Papers

Systematic trading rests on one article of faith: that regularities found in the past persist. This paper does three things. First, it states that faith as five axioms, each a commonplace practitioners already accept: (A1) a decision may use only what was known when it was made; (A2) what looks like the market changing its rules is the market changing its unobserved state, the machinery being the same in every era; (A3) the future may replay stretches of the past, though not in history's proportions; (A4) states persist for a while; (A5) whatever predictability exists is slight, even for a rule that knows the state. What turns these into axioms is quantification, and the quantities are declared rather than estimated: an invariance defect $\varepsilon_0$, a recurrence bound $\Lambda$ at a block scale $b$ (one declaration in two parts), coherence times $\ell_i$, a signal ceiling $\rho$ and an invariance ratio $\kappa$. These five declarations are the whole of the premises' empirical content. Second, it proves that the axioms force a five-stage canonical form for a quantitative investment system – a declared representation, a predictor within a capacity ceiling, contiguous purged block evaluation aggregated by $\mathrm{CVaR}_{1/\Lambda}$, a budgeted and deflated search, robust sizing at a fraction of the estimate that the budget bounds – each stage necessary: a procedure omitting it does strictly worse under a law the axioms admit. Third, it tests the axioms where they are falsifiable, each only at its declared constants, on real market series: no axiom is so far overturned.

Cyber-physical systems (CPSs) consist of sensors, controllers, and actuators through communication and physical interactions, making them vulnerable to attacks on measurements, control logic, and equipment operation. Graph-based attack detectors, especially graph attention models, can localize such attacks by learning edge-adaptive interactions over communication and physical interaction graphs. However, their computational cost grows rapidly with neighborhood size, and their inference latency can reach tens to hundreds of milliseconds in large-scale or densely connected graphs, delaying time-critical alarm generation. To enable real-time deployment of graph attention mechanisms for attack detection, we propose GraphGHHA, a graph-native attention acceleration layer designed as a replacement for graph attention layers in attack detection units. GraphGHHA combines (i) a graph-local sparse attention branch that is constrained by the adjacency matrix of the CPS, and (ii) a global linear mixing branch to retain system-wide information. A learnable gate combines the two branches node-wise, preserving detection accuracy under strict latency constraints. We evaluate GraphGHHA on a networked heating, ventilation, and air conditioning (HVAC) cyber-physical system under representative attack scenarios and demonstrate up to an eight-fold reduction in detection latency while maintaining high detection accuracy. These results indicate that GraphGHHA enables practical, real-time alarm generation for large-scale CPS monitoring.

This paper develops a direct data-driven framework for robust positively invariant (RPI) set synthesis for unknown linear time-invariant systems under state-feedback and observer-based output-feedback scenarios. The feedback and observer gains, along with the RPI sets, are directly synthesized from noisy offline data by solving semidefinite programs (SDPs), avoiding intermediate model identification or explicit model-uncertainty set construction. In the state-feedback case, a linear-quadratic (LQ)-type feedback gain is first computed, and an ellipsoidal RPI set is then synthesized for the resulting closed-loop dynamics. In the observer-based output-feedback case, offline data are used to compute the observer gain and the corresponding RPI set for the system state through an augmented-state formulation. This design provides a unified method for invariant-set computation in both scenarios, and the direct data-driven formulation avoids the explicit construction and propagation of an intermediate model-uncertainty set. Numerical examples illustrate the effectiveness of the proposed method.

LLM value studies often merge questionnaire ratings, pairwise choices, and values inferred from generated text into one profile. That merge assumes that the three observations describe the same stable preference. STONIC tests this assumption on 5,144 situations from four banks and 35 fixed model configurations. It compares responses rated in isolation, choices made under counterbalanced conflict, spontaneous answers, and later choices between a model's own answer and authored alternatives. 10 of 17 configurations with usable behavioral data preserve the endorsement-choice relation across banks. Every one of the 17 eligible configurations prefers its own earlier answer (median effect 0.790), although option position changes the choice rate in every eligible configuration. Profile shape transfers most strongly from ratings to conflict choices and weakens for spontaneous text. Three-way annotation of 200 L3 responses provides a task-local check of the semantic audit: FULCRA agrees most closely with the human majority, while DeBERTa retains useful rank information after calibration. Hidden states encode the completed decision more clearly than the prompt alone. Thus the models show reproducible behavioral continuity, but the evidence does not support one scorer-independent value identity across interfaces.

