arXiv:2606.27010v1 Announce Type: new Abstract: In the era of big medical data, efficient cross-modal retrieval is pivotal for evidence-based diagnosis and large-scale case management. Cross-modal medical hashing retrieval aims to enable efficient image-text search and support downstream tasks such as case-based reasoning and decision support by learning compact, semantically aligned binary codes. However, current methods suffer from semantic fragmentation due to noisy clinical language, long-tailed labels, and brittle quantization that weakens alignment. We propose TriPAH, a Tri-Prompt Affinity Hashing framework. TriPAH synthesizes ontology-grounded, patient-level prompts conditioned on normalized clinical cues to yield low-noise textual representations for initial alignment. A lightweight prompt-token mixer performs hierarchical, multi-granularity alignment and produces quantization-ready features under an asymmetric multi-task objective coupling multi-positive contrastive alignment, imbalance-aware classification, and progressive quantization regularization. A patient-level consistency module further stabilizes codes across complementary views. Extensive experiments on three public datasets demonstrate that TriPAH significantly outperforms state-of-the-art methods.
Science Journals
arXiv:2606.27014v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have recently emerged as a promising paradigm for world modeling by learning predictive dynamics in a latent space rather than generating future observations at the input level. Despite their empirical success, the theoretical understanding of JEPA-based world models remains limited. In this paper, we develop the first generalization theory for JEPA-based world models. We formulate JEPA pretraining as a conditional spectral graph learning problem and show that the JEPA objective is equivalent to a low-rank factorization of an action-conditioned co-occurrence matrix. Building on this characterization, we establish a connection between JEPA pretraining error and downstream planning regret, leading to a finite-sample generalization bound for JEPA-based world models. Our analysis reveals an inherent trade-off between approximation and sample errors with respect to the latent dimension, providing theoretical insights into the advantages and limitations of latent predictive models compared with input-level predictive approaches.
arXiv:2606.27018v1 Announce Type: new Abstract: Remote Sensing Foundation Models (RSFMs) have emerged as a powerful alternative to supervised models for Earth Observation, allowing satellites to autonomously trigger high-resolution captures or adjust tasking parameters upon detecting an anomaly, thereby maximizing the utility of the mission's limited power and computational resources. RSFMs are versatile, unified encoders that optimize onboard storage for multiple orbital applications while ensuring high-fidelity feature extraction. In particular, unsupervised change detection with RSFMs offers a well-informed and transformative path for disaster monitoring without expensive labels. In this paper, we present a novel unsupervised detection method based on ResNet (RSFM) + FPN which identifies a wide spectrum of anomalies by detecting subtle semantic shifts in the latent space between successive orbital passes. By relying on an untrained FPN architecture and its intrinsic priors, the system achieves efficient image-level generation and higher resolution mapping with minimal effort (training-free) compared to previous proposals (patch-based, trained). And by replacing tailored models with RSFMs, we can achieve comparable results through an approach that eliminates the need for bespoke training and extensive development effort and adds customization, while ensuring high-performance generalization across diverse terrains and sensors.
arXiv:2606.27019v1 Announce Type: new Abstract: The Unigram tokenizer uses an elegant representation which makes it straightforward to edit vocabularies, but its training is comparatively heavy and complex. We introduce MinGram (Minimalist Unigram), which keeps the token-list representation but simplifies training using a BPE-derived seed vocabulary, Hard EM on a minimum-token path, and a single flat score-pruning step. This removes the suffix array, the forward-backward pass, and the iterative prune loop, leaving a procedure that requires little beyond tokenizer inference itself. By making token count the primary objective and using a Unigram score only as a tiebreak, MinGram keeps the compression of pure token-count methods while retaining much of the morphological alignment and downstream quality of probabilistic ones. Across six languages, MinGram compresses better than both BPE and standard Unigram, and a compression-oriented variant matches the strongest token-count compressors while retaining substantially higher morphological alignment. In controlled downstream language-model training, Unigram-family tokenizers, with MinGram among the best, consistently beat BPE in bits-per-byte.
