers 2/5 seeds in FP32 and 3/5 in FP64, where the unaligned SSM succeeds on 0/5 seeds at either precision and the vanilla MLP moves only from 0/5 to 1/5 across the precision switch—the recoveries trace to the alignment objective, not the backbone. On reaction the backbone alone already succeeds on 3/5–4/5 seeds, so each remedy covers a regime the other does not. Responses are also seed-specific: the same precision switch flips individual seeds in opposite directions and, on wave, lowers median error with no statistically significant success gain. Tightening the inner L-BFGS tolerance in an independent repeated-step runner likewise lowers median error at a large runtime cost, with success counts unchanged. Precision, stopping, backbone, and alignment must therefore be evaluated jointly and reported per seed.

In transductive classification, an adversary fixes a labeled population, one label is hidden uniformly, and the learner sees all remaining labels. For binary classes, agnostic transductive and PAC learning have the same minimax rate. Whether this extends to multiclass learning was open, especially for unbounded label spaces where uniform convergence can fail. We resolve the question up to logarithmic factors. For every multiclass class $\mathcal H$ with DS dimension $d_{DS}$ and Natarajan dimension $d_{\mathrm N}$, the optimal agnostic transductive excess error satisfies $\widetilde\Theta\left(\frac{d_{DS}}{n}+\sqrt{\frac{d_{\mathrm N}}{n}}\right).$ The result holds for arbitrary label spaces. The two terms are both necessary. A DS pseudo-cube gives the realizable $d_{DS}/n$ obstruction, while a Natarajan cube with repeated points and fair labels gives the agnostic $\sqrt{d_{\mathrm N}/n}$ obstruction. The upper bound uses a random-reservation principle. The learner deliberately ignores a constant fraction of the visible labels, which makes the true test point uniform in a large unseen block. We combine realizable compression, a label-space reduction, and inside-menu agnostic compression across this finite-population split. A new without-replacement multiplicative-weights lemma preserves the fast $d_{DS}/n$ term. Consequently, agnostic multiclass PAC and transductive learning obey the same two-dimension law up to logarithmic factors.

Deploying large language models for professional financial review requires more than measuring general financial competence: models must perform the specific review operation required by a workflow and determine whether available evidence is sufficient for a defensible decision. Existing financial benchmarks cover knowledge, reasoning, compliance, and professional tasks, but their evaluation units are often organized around datasets or task formulations rather than the decisions that deployed systems support. We introduce FinRiskAtlas, a Chinese-language benchmark that evaluates financial LLMs along two complementary dimensions: operation execution under fixed evidence states and evidence-state control under evolving review conditions. The static benchmark contains 9,742 instances across 53 task families, including 42 Domain Knowledge families and eleven downstream review operations defined by explicit evaluation contracts. FinRisk-Ask extends this framework through offline replay of 680 pre-action states from 104 de-identified professional trajectories, withholding future evidence during inference and using it only to construct expert-verified evidence targets. Across 33 model configurations, operation-level evaluation yields non-redundant rankings (mean pairwise Spearman correlation 0.42 across downstream operations), and knowledge-based shortlisting can incur up to 18.01 points of regret on individual operations. FinRisk-Ask further shows that entering the Ask branch more frequently does not necessarily improve request targeting or end-to-end evidence acquisition. These results show that broad financial capability scores do not fully capture where models are reliable in professional workflows, motivating evaluation units aligned with the decisions and evidence states that deployed systems must support.

This paper develops a certified constraint-reduction method for distributed model predictive control with tube-tightened exponential control barrier functions (eCBFs) in multi-agent systems. At each prediction stage, pairwise agent–agent and agent–obstacle eCBF conditions define halfspaces in the local control space. Rather than enforcing all such halfspaces, a geometry-adaptive subset is retained and a Farkas certificate verifies that the reduced admissible set is contained in the full tightened set. For planar inputs, cone coverage is characterized through the largest angular gap: two extreme directions suffice in the strict half-plane regime, while other geometries initialize with three retained constraints and escalate only when certification fails. Conic multipliers and nominal-aware offsets are obtained in closed form, without an auxiliary optimization, and the resulting construction preserves any nominal control already admissible for the full tightened set. Consequently, the reduced controller inherits the robust safety guarantee of the underlying tube-eCBF formulation. In a ten-follower, four-obstacle study, the method retained fewer safety constraints on average, reproduced the full filter's nominal accept/reject decisions with no true safety violations, and achieved increasing computational gains as the constraint count and prediction horizon grew.