Photorealistic novel view synthesis of people remains challenging at high spatial resolutions and across multiple target cameras, where preserving identity, fine appearance details, and geometric coherence is critical. We build on the next-scale autoregressive paradigm and adapt it for human-centric view synthesis by enabling higher image resolutions, multi-view outputs and stronger cross-view consistency in a single forward pass. We train on a synthetic dataset of human faces spanning diverse identities and apparel. Contrary to diffusion models, this paradigm does not need 2D pre-training and, thanks to its next-scale architecture, it benefits from lower-resolution, general-purpose pre-trainings, with the full-sized purpose-specific images being used only in the last training stages. This enables our architecture to converge with a smaller amount of purpose-specific training data, allowing us to use a smaller but more realistic training dataset. The resulting model produces sharp and realistic views, with the option to synthesize multiple novel viewpoints simultaneously for improved agreement across views. Empirically, we observe gains in perceptual fidelity and cross-view coherence on human subjects, demonstrating that next-scale autoregression is an effective backbone for scalable, multi-output human view synthesis. We also couple our pipeline with an existing transformer-based model for pixel-aligned 3D gaussian lifting from multi-view facial inputs, resulting in accurate and photorealistic 3D models of human faces.

AI and Industry 4.0 readiness assessments often summarise preparedness using a single score for an organisation, application domain or sector. Those summaries can conceal disagreement about the same technology and variation among applications grouped under one sector label. We test how much information is lost through this aggregation using a card-based survey in which 982 respondents provided 15,200 readiness evaluations across 17 named AI and robotics challenges. Readiness is perceived community preparedness and available resources, not personal willingness or audited organisational capability. Respondents frequently disagreed about identical challenges, with card-level readiness standard deviations of $1.03$-$1.26$ on a five-point scale. A crossed decomposition attributes 32.7% of observed variation to stable respondent differences, 7.3% to differences among challenges, and 60.0% to response-level variation that also contains measurement error. Differences among challenge-family means account for only about 2% of variation, with substantially more variation among people, applications and person-family judgements. Manufacturing has the highest mean readiness, yet shop-floor robotics, process-optimisation AI and general decision-support applications are judged differently. Computer-science and AI/ML respondents report higher readiness than non-technical respondents across challenge families, whereas engineering respondents do not report higher Manufacturing readiness. Sector rankings are therefore best used as portfolio summaries rather than evidence that an industry is uniformly ready or behind. Readiness reporting should retain application-level disagreement, disclose whose judgements form the average, and consider ethics, cyber security, literacy and capability needs without collapsing them into a single score.

Long-horizon planning is critical for safe autonomous driving in complex scenarios. Existing methods improve planning continuity with temporal memory, but such memory may become invalid and mislead decisions when the driving command changes. Thus, selectively leveraging useful history while suppressing command-inconsistent memory remains a key challenge. To address this issue, we propose MomADv2, a reliable state-space memory framework for long-horizon end-to-end autonomous driving. At its core, MomADv2 introduces a Selective State-Space Planning Memory Query Module, which filters historical planning queries based on temporal continuity and command consistency, selects planning modes relevant to the current command, and models the evolution of planning intentions through a selective state-space mechanism. To further alleviate local trajectory deviations and error accumulation in long-horizon planning, we design a Flow-Matching Trajectory Residual Refiner. It learns a continuous residual correction field from the refined planning output to the expert trajectory, enabling fine-grained trajectory refinement while preserving the stability of anchor-based planning. Extensive experiments on closed-loop NAVSIM and Bench2Drive, as well as open-loop nuScenes, demonstrate that MomADv2 improves long-horizon planning consistency and reduces the average collision rate by 15.6% over MomAD under 6-second planning.

