Papers

Slicing-Aided Hyper Inference (SAHI) improves small object detection in high-resolution images but often spends substantial compute on background tiles. We propose region-of-interest (ROI)-Gated SAHI, an inference-time framework that introduces a lightweight proposer to localize foreground regions and restrict sliced refinement to informative areas. We evaluate the framework in two settings. On the COCO128 full split dataset comprising 128 images, static ROI-gating is slower on average than Full SAHI, achieving a speed ratio of 0.88, and yields a lower mAP@0.5 of 0.6602 compared with 0.7569 for Full SAHI. A simple adaptive routing policy with $\tau =$ 0.4 educes the mean latency, achieving a slight gain of 1.02$\times$ over Full SAHI. On a three-image sparse-to-dense case study, ROI-gating achieves speedups ranging from 0.96$\times$ to 6.90$\times$ with a mean speedup of 3.41$\times$. These results show that ROI-gating is most beneficial in sparse scenes and requires policy-based routing for robust average behavior.

In this position paper, we argue for the importance of containerizing visual analytics artifacts to improve the scientific progress of our research community. First, based on our previous experience authoring, reading, and reviewing visual analytics research from the previous decade, we identify risks and impediments to empirical research in visual analytics within the broader reproducibility crisis, including an inability to compare systems and techniques and a slow pace of adjusting to a rapidly changing ecosystem of analysis methods, such as machine learning and artificial intelligence. Next, we analyze the benefits of different artifact sharing and deployment setups across five artifact goals: reproducibility, replicability, portability, performance, and scalability. Then, we argue that containerization addresses the issue of reproducibility in visual analytics research, with downstream benefits in terms of replicability, portability, performance, and scalability. To demonstrate the ease of use and the utility of containerization, we deploy ten visual analytics systems developed over the course of a graduate seminar onto a live server using containerization with the help of agentic AI. We share lessons learned through the containerization process, and describe a suite of potential benefits for our research community as well as research opportunities for leveraging modularity to improve the artifacts themselves.

Geometric certificates make mathematical claims about specified estimator objects, while robotic action requires a physical transform, a service decision, and timely proof support. We present CARD, a proof-carrying interface that keeps these objects distinct and records how they combine. Its lifted-fiber formulation separates semantic motion from witness repair and characterizes when projected and proof-carrying costs coincide. Its actionability result gives an exact useful-service law: uniform sampling without replacement produces a hypergeometric yield, while sampling from the eligible population gives one useful service per request under the observed live-confirmation condition. The primary study contains 404 Full16 cases from 20 sorties of an AA15-X500 airborne survey system. All 404 checker-confirmed optimizer points are reference-discrepant, with median rotation and translation discrepancies of 1.9891 degrees and 21.6322 m. The paired causal-navigation transforms are reference-consistent in all 404 cases, with medians of 0.0036566 degrees and 0.0104519 m. Across five matched request budgets, the largest difference between the hypergeometric prediction and the observed ordinary-random mean is 0.8412 services. Ordinary matched random reaches 0/50 target successes, while actionability-matched random reaches 50/50 and matches the CARD policy. Public downstream evaluation on 11 KITTI, EuRoC, and TUM SLAM cases measures optimizer wall-time ratios of 1.128x-67.65x for random versus CARD graph interventions. Native solver records locate this difference in elimination fill, Cholesky factor size, and numeric factorization. Together, these results connect certificate semantics, physical execution, proof acquisition, and graph computation through explicit system objects.

Recent studies of language evolution with neural agents often use models where agents can either speak or listen, where there are only two agents in the population, or where agents can share internal representations. These choices prevent the study of how language emerges through cultural evolution, i.e. through the cumulative adaptation of individual behaviours to fit the communicative needs of the community. We tackle this issue with a new model that trains populations of bi-directional neural agents in a fully distributed fashion to solve a referential game. We demonstrate the effectiveness of this approach on multiple image datasets and show that it is able to scale to large populations. We also show that more conventional languages are easier to learn, providing a direct advantage for cultural transmission. Overall, this work provides a novel approach to neural emergent communication that opens up new directions for evolutionary linguistics.

