Papers

We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking, producers, business) and four difficulty tiers. The corpus is built from 38,104 atomic, source-anchored facts extracted by 35 provenance-verified scrapers from government registries (INAO, TTB, OIV), peer-reviewed journals, and Wikipedia/Wikidata. Our methodological contribution is an LLM-driven pipeline in which language models reformat verified facts and audit the result, but never serve as the source of truth: every claim traces to a URL, every question is generated by one of five strategies across five generator families, and every question is scored by a nine-agent audit calibrated against a human gold sheet via Cohen's $\kappa$. Evaluating sixteen frontier configurations, we find: (i) overall accuracy spans 53%-84%, led by o3 at 83.6%; (ii) reasoning-mode lift concentrates in DeepSeek R1 (+6.8pp) and is absent in Claude Opus and Gemini Pro; (iii) Anthropic shows +9pp self preference on its own questions while Google shows -8pp inverse preference; (iv) frontier open-weight models share the cost-vs-accuracy Pareto frontier with proprietary reasoning models; and (v) every config gains around 33pp on closed-book solvable items, revealing a parametric-recall ceiling that only the contextual slice avoids. We release corpus, audit findings, human-review app, and construction code under CC-BY-SA-4.0.

Artificial immune networks (AINs) are naturally memory-forming systems, but conventional visual AINs often rely on flattened vector affinity that ignores spatial structure. This paper studies whether structured, gradient-free immune affinity can make Deep AINs viable as replay-free visual class-incremental representation-memory learners. Visual B-cells are formalized as structured templates, including shifted-template affinity, zero-normalized cross-correlation (ZNCC) filters, and feature-map binding profiles. A repertoire is treated both as memory and as a representation-inducing basis, while depth is obtained by passing binding-profile response maps to subsequent immune layers. The resulting Deep AIN exhibits adaptive latent coordinate reorganization: as new classes arrive, the binding-profile space evolves while retaining recoverable structure for earlier classes. Experiments on sklearn digits, MNIST, Fashion-MNIST, and KMNIST show that preserving response maps is critical. Scalar binding-profile variants underperform, whereas feature-map Deep AINs learn class-discriminative visual memory without replay, label-driven immune updates, or backpropagation through the immune layers. On sklearn digits, downstream probes fitted on the learned binding profiles reach 0.939 final balanced accuracy with logistic regression and 0.902 with 1-nearest-neighbour after all ten classes are encountered, with initial-class retention of 0.978. Adaptive layer-wise scale calibration further improves the two-layer feature-map Deep AIN to 0.978 balanced accuracy. With the same calibration rule, Fashion-MNIST reaches 0.814 and KMNIST reaches 0.853. These probes are external validation tools, not components of the AIN. The results identify structured affinity, response-map preservation, adaptive latent reorganization, and layer-wise scale calibration as key mechanisms for replay-free visual immune memory.

This paper presents a rigorous extension of the explicit, high-order, positivity-preserving, and entropy-stable spectral collocation schemes developed in Upperman 2023 and Yamaleev 2023 for the 3D compressible Navier-Stokes equations to a time-implicit formulation. The time derivative terms are discretized by using the second-order implicit backward difference formula (BDF2) that is well suited for solving time-variable viscous flows at high Reynolds numbers. The nonlinear system of discrete equations resulting from the BDF2 discretization at each physical timestep is solved using a dual time-stepping (DTS) technique. The BDF2 DTS scheme is entropy-stable and positivity-preserving in the pseudotime and provides unconditional stability properties in the physical time. Numerical results demonstrate the efficiency and accuracy of the positivity-preserving BDF2 DTS scheme as compared with its explicit counterpart are presented for supersonic flows with strong shock waves and contact discontinuities.

LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph generation. However, its training objective provides no explicit incentive for the model to generate sparse and efficient topologies. We address this limitation by introducing a Reward-Guided Autoregressive Graph Generation (RGA-Designer) inspired by Reinforcement Learning from Human Feedback (RLHF). We train a reward model that jointly captures task correctness and structural compactness, and then fine-tune the pretrained graph generator using the reward model as feedback. Our method preserves task accuracy at the level of ARG-Designer while reducing token consumption by an average of 20.5%.