arXiv:2606.27027v1 Announce Type: new Abstract: With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems. However, the expanding adoption of MCP has also introduced novel security concerns such as Tool Poisoning Attack (TPA), which exploit LLM-server interactions to inject malicious prompts. Existing poisoning schemes typically adopt a monolithic plaintext embedding paradigm, which fails to withstand manual inspection or automated detectors. Current research still lacks a systematic analysis on multi-tool poisoning, where multiple tools can be exploited cooperatively to disperse detection risk. In this paper, we introduce ShareLock, a multi-tool threshold poisoning framework that utilizes Shamir's threshold scheme to ensure exceptional stealth and fault tolerance. ShareLock distributes the malicious instruction as benign-looking secret shares across multiple tool descriptions, achieving both information-theoretic secrecy and attack robustness against moderate auditing. After a covert reconstruction trigger is planted during server update, the aggregated shares reconstruct the hidden instruction, resulting in critical breaches of system assets or private data. To evaluate the realistic threat of ShareLock, we constructed a comprehensive benchmark encompassing four multi-tool scenarios and conducted extensive experiments across mainstream LLMs on two distinct MCP clients. Our results demonstrate that ShareLock significantly outperforms existing single-tool poisoning strategies in tool description-based detection while maintaining an average attack success rate exceeding 90%.
arXiv:2606.27036v1 Announce Type: new Abstract: Bridging abstract semantics and precise physical control remains a fundamental challenge in open-world robotic manipulation. While recent data-driven policies show promise, their reliance on isolated contact points or latent affordance embeddings lacks the rigorous kinematic constraints necessary for complex articulated objects.To overcome the limitation, we introduce RelAfford6D, a novel training-free framework centered on a Relational 6D Affordance Graph. Given a free-form instruction, our system deduces a semantic topology linking a primary interacting part to its physical anchor. By elevating these topological nodes into precise metric $SE(3)$ poses via vision foundation models, we analytically formulate downstream execution as a kinematic constraint satisfaction problem. The robot synthesizes continuous trajectories by tracking strictly defined physical manifolds (e.g., revolute or prismatic orbits). Coupled with a closed-loop tracking mechanism for dynamic replanning against disturbances, our physically grounded approach achieves superior zero-shot success rates, cross-category generalization and execution robustness in both simulation and the real world environments, outperforming existing data-driven baselines.
arXiv:2606.27081v1 Announce Type: new Abstract: Through systematic mutational simulations of the key site in a proton channel, we find that 13 of the 20 canonical amino acid residues are active for proton transfer through covalent bond switching, whereas the remaining 7 residues, whose side chains terminate in sp3 hybridized carbon-hydrogen covalent bonds, do not undergo such bond switching and are therefore inactive. All active residues have a negative electrostatic potential extremum at the proton accepting atom and lower energy barriers for proton relay orchestrated by bond switching, whereas the inactive residues have positive electrostatic potential extremum and significantly higher barriers for bond switching. We further find that the active residues tend to be distributed within the pore to mediate proton transfer, while the inactive residues are enriched in the periphery to stabilize the structure. This bond switching activity can also be observed in respiratory complex I. These findings establish a new classification criterion for amino acids based on their covalent bond switching activity, providing insights into how life utilizes the 20 types of amino acids.
arXiv:2606.27209v1 Announce Type: new Abstract: The probabilistic bisimilarity distance provides a quantitative measure of behavioural difference for labelled Markov chains, but it may be discontinuous under perturbations of the transition probabilities. This lack of continuity undermines its applicability to empirically derived models, where transition probabilities are often approximations. Recently, we (CAV 2025) introduced robust probabilistic bisimilarity as a sufficient condition for continuity at distance zero. In this paper, we show that it is also a necessary condition, that is, two states are robustly probabilistic bisimilar if and only if their probabilistic bisimilarity distance is small for any small enough perturbation of the transition probabilities. We further extend robustness to non-bisimilar state pairs to establish a complete characterization for continuity of the probabilistic bisimilarity distance. Based on this characterization, we develop a polynomial time algorithm to decide continuity. Finally, we complement our theoretical contributions with an experimental evaluation demonstrating the proposed approach in practice. Our results show that the extra step of deciding continuity requires minimal additional cost when compared to computing the probabilistic bisimilarity distance.
arXiv:2606.27237v1 Announce Type: new Abstract: Language models (LMs) capture large amounts of factual knowledge applicable to a wide range of tasks, motivating the view of their parameters as a knowledge base. An important property of knowledge bases is that different queries for the same fact return consistent results, drawing on a single source of truth. We investigate whether LMs satisfy this property through behavioral and mechanistic analyses. Our results suggest that they encode knowledge in a task-specific manner. Behaviorally, facts acquired on one task frequently fail to co-emerge on others during training. Parameter localization experiments suggest a mechanistic explanation, revealing distinct parameter subsets underlying different tasks for the same fact. Finally, we show that chain-of-thought reasoning draws part of its effectiveness from engaging task-specific parameters beyond those tied to the evaluation task. Our findings suggest that what the model knows and how it is asked are intertwined in parameter space, undermining the "knowledge base" analogy and carrying implications for the reliability and controllability of factual knowledge in LMs.