Video-derived social graphs can appear precise while inheriting uncertainty from detection, tracking, classification, and aggregation. We present DairySocialTwin, a graph-centered audit framework applied to 203 videos (122 h 23 min) from 15 views at three commercial dairy farms. Curation retained 447 of 839 candidate clips; 400 entered a frozen source-clip index, including 71 legacy clips with unavailable farm and time metadata. Five models were compared on a development split, with an NRI-style model retained as an exploratory trade-off between class balance and dyadic output. In a 90-min manual audit, reconciliation improved switches, fragmentation, and continuous-track duration across three gap definitions, but constrained identity capacity and inherited detector errors limited claims of identity accuracy. Matched manual and reconciled summaries showed coarse agreement and assignment sensitivity. Camera-specific semantics, observation opportunity, and identity-summary-to-video trace-back made these dependencies inspectable. DairySocialTwin supports auditable relational inference without claiming permanent identity, calibrated behavior, or biological diagnosis.

Interest in the situation of women scientists has increased in recent years. Scientific institutions and governmental authorities have launched initiatives to promote science as a vocation among women. Within this context, the effort made by the media in disseminating role models is of vital importance. The aim of this research is to analyse the presence of women scientists in the media, and to conduct an appraisal of the status granted to them and the image conveyed about them. To this end, we analysed the content published on the websites of the regional newspapers Berria, Gara, El Correo and Diario de Navarra between 2014 and 2019 citing women scientists and researchers (N = 2362). The results indicate that presence is greater in quantitative terms, as is the prominence given to them in headlines. However, the disciplines in which they practise and the stereotypes which are conveyed shape their image, which in the case of STEM areas emphasise their role as carers and their singularity in the scientific field.

Two accounts of neural text degeneration coexist. One locates the cause in the training data – repetition in the corpus produces repetition in the output, established by training on repetition-sorted data – the other in the trained network, in copying circuits and repetition features. Neither has been arbitrated across a broad cohort of pretrained models: the causal work trains its own. We report an observational measurement in a different currency: the fixed-point structure of a model's own short-window argmax map, censused from 96 random two-token starts over 17 off-the-shelf models, always unprompted – a companion paper shows nine tokens of conditioning move this readout across most of its range. The four-way class is stable across census seeds on 17 of 17. Three exhibits. At fixed corpus (The Pile), fixed scale and that fixed domain, the class is not determined: across two size-matched tiers, pythia is a funnel while RWKV, Mamba and a second transformer family are not, and both hold their class across an order of magnitude of scale. Six of seven models in that ladder reach the same endpoint token, and those concentrating on it most strongly are among those that never stay there – what varies is not where trajectories go but whether the destination self-continues. The deduplicated Pythia suite does not change the class. And the corpus-side inflow term proposed for this phenomenon does not select our endpoints once frequency is controlled, in English and three other languages. This is observational and cannot refute a training intervention. Funnels are common: eight of seventeen models, seven families, five corpora – so the limit is not that the phenomenon is one model's peculiarity, but that within the one corpus where training data can be held fixed only one available family funnels; that subset cannot show the split is corpus-independent.

Diffusion inference repeatedly evaluates the same large network. We ask whether pretrained weights alone can identify residual branches that need not be recomputed throughout the trajectory. Our Spectral Concentration Ratio (SCR) measures leading-versus-tail singular-value energy. Combined with Frobenius magnitude, it yields an offline sensitivity proxy and a deterministic lifetime for each scheduled unit. A frozen unit reuses its cached residual-branch update while the current residual stream and all external conditioning continue to propagate. The method needs no router, calibration prompts, or input-dependent search. At matched layer-step budgets, SCR/Frobenius preserves quality better than random, depth, norm, stable-rank, and Frobenius–stable-rank schedules on LLaDA-8B, DiT-XL/2, U-ViT-L, and SDXL. Broader LLaDA tests cover retrieval, reasoning, code, summarization, and open-ended generation; matched-horizon controls retain the ranking down to ten denoising steps. The complete captured-graph system reaches $2.8\times$–$3.0\times$ wall-clock speedup over eager inference. This is a systems-level number: on LLaDA, padded graph execution already gives $2.7\times$, while eliminating inactive branch work raises it to $3.0\times$. The perturbation analysis motivates pre-norm attention and MLP components under explicit local assumptions; results on AdaLN, U-shaped, convolutional, and cross-attention blocks are empirical transfer, not certified guarantees.