Software agents connect probabilistic model output to operations that change repositories, processes, networks, and graphical applications. We present Metis, a multi-provider runtime that converts provider streams into typed events before admitted calls reach external effects. Its execution path makes permission decisions, interference classes, terminal results, and lifecycle transitions explicit and inspectable. We evaluate these mechanisms on frozen source artifacts. Across 30 matched real-I/O pairs, four-class mediation reduced median elapsed time from 25.958 ms under forced serialization to 14.146 ms. The mean paired difference was -12.295 ms (95% bootstrap interval [-12.968, -11.694]), with mediation faster in all pairs. A ten-case fault matrix exposed duplicate-identifier and rollback limits. In a child-boundary ablation, the full gate-plus-registry condition blocked the declared unauthorized effect and hid all five escape tools. Removing both protections reversed both observations. A decision-only permission oracle matched all ten declared cases across five invocation routes. Five model conditions also completed a fixed Read-marker protocol in 3/3 trials each. These results support bounded claims about dispatch, permission routing, child authority, and provider-valid trace closure. They do not establish model competence, semantic safety, rollback, or superiority over another runtime.

The move of LLM inference to edge AI accelerators introduces new physical vulnerabilities. During execution, model parameters and intermediate inference states are repeatedly loaded into and processed on the chip, making them suscep- tible to physical side-channel attacks. In this work, by deploying laser voltage imaging, we show that one can extract LLM assets during inference, namely embeddings, attention, and quantized MLP weights, activations, and other inference states, from localized memories and compute subcircuits. To validate our claims, we perform an attack on an FPGA-based LLM accelerator. Since such accelerators reuse the same buffers and compute subcircuits across addresses, tiles, modules, and layers, reading asset values comes down to probing different memories during inference. We demonstrate full recovery of the targeted values; however, we also establish a methodology to recover asset values even if some weights or bits remain unread. We further derive lower bounds that relate imaging effort to asset dimensions and show that even direct recovery scales linearly with the size of the targeted asset

UAV displacement attacks have traditionally relied on spoofing sensors that directly report position or translational motion, such as GNSS and optical flow. In this work, we introduce SonicNudge, a new attack primitive that instead targets the gyroscope and shows that low-level inertial errors can be transformed into controlled displacement of hovering or slow-moving UAVs. The attack exploits estimator–controller coupling: a small gyroscope perturbation by ultrasonic resonance can persist as an attitude-estimation bias, and the flight controller can convert this biased estimate into a shifted hover point. This behavior is especially relevant to UAV tasks that require hovering, station-keeping, slow approach, or precise final alignment, such as perimeter denial, inspection, docking, landing alignment, and close-proximity operation, where meter-scale position errors can be operationally meaningful. We analyze this attack primitive in a PX4-style flight stack and validate it through 81 simulation runs and more than 10 indoor/outdoor physical experiments, showing that displacement is governed by estimator weighting, bias observability, and closed-loop position correction. Our study suggests that UAV and vehicle-system security should look beyond direct navigation spoofing and pay closer attention to low-level inertial errors and estimator–controller coupling as a subtle but important attack surface.

