Papers

We study conformalized quantile regression and conformalized median regression that fit a model on one block of a time series and calibrate the conformal interval on the adjacent block. The existing theory of conformal prediction for time series rests largely on mixing conditions, which are hard to verify from a time-series model and fail for many standard processes, including simple ones with short memory. We replace this theoretical toolbox with the functional dependence measure, which in principle accommodates long-memory observations. The accuracy of the conformal interval length for time series has been understudied. To the best of our knowledge, this paper is the first work that establishes non-asymptotic coverage guarantees and accuracy of interval length simultaneously for split conformal regression on time series. Furthermore, for Gaussian linear processes with long memory, where both the estimation of the center and its calibration converge slowly, we establish a sharper rate for the length error. We show that the calibrated length converges faster than the estimated center itself, and provide a matching lower bound for the usual centers when the calibration block is sufficiently large relative to the training block. To our knowledge, this is the first theoretical analysis of conformal interval length dedicated to long memory.

In-context learning offers an appealing approach to adapt automatic speech recognition (ASR) models to new speakers, accents, and domains by providing speech-text pairs as demonstrations at inference time. Recent work shows that some LLM-based speech models are capable of ASR in-context adaptation, when providing interleaved speech-text demonstrations. In this work, we ask whether in-context adaptation is an inherent ability for all encoder-decoder models. We study two forms of demonstration, collated and interleaved demonstration, across six encoder-decoder models, spanning conventional cross-attention-based and LLM-based architectures. We find that all tested models are able to perform in-context adaptation out of the box, achieving up to 30% relative improvement in the oracle experiments and up to 23% using first-pass hypotheses. Through controlled experiments on three English datasets, we show that lexical and speaker information both contribute to successful adaptation. While interleaved demonstration is effective in certain cases, collated demonstration brings consistent adaptation across the board. Our results suggest that in-context adaptation for ASR is not unique to specific architectures, training, or demonstration approaches.

Open access publishing has moved much of the cost of scholarly communication from readers to authors, while the labor of peer review remains unpaid and unevenly shared. This paper describes the design of Quorum: An Open Journal of Information Technology (jquorum.org), a journal that charges neither readers nor authors and uses peer review as its currency instead. Every first complete review a scholar writes on a manuscript earns one credit, and one credit pays for one submission. Each manuscript receives three double-blind reviews from reviewers matched automatically by expertise, and editorial decisions follow published rules rather than editor discretion. The paper documents the credit ledger, a bootstrapping mechanism called the genesis block, a reviewer search that widens after seven days and opens the paper to volunteers, the decision rules, and the integrity safeguards. An agent-based simulation, run for two simulated years with 40 replications per scenario, evaluates these choices. Without the genesis block, no paper was submitted in any replication. With it, a community growing from 40 to about 330 members submitted about 603 papers, and papers waited a median of 7 days for a full review panel. The day-7 escalation had a modest effect in a large community but a decisive one in a small community of about 60 members, where removing it left 48.8% of papers without a panel after 60 days, compared with 4.6% with it. Unspent credits also accumulated to about 3.7 per member after two years, which points to a policy choice the journal will face as it grows.

We present an interactive computational framework for exploring the torus parametrization of the one-dimensional Fibonacci quasicrystal and its local hull. While cut-and-project schemes and Fourier analysis of local functions have been actively explored, a purely algebraic treatment still requires deeper geometric intuition regarding the underlying dynamical systems to advance these methods further. We develop an open-source interactive Python/Jupyter tool that links coordinates in the fundamental domain of the embedding lattice directly to the physical tiling and word generation, offering a transparent visual analysis of translation orbits and singular boundary cases. The tool is the basis for our further computational work, and it can also be used in teaching and to illustrate the geometry of the local hull.

