arXiv:2605.19371v1 Announce Type: new
Abstract: Diffusion models are widely used in image generation, with most relying on noise-based corruption and denoising. A distinct branch instead uses blur as the main corruption, preserving better color budgets and multi-scale detail by providing multi-scale priors. However, blur-based models remain in SDE-based frameworks and are not integrated into ODE-based frameworks, such as Flow Matching (FM). Meanwhile, in the blur-based formulation, the classical inverse heat-dissipation (IHD) process faces an ill-posed challenge. Moreover, under the data-manifold assumption, regressing blurred images from high-dimensional noise (or velocity) space is also difficult. We propose Heat Dissipation Flow Matching (HDFM), which introduces a continuous blurred (heat-dissipation) process into FM to inject multi-scale priors. HDFM aligns an interpolated heat-dissipation path to address ill-posedness and adopts $x$-prediction to mitigate high-dimensional regression difficulty. Toy experiments and ablation studies show that HDFM consistently benefits from both blur and $x$-prediction. The performance of HDFM outperforms most baseline methods on all datasets.
Science Journals
arXiv:2605.19928v1 Announce Type: new
Abstract: Counterfactual Regret Minimization (CFR) is the dominant algorithmic family for solving large imperfect-information games, underpinning breakthroughs such as Libratus and Pluribus in No-Limit Texas Hold'em poker. In real-time game-playing systems, the solver must compute a near-equilibrium strategy within a strict time budget of only a few seconds per decision, and the number of CFR iterations completed in this window directly determines play strength. We present \textbf{Parallel CFR}, the first parallelization framework for real-time depth-limited CFR solving that seamlessly integrates pruning, abstraction, and advanced CFR variants. We decompose each CFR iteration into a pipeline of seven stages and identify two orthogonal dimensions of parallelism: \emph{by information set} and \emph{by tree node}. Leaf node evaluation is offloaded to GPUs via batched neural network inference, creating a heterogeneous CPU--GPU pipeline. Experiments on Heads-Up No-Limit Texas Hold'em demonstrate that Parallel CFR achieves $3.3$--$3.4\times$ speedup over the single-threaded baseline on postflop streets, with per-iteration time of ${\sim}47$--$54$~ms on a depth-limited game tree with over $1$ billion histories. All experiments run on a single desktop-class device (NVIDIA DGX Spark), enabling hundreds of CFR iterations within a typical real-time decision budget without requiring datacenter-scale infrastructure.
arXiv:2605.18618v2 Announce Type: replace
Abstract: Constrained machine learning enables fairness-aware training, physics-informed neural networks, and integration of symbolic domain knowledge into statistical models. Despite its practical importance, no general method exists for the non-convex, non-smooth, stochastic setting that arises naturally in deep learning. We propose the Stochastic Penalty-Barrier Method (SPBM), which extends classical penalty and barrier methods to this setting via exponential dual averaging, a stabilized penalty schedule, and the Moreau envelope to handle non-smoothness. Experiments across multiple settings show that SPBM matches or outperforms existing constrained optimization baselines while incurring only linear runtime overhead compared to unconstrained Adam for up to 10,000 constraints.
arXiv:2605.19203v1 Announce Type: new
Abstract: This paper presents a customized weighing unit developed for the Tsinghua tabletop Kibble balance. The system is based on a flexure hinge mechanism sourced from a commercial weighing cell, with a major modification to the feedback control loop. The redesigned loop incorporates a capacitive displacement sensor for high-resolution position detection and a novel PID control strategy that ensures both fast dynamic response and high static stability. Initial characterization results demonstrate a repeatability better than 0.1 mg in air for 1 kg mass exchanges, validating the system's potential for high-accuracy mass metrology in Kibble balances.
arXiv:2605.18929v1 Announce Type: new
Abstract: The NESSA (Neutron Source in Uppsala) facility hosts a compact 14 MeV deuterium-tritium sealed tube neutron generator at the {\AA}ngstr\"om Laboratory, Uppsala University. The generator, housed in a bunker inside the FREIA hall, reaches a maximum yield of $4.7\times10^{8}$ n/s. This paper describes the facility: the generator, the bunker and its shielding, the detector systems, and the Monte Carlo models used to characterize the neutron field. We also report the first commissioning measurements: yield calibration with $^{93}$Nb activation foils, fission chamber response at two positions, and simulated air and structural activation. Initial indium foil activations and single event effect (SEE) tests on silicon devices are also presented. The facility will be used for nuclear data measurements, neutron detector response studies, moderation and thermalization experiments, irradiation testing of electronics as well as for training and education.
