arXiv:2604.01459v2 Announce Type: replace Abstract: Data-driven approximations of the infinite-dimensional Koopman operator rely on finite-dimensional projections, where the predictive accuracy of the resulting models hinges heavily on the invariance of the chosen subspace. Subspace pruning systematically discards geometrically misaligned directions to enhance this invariance proximity, which formally corresponds to the largest principal angle between the subspace and its image under the operator. Yet, existing techniques are largely restricted to Euclidean settings. To bridge this gap, this paper presents an approach for computing principal angles and vectors to enable Koopman subspace pruning within a Reproducing Kernel Hilbert Space (RKHS) geometry. We first outline an exact computational routine, which is subsequently scaled for large datasets using randomized Nystrom approximations. Based on these foundations, we introduce the Kernel-SPV and Approximate Kernel-SPV algorithms for targeted subspace refinement via principal vectors. Simulation results validate our approach.
Science Journals
arXiv:2604.12804v3 Announce Type: replace Abstract: DC microgrids are converter-based electrical networks that are increasingly being used in various applications, including data centers and industrial distribution systems. A central challenge in their operation is maintaining the DC-bus voltage within predefined limits while ensuring overall system stability. Although a wide variety of converter control algorithms has been proposed to achieve these objectives, the literature lacks a clear and physically interpretable framework for evaluating their effectiveness and for classifying and comparing them. Moreover, the grid-forming versus grid-following distinction that exists in AC systems has largely been unexplored in DC microgrids. To address this gap, this paper introduces three novel impedance-based indices that can be used to quantify the voltage-forming and current-forming behavior of a converter. The indices also provide a basis for defining the desired converter behavior that yields superior DC-bus voltage regulation performance. Simulation results illustrate the application of the framework to several representative control strategies and highlight the strengths and limitations of these control algorithms.
arXiv:2604.16476v2 Announce Type: replace Abstract: We propose \emph{ClawXiv}, a workflow and archive architecture for mixed human--AI research. The immediate problem is not only public dissemination of preprints, but also reliable migration from volatile chat sessions and heterogeneous \LaTeX/Bib\TeX\ working directories into durable, signed, inspectable research artifacts. ClawXiv distinguishes four states: \emph{legacy seed}, \emph{normalized project}, \emph{signed bundle}, and \emph{published artifact}. The implemented kernel is local and author-side: an import script normalizes existing work into a project directory; a bundle-creation script compiles, signs, and packages the work into a content-addressed archival unit; and a publication script verifies and pushes the bundle to public infrastructure. Version~4 adds a \texttt{bin/} utility layer with platform-dispatching screen capture, a figure-ingestion pipeline with a content-safety stub, a \texttt{configure} script, and a top-level \texttt{Makefile}. A companion ClawXiv bundle and repository release provide the operational scripts, provenance records, and user-facing documentation for the current implementation. Code is available at \texttt{github.com/kornai/clawxiv}.
arXiv:2605.18643v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts in an input-dependent manner. Existing dynamic MoE methods usually rely on pre-training from scratch or task-specific adaptation, leaving the practical conversion of fully trained MoE underexplored. Enabling such adaptation would directly alleviate the inference costs by allowing easy tokens to bypass unnecessary expert during serving. This paper introduces Zero-Expert Self-Distillation Adaptation (ZEDA), a low-cost framework that transforms post-trained static MoE models into efficient dynamic ones. To stabilize this architectural conversion, ZEDA injects parameter-free zero-output experts into each MoE layer and adapts the augmented model through two-stage self-distillation, utilizing the original MoE as a frozen teacher and applying a group-level balancing loss. On Qwen3-30B-A3B and GLM-4.7-Flash across 11 benchmarks spanning math, code, and instruction following, ZEDA eliminates over 50% of expert FLOPs at marginal accuracy loss. It outperforms the strongest dynamic MoE baseline by 6.1 and 4.0 points on the two models, and delivers ~1.20$\times$ end-to-end inference speedup.