A pair of photons entering a Hong-Ou-Mandel interferometer will bunch or anti-bunch depending on the symmetry of their state in the measured degree of freedom, resulting in constructive or destructive interference. For photon pairs generated through spontaneous parametric down-conversion, this symmetry can be engineered through linear transformations and projections applied to the photon pairs, or by tailoring the pump field. Here, we adopt the latter approach to demonstrate that the pump's parity affects the shape and frequency of the transition from constructive to destructive interference. We demonstrate this concept theoretically and experimentally using a rotating structured pump mode encoded in the Hermite-Gaussian and Laguerre-Gaussian bases. In the former case, we show that the transition exhibits a rich structure unique to the mode family, resulting in enhanced sensitivity as the mode order increases. In the latter case, we demonstrate, as with NOON states, an integer enhancement in angular resolution by a factor proportional to the orbital angular momentum content, thereby opening the possibility of Hong-Ou-Mandel-enhanced rotation sensing.

This manuscript is an English translation and extended version of a paper originally published in Japanese(otomo 2021) Recent years have seen a rapid expansion in applying satellite remote sensing and big data to economic analysis. In particular, satellite-observed nighttime light intensity has proven to be closely correlated with key socio-economic indicators, including gross domestic product, employment rates, population density, and educational attainment across countries. In this paper, I first outline the methodology for calculating regional nightlight intensity across Japanese prefectures and municipalities. Next, to evaluate the versatility of nightlight data, I examine the relationship between city-level nightlight intensity and various public socio-economic metrics, using Japan as a case study. The findings suggest that nightlight intensity can serve as a effective proxy for these diverse indicators. Finally, I explore the potential of nightlight data for enabling rapid economic impact assessments during sudden social disruptions, such as the COVID-19 pandemic.

This study investigates the feasibility of coexistence between an incumbent fixed service (FS) and a 6G network in the same location under spectrum sharing. For coexistence to be possible, a protection criterion must be met. Regulatory agencies define this criterion as the ratio of inter-network interference to noise at the FS receiver. Simulation results indicate that this coexistence is not possible without the implementation of some interference mitigation strategy. To this end, a distance-based protection zoning and two user selection strategies were investigated from the fixed service perspective, assuming the 6G network is in uplink. The results indicate that meeting the protection criterion can be achieved when only few users in uplink are selected, while still providing optimistic capacity performance for such selected users in the shared band.

This manuscript is an English translation and extended version of a paper originally published in Japanese (2022). Driven by remarkable advances in remote sensing and big data processing, spatial technologies are increasingly leveraged in economic research. While satellite nighttime light intensity is widely recognized for tracking macroeconomic parameters - such as regional GDP, employment, and population - less attention has been paid to fine-grained spatial processing methodologies for local tourism economies. This study first details a raster processing technique applied to nightlight imagery. It then focuses on Yuzawa Town (Uonuma District, Niigata Prefecture), analyzing the local economy and sports/tourist attractions. Specifically, I investigate the spatio-temporal relationships between tourist arrivals and various local statistical datasets. Furthermore, this paper highlights how nightlight data can capture intra-municipal economic dynamics that remain undetectable through standard macroeconomic indicators.

We study Riesz and reverse Riesz inequalities for the fractional powers of the Laplacian $\Delta$ on the unbounded Vicsek set. The space carries its Hausdorff measure $m$. The gradient $\partial$ is a weak gradient defined on the skeleton, and it is measured with respect to a length measure $\nu$ that is singular with respect to $m$. The relevant fractional order for the Riesz inequalities is not $1/2$ but $\gamma_{p}=\frac{d_f+p-1}{pd_w}$, where $d_f=\log_{3}5$ and $d_w=d_f+1$. For $p\in[1,2]$, we prove the weak-type reverse Riesz inequality $\|(-\Delta)^{\gamma_p}f\|_{L^{p,\infty}(m)}\lesssim\|\partial f\|_{L^p(\nu)}$. The corresponding strong estimate fails for $1\le p<2$, whereas the weak estimate fails for $2<p<\infty$, even after heat regularization. For the Riesz transform $\mathcal{R}_p=\partial(-\Delta)^{-\gamma_p}$, we show that $\mathcal{R}_1$ is not of weak type $(1,1)$ but that $\mathcal{R}_p$ is bounded from $L^p(m)$ to $L^{p,\infty}(\nu)$ for $p\in(1,2)$, and from $L^{p,1}(m)$ to $L^p(\nu)$ for $p\in(2,\infty)$. However, if $p \ge 1$, $\mathcal{R}_p$ is bounded from $L^p(m)$ to $L^p(\nu)$ only for $p=2$.