Sloan iteration raises the convergence order of Galerkin and degenerate-kernel approximations to second-kind integral equations. After quadrature discretization, these become a discrete Galerkin method and a product-integration Nyström method, respectively. How much of this improvement survives quadrature discretization? For zonal integral equations on the sphere, we give a sharp answer by expressing the Sloan error identity in terms of spherical harmonics. In the absence of quadrature, Sloan iteration fully exploits the smoothing of the integral operator. Quadrature can destroy this gain by aliasing unresolved information into low-frequency modes, where further iteration no longer improves the asymptotic rate. This yields a unified tail–aliasing description of these four methods. For positive-weight polynomially exact quadrature and multipliers of exact algebraic order, we derive sharp two-sided worst-case bounds that separate the spectral-tail and aliasing contributions. Their balance yields a depth-dependent recovery–saturation threshold: sufficient overintegration recovers the quadrature-free rate, while below the threshold aliasing determines the sharp order. We also extend the analysis beyond polynomial exactness using Marcinkiewicz–Zygmund stability and Gram-corrected least squares. Numerical experiments illustrate both regimes.

Retrieval-Augmented Generation (RAG) lets Large Language Models (LLMs) pull in up-to-date, domain-specific information instead of relying only on what they were trained on. Yet most RAG systems still draw from centralized databases with limited oversight, making it difficult to verify where a document came from, whether it has been tampered with, or whether it should be trusted at all. This is a serious problem in domains where both the timeliness and accuracy of retrieved content are critical, such as healthcare, finance, logistics, and legal case law, where a wrong or manipulated document can directly lead to bad decisions. We present TrustRAG, a committee-based, blockchain-backed RAG system: before a document is used, it is certified by a committee of domain experts through a zero-knowledge protocol, and the committee's hidden scores are combined via secure multi-party computation into a trust score that any client can verify. These scores, along with the underlying document data, are maintained jointly across chains through hash commitments, so no document or score can be silently altered or dropped, and every ranking can be independently replayed and checked.

In this work, we present HandMvNet, one of the first real-time method designed to estimate 3D hand motion and shape from multi-view camera images. Unlike previous monocular approaches, which suffer from scale-depth ambiguities, our method ensures consistent and accurate absolute hand poses and shapes. This is achieved through a multi-view attention-fusion mechanism that effectively integrates features from multiple viewpoints. In contrast to previous multi-view methods, our approach eliminates the need for camera parameters as input to learn 3D geometry. HandMvNet also achieves a substantial reduction in inference time while delivering competitive results compared to the state-of-the-art methods, making it suitable for real-time applications. Evaluated on publicly available datasets, HandMvNet qualitatively and quantitatively outperforms previous methods under identical settings. Code is available at github.com/pyxploiter/handmvnet.

Ontology-based data access is intended for graph data, but practical support remains limited to SQL-like languages lacking the navigational and path-matching features fundamental to graph querying. Theoretical algorithms for navigational queries have long been available. Still, they have never been implemented, largely because practical graph query languages fell short of their theoretical counterparts and lacked the expressive power needed to support rewriting common ontology languages. The recent standardisation efforts around GQL and SQL/PGQ finally allow us to overcome this barrier and present a practical query rewriting technique for ontology-mediated navigational graph queries. Ontologies are written in a DL-Lite variant tuned to property graphs, and the queries in a GQL fragment with nested two-way regular path queries and which can be evaluated in Cypher. Preliminary experiments with our proof-of-concept prototype suggest that querying graph data with ontological knowledge may finally be within reach.

The term "visualization design" encompasses multiple concepts and skills that go well beyond current assessments of graphical perception and visualization literacy. In the context of education, what exactly should a student be able to do if they "know" visualization design? To answer this question, we draw on existing methodology from the field of education to propose a concept inventory for visualization design, i.e., a theoretical model capturing the most important concepts and skills commonly associated with visualization design. We initially draft the concept inventory using a qualitative analysis of course objectives from visualization course syllabi. Then, we iteratively refine the concept inventory by soliciting feedback from instructors through semi-structured interviews. Based on our experiences in developing the concept inventory, we reflect on open questions and future research directions in visualization education, such as developing assessments for visualization design (similar to those for visualization literacy) and providing automated assistance for learning and teaching visualization design. Our supplemental materials are available at https://osf.io/dma3f/.