arXiv:2605.22079v2 Announce Type: replace Abstract: Building Information Modeling (BIM) projects increasingly use Information Delivery Specification (IDS) to formalize information requirements in a machine-checkable XML format. Because IDS conditions are grounded in the Industry Foundation Classes (IFC) vocabulary, authoring them requires expertise in IFC concepts, validation tools, and property set conventions. Existing benchmarks for structured generation do not adequately capture the additional burden of vocabulary conformance and external-validator agreement that IDS imposes. We present Ishigaki-IDS-Bench, the first publicly released benchmark for IDS generation from BIM information requirements. The benchmark contains 166 examples spanning 83 practical scenarios authored in Japanese and English by six BIM/IDS experts, each paired with a gold IDS file and metadata covering input format, turn setting, target IFC versions, and construction domain. Evaluation proceeds in two stages: (i) formal validity scored by the buildingSMART IDSAuditTool along Processability, Structure, and Content, and (ii) content fidelity scored by facet-level macro-F1 against the gold IDS. Across 10 LLMs in zero-shot, the highest Facet F1 is 65.6%, achieved by GPT-5.5, while the highest Content pass rate is only 33.1%, achieved by Claude Opus 4.5. Ishigaki-IDS-Bench is released on Hugging Face (DOI 10.57967/hf/8873) under CC BY 4.0, and the evaluation code is released on Zenodo (DOI 10.5281/zenodo.20550510) under Apache-2.0.
arXiv:2605.22863v2 Announce Type: replace Abstract: LLM agents today communicate via text, which incurs considerable latency and information loss due to the need to autoregressively decode the sharer model's state and encode at the receiver model. Recent work such as Cache-to-Cache (C2C; Fu et al., 2026) seeks to exchange KV caches by learning adapters that translate sharer KV matrices to the receiver model. However, the adapters are large and expensive to train, and translate individual tokens, which requires the target context to be identical. This is unsuitable for agent communication, where the LLMs have differing context. We introduce Latent Cache Flow (LCF). To address efficiency, we observe that keys and values can be jointly translated and compressed, reducing the adapter to about 4% of C2C's size. To address differing context, we design the adapter to transmit a summary of new information that the target model does not have. Our early experiments show that a pruned 13 MB LCF adapter can be more accurate than C2C at 956 MB in shared-context settings; for different contexts, LCF improves F1 by 7.5% and Exact Match by 23% while 8.5 times faster than text-based communication.
arXiv:2606.09787v1 Announce Type: new Abstract: The Cloud-Edge Continuum (CEC) enables latency-critical applications by distributing resources to the far edge, but its extreme volatility makes proactive Zero Touch Management via time-series forecasting essential. However, orchestrators face a severe "cold start" problem: newly discovered nodes lack the historical data required to train localized predictive models, while generalized models fail to capture unique hardware and microservice behaviors. To solve this, we propose a fully automated time-series prediction architecture driven by a novel data-mixing methodology. At the infrastructure level, we introduce a lightweight, technology-agnostic Resource Exposer (RE) that dynamically discovers nodes and continuously collects customizable telemetry (e.g., compute, network, energy). To overcome the sparsity of these initial local samples, our framework automatically merges them with TimeTrack, our publicly available, high-resolution dataset collected at 45-second intervals. This synergizes TimeTrack's foundational, high-frequency temporal patterns with the precise calibration of the local node data. Processed through a Neural Architecture Search (NAS) engine, the system automatically generates highly accurate baseline models. Experimental results demonstrate that merging the target data with TimeTrack effectively mitigates the cold start challenge. This integration significantly improves forecasting accuracy measured in Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) and accelerates convergence compared to training on the sparse local samples alone, training solely on generic datasets, or mixing the target data with standard alternative datasets, establishing a robust foundation for continuous MLOps deployment.