arXiv:2605.18769v1 Announce Type: new
Abstract: Personalized Retrieval-Augmented Generation (RAG) relies on accurately selecting user-relevant documents. In practice, existing RAG approaches often suffer from high retrieval costs and overlook that collaborative signals from similar users can enhance personalized generation for the current user. We propose ClusterRAG, a Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation. ClusterRAG represents users through their profile documents, organizes users into semantically coherent clusters using density-based clustering, and performs retrieval at both the cluster and document levels via cluster-level similarity and fine-grained ranking. Extensive experiments on the LaMP benchmark demonstrate that jointly leveraging the target user's profile and profiles from top similar users consistently yields the best performance across diverse tasks. Further analysis shows that ClusterRAG integrates seamlessly with different dense retrievers and rankers, and remains effective when paired with both fine-tuned and zero-shot language models.
arXiv:2303.09838v4 Announce Type: replace
Abstract: Battery models generally fall into two categories: physics-based models and ECM models. Physics-based Doyle-Fuller-Newman (DFN) models can accurately simulate the battery internal electrochemical processes, but to properly account for thermal effects requires a strong coupling between a DFN model and a 3D thermal model, which is computationally unaffordable. Distributed Equivalent Circuit Network (ECN) models can perform simulations with high speed and reasonable accuracy. However, these models rely heavily on the characterisation experiments for ECN parameter identification, which is resource-intensive and can lead to inaccurate parametrisation outcomes due to internal thermal inhomogeneity. To harness the strengths of both models, we propose a computational framework to integrate electrochemical DFN model and 3D distributed ECN model together. Using this framework, we simulate constant current discharge experiments of Kokam 7.5 Ah pouch cell (Model SLPB75106100) and compare the simulations with the commonly-used lumped DFN-thermal model. The computational model outperforms the lumped DFN model at low-temperature and/or high C-rate scenarios significantly. The largest predicting error of the framework at 3 C-rate &Tam = 25oC and at 1 C-rate &Tam = 0 oC is approximately 1/3 of that for DFN model. At 3 C-rate &Tam = 5oC, the difference between these two can rise to 377 mV. By integrating DFN and 3D-distributed ECN together, the computational framework can simulate the complicated interplay between electrochemistry, thermal process, and electricity within a cell fast and accurately. We anticipate this computational framework to be a valuable toolset to assist researchers and engineers in the design and control of Li-ion batteries.
arXiv:2605.19050v1 Announce Type: new
Abstract: Generating stable molecular conformations typically forces a tradeoff between the physical realism of energy-based relaxation and the sampling efficiency of data-driven generative models. While machine learning force fields (MLFFs) can sample stable conformations by relaxing molecular geometries according to physical forces, they require costly ab-initio training data. Conversely, diffusion models (DMs) learn from equilibrium data alone but are dependent on noise schedules and time-step conditioning. In this work, we propose generative pseudo-force fields (GPFFs) to bridge these paradigms by training an MLFF on a quadratic pseudo-potential energy surface relative to reference equilibrium structures. Because no ab-initio calculations are required for the perturbed geometries, non-equilibrium training data can be generated on the fly by perturbing the equilibria with Gaussian noise. We show that GPFFs constitute a time-step-agnostic variant of variance exploding DMs: the score comes from the predicted pseudo-forces but because force magnitudes implicitly encode the noise level, no time-step conditioning is needed. Our GPFF can hence be used as a drop-in replacement in standard diffusion sampling (ancestral, Heun) but also facilitates more efficient, adaptive variants and an MLFF inspired direct denoising scheme. Our proposed sampling algorithms support arbitrary structural priors and geometric constraints. On QM9, GPFF has 100 % validity at 256 neural function evaluations (NFE) and over 50 % at just 6 NFE, outperforming diffusion baselines across all samplers. Combined with custom priors, we showcase the fast and accurate generation process of our method in a molecular editor for a drug design setting, where a molecule is generated in real time.