Recovering hidden transport mechanisms from sparse spatiotemporal observations is a fundamental inverse problem in scientific machine learning. In brain tracer imaging, dynamic contrast-enhanced MRI (DCE-MRI) provides time-resolved measurements of tracer concentration, while the underlying velocity and source mechanisms governing tracer propagation remain unobserved. We formulate this problem as physics-informed latent-state inference, in which the transport field itself is the primary object of inference rather than an auxiliary variable used only to reconstruct observed densities. We propose Physics-Informed Neural Optimal Mass Transport (PI-NOMT), a framework that represents density, velocity, and source as continuous neural fields and combines a continuous neural density teacher, recursive differentiable advection–diffusion–source rollout, unbalanced optimal-transport regularization, and governing-equation supervision. Physical laws act as structural priors that constrain the space of admissible transport mechanisms, while observed tracer dynamics provide evidence for estimating the latent transport state. We evaluate PI-NOMT on a synthetic benchmark with known ground-truth transport and on DCE-MRI sequences from nine control rats. On the synthetic benchmark, PI-NOMT accurately recovers the prescribed velocity field, including its magnitude, direction, and integrated trajectories, rather than merely reconstructing endpoint densities. Across the nine rat datasets, the framework yields sub-percent local endpoint error, consistent physical speed scales, and low post-training PDE and incompressibility residuals. These results support physics-informed latent-state inference as a general framework for recovering hidden transport mechanisms from observed dynamic scalar fields.

We continue the study of selection principles in the uncountable setting initiated in [18] and further developed in [1]. We investigate several problems posed in [1] concerning the Scheepers diagram, the $\kappa$-Hurewicz Conjecture, and related questions on $\kappa$-Menger and $K_\kappa$-spaces. We determine the Scheepers diagram in the uncountable setting up to three unresolved implications and compute the critical cardinalities of several properties occurring in the diagram. For weakly compact $\kappa$, we show that there is a model of ZFC in which the $\kappa$-Hurewicz Conjecture fails; in particular, it cannot hold under GCH at $\kappa$. Moreover, any model in which $\kappa$ is weakly compact and the $\kappa$-Hurewicz Conjecture holds must satisfy $2^{\mathfrak{b}_\kappa} = 2^\kappa$. We also study the existence of $\mathfrak{b}_\kappa$-scale sets which are $K_\kappa$-spaces and derive a necessary tree-theoretic condition for such an example. Under the additional assumption of the Perfect Subtree Property, no $\mathfrak{b}_\kappa$-scale set is a $K_\kappa$-space. Consequently, under this assumption, every $\mathfrak{b}_\kappa$-scale set yields an alternative example of a $\kappa$-Menger space which is not a $K_\kappa$-space.

Self-evolving vision-language models train on questions they generate from unlabeled images. Since these questions have no gold answers, prior methods label them by majority vote over sampled answers or by a model judge. In a human evaluation, we find that 24% of majority-vote labels and 18% of model-judge labels produced during self-evolution are wrong. To address this problem, we present Verifiable QA Generation for Self-Evolving Models (VQS), which changes how the model judges answers. Instead of voting on an answer, the model parses each image into a structured record, such as a scene graph, a chart table, or a diagram graph. Fixed programs then write a question from the record and compute its answer. The model still acts as a visual checker, but it only confirms the individual facts the program reads, one short claim at a time. These claim-level checks select the parser's training targets, so the parser also improves without labels. Human raters find 94% of VQS answers correct, against 76% for majority voting. Across ten benchmarks, VQS improves Qwen3-VL by up to 3.18 points at the 2B, 4B, and 8B scales and outperforms the strongest self-evolving baseline at each. Gains keep growing over three training rounds, reaching 3.84 points at 2B. Code is released at https://github.com/ahmedheakl/VQS

Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically construct complex perception-planning pipelines or introduce world models that explicitly predict future states, resulting in a complex system architecture. Inspired by the transferability of general-purpose visual representations, we argue that combining sufficiently strong visual representations with representation world modeling can support effective planning without relying on complex inference-time auxiliary modules. Based on this insight, we present ReDrive, an end-to-end driving framework that strengthens planning-oriented visual features via future representation prediction. To achieve this, ReDrive adopts a three-stage training pipeline consisting of driving video pretraining, joint world-modeling and planning training, and planner adaptation. This yields a strong planning-oriented representation and a high-performance planner, while requiring neither auxiliary perception modules nor future prediction at inference time. Experiments on NAVSIM demonstrate strong performance, achieving 91.0 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2. These results show that shaping representations with world modeling is sufficient to enable high-performance end-to-end planning while retaining a simple encoder-planner inference pipeline.

Target-speaker automatic speech recognition (TS-ASR) aims to recognize a designated speaker while suppressing interfering speech in multi-talker environments. Conventional TS-ASR typically relies on an enrollment utterance, whereas text-guided methods use known lexical content, such as a wake word, to identify the target speaker from the observed mixture. These two cues provide complementary information but are usually studied separately. We propose a Unified Dual-Cue TS-ASR framework that supports text cues, enrollment speech, or both within a single model. Text cues interact with the mixture representation to extract target-speaker information conditioned on known lexical content, while an independent enrollment utterance provides complementary speaker information. Cross-attention cue-conditioning modules are integrated into shared Conformer blocks, and negative-cue sampling provides cue-validity supervision during dual-cue training. Experiments on 30,000 two-speaker mixtures across five recording/domain conditions and four oracle text-cue lengths show that, with five-character text cues, the concatenated dual-cue method achieves 8.80% CER, compared with 17.32% for text-only and 29.06% for enrollment-only inference. It also outperforms parallel dual-cue fusion (9.49% CER) and yields lower dual-cue CER across all five evaluation subsets. These results demonstrate the benefit of jointly exploiting complementary lexical and speaker information for target-speaker ASR.

Mean-field control barrier functions (MF-CBFs) enforce swarm safety through constraints on the agents' distribution. Previous formulations, including applications to stochastic coverage and shepherding, use first-order differential inequalities. These cannot directly enforce constraints whose barrier functions yield control-free first derivatives. Thus, we develop the theory of higher-order MF-CBFs, which ensures the positivity of the barrier functionals through higher-order differential inequalities, as in their finite-dimensional analogs. More specifically, we introduce the notion of relative degree for mean-field safety functionals and develop an analytic framework for computing their higher-order derivatives. Moreover, for practical examples of cross-correlation and self-correlation functionals, we show that repeated differentiation along mean-field dynamics is structure-preserving and reduces to kernel recursions. As an illustration, we apply higher-order MF-CBFs to double-integrator swarm tracking and avoidance problems, where position-only constraints lead to MF-CBFs of relative degree two.

Contextualization, the core operation of language modeling, transmits information across words to build sentence-specific word representations. Prior works mainly study contextualization, focusing on individual words and attention heads as a growing discrete dictionary, lacking a global view of their general behavior. Therefore, we propose a general principle: Globally, we find and estimate that different words carry different amounts of information, and less-informative words tend to absorb more contextual information. Specifically, these low-information words do not absorb contextual words uniformly, and finer-grained selectivity enables more precise routing to promote information transmission between matched words. Moreover, to find what mechanism causes such processing, we reinterpret attention heads as channels gated by their singular vectors and find that: (1) these singular vectors point to the hidden states of more informative words, allowing such words to write their information to others more strongly to act as information sources, and vice versa; and (2) these singular vectors can be viewed equally as hidden state features, enabling automated interpretation of attention heads beyond prior heuristic head discovery, also embedding heads into a continuous space rather than treating them as discrete, independent dictionary entries.