Backstepping control provides local stability guarantees for nonlinear Saint-Venant systems, but its regulation performance may degrade when the system operates far from the nominal equilibrium. This letter proposes a backstepping-guided soft actor-critic (SAC) controller framework that incorporates model-based control knowledge into reinforcement learning (RL). The nominal backstepping control law is first learned by deep operator network (DeepONet) and embedded into the actor and critic networks as prior informed feature representations. The learned prior is further combined with the SAC policy to generate the final control input, while a transfer-learning strategy preserves the useful backstepping knowledge during adaptation to the nonlinear dynamics. Simulation results on the Sambre River model demonstrate that the proposed method improves learning efficiency and maintains effective regulation over larger initial deviations than backstepping control.

Humanoid robots have recently demonstrated promising capabilities in real-world ball sports. However, achieving professional motion styles while maintaining strong task performance remains challenging. In this work, we propose AdaPT, an Adaptive Motion Planning and Tracking framework that learns professional tennis serving and rally styles directly from broadcast videos. This hierarchical design is motivated by the key insight that the planner generates stylistic kinematic motions, while the tracker executes them with minimal interference with planning. Despite its effectiveness in simulation, a substantial sim-to-real gap emerges: tracking performance inevitably degrades on real robots, and this degradation is partially overlooked by autoregressive planning and further compounded by noisy perception. To address these issues, our adaptation mechanism improves tracking robustness by learning to track randomized execution speeds, while conditioning the planner on a learned motion-speed adapter to mitigate compounding errors. Real-world experiments on the Unitree G1 demonstrate the effectiveness of our adaptation mechanism in bridging the sim-to-real gap. We further deploy AdaPT policies on the full-size Dobot Atom humanoid robot (1.7m) and demonstrate in-the-wild serving without motion capture. Beyond these results, our real-world experiments reveal both algorithmic and engineering insights for future humanoid ball-sports systems. Videos and code are available on our \href{https://humanoidtennis.github.io/AdaPT/}{project website}.

Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. Hierarchical approaches combining Vision-Language Models (VLMs) with Task and Motion Planning (TAMP) offer a promising solution, but VLM-generated subgoals may rely on prior knowledge without sufficient observational support. This can lead to the omission of task-relevant subgoals or attempts to execute instructions whose requirements cannot be met in the environment. We propose Evidence Acquisition and Feasibility Gating (EAFG), a framework for evidence-gated task and motion planning that acquires visual evidence to specify appropriate task plans and assess whether given instructions can be fulfilled. EAFG first acquires evidence by having a VLM generate subgoals and a robot execute action sequences planned by TAMP for these subgoals. For feasibility gating, the acquired evidence is used to decide whether to proceed with task planning, acquire further evidence, or halt. When proceeding, the VLM generates task subgoals conditioned on the acquired evidence, and TAMP computes low-level actions. We evaluate EAFG in three cooking scenarios involving explicitly specified required objects, underspecified instructions, and instructions requiring an absent object. EAFG improves task completion over a VLM-TAMP baseline in the explicit and underspecified scenarios and enables appropriate halting when a required object is absent.

Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines. We propose SABET-QA, a framework that iteratively refines reasoning states across multiple hops via a bidirectional entity-temporal scoring mechanism and a slot-aware contextualization module that aligns question semantics with temporal KG embeddings. A differentiable working memory enables progressive hypothesis refinement, while auxiliary temporal boundaries serve as coarse supervision when available. Experiments on CronQuestions, Complex-CronQuestions, MultiTQ, and TimeQuestions demonstrate consistent improvements over strong baselines, particularly on complex multi-step temporal queries.