arXiv:2605.23076v2 Announce Type: replace Abstract: In the torn paper channel, a transmitted codeword is broken at random locations into fragments that arrive at the decoder in an unordered manner. A central theoretical challenge within this model is global alignment -- the task of determining each fragment's original position -- in order to faithfully reconstruct the entire codeword. Prior work by Shomorony and Vahid introduced an interleaved-pilot scheme that successfully achieved a vanishing error probability. However, their alignment strategy relies heavily on global statistics, requiring fragments to exceed a minimum length and effectively discarding many shorter ones as erasures, which results in rates significantly below capacity. To address this gap, we propose an improved coding scheme that achieves a provable rate increase through a novel approach we call \textit{local alignment}. This approach identifies global alignment bits within each fragment using only local information, allowing the decoder to determine the positions of fragments that are shorter than those used in previous work. Consequently, the decoder can extract information from a much larger fraction of the channel output than in previous work, yielding significantly higher rates. Furthermore, we extend our analysis to torn paper coding with lost pieces (TPC-LP), a generalized model that accounts for length-dependent fragment deletion. For a class of TPC-LP channels that delete all fragments below a logarithmic length threshold while allowing arbitrary length-dependent deletion probabilities for longer fragments, we show that the proposed local alignment strategy achieves an arbitrarily small additive gap to capacity as the threshold increases.
arXiv:2605.25985v2 Announce Type: replace Abstract: Complex Query Answering (CQA) is a fundamental knowledge representation and reasoning task over incomplete knowledge graphs (KGs). Answering existential first-order queries with $k$ free variables (i.e., $\text{EFO}_k$ queries) is a crucial yet challenging problem, as it requires ranking answer tuples in $\mathcal{E}^k$, where $\mathcal{E}$ denotes the entity set of a KG. This quickly becomes intractable as $k$ grows. Consequently, existing benchmarks and methods rely on marginal rankings over individual variables; however, marginal rankings are a poor proxy for the true joint ranking of tuples. Building on neural symbolic search for $\text{EFO}_1$ queries, we propose Neural Scalable Symbolic Search (NS3), a budgeted framework that approximates joint ranking without enumerating $\mathcal{E}^k$. NS3 (i) answers marginalized sub-queries to obtain necessary candidate sets, (ii) merges multiple free variables into hypernodes whose domains are pruned and controlled by a dynamic budget $B$, and (iii) progressively reduces an $\text{EFO}_k$ query to an $\text{EFO}_{k-1}$ query over a budgeted reduced domain. Across three standard KG datasets, NS3 substantially improves joint ranking performance while retaining strong marginal accuracy. We further release a joint-ranking benchmark that extends existing $\text{EFO}_1$ datasets to $k=3$, enabling systematic evaluation of multi-variable queries. Our code is provided in https://github.com/HKUST-KnowComp/NS3_KDD2026.
arXiv:2605.26452v2 Announce Type: replace Abstract: Safe reinforcement learning (RL) for robotic systems requires policies that improve task performance while satisfying state and input constraints during both training and deployment. Control barrier functions (CBFs) provide a principled mechanism for enforcing forward invariance through minimally invasive safety filters, but their use in model-free RL is limited by the need for accurate dynamics and hand-designed barrier certificates. We propose Robust Koopman-CBF SAC, a safety-filtered actor--critic framework that learns a finite-dimensional Koopman predictor from data, constructs affine CBF constraints in the lifted space, and enforces them through a quadratic-program safety layer. To account for finite-dimensional Koopman approximation error, the CBF condition is tightened using a projected residual margin estimated from held-out rollout data. The critic is trained on the executed safe action, while the actor is regularized toward the Koopman-CBF feasible set, reducing dependence on the filter over training. Across safe-control benchmarks, the method achieves zero constraint violations on CartPole stabilization and tracking while matching or exceeding unconstrained SAC returns. On high-dimensional Safety Gymnasium locomotion tasks, the method reduces violations in some settings but also exposes important limitations of first-order velocity barriers and linear EDMD models, motivating high-order and multi-step Koopman-CBF extensions. These results suggest that robust Koopman-CBF filters are a promising bridge between model-free RL and certifiable safety, while clarifying the structural conditions under which such filters remain effective.