Processing-in-Memory (PIM) promises to reduce data movement overhead by executing computation in or near memory, but its realized application speedup remains highly design-dependent. Non-offloadable host execution, host-PIM transfers, limited PIM capacity, and device programming latency can limit end-to-end speedup, making fast early-stage design-space exploration (DSE) essential. However, existing PIM evaluation methods remain limited: circuit- and device-level tools cannot capture these end-to-end PIM performance factors, while cycle-accurate simulation is too slow for iterative DSE. To address this gap, we present VIPER, a unified, lightweight, and architecture-aware performance evaluation framework for PIM DSE. VIPER profiles host execution once and combines the measured host behavior with a PIM-aware analytical engine that sweeps PIM-side parameters across candidate designs. It supports both Processing Near Memory (PNM) and Processing Using Memory (PUM) under task-offloading and data-triggered execution by capturing host-PIM transfer, array access, in-memory computation, device programming latency, and capacity-induced partitioning, providing rapid architecture-aware performance estimates for iterative DSE without repeated cycle-accurate simulation. We validate VIPER against a commercial UPMEM system and more than 400 cycle-accurate gem5 configurations. VIPER predicts the UPMEM offloading decision and break-even region a priori, and, with a refined transfer model, captures the measured peak-and-rolloff behavior with 12% mean speedup error across the DPU sweep (6% up to the 256-DPU peak). Against gem5, VIPER achieves less than 10% error while reducing evaluation time from hours to under one minute. Case studies of UPMEM, ReRAM/FeFET crossbars, and IMCRYPTO show that architecture-aware DSE reveals key performance trade-offs that device-level evaluation misses.

Query planners are typically expected to produce optimized plans quickly, leading many researchers (including the authors of this paper) and practitioners to design systems that assume query planning is a low-cost operation. Using a lightweight agentic search, we show that this assumption does not always hold. Across seven DBMSes, including four commercial systems, we find at least one query per system that takes more than three minutes to plan. In addition to being slow to plan, such queries risk tying up database resources without performing useful work, creating a potential denial-of-service vector. We analyze the queries our search uncovers and compare how the seven systems respond to each pattern. We find that although the queries triggering slow planning are largely DBMS-specific, recurring pathologies involving correlated subqueries, CTE expansion, repeated subquery expressions, disjunctive joins, and constant folding affect multiple systems. We release our uncovered queries along with a curated suite of parameterized query pathologies that researchers and database engineers can use to test planner robustness. Overall, our results show that query planning cannot always be treated as a predictably inexpensive operation and that its latency and robustness deserve further attention from both database researchers and engineers.

Discrete Diffusion Models (DDMs) have recently been introduced to recommendation systems, modeling user history as a token generation process via iterative denoising. However, while effective at capturing user-level sequential patterns, these methods often fail to explicitly integrate item-based collaborative filtering information, a critical component for accurate recommendation. This deficiency manifests in two key aspects: (1) the item representation is often semantic-focused, lacking collaborative priors for diffusion training; and (2) the denoising process employs a uniform noise schedule, treating all tokens indiscriminately and ignoring item-level adaptive structural dependencies. To bridge this gap, we propose ANR-DiffRec, a unified framework designed to encode item-based collaborative structures into discrete diffusion for generative recommendation. First, we explicitly incorporate an item co-occurrence matrix to guide semantic ID generation, providing a structured collaborative prior for discrete diffusion training. Second, we introduce an item-based adaptive noise rescheduling mechanism that dynamically adjusts denoising weights according to both local contextual recoverability and behavior-aware item dependencies. Specifically, the proposed strategy jointly models intra-item structural context and inter-item collaborative signals, enabling structure-aware denoising during diffusion training. Extensive experiments on multiple benchmarks demonstrate that our method consistently outperforms state-of-the-art generative recommendation models. Code: https://github.com/CalmaQi/ANR-DiffRec.

Interactive clinical agents operate under partial observability, so reliable care depends on reaching the correct diagnosis through evidence-grounded, safe interactions. Yet existing agents struggle to convert experience into reusable process knowledge with explicit provenance and authority. To address this gap, we introduce MediSkill-Evo, which self-evolves governed process knowledge without fine-tuning the backbone. It realizes this self-evolution by updating clinical, process, symbolic, and visual knowledge in four typed banks under type-specific validation and scope rules. The Process-Constrained Preference Harness then turns validated knowledge into action by grounding candidates in evidence and prioritizing safer decisions. We evaluate on 300 MIMIC-IV-derived FullChain encounters, 180 hard-isolation conditions covering six process obligations, and 100 multimodal NEJM image-diagnosis cases. On Qwen FullChain, MediSkill-Evo improves diagnosis accuracy by 7.81% and treatment-intent coverage by 70.67% over the best-performing prior agent, while reducing critical failures by 43.04%. Under stress, it improves the stress-process composite by 7.77% and required-action completion by 12.41% over the best-performing agent for each metric, with stronger patient-fact, temporal-evidence, and triage-red-flag recovery and no controller-scored errors in unavailable-evidence, treatment, and triage safety checks. On multimodal NEJM diagnosis, MediSkill-Evo with optional MedSAM localization improves diagnosis accuracy by 2.56% and core score by 18.96% over the best-performing memory agent. Code is available at https://anonymous.4open.science/r/mediskill-evo_anonymous-68E7.