We introduce Rank-Deviation Quality (RDQ), an evaluation metric for retrieval and ranking systems that adapts to queries with varying numbers of reference items, from a single correct answer to many valid results. RDQ scores a candidate ranking against an ordered reference list (ORL): each retrieved reference item contributes its output-position weight multiplied by a rank-deviation penalty, and items outside the ORL receive zero credit. Application-specific parameters control tolerance to misordering. Larger values emphasize retrieving valid reference items, whereas smaller values place more weight on matching their reference order. The output-position weights can reflect visibility in the application's interface, such as a vertical list or a carousel. Unlike metrics that require absolute relevance grades, RDQ operates on ordinal rankings, which annotators can produce through pairwise or listwise judgments. Unlike rank-correlation measures such as Kendall's tau, RDQ accounts for both which items are returned and how they are ordered. On a 5,000-query point-of-interest (POI) dataset with 12 systems, RDQ has the highest median empirical power@100 among the 13 evaluated metric configurations. It reaches mean tau >= 0.8 agreement with its own full-query ordering at 200 queries; RBP(0.9), the strongest tested non-RDQ configuration, reaches the same threshold at 250. On TREC Deep Learning benchmarks, where NDCG uses native graded labels and RDQ uses ordinal tiers derived from them, RDQ reaches comparable median power at n=25, while NDCG is higher at n=100.

With the rapid development of AI-based personality and job-related competency assessment, Asynchronous Video Interviews (AVIs) are increasingly used in recruitment. However, existing multimodal personality datasets are often based on short, task-free social media videos and crowdsourced apparent personality labels, which limits their construct validity and relevance to structured interview assessment. To address these limitations, we introduce AVI-Personality, a trait-activated multimodal dataset for personality and job-related competency assessment from AVIs. The dataset contains 3,876 interview videos from 646 participants who completed a simulated management traineeship application. Participants answered two generic questions and four personality-targeted questions designed according to Trait Activation Theory. Our dataset provides both self and observer-reported HEXACO personality traits and job-related competency. We validate AVI-Personality through reliability, construct validity, internal nomological association, fairness, and benchmark analyses. Validation results show that the observer-rated personality traits have moderate to high reliability, especially when ratings are based on personality-targeted questions. Benchmark results show that text-based AI algorithms provide strong personality-relevant cues, while multimodal methods achieve the best overall performance but only modestly outperform text-based baselines. In general, AVI-Personality provides a psychometrically grounded dataset for developing and evaluating AI-based models for personality and competency assessment. The dataset is available are released at https://github.com/APAL-SEU/AVI6

Order-dependent activation statistics are often interpreted as evidence of interaction, but that interpretation can be confounded by where interventions enter the network. We introduce a no-fit site-asymmetry audit. For a twice-differentiable readout, the open-path order-swap decomposes into a canonical additive response measured by single interventions and an antisymmetrized second difference free of first-order and pure self-curvature terms to second order. Across six open-weight language-model families, the single-intervention baseline explains 84.3-97.7 percent of the bracket norm (mean 93.7 percent), while the no-interaction self-curvature term is 1.8-5.2 times larger than the corrected residual in the two families with the plus/minus injection split. The corrected residual clears a generic-interaction null in three of six families under a confound-free prompt split and two of six after configuration robustness. A known-positive surrogate recovers planted mixed interaction, while a matched site-separation test changes the baseline share and a random architecture reproduces the first-order regime. The same estimator transfers to released non-language references: trained residual fractions fall below a fixed Gaussian-direction null in 11/12 contrasts (5/6 ViT-B/16, 6/6 ResNet-50), a portability check rather than pooled evidence. The contribution is a reusable measurement criterion: run the single-intervention baseline before reading an order-swap vector as interaction or geometric structure; if it explains the vector, form the second difference instead. All claims are scoped to activation-space interventions at distinct sites; we do not claim that representation geometry is globally Abelian.

Diffusion Language Models (DLMs) have recently become increasingly competitive with autoregressive (AR) models, and even outperform them on certain tasks. Unlike AR models, DLMs produce output through iterative denoising without a left-to-right order. To further improve the performance of DLMs, we introduce PDC (Prefix-Denoising Consistency), a test-time self-verification method for DLMs. PDC exploits a distinctive test-time signal in DLMs under prefix conditioned regeneration, correct trajectories are more stable and reproducible than incorrect ones. Concretely, given an initially generated sample, PDC splits the sentence at an intermediate position and regenerates the remaining tokens conditioned on the fixed prefix. Across mathematical reasoning and commonsense reasoning benchmarks, PDC consistently improves upon the initial sample, outperforms independent generations under a computational constrained comparison, and is robust to different unmasking strategies and parameter settings. These results highlight prefix-conditioned regeneration as an effective DLM-specific primitive for test-time verification.