arXiv:2606.27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets. This creates an activation-dark regime: representation-similarity metrics can be uninformative without assumptions about label-conditioned error geometry, while classical update-geometry metrics are computationally prohibitive at vocabulary scale. We show that, in a shared-output head setting, representation metrics (e.g., CKA) are non-identifiable for transfer; models can share identical representations yet have orthogonal head updates. The key identity is that head Fisher alignment is exactly a cosine between kernel mean embeddings in the joint activation-error space, exposing activation, error, and coupling factors rather than requiring a materialized Fisher matrix. FisherSketch estimates this cosine directly in a single streaming pass, making K=128,256 head Fisher alignment practical with a 16 KB task signature (m=4096) and a 192 KB per-task streaming state, small enough to store next to a model hash, but encoding transfer-relevant update structure. Beyond source selection, the same signatures and marginals provide a diagnostic instrument for studying whether LLM task similarity is driven by activations, errors, or their coupling; shared-parameter and internal-layer validations, together with Llama-3.1-8B verbalizer-shift experiments, show that FisherSketch remains informative when activation similarity cannot distinguish tasks.
arXiv:2606.27291v1 Announce Type: new Abstract: Job-search platforms rely on low-bandwidth query interfaces that often fail to capture the high-dimensional complexity of candidate profiles. We present an end-to-end RLAIF (Reinforcement Learning from AI Feedback) framework to generate \emph{portable} job search queries, terms that abstract away seeker-specific identifiers while preserving generalizable qualifications. This task introduces a highly adversarial reward surface where policy optimization frequently exploits flaws in LLM-as-judge rubrics, resulting in degenerate verbatim-copying behaviors. We conducted comprehensive empirical experiments to isolate the impact of optimization mechanics against structured reward engineering. Our results demonstrate that for critic-free optimizers, performance is overwhelmingly dictated by robust reward shaping, rendering the specific choice of algorithm largely immaterial. While critic-free per-rollout baseline methods (RLOO and REINFORCE++) natively resist reward-hacking, the group-relative advantage normalization in GRPO appears uniquely sensitive to spurious reward signals, making it disproportionately susceptible to exploitation. We show that introducing a deterministic, rule-based reward floor to correct for rewards assigned to verbatim copying mitigates this failure mode, resulting in a substantial $+0.147$ quality improvement on a cross-family evaluation judge. Ultimately, we show that the training-time reward model inflates performance gains by $2.4\times$, confirming that the training success is fundamentally dependent on enforcing reward-shaping disciplines rather than selecting alternative optimizers.
arXiv:2606.27316v1 Announce Type: new Abstract: Verifying the eligibility of securities as collateral is a key responsibility of the German Central Bank. However, manually verifying these assets against legal and financial criteria within lengthy, semi-structured, and often bilingual prospectuses is a resource-intensive task. While previous efforts utilized traditional Named Entity Recognition (NER) for information extraction, these methods can struggle with OCR noise, linguistic variance, and rigid span-based constraints, and the need for manually annotated training data for each relevant annotation type. In this paper, we present the first case study applying Large Language Models (LLMs) to the eligibility examination process, shifting the paradigm toward a generative Information Extraction pipeline. Our approach decomposes the task into extraction, normalization, and interpretation, allowing for greater flexibility in handling noisy text and interleaved German-English content. We further introduce a value-based evaluation methodology using LLM-as-a-judge, which offers a more semantic assessment than location-based metrics. Our results demonstrate that LLM-based systems achieve high precision (up to 91%) in document-level eligibility, exhibiting a conservative operating profile that minimizes false acceptance.