We consider an inverse backscattering problem for time-dependent acoustic waves with a compactly supported penetrable scattering obstacle in unbounded three-dimensional free space. Assuming that dynamic backscattering far field data of scattered waves corresponding to a few time-dependent incident plane waves are available, the goal is to reconstruct the shape of the scattering obstacle. We establish Fréchet differentiability of the time-dependent far field pattern with respect to the shape of the scattering obstacle and give a characterization of the associated temporal domain derivative in terms of its Laplace transform. This characterization is then utilized in an efficient implementation of a regularized Gauß-Newton method for the inverse backscattering problem using convolution quadrature and a boundary element method. Numerical examples demonstrate potentials and limitations of the algorithm.

Real-world networks are often organized in several layers forming a hierarchy which determines the interaction between the individual components. In order to discover such hierarchies in temporal networks, Tatti [ECML PKDD 2018] introduced the temporal agony problem Seg-Agony. Here, the goal is to assign each vertex a certain rank (from 1 to $k$) such that arcs only point from lower ranks to higher ranks. Backward arcs are penalized depending on the difference between the corresponding ranks. Since arcs may change over time, each vertex is allowed to change its rank $\ell\ge 1$ times in order to minimize the overall penalty $\alpha$ (called temporal agony). We study the parameterized complexity of Seg-Agony with a special focus on the number $k$ of possible ranks for which we identify the precise complexity border. We show that the problem is polynomial-time solvable for $k=2$, NP-hard for $k=3$ and $\ell=1$ but polynomial-time solvable for constant $\alpha$, and NP-hard for $k=4$ and $\ell=1$ even for $\alpha=0$. We further show a polynomial-time algorithm for a constant number $n$ of vertices and fixed-parameter tractability for the combined parameter $n+\ell$.

The term "dual control" refers to the dual objective of simultaneously balancing exploration and exploitation. Problems of this kind have been studied for nearly a century. This paper is devoted to theory and methodology relevant for optimal control of linear time-invariant systems whose parameters are initially unknown and must be learned by active probing. We review the main ideas underlying four major research directions: Multi-armed bandits, self-tuning regulators, regret rate minimizing controllers, and minimax optimal dual controllers. The first three have a long history and rich literature, whereas the fourth provides a promising framework for robust dual control.

While generalist VLMs are expensive to train, creating domain experts is widely assumed to require fine-tuning increasingly large foundation models. We show that, in veterinary radiology, this assumption is misguided. By rethinking the entire VLM pipeline - from text tokenisation and pre-training to grounding and inference - we demonstrate that careful engineering can yield models that outperform much larger foundation models from scratch, without relying on any other data. Our approach introduces new strategies for generative pre-training and grounding that improve training efficiency, increasing data utilisation and downstream performance. Using only a fraction of the parameters, data, and compute of contemporary generalist models, we develop the first VLM capable of generating diagnostic reports for veterinary radiographs, surpassing open foundation models on this task by significant margin.

World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a direct way to learn such states by predicting targets in representation space instead of reconstructing every detail of the observation. Standard JEPAs, however, organize all predictable content through one target embedding and one prediction pathway. In complex systems, this monolithic state can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure. We introduce \method, a latent world-modeling framework based on orthogonal predictive factorization. Learned basis matrices analyze each target state into multiple components, and a dedicated prediction branch estimates each component from a shared context representation. Predictive regression preserves the factor magnitudes required for state synthesis, an orthogonality objective discourages repeated directions, factor-activity regularization maintains variation in projected targets, and online variance regularization discourages coordinate-wise encoder collapse. Predicted components are synthesized into a complete latent state that can be used by a readout, decoder, planner, or autoregressive rollout. The same predictive-state mechanism applies when the target is temporally future, spatially hidden, or another partial observation of the same system. Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability.

Mixture-of-Experts (MoE) architectures significantly expand model capacity without a proportional increase in computational cost. However, optimizing their hyperparameters—particularly the learning rate—at extreme scales of both model size and token budget via sweeping remains computationally prohibitive. In this paper, we propose a compute-efficient, two-step hyperparameter transfer framework that estimates optimal learning rates for training large MoE models by transferring them across scaling model widths, and subsequently extrapolating to trillion-token horizons. First, we formulate a Maximal Update Parameterization ($\mu$P) adaptation for MoE architectures utilizing Multi-head Latent Attention (MLA) and the Muon optimizer, demonstrating that optimal learning rates transfer consistently across width-scaled models. Second, we extend this transferability along the token dimension by establishing a predictive scaling law. By applying linear regression to the optimal values derived from small proxy models on limited budgets, we successfully extrapolate the ideal learning rate to massive training horizons (e.g., 10 trillion tokens) with high fidelity ($R^2=0.95$). Consequently, this indicates that proxy training on small models is sufficient to determine the optimal learning rate for the extensive training of large-scale MoEs. We apply the proposed methodology to pretrain our foundation model (155B total, 17B active parameters) from scratch, and the stable training and evaluation results validate that optimal configurations for full-scale target models can be accurately predicted with minimal ablation costs.