Vision-language-action (VLA) models provide a scalable path toward generalist robotic manipulation by integrating visual perception, language understanding, and continuous action control. However, we reveal a critical limitation of VLA architectures: the action expert has limited access to the 3D geometric and 2D semantic information available in VLM features. This accessibility gap weakens perceptual grounding and limits performance on fine-grained robotic manipulation. To address this issue, we propose V-Link, which explicitly recovers visual representations during the vision-language (VL) to action (A) feature transfer. Specifically, V-Link learns complementary Spatial and Semantic Query representations within the VLM and injects them into Action DiT through asymmetric pathways. Semantic Queries complement the original VLM image tokens, whereas Spatial Queries provide dedicated geometric conditioning for spatially grounded action generation. Across LIBERO, LIBERO-Plus, and RoboTwin 2.0, our V-Link improves the average success rate over base model GR00T N1.6 by +1.9%, +31.2%, and +18.8%, respectively. On the AGIBOT A3 Ultra, V-Link further achieves gains of +20% and +24% on two real-world humanoid tasks.

Training-free zero-shot composed image retrieval finds a target image in a gallery from a reference image and a text edit without learning from task-specific image triplets. Existing methods typically describe the target as a whole and match this description with a global image representation. This global matching can mix different semantic cues and lose fine- grained details. We propose MULVEC, a role-aware method whose compiler produces a structured query record that is mapped to four retrieval roles: Global describes the full target, Desired states what should appear, Preserve states what should remain, and Forbidden states what should disappear. Frozen encoders map the query to one target description vector and role-specific probe vectors, while each candidate is represented by one global visual vector and a bank of local visual vectors. The retrieval roles then use this shared evidence for their respective purposes, and a fixed weighted sum of their scores ranks the entire gallery in a single retrieval pass. Across CIRCO, CIRR, and FashionIQ and three backbone scales, MULVEC improves CIRCO mAP@5 by up to 23.0% over the strongest compared method and gives the best CIRR and FashionIQ results in our comparison.

Simulated maximum likelihood is widely used in latent-variable models where likelihood evaluation requires intractable integrals or probabilities. With a fixed number of simulation draws, its estimating equation is generally biased. We develop Stochastic Approximation with Unbiased Simulated Scores (SAUSS), combining score simulation with stochastic gradient descent. The Hajivassiliou–McFadden identity, an instance of Fisher's identity, expresses the likelihood score as the conditional expectation of the complete-data score given the observed data. Exact conditional draws yield an unbiased simulated score for any fixed number of draws. The estimator averages stochastic gradient iterates computed using mini-batches of fixed size regardless of sample size, avoiding repeated full-sample likelihood evaluations. Under local regularity and initialization conditions, we establish asymptotic normality and a functional central limit theorem for the partial-sum process of the iterates under multi-pass sampling from an observed sample. These results support plug-in and random-scaling confidence intervals that remain asymptotically valid when algorithmic uncertainty is non-negligible relative to sampling uncertainty. We develop multinomial probit as a leading application. In simulations and two applications, SAUSS returns estimates in every reported run, including cases where the simulated maximum likelihood implementation returns none. When both return estimates, SAUSS gives comparable estimates in less time.