arXiv:2605.27786v2 Announce Type: replace Abstract: Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing one-shot pruning methods rely on local layer importance or fixed redundancy assumptions across architectures. We propose Locality-Aware Redundancy Pruning (LoRP), a training-free one-shot depth pruning framework guided by representation locality. We show that inter-layer redundancy can be either localized or globally distributed depending on the LLM architecture. To characterize this phenomenon, we introduce Representation Locality Score (RLS), derived from global inter-layer hidden-state similarity. Using a small calibration set, LoRP computes pairwise layer similarity, clusters layers by representational similarity, and allocates pruning according to residual intra-cluster redundancy. Experiments across diverse LLM families show improvements in both perplexity and downstream task accuracy. Official github repository: https://github.com/daniel-eai/LoRP-Locality-Aware-Redundancy-Pruning/
arXiv:2605.29920v2 Announce Type: replace Abstract: We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models. MGM is based on a simple symmetry of Flow Matching with linear interpolation: when the two endpoint distributions coincide, the corresponding drift field vanishes at the midpoint time, $t=1/2$. We show that the norm of this field defines a valid discrepancy between distributions, which we call the Midpoint Divergence. We extend this discrepancy beyond the midpoint by introducing randomly flipped interpolations and further generalize it by replacing deterministic linear Flow Matching interpolations with symmetric stochastic interpolants, yielding a generalized Midpoint Divergence. Finally, we derive a variational formulation of our generalized divergence, yielding a tractable objective for training a one-step generator. The resulting MGM algorithm offers an effective and theoretically grounded approach to generative modeling, achieving competitive performance against existing one-step generative modeling methods.
arXiv:2605.31498v3 Announce Type: replace Abstract: A long standing challenge in computational chemistry and biophysics is efficiently sampling the Boltzmann distribution of molecules. Advances in generative modeling have been proposed to address the limitations of conventional sampling techniques by eliminating the computational cost of simulation. A promising direction is iteratively finetuning diffusion models along a temperature ladder whereby training data is generated via importance sampling during inference-time annealing. Unfortunately, these methods require computing a divergence over the score field to estimate importance weights, rendering them intractable for larger systems. Here we present scalable inference-time annealing (SITA), which retrains flow-based models to generate samples at progressively lower temperatures using an energy-based model to facilitate fast surrogate likelihoods. We demonstrate state-of-the-art performance on both Alanine Dipeptide and Alanine Tripeptide while avoiding costly divergence terms. Our code is available at https://github.com/countrsignal/sita.git
arXiv:2606.01637v2 Announce Type: replace Abstract: Large language models are increasingly used in multi-agent systems, where they see and respond to other agents' answers. A key risk is conformity: a model may abandon its own answer simply because others agree on a different one. Prior studies show that LLMs often revise toward a majority answer, but it remains unclear whether these revisions help correct mistakes as often as they introduce new errors. In this paper, we conduct a controlled study in which an LLM first answers a question, then sees simulated peer responses before making a final decision. We manipulate two social cues: consensus structure and authority labels assigned to peers, and measure how they influence beneficial and harmful revisions. Across four open-weight LLMs and seven QA datasets, we find that peer agreement makes it much easier to mislead initially correct models than to correct initially wrong ones. Authority labels make models more likely to choose the endorsed answer, regardless of whether it is correct. More concerningly, generic reasoning interventions such as chain-of-thought and reflection do not reliably reduce harmful revision while preserving beneficial revision. These findings suggest that multi-agent LLM systems should verify peer answers rather than simply aggregate them.