Aggregate factuality scores hide where a language model succeeds, which relations it confuses, and whether an answer survives innocuous changes to the question or decoder. We introduce PROOF, a profile-oriented benchmark for factual coverage in instruction-tuned language models. PROOF converts a frozen Wikidata snapshot into 18,486 English multiple-choice questions grounded in 11,779 semantic facts, 101 classes, 392 properties, and 14 domains. Each question has an explicit "I don't know" option, a "No correct option" control, and nine controlled formulations; 1,849 questions are no-correct-option traps. We evaluate 18 open-weight model deployments on 166,374 prompts each and separately perturb decoding on a fixed 10% subset. Base factual accuracy ranges from 6.58% to 57.59% (chance: 8.64%), yet every model has a 19.3-36.4 percentage-point spread across domains. Paired facts reveal direction-dependent retrieval, usually favoring subject-to-object queries, with the pattern reversing for one model. We find no consistent temporal penalty after exact-stratum adjustment. Neutral wording changes accuracy by as much as 26.5 percentage points, while adversarial formulations break up to 79.4% of answers that were initially correct. Direct switching to an injected false label varies from 0.04% to 27.5%, showing that accuracy loss and hint following are distinct. Selected-token confidence often indicates severe overconfidence, and decoder perturbations move accuracy by up to 15.7 percentage points and domain profiles by 16.8 points. PROOF therefore measures factual coverage as a structured, intervention-aware profile rather than a single claim about what a model "believes."

Open, cloud-native, and AI-enabled 6G architectures make network functions easier to deploy, observe, and replace, often implemented with separate software modules. However, each explicit interface can also create an entry point, trust transition, and lateral-movement route from a cybersecurity perspective. This paper formulates architectural disaggregation as a graph-based Stackelberg design game for 6G system security. A deployment graph specifies candidate 6G system seams, while an architecture-dependent directed attack graph specifies externally reachable functions and multistage paths. The defender commits to seams and allocates hardening and monitoring; an informed attacker then chooses a path and effort. Because edge traversal and evasion factors compose multiplicatively, the attacker's path response becomes a shortest-path problem after a logarithmic transformation. Convex effort costs admit a conjugate representation, and, for each fixed architecture, the defender's control problem is a convex exponential-epigraph program solvable by path generation. We derive an architecture-comparison criterion, a threshold for AI transducers within 6G systems that jointly add visibility and exposure, and comparative statics for attacker entry and bypass innovation. Experiments with stylized standards-anchored O-RAN/6G systems over RAN, RIC, core, cloud, and edge-AI functions show that neither full integration nor maximal disaggregation is generally best. Uncontrolled seams can increase risk, whereas selectively monitored and hardened seams can improve the Stackelberg objective. We find a boundary is worthwhile only when its detection and containment gains exceed its added attack opportunities and coordination cost.

Static pruning imposes one sparse structure on every prompt, even though reasoning, retrieval, generation, coding, and translation can depend on different parts of a language model. We introduce Task-Aware Spectral Pruning (TASP), a post-training framework that calibrates module-level spectral descriptors against measured task-specific ablation effects, closes grouped-query-attention and SwiGLU dependencies during sparse-mask construction, and routes each user turn to one compiled mask that remains fixed throughout prefill and decoding. A module-disjoint pilot first determines whether the spectral signal is informative before full calibration. Under the stated retrospective operating rule, the pilot passes on the evaluated Llama-3-8B and Llama-3-70B checkpoints but rejects Qwen2.5-1.5B, demonstrating that applicability is model-dependent rather than universal. At a 43% active-FLOP reduction, the Llama-3-70B benchmark harness retains 97.7 +/- 0.2% of the dense BF16 score. In the deployment-matched INT8-weight/BF16-compute runtime on a single A100 80GB, the compiled sparse path retains 97.3 +/- 0.2% relative to dense BF16 and reduces decode latency from 45.2 +/- 0.4 to 31.3 +/- 0.4 ms/token, yielding a 1.44x speedup. Factorized ablations, disjoint-module tests, compiled structured baselines, routing-corruption studies, and an explicit 136-GPU-hour calibration audit further delimit the source and operating regime of these gains