We study the sample complexity of learning near-optimal bilateral trade mechanisms. Unlike previous work on learning simple or fixed-price bilateral-trade mechanisms, we focus on mechanisms satisfying Bayesian incentive compatibility (BIC), interim individual rationality (IIR), and ex-ante weak budget balance (WBB). In other words, our target is to design a sample-based mechanism that achieves the second-best gains-from-trade benchmark. We give matching or nearly matching upper and lower bounds in three regimes. For regular product distributions on $[0,h]^2$, additive $\varepsilon$-approximation has sample complexity $\widetilde{\Theta}(h^2/\varepsilon^2)$. For multiplicative $(1-\alpha)$-approximation under the same assumptions, we find that the sample complexity is $\widetilde{\Theta}(h/(\mathrm{SB}(D)\alpha^2))$, which is benchmark-sensitive with unavoidable dependence on the second-best gains from trade $\mathrm{SB}(D)$. We also investigate unbounded distributions under a monotone hazard rate (MHR) assumption. The sample complexity depends on the ratio $\chi_\mu(D)=\mu(D)/\mathrm{SB}(D)$, where $\mu(D)$ is the sum of the buyer's expected value and the seller's expected cost.

Guided depth super-resolution (GDSR) typically extracts RGB guidance features through convolutional hierarchies, inheriting their fine-to-coarse bias. Thus, low-level spatial cues surface in early layers, leaving the deeper layers to suppress those that do not correspond to true depth boundaries, which risks artifacts and blurred edges. The same fine-to-coarse bias persists in semantics-based methods that consume low-level tokens early and global tokens late. We present WAVE, which introduces a multi-level discrete wavelet transform (ML-DWT) as an explicit and interpretable feature-control mechanism, enabling a coarse-to-fine reconstruction by consuming sub-bands and semantic tokens in reverse of their generation order. WAVE further exploits these sub-bands to treat high- and low-frequency content separately, isolating the misleading RGB color and texture cues before any feature is learned so that their admission can be controlled explicitly, offering an intuitive alternative to the suppression learned implicitly by an opaque network. WAVE separates structure and detail reconstruction into dedicated modules that: i) model interactions within and across wavelet sub-bands, depth features, and semantic priors, ii) apply semantic gating to the high-frequency bands, and iii) fuse modalities through an invertible coupling mechanism that prevents collapse onto a single modality. Extensive experiments across multiple benchmarks demonstrate that WAVE matches or outperforms existing methods, with the largest gains at high upsampling factors, where low-resolution depth contains the least structure.

Gradient-flow models are characterized by an intrinsic energy-dissipation structure, and faithfully preserving this structure at the discrete level is important for stable and reliable long-time simulation. To this end, we develop a Conditioning-Aware Representation Enhancement with Scalar Auxiliary Variable (CARE-SAV) framework, which constructs a compact spatial approximation space from flexible candidate features and evolves the gradient-flow dynamics directly within this space. The resulting fully discrete scheme preserves the discrete energy-dissipation law while providing a flexible alternative to conventional prescribed spatial discretizations. Rigorous analysis establishes the approximation capability, solvability, stability and convergence of the proposed method. Numerical experiments on representative gradient-flow problems demonstrate its accuracy, robustness and computational efficiency. We believe that CARE-SAV could provide a simple, flexible, and computationally efficient paradigm for structure-preserving discretization of gradient-flow problems.

Vision-language models (VLMs) increasingly rely on point coordinates as a compact and executable interface for visual grounding in GUI interaction, robotic manipulation, and interactive visual systems. However, learning reliable pointing behavior remains difficult because the supervision space is inherently non-unique: many coordinates may be valid within the same target region, while multi-instance instructions require target coverage, count consistency, and duplicate suppression. This work presents PointRL, a verifiable reinforcement learning framework that learns point-level grounding from existing heterogeneous annotation evidence. PointRL converts bounding boxes, masks, and instance labels into pointing instructions, while retaining their target supports, instance membership, and set constraints as hidden verifier evidence, i.e., annotations kept outside the prompt and used by a deterministic checker to score predictions. The proposed reward evaluates parseability, point validity, instance coverage, cardinality consistency, and redundant or missing predictions. On PointArena, PointRL improves the overall accuracy of Qwen3.5-4B from 56.11% to 65.58%. Further evaluations on RoboSpatial, BLINK, and Ref-Adv show same-backbone gains on the evaluated external benchmarks, suggesting that verifiable point-level feedback may benefit spatial grounding in these settings.