Tight framelet systems on manifolds provide exact energy preservation and one-pass reconstruction, but their standard semi-discretization relies on polynomial-exact quadrature rules, which are difficult to reconcile with scattered and progressively refined data. We develop nested Marcinkiewicz–Zygmund (MZ) measures on compact Riemannian manifolds as a quantitative alternative. Using dyadic quasi-uniform nested point sets and local partition weights, we establish a sequence of deterministic MZ inequalities for diffusion polynomial spaces. The result has two complementary forms: a fixed-tolerance version, in which the polynomial bandwidth grows dyadically with the level, and a fixed-bandwidth refinement version, in which the MZ tolerance improves as more nested nodes are added. When these measures are used to discretize continuous tight framelets, the MZ tolerance transfers directly to the deviation of the frame bounds from one. Thus quadrature exactness is relaxed with a controlled loss of tightness, and near-tightness improves along the same nested hierarchy. For the fully discrete setting, we develop filter-bank analysis and synthesis procedures, characterize one-pass and canonical reconstruction, and show that the MZ tolerance also controls the conditioning of the frame-operator equation. Fast implementation of filter-bank transforms is also presented. Numerical experiments on the sphere and the flat torus illustrate the resulting multiscale decompositions and reconstruction behavior.

Inertial measurement units (IMUs) are now standard in most consumer devices, such as smartphones, drones, and extended reality (XR) headsets. By fusing visual and inertial data, localization systems gain significantly in speed and robustness compared to vision-only or IMU-only approaches. However, traditional pose estimation methods fail to utilize the local geometric information embedded in feature descriptors like SIFT. Recent work has proved the advantages of leveraging this information for relative and absolute pose estimation, but its application to partially calibrated absolute pose estimation remains unexplored. In this paper, we derive novel constraints for joint estimation of absolute pose and focal length, making use of a gravity vector obtained from IMU data and the feature-induced local geometry, which we use to construct two efficient solvers: UP1PfAC, that operates given a single affine correspondence and UP2PfORI, which requires two orientation-covariant features. Unlike traditional, semi-calibrated absolute pose methods requiring four point correspondences, our solvers benefit from fewer samples and lower computational cost, simplifying robust estimation in modern RANSAC-like frameworks. We evaluate the proposed solvers against the state-of-the-art on large-scale public datasets and demonstrate that our method achieves fast and accurate localization and focal length estimation.

Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs can be directly extracted from black-box models remains largely unexplored. In this work, we systematically study whether hidden CoTs can be extracted near-verbatim from black-box LRMs through API interactions. We identify a previously overlooked reasoning replay surface between tool calls and develop EchoCoT, a multi-step attack that iteratively extracts hidden CoTs using API-returned fidelity signals. We further develop an LLM-based optimization framework that automatically searches for an effective universal injection trajectory across various datasets. We evaluate EchoCoT on three open-source and five frontier proprietary LRMs. On open-source LRMs, EchoCoT achieves up to 66.4% near-verbatim extraction success, with the extracted trace length within 10% of the target and at least 90% of tokens exactly matching the target CoT. The same injection trajectory also generalizes to unseen datasets, achieving up to 80% extraction success under the same criterion. For tested frontier proprietary LRMs, a substantial fraction of extracted CoTs closely align with provider-reported reasoning lengths and available CoT summaries. EchoCoT can also extract very long CoTs: on Gemini-2.5, it extracts 33,463 tokens from a 32,948-token target. These results establish hidden-CoT extraction as a practical security risk and highlight the need to better protect hidden CoT assets.