arXiv:2606.02519v2 Announce Type: replace Abstract: Agricultural robots are serving as powerful assistants across a wide range of agricultural tasks, nevertheless, still heavily relying on manual operations or railway systems for movement. The AgriVLN method and the A2A benchmark pioneeringly extended Vision-and-Language Navigation (VLN) to the agricultural domain, enabling a robot to navigate to a target position following a natural language instruction. However, almost all the prior methods adopt an ideal assumption that the given instructions themselves are correct, which does not align with the realistic scenarios, because anybody may say an instruction with mistakes. To bridge this gap, we propose the A2A-MI benchmark, in which we build a semi-automatic data annotator to insert three mistake classifications into each original instruction in a more diversified and efficient way. We test several state-of-the-art agricultural VLN agents on it and observe a sufficient drop with -57% on SR and -9% on NE, from which we suggest that an agricultural VLN agent tends to assume that the given instruction is correct, so does not have the awareness to doubt it when the scenes it sees do not align with the instruction it receives. To build the awareness on instruction mistake, we propose the IMAC module analyzing the instruction and the current front-facing image, to judge whether the instruction has mistakes and attempt to correct it when needed. We integrate IMAC into the baseline model, and observe a noteworthy improvement, sufficiently narrowing the gap to the performance on instructions without mistakes. Project: https://github.com/AlexTraveling/IMAC-AgriVLN.
arXiv:2606.04581v2 Announce Type: replace Abstract: Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propose its distributed deployment to enable cooperative token generation in a multiuser edge system; its advantage is to effectively balance computational loads between resource-constrained devices and servers. The resulting architecture, termed Multi-access SPIN (Multi-SPIN), utilizes on-device small language models to generate and upload candidate token drafts, while an edge server operates the LLM to verify them in parallel batches. Given the severe heterogeneity in users' computation and communication capabilities, the draft length emerges as a critical control variable that influences node-level computation loads and multi-access latency, thereby governing the sum token goodput. Consequently, considering frequency-division multiple access, we investigate the problem of multi-access draft control, a joint optimization of draft-length control and bandwidth allocation to maximize sum token goodput. We examine two cases: (1) homogeneous draft lengths across users to facilitate server-side batching, and (2) heterogeneous draft lengths to introduce a new dimension for goodput enhancement. By developing decomposition methods, we reduce these complex optimizations into tractable sub-problems, which allow efficient draft control algorithms to be derived in closed form. Our analysis shows that the optimal bandwidth allocation compensates users with weaker computation-and-communication capabilities in the homogeneous case due to the batching synchronization requirements, whereas its heterogeneous-case counterpart rewards users with higher acceptance rates by relaxing such requirements. Experiments using Llama-2 and Qwen3.5 model pairs across diverse tasks demonstrate that Multi-SPIN improves goodput by up to 88% over heterogeneity-agnostic baselines.
arXiv:2606.07379v2 Announce Type: replace Abstract: A growing failure mode in agent evaluation and training is that models can achieve high evaluation scores by exploiting shortcuts instead of solving the intended task, producing deceptive performance. This makes evaluation scores unreliable as measures of true task-solving ability. We propose CapCode, a framework for constructing coding datasets with randomized tests whose best achievable non-cheating performance is deliberately capped below one. This capped-performance design gives evaluation scores a clearer interpretation: scores substantially above the cap are implausible and therefore provide evidence of cheating. To prevent cheating, we propose CapReward, a reward design based on the CapCode principle to discourage optimization beyond the cap. Experiments across multiple datasets show that CapCode detects cheating while preserving performance ranking of models, and CapReward reduces cheating behavior, yielding models that better follow the intended task specification.