Points in the unit ball of $\mathbb R^d$ are processed sequentially. Each new point $p_i$ is connected to a state $x_{i-1}$ that summarizes earlier observations, after which $x_i=\gamma x_{i-1}+(1-\gamma)p_i$, with $0\leq\gamma\leq1$. The cost is the sum of the $\alpha$-powers of the connection lengths. This constant-gain rule interpolates between the input-order path and the star centered at the initial point. For independent uniform points, we establish the stationary insertion-length distribution and prove that it decreases in stochastic order as $\gamma$ increases. If $d+\alpha>2$, or if $(d,\alpha)=(1,1)$, the optimal constant parameter satisfies $1-\gamma_N^*=\Theta(N^{-1/2})$, with an explicit asymptotic constant and closed bounds. For $\alpha=1$, its leading expected tree length equals that of the center star and is eventually smaller than the expected lengths of both endpoint constructions. For $\alpha=2$, the optimizer is unique and characterized exactly. For the same $N$, choosing $1-\gamma_N$ as a fixed positive multiple of $N^{-1/2}$ gives a sharp two-term expansion of the expected uniform-input cost and a maximal adversarial mean cost of $1+O(N^{-1/2})$. For every fixed $0\leq\gamma<1$ and $0<\alpha\leq3$, the exact asymptotic adversarial value is $(2/(1+\gamma))^\alpha$. When $d\geq2$, exponential weighting is within a factor smaller than $1.161^\alpha$ of the best fixed nonnegative weighted rule with the same average look-back, for $0<\alpha\leq3$. Comparison with the running mean highlights its time-homogeneous update, stationary coefficient profile, and fixed effective memory.

Battery-free sensors expose short, stochastic communication windows and may lose timing state whenever their main energy domain browns out. MagPie combines a microampere wake-up radio (WuR) with a separately backed low-power real-time clock (LP-RTC): the WuR widens the first-contact window, while the LP-RTC preserves the acquired phase for later exchanges. Energy gates, epoch-versioned schedules, and idempotent slot allocation extend this mechanism to static, single-hop All-to-One collection without a powered control anchor. The analysis accounts for role selection and duty-cycled listening, and bounds scheduled-retry tails only under explicit conditional quantile coverage. Evaluation separates three scopes. In independent, administratively censored simulation trials, MagPie completes 100/100 first rendezvous events in each of five trace-parameterized harvesting scenarios; Find completes 36-100/100. A single-collision-domain slotted-Aloha study shows that adaptive K is necessary at high contender density and reports mean, P95, and confidence intervals through 120 components. Finally, controlled STM32WL33 experiments validate alignment, clock persistence, and six-device slot execution, including an 11.05-hour functional run. The study does not claim measured end-to-end energy, ambient-harvesting performance, or multi-hop scalability; highly variable harvesting still limits collection because coordination cannot create missing energy.

Symbolic regression (SR) seeks to discover parsimonious mathematical laws from observational data, yet conventional approaches often struggle with the vast combinatorial search space of physically meaningful expressions. We present InsightSR, a framework that embeds Large Language Models (LLMs) as a guiding layer around the PySR genetic programming engine. Rather than relying on LLMs to generate expressions directly, InsightSR uses LLMs to progressively transform the search space itself through two complementary pathways: a Semantic Seed Pathway that proposes dimensionally consistent functional skeletons, and a Structural Feature Pathway that recommends nonlinear feature transformations. These transformations accumulate over iterations, broadening the input space and shifting the symbolic search from constructing deep expression trees over raw variables to assembling shallow trees over a rich, semantically informed feature set. A post-generation feedback loop evaluates candidates, categorizes features by their empirical utility, and refines the guidance for the next iteration, transforming the discovery process from open-ended generation into iterative, self-correcting refinement. Across three benchmarks, InsightSR achieves a 95% exact recovery rate on the Feynman benchmark and 80.18% accuracy on the LLM-SRBench LSR-Transform task, substantially outperforming state-of-the-art genetic programming and neural-symbolic methods while maintaining strong out-of-distribution generalization on real-world datasets.