This paper revisits the 1996 article Internet and Enterprise Strategy and assesses how its propositions were confirmed, transformed, or contradicted as digital connectivity evolved into an AI-enabled enterprise environment by 2026. The reassessment combines historical interpretation with a structured comparison of Internet-enabled capabilities, industry structure, value-chain transformation, platform intermediation, cybersecurity, data governance, artificial intelligence, and digital sovereignty. The analysis shows that the article correctly anticipated the strategic relevance of electronic markets, cybermediaries, transaction security, online communities, and internal rules for Internet use. However, the contemporary Internet exceeds the original framing: it is now a platformized, data-intensive, cloud-dependent, regulated, geopolitically contested, and increasingly AI-mediated environment. The paper argues that this progression from connectivity to AI-enabled enterprise systems does not replace Internet strategy; it extends it. For many firms, enterprise strategy is now enacted through digital infrastructures, algorithmic coordination, ecosystem participation, and governance capabilities.

Cross-modality MRI synthesis using deep learning can streamline clinical workflows, compensate for missing image contrasts, and reduce examination time; however, existing methods often require substantial computational resources, limiting their practical accessibility. To address this limitation, we propose and investigate a lightweight yet effective framework, termed the Dual-path Adaptive Fusion Network (DAFNet), for T1-to-T2 images synthesis. DAFNet is based on cGAN (conditional generative adversarial networks) structure, and the generator employs a dual-path encoder that adaptively combines depth-wise separable convolutions and dilated convolutions to capture both fine-grained details and broader contextual features. A novel Dual-path Adaptive Fusion Module (DAFM) is introduced to dynamically combine these feature streams through channel-wise complementary weighting, enabling efficient and adaptive feature integration. This fusion mechanism is further applied to the final skip connection to enhance reconstruction fidelity, while the decoder adopts a standard transposed convolution architecture. Coupled with a conventional conditional GAN discriminator, the proposed model maintains low computational complexity while improving perceptual image fidelity. Experimental results demonstrate that DAFNet achieves superior performance compared with baseline U-Net and conventional cGAN models, reaching a peak signal-to-noise ratio (PSNR) of 26.43 dB while significantly reducing model size. This result indicates that DAFNet provides an effective balance between synthesis fidelity and computational efficiency, making it a promising solution for deployment on standard computing hardware and for broader clinical and research applications in MRI contrast synthesis.

Large language model (LLM) agents increasingly undertake extreme-long (xlong) horizon tasks, where a single execution can span hours, hundreds of model–environment interactions, and nearly 1M tokens per rollout. Applying online reinforcement learning (RL) to such executions poses two fundamental challenges: (1) severe execution variance and prolonged rollout delays cause massive GPU idling; and (2) complex non-linear branching generates massive trajectory redundancy, crippling training efficiency. To address these, we presents QwenGyre, an end-to-end framework for xlong-horizon online RL. QwenGyre elastically reallocates GPUs between rollout and training without interrupting live executions, while its trajectory processor reconstructs branching histories, scores partial progress, and deduplicates redundant paths to bound training costs. Scaled to our flagship model, Qwen~3.8 2.4T, with 700K tokens per rollout, QwenGyre yields a 6.0% absolute gain on NL2RepoBench (52.5% $\to$ 58.5%) in 48 steps. Across our evaluations on diverse domains of training datasets, QwenGyre delivers up to $1.85\times$ and $1.78\times$ speedups over Colocate and Async, respectively.

Cloud computing and high-performance computing (HPC) typically follow different paradigms: cloud services are often orchestrated using Kubernetes, whereas HPC workloads are managed through batch schedulers such as Slurm. Growing demand for shared computational resources increases the need for interoperability between these environments. This study uses Podman as a user-accessible tool to benchmark quantum chemistry software distributed as precompiled executables. Containerized and on-system execution are compared across CPU-optimized builds and multiple compute nodes, without additional network optimizations. The results demonstrate that performance depends on software compilation, startup overhead, and execution configuration. Container preparation can dominate short-task workflows, while long-running calculations require monitoring of computational progress. These findings highlight the importance of workload-specific benchmarking and user-level monitoring when deploying scientific applications in containers on HPC systems.