Homomorphic-encryption blockchain frameworks for IoT sensor aggregation generally rely on classical cryptographic hardness assumptions and seldom account for network topology in liveness and performance analysis. This work introduces Phi-PHE-BC, a topology-aware homomorphic blockchain architecture for secure and privacy-preserving IoT sensor data aggregation. The framework combines threshold Paillier decryption with graph-parameterized security and performance analysis, linking protocol behavior to the validator graph. On-chain Paillier ciphertexts support homomorphic aggregation while providing IND-CPA confidentiality under the Decisional Composite Residuosity assumption, and authentication signatures provide EUF-CMA transaction integrity. Threshold partial-decryption shares are protected by a noise-flooding wrapper that provides information-theoretic privacy under the configured statistical-hiding condition. Under partial synchrony and Byzantine fault-tolerance assumptions, liveness requires validator connectivity kappa(Gv) >= f+1. We derive topology-dependent throughput bounds for tree, star, mesh, and scale-free networks, together with a per-block communication-cost model. A game-theoretic analysis shows that honest validator participation is a dominant strategy under the stated utility model, yielding an all-honest Nash equilibrium. Experiments on Hyperledger Fabric 2.5 show lower end-to-end latency than the selected traditional PHE-blockchain baseline while maintaining controllable threshold-decryption overhead. Results across topology scaling, validator sensitivity, threshold decryption, and Byzantine-load experiments indicate that Phi-PHE-BC is a practical architecture for secure, privacy-preserving, and topology-aware IoT sensor aggregation.

Recent LLM-agent systems make conflicting design bets: decompose work across many narrow agents, or use one strong tool-using agent. This pilot studies that choice on bounded cross-border VAT determination with reverse charge, where every case has an oracle label and each intermediate decision is independently scoreable. We hold the activity surface fixed (subtasks, tools, I/O schemas, validation checks, orchestrator, base model, and merge policy) and vary only the assignment of subtasks to workers across four orchestrated configurations, from one wide worker to five narrow ones, against S0, a tuned no-orchestrator single agent, with a deterministic rule engine as oracle. The program spans 4,400 runs: a 40-case, five-repeat main sweep, matched-token arms separating prompt-budget from agent-count effects, and three failure-injection arms, all judged against pre-registered falsification criteria. The two intermediate configurations lead on accuracy (0.830, against endpoints at 0.720 and 0.770) but miss the pre-stated bar against the fine endpoint, so the intermediate-optimum hypothesis remains unsupported at pilot scale. The single agent does not Pareto-dominate the orchestrated set. The matched-token criterion fires: the budget-matched single agent lands 6.5 points below the leader, but the interval includes zero, so any advantage is consistent with a prompt-budget explanation. Under injection, availability faults are absorbed at every granularity, with wide-scope restart over-recovering its baseline by +0.160, while one schema-conforming hallucinated record degrades every configuration and inverts the ordering, hitting fragmented configurations hardest. The contribution is a bounded, preregistered pilot heuristic for right-sizing decomposition (place one partition boundary at the dependency-layer midpoint), released with oracle, dataset, harness, raw traces, and analysis pipeline.

KellyBoost is a single multi-output XGBoost model whose softmax output is the portfolio: with y the vector of per-asset holding-period returns, the training loss is - log(1 + w y), the negative log growth rate, so the fitted model is the growth-optimal (Kelly) allocation conditioned on the features. The objective is exact rather than a surrogate: we derive the gradient, the analytic diagonal Hessian and the full Hessian in closed form, verify them by finite differences, and ship a dependency-free reference engine.