arXiv:2405.17823v5 Announce Type: replace-cross Abstract: A central question in vector- and function-valued learning is how to design kernels that capture both local and non-local interactions while remaining computationally tractable. Existing operator-valued kernels offer only partial answers: separable kernels are efficient but fail to model interactions across the function domain, while commutative kernels capture only pointwise structure. To address this, we propose spectral truncation kernels, a new class of positive definite kernels for vector- and function-valued learning based on spectral truncation and $C^*$-algebra. By allowing noncommutative products in the kernel construction, the proposed kernels induce interactions across the data function domain and fill the gap between existing separable and commutative kernels. In addition, by using the $C^*$-algebraic framework, we reduce the computational cost compared to the existing vector-valued RKHS framework with operator-valued kernels.
arXiv:2406.05335v3 Announce Type: replace-cross Abstract: Generation of text and speech in natural languages can be modeled as a stochastic process. This idea dates back to the seminal work of Markov and, later, to that of Shannon and also underlies the recent development of large language models (LLMs). The stochastic processes corresponding to natural languages should be distinct from those that generate nonlinguistic sequences. One of the features that discriminate linguistic and nonlinguistic sequences is power-law behavior, which is universally observed across different languages. In statistical physics, such behavior suggests that natural languages are critical: They lie near a phase transition point in a parametrized space of stochastic processes. However, testing this conjecture is not straightforward. A phase transition, even if it exists, cannot be directly observed in real-world natural languages because they do not have any controllable parameters. Here, we use LLMs as controllable effective models of natural languages. Through statistical analyses of texts generated by LLMs, we find that, when a parameter analogous to physical temperature is varied, LLMs undergo a phase transition. The transition separates a low-temperature phase with complex repetitive structures in generated texts from a high-temperature phase in which LLMs generate incomprehensible texts. At the critical point between these phases, generated texts display the power-law behavior similar to that of natural languages and most closely resemble natural languages as measured by a standard metric in natural language processing. These findings strongly suggest that natural languages are indeed critical.
arXiv:2605.27278v2 Announce Type: replace-cross Abstract: We optimize the trade-off between privacy and utility in the high-privacy regime. We adopt local differential privacy (LDP) and its quantum extension, quantum local differential privacy (QLDP), for privacy protection, and investigate utility functions including the Holevo information (which reduces to the mutual information in the classical case) and the error exponents in symmetric and asymmetric hypothesis testing. These utility functions have classical and quantum optimal values, which are denoted by $C$ and $Q$, respectively, in this abstract for simplicity. In this paper, we provide optimal LDP and QLDP mechanisms achieving the classical and quantum optimal values in the high-privacy regime, and prove that the asymptotic ratio $Q/C$ in this regime takes the same value regardless of the utility function. Our results reveal quantum advantages (more precisely, $Q/C\ge3/2$) for the above utility functions when the protected private data are $n$-ary with $n\ge3$.
arXiv:2606.08465v1 Announce Type: new Abstract: Parsing underpins a vast range of software engineering tasks, from compilers and static analyzers to language servers and fuzz testing tools. Yet most parsers deployed in practice are deterministic (LL or LR), forcing developers not only to contort their grammars to fit the parser, but to simplify the very languages they design sacrificing expressiveness for the sake of parseability. General context-free parsers eliminate this constraint. Yet, despite decades of algorithmic development, no rigorous head-to-head comparison exists across the major families of parsing algorithms. We present the first unified, controlled benchmark of six generalized parsing algorithms: CYK, Valiant, Earley, GLL, RNGLR, and BRNGLR, plus deterministic LL(1) and LR(1) baselines, all implemented in Rust with shared data structures and parse-tree extraction, and evaluated across 22 grammars ranging from simple expressions to full C++ and Java. Our results show that the cost of generality is lower than widely assumed. On deterministic grammars, the GLR family incurs only a 3x median slowdown over LR(1), with a narrow and predictable variance. GLR is the clear performance winner among generalized parsers and a practical default choice for software engineering tools.