The proportion mediated (PM), the indirect effect divided by the total effect, is intuitive when direct and indirect effects act in the same direction. Under inconsistent mediation, however, opposing pathways partially cancel, so PM can fall outside the unit interval and becomes unstable as the total effect approaches zero. We propose two complementary effect-scale measures: the mediated magnitude share (MMS), which quantifies the absolute magnitude of an indirect pathway relative to the combined absolute magnitudes of the direct and indirect pathways, and the degree of suppression, which quantifies the fraction of this combined magnitude cancelled by opposing pathways. Both measures are bounded between 0 and 1, and MMS reduces to PM under consistent mediation. We extend both measures to multiple indirect pathways and, through a logarithmic transformation, to binary outcomes on ratio scales. In simulations with continuous and binary outcomes, PM estimates were highly dispersed when the total effect was small relative to the pathway magnitudes, whereas estimates of MMS and the degree of suppression remained bounded. We illustrate the measures using previously published estimates from the Adolescents Training and Learning to Avoid Steroids (ATLAS) program, where PM was $-0.30$, MMS was $0.19$, and the degree of suppression was $0.38$, showing how the two measures describe the relative pathway magnitudes and their cancellation under inconsistent mediation.

Evaluating code data as a single corpus can obscure which types of code data benefit which models and downstream tasks. Effective data selection requires understanding both the benefits of individual categories and whether these benefits persist when categories are combined. We introduce a decompositional lens for studying these effects in LLM post-training. We first decompose an execution-verified code corpus into interpretable categories based on the computational patterns of its solutions. Through controlled fine-tuning experiments, we compare individual categories with a balanced mixture across instruction-tuned models on question answering, mathematics, and code generation. The resulting response maps reveal recurring gains in average question-answering performance, while the same category can improve one model or task and degrade another. The best-performing category also varies with the starting model and target task. We then compose compact mixtures guided by these results and examine whether benefits observed in individual categories persist under joint training. On selected model–task pairs, mixtures whose constituents each improve the target task outperform both their best constituent and full-corpus training while using roughly 10–15% of the full corpus. These exploratory findings illustrate a less is more pattern and highlight how the value of code data in post training depends on which categories are combined for which model and task.

Modeling temporal dependence and uncertainty is central to forecasting with world models. The Visual Bayesian Regression World Model combines visual features, physical histories and known covariates through interpretable regression, within a modular architecture supporting trend, seasonal and cycle dynamics. Visual compression reduces representation dimension, while Bayesian variable selection reduces active regression dimension. Posterior prediction combines forecasts across predictor subsets using their posterior probabilities as weights and accounts for parameter uncertainty and future disturbances. The model forecasts joint visual–physical states recursively and physical targets directly. Across four forecasting tasks spanning object motion, vegetation greenness and solar power, ViBR-WM achieves lower mean overall physical-target error than Temporal Straightening, ConvLSTM, PredRNN and SimVP on every task. Repeated fitting and resampling support these overall gains.

The shipped Laya Typed-Decisions checkpoint, a 421M-parameter ModernBERT-large assessor that answers typed choice/noul/score questions over workflow state, is uniformly under-confident. The signed confidence-accuracy gap is $-0.214$, every occupied reliability bin's accuracy exceeds its confidence, and that sign uniformity collapses every binned ECE variant to the same value, $0.214$. The card frames the risk as over-confidence; the measured direction is the opposite, and the direction decides which way a confidence-gated cascade fails. A single disjointly fitted temperature ($T=0.469$, sharpening) removes most of the miscalibration (held-out ECE $0.204$ to $0.037$) and outperforms the shipped per-option-count table. The frozen selection rule instead chose isotonic regression, which overfit and failed its held-out NLL contrast on both tracks, so hypothesis H2 is not supported. Re-running the released checkpoint on its full official test split reproduces the card's headline accuracy ($0.767$ vs. $0.766$). The retrospective E1 reproduction preceded the analysis freeze; E2-E8 were prospectively preregistered, and 20 of 22 executed confirmatory tests reject under Benjamini-Hochberg FDR at $q=0.05$ (two descoped). The frozen gate beats random escalation but misses its 10% accepted-set error target on both tracks, an exploratory out-of-distribution probe finds no zero-shot transfer (accuracy $0.617$), and every score measures agreement with a synthetic teacher whose self-agreement ceiling ($0.735$) the specialist exceeds. Per-decision predictions, run manifests, and the frozen preregistration are in the ancillary files. The author has no affiliation with the model's publisher, the dataset's publisher, or TypeSafe.