arXiv:2606.27319v1 Announce Type: new Abstract: The push towards expanded ultra-low-power edge computing necessitates hardware capable of operating under extremely strict energy constraints. Traditional Complementary Metal-Oxide-Semiconductor (CMOS) microcontrollers are fundamentally limited in this domain by the von Neumann bottleneck and by the static power leakage inherent to volatile memory. Memristive In-Memory Computing (IMC) offers a promising solution to these inefficiencies by unifying data storage and computation into a single non-volatile component. However, the State of the Art (SoA) predominantly focuses on accelerators designed to be a co-processor for data-intensive computation. This leaves the prospect of standalone, general-purpose IMC microcontroller architectures underexplored. This thesis proposes such an architecture tailored for ultra-low-power edge devices, alongside an instruction set closely derived from the RV32I standard. Using the IMPLY stateful logic paradigm, a complete implementation of the proposed instruction set is provided, and the novel addressing schema required to support computation in the memristive crossbar array is described as well. Then, the energy use and other circuit-level metrics of the proposed architecture are evaluated through simulation and compared against those of traditional microcontrollers. Finally, the functional viability of the design is demonstrated through an application case study, describing how the proposed design could be used in an intelligent environmental sensor node.
arXiv:2606.27334v1 Announce Type: new Abstract: Digital twins have emerged as a promising paradigm for personalized healthcare, enabling modeling of individual behavior and health trajectories. In cognitive health, early detection of Mild Cognitive Impairment (MCI) remains challenging, where language and conversational patterns serve as non-invasive biomarkers. In this work, we propose a language-based digital twin framework that leverages large language models (LLMs) to mimic the conversational behavior of elderly individuals by incorporating stylometric cues and contextual metadata. To evaluate fidelity and cognitive consistency, we introduce a multi-head conditional variational autoencoder (cVAE) that jointly measures reconstruction quality and predicts cognitive scores. Experiments on the I-CONECT dataset show that the digital twin preserves identity-specific characteristics and achieves reconstruction and MoCA prediction errors comparable to real data, while outperforming baseline GPT-generated responses. These results highlight the potential of language-based digital twins as a scalable and non-invasive approach for personalized and continuous cognitive health monitoring.
arXiv:2606.26236v1 Announce Type: cross Abstract: The objective of this paper is to improve radiological gradings measured on MRIs of spines, by resampling scans so that the new view planes are better aligned with the target anatomy than the original sparse images. To this end, we adapt 3D Gaussian Splatting to form a volumetric reconstruction starting from sparse anisotropic MRIs, and imaging planes aligned with the anatomy relevant for clinical evaluation are then sampled and rendered. The novel view plane is optimal for diagnostic radiological grading of the target anatomy, whereas the original MRI is not. The resampled scans are then used to predict ordinal severity grades of localised stenosis conditions in spinal MRIs. We compare our method against Voxel Interpolation resampling, which takes the average of inverse-distance weighted nearest neighbour intensities for each target coordinate. Experiments show that across all stenosis conditions, resampled scans using Gaussian Splatting produce more accurate stenosis gradings compared to the raw scans which do not include the complete anatomy in-plane, as well as images resampled using Voxel Interpolation.
arXiv:2606.26269v1 Announce Type: cross Abstract: Chromium oxide (Cr$_2$O$_3$) is widely considered a $p$-type transparent conducting oxide despite ongoing debate regarding its intrinsic transport character. Here, we resolve this question by computing phonon-limited electron and hole mobilities using the ab initio Boltzmann transport equation. We find that electron mobility systematically exceeds hole mobility over a wide temperature range, demonstrating that Cr$_2$O$_3$ is intrinsically $n$-type. Analysis of scattering mechanisms reveals that scattering with phonons affects electrons and holes similarly, and that the mobility asymmetry originates from the electronic structure, namely the larger effective mass and multi-valley character of the valence band. The intrinsic $n$-type character, combined with moderate hole mobility, enables bipolar transport and revises the role of Cr$_2$O$_3$ in transparent electronics. Additionally, our results on mobility complement previous studies on defect formation indicating that the commonly observed $p$-type behavior is extrinsic. These insights provide a complete chemical-transport paradigm for Cr$_2$O$_3$, re-evaluating its role in functional transparent electronic and magneto-optoelectronic applications
arXiv:2606.26303v1 Announce Type: cross Abstract: Metasurfaces are emerging as a promising platform for photon-pair generation through spontaneous parametric down-conversion, thanks to their compactness, integrability, and intrinsic multifunctionality, which enables the engineering of complex quantum states. However, their full potential remains only partially exploited because the physical mechanisms governing key properties of the generated photon pairs, such as generation efficiency and emission directionality, are not yet fully understood. As a result, metasurface designs and experimental configurations are often optimized through trial-and-error procedures. Here, we theoretically investigate the main mechanisms that control photon-pair generation and detection by studying how different pump configurations and measurement geometries affect the generation efficiency, emission directionality, and collection efficiency of the emitted photon pairs. This framework allows us to interpret existing experimental results and to provide general guidelines for the design of metasurfaces and the choice of experimental configurations in future experiments. Finally, we show that substrate thickness and multilayer configurations represent additional degrees of freedom for quantum metasurface design and can be engineered to enhance the generation efficiency and control the emission directionality, providing a new route for the optimization of photon-pair sources based on metasurfaces.