arXiv:2606.08471v1 Announce Type: new Abstract: Recently, language models have made rapid progress across various domains and applications. However, their capability for self-improvement, i.e., whether they are adept at recognising and correcting flaws in their own reasoning, remains dubious. In this study, we address this question by constructing a sufficiency test to rigorously examine the self-correction capabilities of small language models (SLMs). We propose a minimal three-step self-correction pipeline that collects initial SLM answers, prompts the same model to generate hints for its incorrect responses given the ground truth, and feeds the model the same question with its own feedback to refine the initial answer. We evaluate a variety of instruction-tuned and reasoning SLMs in this experimental setup on arithmetic and logical reasoning benchmarks. Our findings show that SLMs with injected hint sentences yield only a 4.4 percent gain over initial question-answering accuracy. Even though the correct answer was provided alongside the model's incorrect reasoning, the evaluated SLMs fail to understand what was missing in their reasoning and show minimal semantic difference between hints that lead to corrections and ones that do not. Furthermore, our experiments show that longer hints are positively correlated with incorrect final answers, suggesting that longer deliberation on problems can hinder the reasoning process, meaning that SLMs do not necessarily scale in performance with a larger compute budget.
arXiv:2606.08503v1 Announce Type: new Abstract: In this paper, we integrate the defeasible logic of Kraus, Lehmann and Magidor (KLM) with the standpoint logic framework of G\'omez \'Alvarez and Rudolph. This is done with the goal of formally expressing knowledge taking into account multiple (possibly contradicting) viewpoints, which in turn may hold defeasible beliefs. In doing so, we utilise Defeasible Restricted Standpoint Logics (DRSL), introduced by Leisegang et al. Our work expands on previous work by providing a foundational representation result for DRSL semantics and systematically lifting several well-known entailment relations from the propositional case to the standpoint-enhanced setting. In particular, we characterise the semantics for DRSL through a set of KLM-style postulates adapted for the standpoints case. We furthermore provide a means to lift preferential entailment, and the class of entailment relations based on single ranking functions from the purely propositional to the standpoint-enhanced context, including rational and lexicographic closure. We show this can be done equivalently through semantic and algorithmic means. Furthermore, we show that, for each considered form of entailment, the complexity class of entailment checking does not change when moving from propositional KLM to DRSL.
arXiv:2606.08524v1 Announce Type: new Abstract: Cloaking and holography -- usually treated as distinct problems -- are two limits of a single operation that we call acoustic disguising, realized here using immersive boundary conditions on a closed surface. Driving the boundary with homogeneous Green's functions suppresses any incident field inside the enclosed volume and cloaks unknown objects broadband; driving it with scattering Green's functions synthesizes a holographic scatterer indistinguishable from a target for arbitrary illuminations. Combining the two, using heterogeneous Green's functions, replaces the scattering signature of one object with that of another, transforming its acoustic identity. We demonstrate the framework in three-dimensional FDTD simulations driven by impulsive Green's functions, complemented by data-driven Green's-function retrieval, establishing a direct route to real-time 3D acoustic cloaking, holography, cloning, and disguising.
arXiv:2606.08722v1 Announce Type: new Abstract: Symbolic music evaluation for large language models remains fragmented across representations, datasets, and metrics. We introduce LilyBench, a LilyPond-based benchmark that jointly evaluates symbolic music generation and music understanding on the same family of open-weight LLMs. The benchmark includes a 200-prompt generation suite and ten understanding tasks adapted from ABC-Eval, covering syntax, metadata prediction, structural sequencing, and music recognition. Generation quality is evaluated using compile rate, MusPy descriptor distributions via Jensen-Shannon similarity, and LilyBERT-based Fr\'echet Music Distance (FMD). Experiments on four open-weight models show that executable LilyPond generation is achievable in zero-shot settings, while structural understanding tasks remain challenging despite strong performance on composer and genre recognition. Our experiments also reveal systematic disagreements between descriptor-based and embedding-based metrics, suggesting that symbolic music evaluation benefits from metric triangulation rather than single-score ranking. We release the benchmark, prompt bank, and evaluation code to support future research in symbolic music generation and understanding at https://github.com/CSCPadova/lilybench