User representation learning in real-world industrial scenarios is commonly scaled by increasing user amount, behavioral sequence length and model size. However, existing methods face two challenges: (i) Bottleneck for raw data scaling at billion-scale capacity, as performance exhibit diminishing performance gains with larger-scale raw text user behavioral input, which can be mitigated by tokenization. (ii) Lack of quantitative analysis of how tokenization configurations should scale with data size. In this report, we propose User Behavioral Densing Law for characterizing the quantitative relationship between data scale and the minimum sufficient tokenization capacity. Firstly, we conduct a pilot study on raw & tokenized scaling comparison on billion-scale Alipay dataset, revealing the raw data scaling bottleneck and the sustained gains enabled by tokenization. To derive the scaling pattern governing the minimum sufficient tokenization configuration at different data scales, theoretical analysis and systematic experiments are employed to summarize the quantitative scaling pattern. We find an approximately linear relationship between the logarithms of minimum sufficient tokenization capacity and input data size measured by tokens, and the scaling slope varies systematically with the tokenization method and data source, reflecting differences in representation-space redundancy and intra-source uniqueness. Guided by the proposed law, we further develop ALGN, an adaptive variable-length tokenization method that improves capacity allocation. Extensive experiments across diverse data sources, tokenization methods, and downstream tasks demonstrate the generalizability and reliability of the User Behavioral Densing Law, providing practical guidance for tokenization configuration selection in large-scale user representation learning. Moreover, ALGN outperforms existing baselines.

Structured data exists in many forms (tables, knowledge graphs, charts, and time series), and converting it into text may involve different generation tasks. However, most prior work on data-to-text (D2T) generation has focused on specific tasks and datasets, relying either on task-specific training data or on the zero-shot capabilities of large language models. We study cross-domain D2T generation in a setting where neither in-domain training text nor test references are available, and where domains, generation goals, and input structures vary substantially. We compare data-driven knowledge distillation (DDKD) against zero-shot inference and fine-tuning on out-of-domain D2T data, and introduce structure-preserving augmentation via structural subsampling and perturbation. Experiments on five benchmarks show that, at constant model size (1.7B parameters), DDKD consistently outperforms both fine-tuning and zero-shot inference. Moreover, the resulting small models outperform a much larger finetuned model on two of the five domains, achieving comparable performance on the remaining three. We further construct QUINTD-5, a fivefold extension of QUINTD-1, and show that simply scaling real target-domain inputs yields only modest gains, whereas our augmentation strategy remains more effective and more cost-efficient for cross-domain distillation.

English Wikipedia is often treated as the default encyclopedic source, yet non-English Wikipedia editions can contain richer locally grounded information for long-tail figures. We study cross-lingual biography enrichment: enriching an existing English biography with facts supported by a non-English biography about the same person. Focusing on women from non-English-speaking contexts, we introduce CLAW-4L, a benchmark consisting of 300 Wikipedia biography pairs linking an English biography with its French, Chinese or Azerbaijani counterpart, along with claim annotations and a fine-grained claim-pair relation corpus. We propose a claim-based enrichment framework that extracts English claims from both biographies, aligns them to identify enrichment evidence from the non-English biography, and rewrites the English biography using the selected claims. Our results show that non-English Wikipedia biographies provide valuable evidence for improving English biography coverage, while lower-resource settings remain challenging.

Video generation is progressing beyond isolated clips toward long-form narratives and interactive worlds, requiring models to preserve identities, follow user controls, and remain stable over extended rollouts. We present JoyAI-Echo-1.5, a unified audio-visual generation system with two purpose-built variants. The long-video variant introduces composable cross-shot memory that aggregates visual evidence across multiple prior shots and speaker cues derived from speech-filtered full-shot audio, enabling persistent character appearance and voice identity across flexible combinations of text, image, and memory conditioning. The world-model variant converts heterogeneous navigation inputs into calibrated metric 6-DoF camera trajectories and injects them through a geometry-aware conditioning pathway, enabling controller-agnostic interaction across flexible viewpoints. To support efficient long-horizon generation, we transform a bidirectional audio-visual backbone into a causal few-step generator using progressive teacher forcing and short- and long-horizon Self-Gradient Forcing on self-generated rollouts. Experiments demonstrate strong performance in both settings. JoyAI-Echo-1.5 achieves improvements over existing long-video baselines in cross-shot consistency, visual quality, text alignment, and speech fidelity. Its world-model variant ranks first on WBench, with an average score of 81.7, and achieves leading visual quality and long-horizon persistence on SANA-WM-Bench. Together, these results indicate that memory, geometric control, and rollout-aware training provide a practical foundation for generating coherent stories and continuously evolving interactive worlds. Project page: https://echo-team-joy-future-academy-jd.github.io/Echo-1.5-Page/.