arXiv:2605.19053v1 Announce Type: new
Abstract: This paper proposes a channel estimation method for Multiple-Input Multiple-Output (MIMO) systems based on Canonical Polyadic (CP) decomposition applied to a mode-factorized tensor representation of the channel. The proposed approach reshapes the original low-order channel tensor into a higher-order tensor by factorizing its modes into multiple virtual modes, thereby introducing additional dimensions. By exploiting the sparse structure of MIMO channels and the plane-wave propagation model in the far-field regime, the proposed mode tensorization enhances the separability of individual propagation paths. It is shown that increasing the number of tensor modes improves component separation and provides inherent denoising effects. Building on these properties, a mode-tensorized CP decomposition (MTCPD) algorithm is developed. In addition, a metric for analyzing the virtual factors obtained from MTCPD is proposed, enabling estimation of the canonical rank and selection of the most informative components contributing to overall system performance. Numerical results demonstrate that the proposed method improves channel estimation accuracy compared to conventional tensor-based approaches, particularly under low signal-to-noise ratio conditions.
arXiv:2510.14933v3 Announce Type: replace-cross
Abstract: Electric dipole moment (EDM) measurements using paramagnetic molecules have significantly advanced over the last decade. Traditionally, these experiments have been analyzed in terms of the electron EDM. However, paramagnetic molecules are also sensitive to hadronic sources of charge-parity (CP) violation, highlighting the need for a new framework to interpret the experimental results. In this Letter, we introduce an effective field theory framework to relate molecular EDMs to the EDMs of neutrons and protons. We identify the dominant contributions through power counting and pinpoint the necessary nuclear matrix elements. As a practical application, we employ the nuclear shell model to calculate these nuclear matrix elements for the polar molecule BaF. Finally, we estimate the limits on the nucleon EDMs set by current molecular EDM experiments.
arXiv:2511.18420v3 Announce Type: replace
Abstract: Function-correcting codes (FCCs) are designed to provide error protection for the value of a function computed on the data. Existing work typically focuses solely on protecting the function value and not the underlying data. In this work, we propose a general framework that offers protection for both the data and the function values. Since protecting the data inherently contributes to protecting the function value, we focus on scenarios where the function value requires stronger protection than the data itself. We first introduce a more general approach and a framework for function-correcting codes that incorporates data protection along with protection of function values. A two-step construction procedure for such codes is proposed, and bounds on the optimal redundancy of general FCCs with data protection are reported. Using these results, we exhibit examples that show that data protection can be added to existing FCCs without increasing redundancy. Using our two-step construction procedure, we present explicit constructions of FCCs with data protection for specific families of functions, such as locally bounded functions and the Hamming weight function. We associate a graph called minimum-distance graph to a code and use it to show that perfect codes and maximum distance separable (MDS) codes cannot provide additional protection to function values over and above the amount of protection for data for any function. Then we focus on linear FCCs and provide some results for linear functions, leveraging their inherent structural properties. To the best of our knowledge, this is the first instance of FCCs with a linear structure. Finally, we generalize the Plotkin and Hamming bounds well known in classical error-correcting coding theory to FCCs with data protection.
arXiv:2605.19055v1 Announce Type: new
Abstract: The non-redundancy (NRD) of a constraint satisfaction problem (CSP) is a combinatorial quantity closely tied to the behavior of CSPs in various computational models including their sparsification, kernelization, and streaming complexity. A primary open question in the study of non-redundancy is the identification of which CSP predicates have near-linear NRD. Recent works by Carbonnel [CP 2022], Khanna, Putterman and Sudan [STOC 2025], Brakensiek and Guruswami [STOC 2025] and Brakensiek, Guruswami, Jansen, Lagerkvist, and Wahlstr\"om [2025] have introduced various forms of gadget reductions between CSPs to relate their non-redundancy.