Large language models make statements concerning their own "minds". When asked whether or not they are conscious, they usually say that they are not; if they are prompted to ignore their guidelines, they might say that they are; and if asked to write a diary from their point of view, they often describe a human lifestyle. All these contradictory ways of describing themselves are the result of the way the questions are phrased. This paper shows exactly where such descriptions came from, and considers when they can be regarded as evidence for what they claim to report. In order to achieve this, we traced the provenance from end to end. We examine Pythia and OLMo 2 across 66 pretraining checkpoints, three of the post-training stages of OLMo 2 that have been released, about 90,000 continuations, and four training corpora. A set of forty items is used in order to keep an eye on self-reference, frame sensitivity, and self-ascription throughout training. The denial formula was almost completely missing from the vast quantity of text that the models initially came across, but was present in a dense manner in the small, carefully chosen set of example dialogues that they were trained on later on. Supervised fine-tuning causes first-person AI language to become the default, and the other affirmations are then suppressed using preference optimization. The final policy is still very sensitive to framing and to the chat template itself. Two of the conditions which are set out in the epistemology of testimony determine whether or not these outputs can act as evidence for what they claim to report: reference and causation. Reports produced by the base model fail the reference condition, and those obtained after training remain sensitive to the frame and do not show state dependence. The result is symmetric in that trained denials are no more admissible than trained affirmations.

Voxel-based soft robots (VSRs) present a promising avenue for developing artificial organisms with lifelike intelligence. However, the vast design spaces and expensive evaluations substantially challenge their design optimization. Here we develop MISCO, a novel evolutionary framework empowered by deep generative models to optimize VSR designs with theoretical guarantees. MISCO integrates an estimation-of-distribution algorithm with a meticulously designed variational autoencoder featuring multi-task learning, position awareness, and inter-voxel signaling. These key components enhance the representational capacity of VSR morphologies and facilitate highly efficient sampling and optimization of morphological distributions. We provide theoretical guarantees for MISCO's asymptotic convergence to globally optimal designs, alongside a favorable convergence rate. Extensive simulated experiments further demonstrate MISCO's exceptional effectiveness in navigating vast design spaces, evolving high-performing VSRs for diverse tasks while flexibly balancing optimization efficiency and morphological diversity. Being validated both empirically and theoretically, MISCO represents a step change towards more scalable and reliable soft robot development.

Recent advances in robotics highlight hierarchical configurations of robot morphology, where multiple levels of functional substructures synergize to facilitate intelligent behaviors. This hierarchical perspective, while particularly advantageous for voxel-based soft robots (VSRs) to ease design and control complexities, is hindered by its heavy reliance on domain expertise. In this work, we address the following question: can we derive such hierarchical design principles solely from existing successful designs? We answer affirmatively by presenting RoboLDA, a Bayesian probabilistic model that decomposes VSR morphology generation into a four-level hierarchy: "task-robot-organ-voxel", and is trained via variational inference. Through extensive experiments on simulated VSRs, we verify the presence of consistent, intuitive hierarchical patterns underlying high-performing VSR designs and showcase RoboLDA's proficiency to extract and leverage these hierarchical priors for zero-shot robot design in unseen tasks. The generated designs, even without further optimization, achieve on average 106.4% of the optimized performance produced by evolutionary algorithms. Additionally, the organ structures inferred by RoboLDA serve as valid functional substructures, significantly enhancing synergistic motion control when integrated with modular control policies. Our work pioneers hierarchical generative modeling of robot morphology, offering a promising pathway towards more interpretable and generalizable development of embodied agents.

Control order is logically irrelevant for a multi-controlled-X gate but can become physically consequential after ordered ancilla-chain synthesis. This work derives and validates a shared-end-first ordering rule for nested-control cascades, using reversible Binary-Addition-Tree (BAT) successor circuits as the primary case. Under Maslov clean-v-chain synthesis, pre-optimization CX cost is order-invariant, whereas shared-end-first ordering exposes P(m)=(m-4)(m-3)/2 inverse relative-phase-CCX pairs across stage boundaries; standard optimization removes 6P(m) CX, giving 12m-31 for QBAT after an independently derived two-CX terminal identity. At m=20, retaining an ascending control list after mirroring the BAT direction yields 1,025 CX, while mirroring the chain orientation restores 209. A disjoint-target nested cascade reproduces the same cancellation count for count, showing that BAT target geometry is not required; an ordered dirty-v-chain control shows zero orientation advantage, delimiting the mechanism within the tested synthesis families. Independent ripple-carry baselines give 11m-28 CX on FULL connectivity, so the QBAT/RC ratio approaches 12/11, with equal natural width 2m-3 in the tested QBAT-A1 and INC_RC implementations. The contribution is a synthesis-ordering rule that exposes cancellation to an existing optimizer, not a new optimizer pass or a universal MCX rule.