Instance encoding is a popular empirical technique for privacy enhancement when sharing data to an untrusted server. It transforms sensitive data through an encoding process before sharing, with the hope that the encoding process retains utility but makes it hard to reconstruct the original data. However, most work offers no theoretical guarantee that the encoding process is actually irreversible. A recent work derived a mean-squared error (MSE) bound limiting any adversary's reconstruction accuracy, offering one of the first theoretical results in this domain. This bound, however, has three critical limitations: it is often too loose, only works with randomized encoders (excluding many deterministic encoders practitioners use), and only bounds MSE. We introduce a family of new bounds that (1) are tighter, (2) applicable even to fully deterministic encoders, and (3) can extend beyond MSE to other norm-based similarity metrics, by properly accounting for the encoder's spectral structure. We evaluate our bounds across a range of encoders, datasets, and attacks, showing they hold consistently and improve upon the existing bound.

Developers use automated Move refactorings to improve the modular structure of source code and the assignment of responsibilities. Class- and method-level Move refactorings are automated in modern IDEs, but statement- and expression-level moves that adjust method boundaries remain largely unautomated. We formalize five variants of Move Statement refactoring as preconditions and steps grounded in four basic conditions covering data reachability, execution count, side effects, and syntactic constraints required for compilation, of which all but the side-effect condition are checked statically. Combined with existing techniques, this also yields finer-grained moves of expressions and partial expressions. We further refine the formalization iteratively against a real project, deriving twenty additional preconditions and steps that handle Java syntactic diversity in practice. We evaluate applicability and compilability on ten projects, and behavior preservation in a case study on one of them: Move Statement refactorings yield compilable code in 93.3-97.0% of applicable cases, and the case study shows that the observed behavioral changes stem from side-effect reordering left to developer judgment, not from defects in the statically checked conditions.

Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminism, reporting a >200x slowdown for a steganographic adversary under benign prompt traffic. This bound assumes a passive attacker; we show it degrades sharply against an adversary who instead controls the prompt distribution. Because the verifier's admissible-token-set size is driven by the model's own output entropy, prompts engineered to break grammatical and sub-word structure – rather than benign conversational traffic – widen that set and open a materially larger covert channel. Across six instruction-tuned models spanning 1B to 32B parameters and three random seeds, our strongest attack (character- and script-level disruption) roughly doubles bits leaked per token relative to benign prompts, cutting the slowdown factor to 60x - 118x. These results indicate that static, benign-traffic-calibrated thresholds are insufficient for this defense, and that jitter-forgiveness thresholds should instead be calibrated dynamically against local token entropy.

Transforming digital research infrastructure (DRI) to align with UK Net Zero targets requires significant action from organisations in this space. Although high level strategies and recommendations exist, it is not always obvious how to translate these into concrete results. Here we present a case study from the Science and Technology Facilities Council's Scientific Computing Department (SCD). This department consists of over 200 staff supporting tens of thousands of researchers, and is spread over significant cloud and high performance computing infrastructure, as well as a diverse ecosystem of software across computational biology, materials science, engineering, and mathematics. We show how we developed the sustainability strategy for SCD across themes of emissions monitoring, user education, best practice, setting sustainability standards, and providing long-term support to sustainability work. We discuss the successes and difficulties in establishing this strategy, and how this could serve as a template for other departments and facilities.

Forecasting long-range influenza-like illness (ILI) matters for public health readiness. Publicly available surveillance datasets typically pair numeric epidemiological signals with textual information that is noisy, loosely structured, only indirectly related to near-term trends, and often lagged relative to the numeric signal. Fusing the two therefore requires careful design. We propose Dual-Stream Attention (DSA), a multimodal deep learning framework that forecasts 12-week-ahead ILI activity from a 36-week multimodal history by letting the numerical and textual streams condition each other. Using the Time-MMD health-domain dataset, DSA separately encodes the two modalities with a Transformer-based numerical encoder and a domain-adapted headline encoder, then couples them through a bidirectional Cross-Modal Attention (CMA) mechanism: the text (news headlines) conditions the interpretation of the numeric signal and vice versa. The CMA output then passes to a causal temporal model for forecasting. Evaluated across ten random seeds, DSA achieves a median test MSE of 0.416, versus 0.668, 0.607, and 0.851 for iTransformer, TaTS, and GPT4MTS, corresponding to mean-error reductions of 54.95%, 37.29%, and 67.23%, with paired Cohen's d of 0.555, 0.337, and 0.345, respectively, and ranks first in 100% of bootstrap draws. It also has substantially lower worst-window error than all baselines. On an external-geography dataset, DSA again ranks first among nine evaluated baselines. Ablations show the advantage does not depend on text-encoder choice or language-model fine-tuning, and that bidirectional attention outperforms either direction alone. Finally, perturbation-based faithfulness analysis shows the learned CMA is functionally informative under targeted masking, with a stronger effect in the text-to-numerical direction.