The primary contribution of this work is to recontextualize many of these gadget reductions in a framework which we call hypergraph projections. By studying a quantity we call the shrinking factor of these hypergraph projections, we can more precisely predict when a gadget reduction between predicates can yield a super-linear NRD lower bound, greatly improving on the analysis of previous works. To illustrate the power of our framework, we identify some concrete CSP predicates whose non-redundancy is at the cusp of our understanding and show how our methods give lower bounds that could not have been achieved with these previous methods. We also demonstrate how these gadget reductions can be automatically deduced using SAT solvers, thereby opening up novel computational avenues for discovering further relationships between the non-redundancy of various CSPs.
arXiv:2405.18179v2 Announce Type: replace
Abstract: This article rethinks the role of arts in STEAM education, emphasizing its importance in AI literacy within K-12 contexts. Arguing against the marginalization of arts, the paper is structured around four key domains: language studies, philosophy, social studies, and visual arts. Each section addresses critical AI-related phenomena and provides pedagogical strate-gies for effective integration into STEAM education. Language studies focus on media representations and the probabilistic nature of AI language models. The philosophy section examines anthropomorphism, ethics, and the misconstrued human-like capabilities of AI. Social studies discuss AI's societal impacts, biases, and ethical considerations in data prac-tices. Visual arts explore the implications of generative AI on artistic processes and intellec-tual property. The article concludes by advocating for a robust inclusion of arts in STEAM to foster a holistic, equitable, and sustainable understanding of AI, ultimately inspiring technologies that promote fairness and creativity.
arXiv:2511.04830v2 Announce Type: replace
Abstract: We investigate a two-state conformational conversion system and introduce a novel structure-preserving numerical scheme that couples a local discontinuous Galerkin space discretization with the backward Euler time-integration method. The model is first reformulated in terms of auxiliary variables involving suitable nonlinear transformations, which allow us to enforce positivity and boundedness at the numerical level. Then, we prove a discrete entropy-stability inequality, which we use to show the existence of discrete solutions, as well as to establish the convergence of the scheme by means of some discrete compactness arguments. As a by-product of the theoretical analysis, we also prove the existence of global weak solutions satisfying the system's physical bounds. Numerical results validate the theoretical results and assess the capabilities of the proposed method in practice.
arXiv:2605.17635v2 Announce Type: replace-cross
Abstract: A fast simulation of the detector response is a vital task in high-energy physics (HEP). Traditional Monte-Carlo methods form the backbone of modern particle physics simulation software but are computationally expensive. We present a machine-learning-based approach to fast simulation of the Focusing Aerogel Ring Imaging Cherenkov (FARICH) detector response. Given a particle track and momentum, the goal is to generate realistic samples of photon hits on the detector matrix. We propose a conditional Generative Adversarial Network (cGAN) with a lightweight convolutional architecture that reproduces the projected detector response conditioned on particle parameters. We compare the cGAN against a linear statistical baseline using metrics applied to probability maps and to the reconstructed velocity distributions. The cGAN produces realistic samples and provides a significant speed-up over Monte-Carlo simulation.
arXiv:2605.18792v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge conflicts when retrieved contextual knowledge (CK) and parametric knowledge (PK) disagree or are both unreliable. Existing approaches mainly coordinate which source to use, without explicitly asking whether each answer path is correct. We argue that faithful RAG requires LLM self-awareness, namely the ability to recognize the limits of its own knowledge and reasoning. To ground this problem, we construct a model-specific, ground-truth-aligned knowledge-conflict benchmark by evaluating LLM backbones on PK-only and CK-conditioned answer paths over approximately 69K query-context instances per backbone, drawn from five conflict-QA datasets. We then introduce SABER, a Self-Aware Belief Estimator for RAG that requires no LLM fine-tuning. SABER combines a self-prior with PK-side and CK-side conditional reasoning representations from multi-trace inference, then estimates reliability beliefs with two lightweight predictors to drive a 4-cell decision over trust PK, trust CK, trust either, or abstain. Across four LLM backbones, SABER improves end-to-end accuracy and conflict-specific faithfulness over ten inference-time and fine-tuning baselines, with the largest gains on conflict-heavy datasets. Under abstention, SABER's risk-coverage curve Pareto-dominates every prompt-based abstainer, providing a tunable balance between coverage and answer risk. Our code is available at https://github.com/xizhu1022/SABER.