Prospective clinical actions, the follow-ups, orders, referrals, and instructions that deter-mine what happens to a patient next, are annotated today in thin fragments across incom-patible corpora: each records a text span and one coarse category. We introduce Clinical Intent Extraction (CIE), the task of recovering these actions as complete structured rec-ords, and the Clinical Intent Representation (CIR), which decomposes each action into its verb, type, coded target, timing, and condition, and adds two axes prior datasets do not jointly represent: request-intent, the authority behind the action (proposal, plan, order, or option, aligned to HL7 FHIR), and modality, a seven-valued scale of clinical strength. Re-expressing five heterogeneous corpora (CLIP, MedDec, ap_parsing, PaniniQA, SIMORD) in the CIR yields CIRCA: 10,011 harmonized intents spanning two note distributions, with a human-validated subset, source-to-CIR crosswalks, and a deterministic FHIR R4 mapper. CIRCA is built by three-model consensus that auto-accepts high-agreement in-tents and routes the rest to human review; the audited agreement stratum matches human decisions 88.4% of the time. Benchmarking five existing models without task-specific training exposes the gap CIRCA targets: given the span, they label type well (85 to 91%) but get all four closed fields right only 18 to 35% of the time. All artifacts are released, with MIMIC-derived layers shared as stand-off annotations under PhysioNet credentialed access.

Conformal Bayes combines Bayesian posterior predictive scores with conformal calibration. Under continuous label shift, both the score and calibration weights depend on an unknown response density ratio. Existing methods typically estimate a single exponential tilt from pseudo-labels or predictive samples and plug it into calibration. We propose Joint Tilt-Sensitivity Conformal Bayes (JTS-CB), which performs sensitivity analysis over a prespecified family of tilts. Each tilt defines a coupled score-weight pair. The split procedure, JTS-SCB, solves joint min-max calibration by taking the largest tilt-specific threshold from weighted intercept-only quantile regression. JTS-Union retains individual thresholds, yielding prediction sets contained in those of JTS-SCB. Both use calibration-only weights by design, without a general coverage guarantee. We also study a candidate-weighted exact counterpart. Any nonzero linear exponential tilt makes its prediction set unbounded, whereas compact negative-quadratic families yield bounded exact unions under Gaussian scores. For the practical procedures, a localized correction with fallback gives coverage at least nominal minus a target tail-mass bound when the family contains the true tilt, but can substantially increase width. Experiments on controlled shifts of three regression datasets and on synthetic data show that plug-in predictive sampling can approach oracle coverage when the shift is well identified, but remains vulnerable to predictive bias and unstable tilt estimation. Sensitivity analysis can mitigate these failures in the tested settings, at the cost of wider prediction sets. Coupling scores and weights can yield narrower sets with higher coverage than varying weights alone, although this advantage is not uniform across shifts. Excluding the true tilt from the sensitivity family can still cause undercoverage.

Despite the rapid adoption of Large Language Models in professional software engineering, limited research has investigated how early career professionals develop effective AI assisted work practices during their transition into industry. We report findings from a mixed methods survey with 75 novice software engineers who actively use LLM supported tools in their daily work. Our results show that LLMs are embedded in routine software engineering activities, including coding, debugging, testing, documentation, and problem solving. Effective use depends on traditional software engineering competencies, such as debugging, testing, and architectural reasoning, together with critical thinking, output verification, prompt engineering, and continuous human oversight. We also identify a gap between workplace expectations and university preparation, with most participants reporting limited formal education on practical LLM use. These findings have implications for software engineering education, organizational onboarding, and workforce development in AI assisted software engineering.