Large Language Models (LLMs) do not natively track the path of exclusions that a coherent discourse demands. When an input rests on a fabricated authority, a misapplied mechanism, or a surreptitious analogy, an unsteered LLM tends to engage with it as if it were well-posed, and this affects its generation. POLANYI++, an LLM-steering method that uses heuristics, ontologies and problem-solving methods for tacit-knowledge extraction, produces an Extended Knowledge Graph (XKG) in OWL2, but when a sophisticated nonsensical input is reified into the graph alongside the legitimate triples, it gets hardly detectable by automated reasoners, since the XKG is generated jointly with the wrong assumptions. We introduce DARKSIDE, a coherence-auditing method on top of POLANYI++. DARKSIDE formalises an explicit data structure of accumulated exclusions over discourse time, complemented by a warrant axis that classifies each named referent as Warranted, Unattested, Misattributed or Fabricated. The method is anchored in nine theoretical fragments unified under a shared deep frame of path integrity. The resulting DARKPOLANYI is evaluated as a steering layer over Gemini 3 on BSBench, a 100-item adversarial corpus of sophisticated-sounding nonsense across multiple domains, with Claude Sonnet 4.6 as an independent judge. DARKPOLANYI scores 1.89/2 mean versus 0.95/2 for the unsteered Gemini 3 Pro baseline; on the 97 cases with valid judgments in both arms, paired McNemar gives a paired bootstrap mean-diff = +0.92 (95% CI [+0.75, +1.08], p = 0.0001). The evidence supports an architectural claim: when an LLM forward pass is wrapped in an ontology-mediated auditing, structurally inevitable hallucination can be partially recovered. The XKG functions as the missing memory that LLMs lack, and the warrant axis as an epistemic firewall.

Transform-based tensor products, including the T-product and its more general form, namely the higher-order tensor-tensor product, have become fundamental tools for multilinear data analysis in applications such as image processing, signal reconstruction, and robotics. While invertible transforms enable tensor computations to be carried out via matrix operations in the transform domain, the resulting storage and computational costs remain prohibitive for high-dimensional, higher-order tensors. To address this challenge, we integrate low-rank tensor decomposition techniques, specifically tensor train decomposition (TTD) and hierarchical Tucker decomposition (HTD), into transform-based multilinear algebra to improve computational and memory efficiency. In particular, we develop TTD- and HTD-based formulations for the T-product and its associated key algebra, such as block diagonalization and tensor singular value decomposition, by operating directly on the factor matrices or tensors of the decompositions. The framework is further generalized to the higher-order tensor-tensor product and applied to multilinear model order reduction problems. We demonstrate the effectiveness and efficiency of our framework with numerical examples.

Solid-state drives (SSDs) are built on NAND flash memory and expose it to the operating system through a block-based storage interface. As NAND flash has special read/write constraints due to its hardware nature, a translation between OS-level I/Os and raw flash memory I/Os is needed. This results in a flash translation layer (FTL) that creates a “trusted computing base” due to its physical isolation from the OS. Building on this trusted computing base, some security designs (e.g., data recovery from malware attacks) can ensure strong data security properties even if the OS is compromised. However, they mostly require modifying the FTL's firmware code, which is hard in practice because the traditional block-based FTL does not provide an interface to modify its internal functions. New flash storage interface designs, such as open-channel SSDs or zoned namespaces, have moved key FTL functions into the OS. These interfaces ease modification of FTL functions, at the cost of blurring the trusted boundary, as the FTL is no longer isolated from the OS. In this work, we have introduced SxSSD, a secure yet extensible software-defined SSD design. By decoupling internal policy definitions from primitive FTL mechanisms, we allow trusted applications to dynamically and securely define FTL policies and the exposed storage interface (achieving increased flexibility compared to open-channel and zoned namespaces SSDs). Most significantly, SxSSD retains the isolation of traditional FTL execution (achieving security similar to traditional block-based SSDs). We have identified and addressed key security challenges introduced under a compromised OS. In addition, we have implemented a prototype of SxSSD and evaluated its overhead with different FTL policies and storage interfaces. Experimental evaluation demonstrates that the overhead incurred by SxSSD is small compared to native FTL implementations.