arXiv:2605.18758v1 Announce Type: new
Abstract: Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requires agents to process transient audio cues and temporal video dynamics that are tightly coupled with the moment of action. To bridge this gap, we introduce OmniGUI, the first step-level benchmark designed to evaluate GUI agents in omni-modal smartphone environments. OmniGUI provides continuous, interleaved multimodal inputs comprising static images, synchronous audio, and video clips at every action step. The dataset encompasses 709 expert-demonstrated episodes (2,579 action steps) across 29 applications, systematically annotated with objective multimodal dependency levels. Because dedicated omni-modal GUI agent frameworks are currently in their nascent stage, we select foundational omni-modal models capable of natively processing interleaved inputs to serve as agent proxies for our initial baselines. Our empirical evaluation reveals that while current models exhibit competency on visually static tasks, their action prediction performance degrades significantly in environments requiring synchronous temporal and auditory signals. Furthermore, ablation studies isolate specific operational bottlenecks, notably cross-modal interference when processing task-irrelevant environmental noise. The complete dataset, evaluation pipeline, and baseline prompts are provided in the supplementary material. Project page: https://omni-gui.github.io.
arXiv:2605.19141v1 Announce Type: new
Abstract: Large language models are increasingly deployed as automated judges to evaluate the strength of arguments. As this role expands, their legitimacy depends on consistency, transparency, and the ability to separate argumentative structure from rhetorical appeal. However, we show that holistic judging - a common LLM-as-a-Judge practice where a model provides a global verdict on a debate - suffers from substantial inter-model disagreement. We argue that this instability arises from collapsing a debate's complex interaction structure into a single opaque score. To address this, we propose GRASP (Gradual Ranking with Attacks and Support Propagation), a deterministic framework that aggregates stable local interaction judgments into a global ranking via a convergent attack--defense propagation operator. We show that local interaction judgments are more reproducible than holistic rankings in LLM-as-a-Judge evaluations, allowing GRASP to produce more consistent global rankings. We further show that GRASP scores do not correlate with human "convincingness" labels, highlighting a vital sociotechnical distinction: GRASP does not measure persuasion, factuality, or rhetorical appeal, but structural sufficiency - a defense-aware notion of argument robustness over the explicit interaction graph. Overall, GRASP offers a transparent and auditable alternative to holistic LLM judging.
arXiv:2605.18923v1 Announce Type: cross
Abstract: Accurate selection of bovine embryos is a challenging task, as current practice relies on a single expert assessment on the seventh day after insemination, resulting in high rates of pregnancy loss. Time-lapse videomicroscopy provides detailed information on early development, but is difficult to exploit because of complex motion patterns and time-consuming analysis. We propose TransFACT, a transformer-based framework for modeling early developmental stages and embryo transferability using 2D time-lapse videos from the first four days of development. TransFACT combines frame-level temporal features with stage-level representations, using developmental stages as auxiliary supervision to predict transferability on day four. Our experiments demonstrate that TransFACT, by leveraging an existing method designed for action recognition, achieves superior performance than its competitor in predicting embryo transferability.
arXiv:2510.25348v2 Announce Type: replace
Abstract: Information cascade popularity prediction is a key problem in analyzing content diffusion in social networks. However, current related works suffer from three critical limitations: (1) temporal leakage in current evaluation--random cascade-based splits allow models to access future information, yielding unrealistic results; (2) feature-poor datasets that lack downstream conversion signals (e.g., likes, comments, or purchases), which limits more practical applications; (3) computational inefficiency of complex graph-based methods that require days of training for marginal gains. We systematically address these challenges from three perspectives: task setup, dataset construction, and model design. First, we propose a time-ordered splitting strategy that chronologically partitions data into consecutive windows, ensuring models are evaluated on genuine forecasting tasks without future information leakage. Second, we introduce Taoke, a large-scale e-commerce cascade dataset featuring rich promoter/product attributes and ground-truth purchase conversions--capturing the complete diffusion lifecycle from promotion to monetization. Third, we develop CasTemp, a lightweight framework that efficiently models cascade dynamics through temporal walks, Jaccard-based neighbor selection for inter-cascade dependencies, and GRU-based encoding with time-aware attention. Under leak-free evaluation, CasTemp achieves state-of-the-art performance across four datasets with orders-of-magnitude speedup. Notably, it excels at predicting second-stage popularity conversions--a practical task critical for real-world applications.
arXiv:2512.07068v3 Announce Type: replace
Abstract: Uniform Meaning Representation (UMR) is a novel graph-based semantic representation which captures the core meaning of a text, with flexibility incorporated into the annotation schema such that the breadth of the world's languages can be annotated (including low-resource languages). While UMR shows promise in enabling language documentation, improving low-resource language technologies, and adding interpretability, the downstream applications of UMR can only be fully explored when text-to-UMR parsers enable the automatic large-scale production of accurate UMR graphs at test time. Prior work on text-to-UMR parsing is limited to date. In this paper, we introduce two methods for English text-to-UMR parsing, one of which fine-tunes existing parsers for Abstract Meaning Representation and the other, which leverages a converter from Universal Dependencies, using prior work as a baseline. Our best-performing model, which we call SETUP, achieves an AnCast score of 84 and a SMATCH++ score of 91, indicating substantial gains towards automatic UMR parsing.