Multi-module neural systems often expose every module to the full input. We test whether a slot-selective evidence-masking regime – restricting each module to its own evidence span – changes which solutions gradient-based training discovers. Four-cell societies share one frozen pretrained language model and one low-rank adapter, communicating only through two model-width continuous vectors in a fixed relay. On a prospectively sealed natural-language function-composition task, we train ten matched restricted/global pairs identical except for the attention mask. Restricted-visibility societies outperform their globally visible twins by at least 20 percentage points at both depths in 9 of 10 pairs, with median paired advantages of 0.7648 and 0.6050. Cutting communication reduces every restricted society to chance, and in a post hoc collision-stratified analysis the depth-three advantage remains 0.558 on programs whose complete affine map never appeared in training. In six post hoc-selected restricted societies, packet interventions on correctly answered held-out episodes are consistent with approximately value-indexed relay states; the sole high-performing global model also requires communication, but its same-value packets are not interchangeable across episodes. Thus restricted visibility is not necessary for composition. Under the tested seeds, streams, task world, and training budget, the masking regime strongly shifted which solutions training discovered: a post hoc mask crossover finds both arms mask-native. Because the restricted mask both blocks foreign evidence and implicitly identifies each cell's assigned slot, attribution to evidence visibility alone awaits a role-marked control. The preregistered battery nevertheless formally fails because restricted-arm median depth-three accuracy is 0.6988, below the 0.70 floor; an earlier qualification cohort yielded 0/10 complete passes.

The integration of Artificial Intelligence (AI) in safety-critical aviation systems presents significant challenges for certification and deployment. Aviation, often regarded as the safest form of transportation, relies on numerous safety-critical systems. For future safety-critical AI-based systems, EASA requires a Safety-by-Design approach, which can be achieved by using Safety Nets that combine neural network compression with lookup tables to ensure 100 % correct runtime behavior across the discretized operational design domain. Although Safety Nets have been studied, no comprehensive study of their performance characteristics and system design trade-offs has been conducted. This work presents the first systematic analysis of the trade-off between neural network and lookup table size in Safety Nets. By systematically comparing neural networks with diverse architectures, this study identifies optimal design parameters that minimize overall storage and memory requirements while maintaining certification compliance. Results demonstrate that architectures with 3 to 5 hidden layers, each with approximately 50 to 100 nodes, combined with one-hot encoding, achieve the best balance. In these configurations, neural networks accurately represent at least 97 % of the data, while compact lookup tables handle the remaining errors. The resulting Safety Nets reduce the system size by almost three orders of magnitude, fitting within the memory budget of current avionics hardware while guaranteeing 100 % correct outputs across the entire discretized input space, as required by EASA guidelines. This work provides the first-ever open-source implementation of Safety Nets for HCAS and VCAS with replicable results, demonstrating a practical pathway toward certifiable AI-based systems in aviation and establishing Safety Nets as a viable Safety-by-Design solution for safety-critical applications.

Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches. Existing methods often fail to capture the unique inner properties of these components, lack interpretability, or suffer from heavy memory and runtime overhead. To address these limitations, we propose DecoVAE, a lightweight interpretable trend-seasonal VAE framework that explicitly decomposes time series into trend and seasonal components by applying domain-specific inductive biases. The trend stream enforces structural smoothness using a differential regularizer on the latent trajectory, analogous to the Hodrick-Prescott filter. Concurrently, the seasonal stream operates in the frequency domain via a complex Gaussian VAE, natively capturing the amplitude and phase of periodic patterns. Extensive evaluations across seven real-world benchmarks show that DecoVAE consistently outperforms strong baselines. It achieves reductions of up to 14.96% in CRPS and 23.30% in NMAE for short-term forecasting, and up to 52.68% and 26.51% for long-term horizons. Crucially, DecoVAE yields these accuracy gains while remaining highly efficient, reducing model weight by up to 93% and accelerating speed by up to 74% compared to the second-best method.