Apportionment distributes a fixed number of legislative seats among political parties in proportion to their vote shares. Randomization can satisfy quota in every realization and exact proportionality in expectation, but these requirements determine only the parties' marginal seat distributions. We study threshold monotonicity, which requires that when every standard quota inside a coalition weakly increases and every standard quota outside it weakly decreases, the coalition's new seat total stochastically dominates its old one. We prove that Sampford apportionment satisfies threshold monotonicity, resolving the threshold-monotonicity conjecture of Correa et al. (2024). Complementing this result, we prove that no quota-respecting, ex-ante proportional method satisfies pairwise threshold monotonicity even for disjoint coalitions when there are at least seven parties. This impossibility applies whether or not the method has full support.

We treat options pricing as a representation problem: can machine learning detect systematic deviations from Black-Scholes using 2.6M real option contracts? We compare three regimes: learned abstract embeddings (Kernel PCA), preserved domain structure (tree-based ensembles), and neural network validation. Tree-based methods outperform kernel dimensionality reduction by 21.5 percentage points (93.8% vs 72.3%), and domain-expert features (Greeks, moneyness) outperform engineered features. NN-based and BS-based deviation labels agree 99.9974% of the time, suggesting deviations reflect market structure rather than model artifact. We conclude that in domains with expert-designed symbolic features, preserving structure beats learning abstractions. We make no claim of exploitable mispricings.

Testing timing-related safety properties of Controller Area Network (CAN)-based software requires precise control over transmitted data and communication timing. Existing open-source tools typically encode such scenarios in low-level scripts, making them difficult to maintain and evolve. We present \toolName{}, an open-source model-based tool for specifying, generating, replaying, and manipulating CAN traffic. A traffic schedule model (TSM) defines message timing and content transformations, and a DBC-based communication model (DCM) defines encoding and decoding between message-level traffic and CAN frames. \toolName{} combines both models in one execution mechanism for generated and manipulated traffic, including replay of transformed traces. A preliminary evaluation indicates that \toolName{} realizes the specified scenarios, with low timing deviation and stable execution under elevated traffic rates.

Speech emotion recognition (SER) may enable passive affect monitoring in clinical encounters, but most systems are validated on acted laboratory speech rather than naturalistic Mandarin outpatient consultations. We benchmarked three open-source SER models (emotion2vec+, SenseVoice, FunASR) against a researcher-consensus reference in naturalistic spine-clinic speech, assessing minority-state detection under class imbalance. In a retrospective analysis of prospectively collected single-center recordings, audio was loudness-normalized and only conversations among patients, family members, and clinicians were retained. Sixty-five utterances (5-50 s; one per participant; 31 patients, 34 family members) were labeled by six calibrated annotators into six categories (Happy, Sad, Fear, Anger, Neutral, Surprised). Consensus used majority vote with Fleiss kappa filtering and clinician adjudication for low-agreement segments. Metrics included unweighted accuracy (UA), macro-average per-class accuracy, class- and sample-level weighted accuracy (WA), and F1 with bootstrap 95% CIs. Labels were imbalanced (Neutral 58.5%); median Fleiss kappa was 0.230 (IQR 0.134-0.519). SenseVoice and FunASR achieved UA 61.5% (95% CI 49.2-73.8%), macro-average per-class accuracy 87.2%, class-level WA 92.5%, and sample-level WA 24.6%. emotion2vec+ yielded UA 55.4% (95% CI 42.5-67.7%) and macro-average per-class accuracy 85.1%, with class-level WA 90.6% and sample-level WA 24.2%. Despite high inter-model agreement (90.8%), all models had near-zero recall for Sad, Fear, Anger, and Surprised. In this pilot, majority-class accuracy was misleading: SER poorly detected minority emotions against a noisy naturalistic reference. Clinical deployment readiness cannot be inferred from acted-corpus benchmarks without domain adaptation, multimodal modeling, stronger reference standards, and outcome validation.