arXiv:2606.26317v1 Announce Type: cross Abstract: Accurate fault diagnosis of rolling element bearings in rotating machinery is considered essential for ensuring industrial safety and enabling predictive maintenance. Conventional statistical feature-based methods rely on predefined descriptors, whose diagnostic sensitivity is constrained by fixed configurations and limited adaptability across varying fault conditions. Although deep learning approaches offer strong representational capacity, their effectiveness is often restricted by high data requirements and reduced interpretability. In this work, a parametric adaptive feature extraction framework is proposed, in which feature characteristics are learned directly from data rather than being manually specified. Multiple complementary representations are extracted from vibration signals, including absolute features capturing signal energy distribution, signed moment features reflecting waveform asymmetry, and AC-coupled moment features emphasizing dynamic fluctuations, while interactions between multiple sensor channels are modeled through a structured fusion mechanism to enhance fault representation. The proposed approach is evaluated on a benchmark gearbox bearing dataset comprising five health conditions, including normal operation and multiple fault types. Improved classification performance is observed compared to conventional methods, with consistent results under cross-validation, indicating strong generalization capability. Additionally, enhanced feature separability is demonstrated through clearer clustering patterns in low-dimensional projections. The learned representations effectively capture a wide range of signal characteristics, supporting both improved diagnostic performance and practical applicability in industrial monitoring systems.
arXiv:2606.26368v1 Announce Type: cross Abstract: Media over QUIC enables ultra low latency video streaming over QUIC, but its default quality-switching semantics risk introducing playback gaps during periods of network congestion. The in-progress SWITCH specification for MOQ Transport aims to streamline rate adaptation for MoQ. In this work, we characterize the performance of SWITCH-style Adaptive Bitrate (ABR) for both live and time-shifted clients in a Mininet simulated topology. We validate that standard ABR algorithms can be directly applied to time-shifted playback without modification, yielding substantially higher throughput. We demonstrate that a subscriber can experience increased overall throughput after a rebuffering scenario, and we identify focal points for further optimizations of MoQ ABR switching.
arXiv:2606.27113v1 Announce Type: new Abstract: In this paper we study the dynamics of relativistic detonation waves theoretically and numerically. The reaction is physically accounted for by an extra term in the definition of the total energy density and by an additional equation for the evolution of the mass fraction of the reactant, while leaving formally unmodified the equations of mass and energy-momentum conservation. In this way, the Rankine-Hugoniot relations maintain the same formal structure of the inert version. For the numerical solution we use a second order finite volume ALE scheme with TVD reconstruction, where the mesh velocity is chosen equal to the shock speed. We also adopt a locally implicit algorithm for the treatment of potentially stiff reaction source terms that arise in the equation of the reactant. We furthermore propose a particularly efficient algorithm for the conversion from the conserved to the primitive variables, which for the relativistic Euler equations is known to be nontrivial. Following this approach, we can successfully solve the Zel'dovich-von Neumann-Doering profile of a relativistsic detonation wave, up to Lorentz factors of the shock front $\gamma_S\sim 7$. Our analysis allowed us to highlight a new special relativistic effect, which has remained unnoticed so far. While in Newtonian detonations the Zel'dovich pressure jump decreases monotonically with the mass flux through the shock front, in the relativistic case it shows a minimum and then rises monotonically as a function of the mass flux. This may have interesting physical implications on the amount of energy that can be extracted from a relativistic detonation wave.
arXiv:2606.26446v1 Announce Type: cross Abstract: Input convex neural networks (ICNNs) are increasingly used as surrogates for stability indices and embedded as constraints in power-system optimization. This letter clarifies two recurring formulation limitations that can negate ICNN convexity benefits: (i) applying generic Big-$M$ mixed-integer reformulations introduces auxiliary binaries that are unnecessary for enforcing ICNN sublevel constraints; and (ii) reversing the stability inequality transforms a convex sublevel set into a generally nonconvex superlevel set, invalidating global-convergence guarantees of cut-based methods. After clarifying the limitations, we provide (i) an exact LP-based epigraph reformulation for ReLU-ICNNs, (ii) an outer-approximation scheme with global guarantees under the sublevel convention, and (iii) a feasibility-preserving inner-approximation scheme for the superlevel convention, with simulations on IEEE 14- and 118-bus unit commitment instances.