We formalize the smooth three-dimensional Poincaré conjecture, together with the Moise smoothing theorem, yielding the topological three-dimensional Poincaré conjecture. The smooth proof follows the Hamilton–Perelman route through Ricci flow with surgery and finite-time extinction.

A submetric space is a topological space equipped with a continuous metric that generates a metric topology weaker than the original one (e.g., a separable Hilbert space with the weak topology). In this paper, we systematically investigate the compactness-related properties of submetric spaces, which make this class of topological spaces a particularly suitable tool for probabilistic applications. As an illustration, we discuss in detail the compactness of the closure of a càdlàg trajectory taking values in a submetric space.

We study circular-mode optics as a framework for transporting and accelerating intrinsically flat beams while maintaining a round transverse projection in physical space. Motivated by the strong degradation of flat beams under low-energy space-charge forces, we develop a coupled-optics description of circular modes, analyze their formation and preservation, and derive lattice design conditions for conserving canonical angular momentum and coupling phase. These conditions motivate rotationally invariant transport and ring cells based on solenoids, symmetric alternating-gradient structures, and indexed dipoles. We further derive space-charge tune-shift and tune-spread expressions for circular-mode beams in uncoupled and coupled lattices, showing that they preserve the leading-order space-charge behavior of round beams while retaining intrinsic eigenemittance flatness. Particle-in-cell simulations with TRACK and ImpactX confirm the generation, transport, and acceleration of circular-mode beams in representative lattices, including regimes with strong space charge. Circular-mode optics therefore provides a promising route toward high-intensity hadron beams and high-luminosity collider applications.

Riftbound: League of Legends Trading Card Game is a trading card game about capturing and holding locations in a king-of-the-hill style contest. Originally released in China in August of 2025, and later released in the United States in October of 2025, the game has been well received for its depth and complexity. In this paper we demonstrate a facet of this complexity by providing sequences of valid game states which construct Universal Turing machines within the game. Each of these machines are constructed with tournament legal decks at the time of writing and strategies assigned are directed by the game state. We also show that given an appropriate board state the machine may be constructed and the computation may be performed in one game turn.

Large language models are increasingly expected to support diverse chemical reasoning capabilities within a unified model. One approach is to develop specialized capabilities separately and consolidate them through multi-teacher on-policy distillation, but this raises two questions: how should specialization be organized, and how should specialist guidance be integrated? We introduce ChemOPD, which addresses both. We estimate task affinities from supervised fine-tuning gradients and solve a constrained mixed-integer program(MIP) to construct partially overlapping specialist groups. During distillation, we retain a generalist teacher trained on all tasks so that specialist guidance supplements rather than replaces its supervision. Our anchor-residual objective gradually increases the routed specialist's contribution on student-generated responses. On ChemCoTBench, affinity-guided specialization produces task-dependent gains over the generalist teacher and improves several capabilities beyond semantic task grouping. Yet stronger teacher-side performance does not automatically yield stronger students: with the same specialists and routes, anchor-residual OPD improves most reported metrics over specialist-only distillation and realizes a larger share of the available teacher gains. These results highlight specialization and capability integration as connected but distinct design problems in chemical reasoning.

Controlling photon statistics is pivotal to many applications in classical and quantum photonics. While steady-state photon statistics have been widely studied, dynamically manipulating these statistical properties in time remains elusive. Herein, we propose a scheme to actively control photon statistics between bunching and antibunching regimes through quantum interference. Our approach relies on a Raman-coupled cavity-atom system with parametric amplification, where time modulating the detuning of the intermediate state allows us to either deepen the photon blockade or enhance photon bunching. Simultaneous modulation of the cavity and intermediate-state detunings produces antibunching that cannot be achieved under static conditions or by modulating either detuning alone. Because the modulation is periodic, the antibunching reappears at regular time intervals, enabling time-gated photon antibunching under continuous-wave operation at a repetition rate determined by the modulation frequency. These results show a versatile mechanism based on Raman-assisted quantum interference for dynamically engineering photon correlations.