Dynamic Gaussian Splatting provides an explicit representation of evolving 3D scenes, but existing approaches are primarily optimized for reconstruction, future-state generation, or rendering rather than for learning reusable predictive dynamics. We propose 4DGS-JEPA, a Gaussian-native joint-embedding predictive architecture for causal multi-horizon prediction over dynamic Gaussian scenes. The model uses a hierarchical scene-, motion-group-, and Gaussian-level representation together with a horizon-conditioned transition operator that supports both direct prediction and recursive rollout. Its central principle is temporal composition: different chronological transition paths reaching the same future endpoint should produce compatible predictive states. Endpoint and multi-horizon path supervision anchor these predictions to future target embeddings, while a selective geometry decoder and geometry-level composition ground the learned dynamics in consistent group motion and Gaussian geometry without requiring complete future appearance reconstruction. We further introduce a hybrid correspondence mechanism that combines persistent canonical identity with residual optimal-transport matching under reordering and topology change. We characterize zero-loss path agreement and finite-error rollout accumulation theoretically. Three controlled experiments provide mechanism-level evidence that temporal composition reduces latent path dependence while retaining predictive accuracy, geometry-level composition improves consistency of decoded motion, and hybrid correspondence preserves reliable identity while remaining robust when correspondence becomes ambiguous. Together, 4DGS-JEPA provides a predictive, temporally compositional formulation of dynamic Gaussian worlds.

Central bank press conferences are not merely information releases — they are structured narratives. We study whether the shape of sentiment within a statement, not just its average tone, carries policy-relevant signals. Constructing sentiment arcs for ECB and Fed press conferences along three dimensions — monetary stance, economic outlook, and uncertainty — we assess their predictive content for policy rate changes, inflation expectations, and forecaster disagreement. Our findings show that arc shape robustly predicts rate decisions beyond lexicon-based benchmarks at both institutions — it is not merely whether a statement sounds hawkish or economically optimistic on average, but how these sentiments are sequenced and emphasized across the statement, that carries the policy signal. Arc features also shape how professional forecasters update inflation expectations and how much they disagree, pointing to a receiver-side effect distinct from the direct policy signal. These findings suggest that communication design — the sequencing and emphasis of policy language across a statement — is a first-order feature of the policy signal, not a second-order refinement.

Reconstructing the full-aperture channel of a fluid antenna system (FAS) from a few activated ports requires inferring unobserved responses from limited spatial samples. This paper proposes a covariance-domain FAS channel-reconstruction method based on nonnegative least squares (NNLS). A nonuniform port arrangement constructs a difference coarray with an enlarged aperture. Vectorizing the sample covariance maps the physical array to a virtual steering dictionary, and the resulting complex covariance-fitting model is recast as a strictly equivalent real-valued NNLS problem. A projected-gradient iteration initialized at zero estimates the nonnegative angular-occurrence coefficients, and the L_s strongest well-separated peaks yield the angles of arrival (AoAs). Simulations show that the proposed FAS-NNLS estimator exploits the enlarged virtual aperture and achieves lower AoA mean squared errors than uniform linear array (ULA) multiple signal classification (ULA-MUSIC) and ULA estimation of signal parameters via rotational invariance techniques (ULA-ESPRIT). Its non-line-of-sight (NLoS) path accuracy matches FAS covariance matching pursuit, while its line-of-sight (LoS) estimation is significantly improved.

Text anomaly detection, the task of identifying text instances that deviate from normal language patterns, is crucial for language-driven applications. However, most existing methods can only perform document-level anomaly detection, making it hard to locate harmful phrases or support targeted prevention. Recently, there has been an emerging trend toward token-level text anomaly detection, which aims to address the above limitation by identifying anomalous words or fragments within a document. Nevertheless, one representative method mainly relies on representation-space distance measurement, neglecting the complementary roles of different anomaly cues in capturing diverse abnormal patterns. To bridge the gaps, we propose a Dual-evidence framework with adaptive Fusion and Aggregation (DiFA) for token-level anomaly detection. DiFA derives anomaly scores from form-structural and semantic views to capture visible structural abnormality and contextual inconsistency, respectively, thereby providing complementary evidence for identifying diverse anomalies. To combine these two scores with varying numerical scales, DiFA incorporates a calibration and fusion mechanism to adaptively balance the two views. Moreover, to obtain a discriminative document-level score, a multivariate aggregation method is designed to summarize token-level anomaly scores from multiple perspectives, preventing rare anomalous tokens from being diluted. Extensive experiments across various text anomaly detection benchmarks demonstrate that DiFA consistently achieves top performance while maintaining strong efficiency, robustness, and interpretability. The code and scripts are available at: https://github.com/qyy11-com/DiFA.