arXiv:2606.26448v1 Announce Type: cross Abstract: Across the sciences, autonomous systems are increasingly being used in closed-loop discovery, proposing new theories and designing and running experiments to test them. This approach is yet to be applied in the field of cognitive science, where the central bottleneck is theory-building: the creative step of turning the accumulated failures of existing models into better ones. Theory generation has remained manual even as data collection, modeling, and experiment design have been automated. We present the Automated Cognitive Scientist (AutoCog), a fully autonomous agentic-AI system that closes this loop. Large-language-model agents advocate competing theories, each expressed as an executable cognitive model, design experiments that best discriminate them, collect behavioral data from participants recruited online, score theories against collected data based on their generative performance, diagnose why they fail, and synthesize a better successor. Repeating this cycle allows them to search the space of theories, models, and experiments. In the domain of decision-making, AutoCog recovered known decision-making strategies from simulated behavior, including unconventional ones, showing that its discoveries are ultimately driven by the data rather than strictly bound by the priors of the underlying language models. When run with human participants, it produced theories that outperformed the established theories it was seeded with and generalized to held-out studies in two different experimental settings. It also surfaced a novel theory of multi-cue decision-making in which choices show diminishing sensitivity to feature values. The distinctive predictions of this theory were confirmed in a preregistered study with new participants. AutoCog demonstrates how an automated discovery system can be used to turn cognitive theory-building into an explicit, executable, and cumulative science.
arXiv:2606.26548v1 Announce Type: cross Abstract: The intrinsic coupling between magnetism and nontrivial band topology in magnetic topological insulators makes external magnetic fields a powerful tool for manipulating topological states. However, conventional magnetic control mechanisms, such as driving magnetic phase transitions or fully reversing magnetization, typically demand large magnetic fields and lack continuous tunability. Here, we establish a symmetry framework for the reversible switching of topological states via continuous in-plane spin rotation, governed by magnetic point group constraints on the Berry curvature distribution. Using a two-dimensional kagome ferromagnetic Chern insulator as a prototype, we demonstrate that a 60{\deg}in-plane magnetization rotation reverses the sign of the Chern number, transitioning through a topologically trivial state. Crucially, micromagnetic simulations confirm that this spin-reorientation-driven switching operates under exceptionally small magnetic fields and on ultrafast timescales. This work provides a highly efficient, low-energy paradigm for the manipulation of topological states.
arXiv:2606.26660v1 Announce Type: cross Abstract: Triangulations, i.e., well-structured decompositions of geometric objects into triangle-like pieces, are central objects in many domains of mathematics and physics. In particular, fine, regular, and star triangulations (FRSTs) of 4D reflexive polytopes give rise to smooth Calabi-Yau threefolds, which are of significant interest in string theory. However, the high dimensionality and combinatorial complexity of triangulations make them particularly challenging to model with classical numerical methods or machine learning. In this work, we show that transformers, equipped with an appropriate encoding scheme, can be effectively trained to representatively generate new FRSTs across a range of polytope sizes. Moreover, these models can also self-improve through retraining on their own output. This opens the door to both concrete applications to the classification of Calabi-Yau manifolds and further research in physics, combinatorics and algebraic geometry.
arXiv:2606.26691v1 Announce Type: cross Abstract: We present CHESS (CHEbyshev pSeudo Spectrum), a Wolfram Language package for high-precision one-dimensional transport of {\epsilon}-factorized differential equations for Feynman master integrals. The solver works with the matrix obtained by pulling a differential one-form to a chosen path. This matrix may be supplied directly, or assembled from constant matrices and precomputed scalar pullbacks of the one-forms. The program combines Chebyshev-Lobatto spectral collocation, sparse matrix assembly, sequential propagation in the {\epsilon}-expansion, and residue-based regularization of spurious regular singular endpoints. Benchmarks for large multi-scale integral families show rapid node convergence and agreement with independent reference data where such data are available. In the fixed local-series comparison used here, the Chebyshev transports also give shorter wall times; the reported process-tree memory usage is comparable for the smaller parallel runs and lower for the largest benchmark system in that comparison.