Audio-visual deepfake detection is an actively studied topic, where one of the main challenges is to develop detectors able to generalize across deepfake generation methods. We conjecture that overfitting can be mitigated by extracting multiple high-level cues from the available audio and visual modalities via pre-trained models. We therefore assemble a wide variety of pre-trained models to extract features that encode mouth movements, face parsing, facial expressions, head pose, gaze tracking, heart rate, audio emotion and speech activity. We further integrate both unimodal and multimodal cues via a Mixture-of-Experts (MoE) backbone to detect deepfakes. We perform in-domain and cross-domain experiments on five benchmarks for deepfake detection (MAVOS-DD, AVLips, PolyGlotFake, BioDeepAV, FakeAVCeleb) to compare our framework (DF-MoE) with state-of-the-art methods. Our results indicate that DF-MoE obtains superior deepfake detection results, surpassing all competing methods. We release our code at https://github.com/vladhondru25/DF-MoE.

Increasing automation in rail transport shifts the train driver's role from active control to prolonged supervisory monitoring. This creates conditions for mental fatigue (MF) and reduced vigilance. Despite the safety relevance of this issue, evidence on the feasibility and robustness of physiological indicators of MF under operational rail conditions remains limited. Most prior work relies on simulators or lab studies. The present study investigated multiple subjective, physiological, and behavioral indicators of MF in professional train drivers across two complementary settings: a high-fidelity train simulator (n=14) and a real-world rail environment (n=6). To our knowledge, this is the first study to deploy a full multisensor battery under actual train operating conditions. In both settings, a standardized protocol was used comprising a baseline drive, a one-hour auditory n-back task as an MF induction procedure, and a second drive. Heart rate variability and breathing rate showed consistent and theoretically expected changes across both environments, suggesting reduced physiological arousal following the fatigue induction task. In contrast, EEG-based frontal theta power and parietal alpha and beta power, electrodermal activity, blink duration, and behavioral indicators did not show clear mental fatigue-related patterns. Real-world data collection revealed substantial technical challenges related to vibration, sensor connectivity, and concurrent high-frequency data acquisition. These findings suggest that autonomic indicators, particularly HRV and breathing rate, represent the most promising and ecologically robust measures for operational fatigue monitoring in train drivers. However, neurophysiological measures require further validation under realistic conditions before deployment in driver monitoring systems, and larger samples are needed to confirm these preliminary patterns.

The performance gap between low- and high-resource languages in LLMs is widely known, but it remains unclear which internal model factors drive these disparities. In this paper, we characterise this gap through the lens of representational geometry. Comparing the geometric properties of hidden representations across 30 languages reveals that LLM geometry is systematically related to language data availability. The most consistent effect is in final layers, where low-resource languages exhibit representational degeneration. To counter this, we investigate the effectiveness of regularisation terms to penalise degeneration during continued pretraining (CPT). Experiments monolingually adapting 9 base LLMs to 10 African languages show that geometric regularisation successfully reduces representational degeneration during CPT. For larger models, cosine similarity-based regularisation marginally improves performance over vanilla CPT, with more consistent gains on the most challenging tasks. We establish that the representational geometry of low- and high-resource languages in LLMs is measurably distinct, and that targeted geometric intervention is a viable strategy for improving CPT for low-resource languages.

The Bitner–Ehrlich–Reingold algorithm generates the binary reflected Gray code with constant work per codeword, using a focus-pointer array. Its compact update is easy to state but gives little indication of why such pointers should exist. This note reconstructs a geometric route to the algorithm. The sequence of flipped bit positions is the ruler sequence, OEIS A007814. We realize its finite prefixes as in-order traversals of recursively expanding trees, decorate each activation with its nearest ancestor to the right, contract all stack operations between successive outputs into successor jumps, and prepare the bounded level-indexed stack by predicting its future slot values. This gives and proves a branch-based loopless generator. The construction grew from an earlier informal public exposition by the author. Viewing horizontal position in the tree as time then explains each stack-slot write as a prediction for the next activation at the same level. Finally, the two possible future roles—an inherited continuation for a right child and a default continuation for a left child—are scheduled together, leading to the two assignments of the published focus-pointer algorithm. The account is a reconstructed derivation, not a claim about the historical reasoning of Bitner, Ehrlich, or Reingold.