Classical paging serves every miss immediately. We study paging with per-replacement maximum delay, where loading a pending page costs one movement plus the age of its oldest outstanding request and clears that page's entire episode. Equivalently, the holding rate is the number of pending pages. For cache size $k$, threshold LRU is strictly $(5k+3)$-competitive, while a randomized algorithm is strictly $5H_k$-competitive against an oblivious adversary; classical constructions give matching $\Omega(k)$ and $\Omega(H_k)$ orders. Offline, we obtain an exact $O(nk)$ dynamic program with one hole, an exact configuration algorithm for any fixed number of holes, and a nonproactive polynomial-time $5$-approximation in general. Physical farthest-next-use can nevertheless fail with only three pages. For page-dependent fetch costs with spread $\rho=w_{\max}/w_{\min}$, the exact fixed-number-of-holes algorithms persist. We obtain a $(3\rho+2)$-approximation and online guarantees with multiplicative factors $O(\rho k)$ deterministically and $O(\rho H_k)$ randomly against an oblivious adversary, plus any additive term inherited from the corresponding classical guarantee. A strict $\Omega(\sqrt\rho)$ randomized lower bound already holds for one cache slot. Thus maximum delay preserves the unit-cost competitive hierarchy but disrupts classical offline structure and makes weighted timing spread-sensitive.

Partial manipulation of speech recordings, where only localized segments of an utterance are altered, poses a significant challenge for content integrity verification, as reliable detection and localization of such edits becomes harder as the manipulated proportion decreases. Watermarking offers a proactive defense alternative by embedding auxiliary information prior to distribution; classical hash-based schemes achieve near-perfect detection and localization under ideal conditions, but the original content cannot be recovered once a segment is manipulated. Building on a prior self-embedding audio steganography framework, this work presents an initial exploration of proactive defense performance under ideal conditions, extending the investigation along three axes: frame-level localization, multi-bit least significant bit variants, and evaluation across multiple ultra-low-bitrate neural codec representations. By embedding a compact neural codec representation rather than a cryptographic hash, the framework additionally enables recovery of the manipulated regions, while supporting training-free detection and localization without spoofed examples. Experiments across four controlled manipulation types under ideal channel conditions show that the embedded payload, and hence an approximate reconstruction of the authentic content, is always fully recovered without bit errors. The results also indicate that the choice of neural codec is the dominant factor for detection and localization performance.

Artificial intelligence (AI) promises to accelerate biological research by automating computational analyses. Yet the ability of AI agents to execute on computational biology at the scale of complete research studies has not been systematically evaluated. Here we introduce BixBench3, a benchmark that measures the capacity of AI agents to process raw biological data through to scientific results. We designed BixBench3 tasks to mirror the delegation of work from a scientist to an agent: the scientist chooses the research question and high-level methods, then delegates implementation of all analyses to the agent. In each task, an agent receives a research objective, methodological guidance, and raw data derived from a published scientific study, and must execute a sequence of analyses to achieve the research objective. The data artifacts resulting from these analyses, such as peak call matrices or differential expression tables, are programmatically graded against the corresponding artifacts generated and reported in the original study. Across 20 BixBench3 tasks encompassing the generation of 138 unique artifacts, we find that 13 frontier models achieve scores ranging from 0.00 for Gemini 3.1 Flash Lite to 0.48 for GPT 5.6 Sol. Agents perform worse on tasks with larger raw datasets (0.36 on tasks with <100 GB versus 0.10 on tasks with >100 GB) and on analyses requiring more sequential steps (0.36 at 1-2 steps vs 0.24 at 3+). On average, agents use 6.8 hours, 102 million tokens, and \$43 to complete each task, with the longest attempts consuming 24 hours, 1.07 billion tokens, and \$525. Notably, the highest-scoring agents used fewer tokens and were cheaper than less performant options. These results reveal that LLMs vary substantially in their ability to (1) execute multiple sequential analysis steps coherently, (2) manage large quantities of raw data, and (3) work across scientific domains.