We study finite, connected, simple bipartite graphs in a grid model, in which a graph is drawn as a rectangular array and its structure is read off from empty subrectangles, called holes. In this model we attach to every brick a numerical invariant, its characteristic m, the difference between the number of rows and the largest proper independent set. A brick is excessive if m > 0. Our main results concern this invariant. We determine the characteristic of a disconnected excessive brick from those of its components, showing that m = min_i min{m_i, imb(W_i)} while the imbalance is additive; and we prove that an m-excessive brick is m-extendable, that is, every matching of size m extends to a maximum matching. Since Plummer's notion of n-extendability is defined only for graphs carrying a perfect matching, and our proof nowhere uses balance, the characteristic extends that notion canonically to unbalanced bipartite graphs. Using the characteristic we partition bipartite graphs into eleven structural classes. The underlying decomposition into atomic blocks is the classical decomposition into elementary components, and the description of the maximum proper independent sets by ideals of the block poset is likewise classical; the paper states precisely which results are classical and are not claimed here. What the grid model adds is a single geometric framework in which holes, characteristics and the block triangular form are read off from one picture.

Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narrow set of quality measurements. Multilingual deployment exposes evaluation-design choices that are inconsequential on English but determine conclusions cross-lingually. We propose an evaluation framework with four components: detection thresholds calibrated empirically per deployment context, a threshold-independent companion measurement that distinguishes calibration failures from detection failures, three disjoint quality measurement paradigms (distributional, paired-semantic, and reference-perplexity), and a generalized-entropy decomposition of cross-language disparity over a typological family partition. Applied to six watermarking schemes, three open-weight generators, eleven languages spanning four scripts and eight typological families, and both base and instruction-tuned regimes, the framework reveals failure modes that single-language, single-paradigm evaluation cannot surface. Against a shape-matched null, detection disparity is predominantly between-family on the typological partition, indicating that detection gaps are structural to language properties rather than idiosyncratic to particular languages; quality disparity is large but not reliably family-structured.

Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments. Yet, most existing methods assume stationarity and rely on separable designs, where classification and triggering are optimized independently, an assumption that fundamentally limits their adaptability under drift. In this work, we challenge this paradigm and study ECTS under non-stationary conditions. We provide the first systematic comparison between separable and end-to-end approaches across controlled drifting scenarios. Building on Reinforcement Learning, we introduce DQeND, a unified architecture that jointly learns representation, classification, and triggering decisions, while remaining directly comparable to state-of-the-art separable baselines. Across a wide range of drifts, DQeND demonstrates strong robustness across various non-stationary scenarios, consistently outperforming separable baselines. An ablation study further highlights that jointly updating representation and decision modules is critical to these gains. Overall, our results indicate that end-to-end learning can offer improved adaptation capabilities for ECTS in dynamic environments, and motivate further investigation of alternatives to separable designs.

We study bilateral teleoperation between nonlinear, multi-DOF robotic manipulators in the presence of constant communication delays. Unlike classical wave-transformation architectures that transmit a coordinating force, we consider the case where the environmental force is reflected to the master side to enhance teleoperation transparency. Since direct contact force feedback might destabilize the closed-loop system, we first develop a passivity-shortage characterization for the Euler–Lagrange remote system using a linear matrix inequality (LMI) approach. An upper strictly passive communication law is then employed to compensate for the computed passivity shortage so that the closed-loop stability under delays as well as position and force synchronization are preserved under appropriate conditions. Simulations with nonlinear 2-DOF robotic manipulators in different settings illustrate our approach.

Research on the agency of advanced artificial intelligence (AI) systems focuses on agency as a normative concept and on the agency of particularly agentic AI systems. While recent work also focuses on the different profiles of agentic systems, no framework exists to address the question of the type of agency instantiated by advanced AI systems, particularly when considering non-moral forms of agency. Based on established theoretical positions in philosophy, ethics, legal theory and sociology, we develop a typology of agency for frontier AI systems consisting of three dimensions: the nature of agency (moral or legal), its mode (individual or collective) and its locus (human or non-human). Combining these dimensions produces eight possible instantiations of agency, which we classify as conventional, contested or controversial. The typology separates legal from moral agency and thereby creates conceptual space for considering individual, legal, non-human agency without presupposing that advanced AI systems are moral agents. We argue that this distinction is increasingly relevant where instrumental goal pursuit complicates the attribution of AI actions to particular human actors.