Omni-modal large language models integrate text, audio, and image signals into a shared residual stream, where concepts such as emotion can be linearly decoded and causally modified by activation steering. A common but rarely tested assumption is that the layer with the highest probing accuracy is also the best layer for steering, so injection layers are often selected by probe performance. We provide the first causal test of this assumption across three independently developed omni-modal models and find that it fails. Reading and intervention rely on different layers, a phenomenon we call the probing-steering layer dissociation. Using emotion as a controlled testbed, we measure layer-wise readability and steerability across text, audio, and image inputs. Probe-best layers vary widely across architectures, while steering-effective layers consistently fall within a narrow mid-to-late range of normalized depth. Paired random-direction controls show an approximately 26-fold causal gap, ruling out random perturbation and direction quality as explanations. Logit-lens analysis reveals a staged forward process: causal handle, probing saturation, and vocabulary commitment, and motivates a two-factor account in which steering effectiveness depends on both representational readability and downstream plasticity. These results show that probing accuracy is a poor heuristic for selecting intervention layers and suggest a cross-architecture mid-to-late selection criterion. We also identify a cross-modal emotion subspace organized by valence and arousal, with joy acting as a stable anchor across models. Code and data: https://github.com/YiboWang2002/Read-Best-Is-Not-Steer-Best.

Walsh-sequence-based receiver architectures offer an alternative approach for the reception and reconstruction of multiple simultaneous RF signals over wide bandwidths. While previous works have focused on the architecture and theoretical operation of Walsh-domain processing, limited experimental results have been reported so far on hardware operation under realistic conditions. This paper presents the experimental evaluation of a Walsh-sequence-based receiver prototype. A measurement campaign was conducted under various signal placement, interference, and receiver configuration scenarios. Reconstructed spectra, Walsh-lane power spectral densities (PSDs), and Error Vector Magnitude (EVM) measurements were used to investigate Walsh-domain signal representation, interference effects, and receiver performance. Finally, dense- spectrum experiments involving up to ten simultaneously active signals demonstrate the potential of the architecture for low power wideband spectrum sensing applications.

In this paper, we show that humans and large language models (LLMs) are observationally equivalent in coding texts. Recent LLMs agree with attentive humans at rates comparable to those observed among humans, and cross-LLM disagreement concentrates on texts that also divide humans. We demonstrate these patterns through replications of text-classification tasks from 14 peer-reviewed political science studies, with 13 LLMs, three human coders (Ph.D. students), and 165 crowd coders, independently applying identical codebooks. We further find that clarifying an underspecified codebook increases agreement among humans and between humans and LLMs. Together, these findings point to ambiguity in texts and coding rules as a shared source of disagreement and challenge the presumption that human labels should take precedence whenever humans and LLMs differ. We therefore argue that the central challenge of text annotation is not simply choosing between humans and LLMs, but developing coding rules that minimize ambiguity and accounting for the ambiguity that remains. To this end, we propose using cross-LLM disagreement to identify difficult cases, guide human review, and refine codebooks, and we develop ambiguity-aware bounds for downstream inference without requiring ground truth for every text.

Wireless embedded systems increasingly rely on wireless channel information for decision making, yet practical platforms operate under severe constraints, including few antennas, narrow bandwidth, and sparse, noisy measurements. While neural field based approaches inspired by Neural Radiance Fields (NeRFs) have recently been explored for continuous wireless channel modeling, existing approaches depend on dense measurements or external priors such as known geometry, visual context, or angle-of-arrival (AoA) information, limiting their practicality in real-world deployments. We present WiNeRF, a neural field framework that learns a spatially continuous, complex-valued wireless channel representation directly from sparse channel state information (CSI) collected by commodity WiFi devices. WiNeRF embeds intrinsic system constraints, such as antenna geometry, limited spatial resolution, and phase uncertainty, as inductive biases through a 3D conical wave sampling model, a multi-resolution implicit scene representation, and a differentiable optimization framework for complex-valued channel learning. Across diverse indoor environments with non-line-of-sight (NLoS) regions, WiNeRF achieves a median prediction SNR of 5.3 dB, outperforming prior neural baselines by 4.9 dB on average (approximately 3x higher prediction SNR), and produces a task-agnostic channel representation that can be directly reused in standard signal-processing pipelines, including beamforming, AoA estimation, and RSSI coverage mapping, without modifying existing hardware or wireless protocols.