arXiv:2605.19341v1 Announce Type: new
Abstract: Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across summarization, question answering, retrieval-augmented generation, and agentic interaction. This fragmentation makes it unclear whether a mitigation that works in one setting reduces hallucinations across contexts. Current benchmarks either require human annotation and fixed references that may be memorized, or rely on observations in settings that are difficult to reproduce. To study root causes, we introduce HalluWorld, an extensible benchmark grounded in an explicit reference-world formulation: a model hallucinates when it produces an observable claim that is false with respect to this world. Building on this view, we construct synthetic and semi-synthetic environments in which the reference world is fully specified, the model's view is controlled, and hallucination labels are generated automatically. HalluWorld spans gridworlds, chess, and realistic terminal tasks, enabling controlled variation of world complexity, observability, temporal change, and source-conflict policy, and disentangling hallucinations into fine-grained error categories. We evaluate frontier and open-weight language models across these settings and find consistent patterns: perceptual hallucination on directly observed information is near-solved for frontier models, while multi-step state tracking and causal forward simulation remain difficult and are not generally solved by extended thinking. In the terminal setting, models also struggle with when to abstain. The uneven profile of failures across probe types and domains suggests that hallucinations arise from distinct failure modes rather than a single capability. Our results suggest that controlled reference worlds offer a scalable and reproducible path toward measuring and reducing hallucinations in modern language models.
arXiv:2605.19509v1 Announce Type: new
Abstract: In recent years, large underwater telescopes have been designed and realized to measure high energy neutrinos from astrophysical objects. Muon tracks produced by the neutrino interaction in the surrounding medium are reconstructed from the arrival time and the number of photo-electrons of the Cherenkov light measured by the Photomultiplier tubes (PMT) array of the detector. For a correct reconstruction procedure, both the scattering of the light in the water and the late and after pulses produced in the PMTs must be considered. In this paper we report on this latter effect which has been measured in our laboratory using a laser in the single photoelectron mode (SPE) on a Hamamatsu R7081MOD 10" PMT with a high quantum efficiency photocathode. The PMT voltage supply was set to provide the 1 photo-electron peak at 10 pC as during normal operation: in this condition we find that the late-pulse contribution is small but not negligible.
arXiv:2605.19888v1 Announce Type: new
Abstract: Gel-elastomer composites, comprising an active swellable hydrogel and a passive elastomer, are a compelling class of programmable material systems (PMS) capable of shape morphing under multiphysics actuation. The precise design of the topology and material distribution unlocks complex programmability instrumental in wearable electronics, soft robots, and drug delivery; however, the structure-function relationship is highly non-intuitive, rendering both trial-and-error and conventional design approaches largely intractable. To address this, we present a topology optimization (TO) framework for the automated design of such structures, enabling systematic exploration of the design space for target functionalities realized via programmable shape morphing. In particular, we propose a multi-material TO framework that concurrently optimizes the structural topology and the spatial distribution of the gel-elastomer phases. The design is represented via a coordinate-based neural network, and the mechanical response of both phases is described within a unified constitutive framework based on the Flory-Rehner theory. Furthermore, we present an end-to-end differentiable design framework with implicit differentiation that accommodates various objective functions, constraints, and discretizations. We demonstrate the framework on shape-programming structures and soft actuators. The framework is further validated through the design of organogel-hydrogel composites for multi-stimuli responsiveness across chemically distinct solvent environments, and of anisotropic hydrogels wherein the local fiber orientation is optimized concurrently with the topology. The codebase implemented in JAX is publicly shared to support benchmarking and reproducibility.
arXiv:2605.19169v1 Announce Type: new
Abstract: We use discrete-event simulation to quantify the impact of fiber latency on the efficacy of geo-distributed AI model training with data parallelism. We conclude that the optimum distances between two AI clusters is 10-100km, over which hollow-core fiber enables 25% higher compute-communication overlap.