We present an analysis of pulsar spin noise based on physically-motivated two-component models of spin wandering. We focus on two models, distinguished by their total angular momentum dynamics: a singular, nonstationary model with a diffusive total angular momentum, and a minimal, stationary model anchored on a conserved total angular momentum. We develop scalable Gaussian process methods and, using mock data, show that the two models are fully testable and distinguishable with full-state observations, i.e., simultaneous independent data on the crust and the superfluid rotational states. This paves a path to testing stationarity in pulsar spin noise, potentially achievable with joint continuous gravitational wave observations and radio timing of pulsars. However, robust inferences and predictions are harder to achieve, and depend on the priors and data quality, when only one component is observationally accessible.

Ultrasound computed tomography is emerging as a promising diagnostic imaging tool. 2D geometries suffer from notorious out-of-plane scattering artifacts. Image reconstruction can be achieved with frequency-domain full waveform inversion and it can be further accelerated by randomly phase-encoding the elementary sources. In this manuscript, we extend our previous results for the 2D geometry of a ring-array to the 3D cylindrical geometry of multiple rings. In particular, we consider the cases of an elementary source described by a single array element (quasi-omni-directional transmission), a line source and a focused transmission respectively. With differences in image quality, we prove that a fully randomized frequency-domain inversion in 3D is capable to reconstruct portions of a human breast surrounded by the cylindrical geometry and detect mm-size masses of varying contrast in dense breast, in reasonable computing times, thus opening the concrete possibility to the design of 3D imaging devices with high sensitivity levels. The methods are applicable to multiple tomographic geometries in 3D and, in principle, can be integrated into next generation medical ultrasound scanners.

Accurate stellar parameters underpin much of astrophysics, from exoplanetary systems to Galactic archaeology. For isolated field stars, masses and especially ages are usually inferred from stellar evolution models, yet these inferences depend on the chosen model grid, and the systematic differences between grids can rival the statistical uncertainties of any single pipeline. We present LACHESIS, a Python package that determines stellar masses, radii, and ages from photometry and spectroscopy while explicitly accounting for the systematic uncertainty from the choice of model grid. We interpolate five independent isochrone grids in [Fe/H], log age, and equivalent evolutionary phase conditioned on the data, sample each with nested sampling, and combine the per-grid posteriors by Bayesian model averaging, weighting each grid by its Bayesian evidence. We validate LACHESIS against a benchmark of Kepler asteroseismic dwarfs and subgiants. Masses are recovered with a robust scatter of ~4% and radii to ~2%, with negligible radius bias (<1%) and a small ~3% mass systematic. Age is recovered with a robust scatter of 30% that depends strongly on evolutionary state; the grid-to-grid systematic contributes a ~9% floor, a subdominant but real term that a single-grid fit omits. Model averaging is better calibrated than selecting a single grid: its credible intervals approach nominal coverage once the reference uncertainty is included, and cover near the nominal rate in injection tests even when the generating model lies outside the ensemble. By marginalizing over an ensemble of stellar model grids, LACHESIS folds the choice-of-grid systematic directly into the posterior, so the reported uncertainties no longer reflect only within-grid data noise. This delivers homogeneous, well-characterized masses, radii, and ages for exoplanet hosts and stellar population studies.

We propose a novel approach to state preparation by embracing the full power of open quantum systems. Instead of working with the whole unitary group in $n$ qubits, we identify a small Lie group $G$ in $(n+3)$ qubits. The dimension of its Lie algebra is $\text{poly}(n)$. Every state can be approximated starting from any fixed input state by repeatedly using partial trace and state preparation in the environment alongside group operations. Moreover, we also identify a single (open system magic) interaction Hamiltonian whose unitary group can be combined with open system quantum technology mentioned above to achieve transitivity on the space of all densities. Similarly, we show that all channels on $n$ qubits can be approximated by using a larger environment, achieving channel universality. The interesting small groups we identify are derived from Lie algebras of local Pauli strings and lead to a new landscape of cheap and expensive states, densities, and channels.

Inference-time scaling adapts pretrained diffusion models to new sampling tasks without additional training. Existing methods rely primarily on Monte Carlo sampling with more particles, yet are premised on the pretrained model being exact. In practice, data and training limitations make the model imperfect, and these methods inherit its error. More particles reduce Monte Carlo error but cannot remove the mismatch between the endpoint and the desired target or the error in tracking the prescribed probability path. We introduce the Energy-based Feynman-Kac Corrector (EBFKC), a framework for energy-based diffusion models that corrects these errors on the fly given a reference energy. We first derive Feynman-Kac dynamics that track a prescribed path exactly in the continuous-time population limit even when the model is imperfect, and approximate these dynamics using sequential Monte Carlo with variance-controlling guidance. To remove the endpoint mismatch, we use the pretrained energy as a surrogate along the diffusion path and progressively incorporate the discrepancy between the learned and target terminal energies. Experiments on Gaussian mixture models, particle systems, alanine dipeptide, and alanine tetrapeptide show that our method closely matches target distributions and molecular free-energy profiles under annealing and reward tilting, whereas standard inference-time scaling baselines retain substantial sampling errors.

Hypernetworks have recently shown success in dynamically adapting the parameters of Large Language Models (LLMs) at runtime based on signals such as task descriptions or additional demostrations. Here we ask: how much adaptation signal can be obtained using only the input query to an LLM?. To answer this, we study query-conditioned Hypernetworks for LoRA estimation. Further, we introduce distributional Hypernetworks, able to produce not only point estimates of parameter adaptors, but also a distribution over possible LoRAs. For this we propose a simple end-to-end loss using a differentiable Monte Carlo approximation and explore multiple distribution parametrizations including regression and convex combination variants. Results show that even using the mean of the learned distribution can outperform deterministic hypernetworks. Crucially, the learned distribution enables a different form of test-time scaling: instead of spending additional compute only by sampling more token sequences from a fixed model, we sample weight updates, yielding multiple adapted models for the same query. Performance improves as more weight samples are considered and remains stronger than corresponding token-sampling adaptation baselines. Finally, we find that generated updates can transfer across queries, suggesting that the hypernetwork learns reusable structure in how the model should adapt. Together, these results show that query-conditioned distributions over weight updates can support both adaptation and test-time scaling.

Text, images, and other rich covariates are increasingly compressed into AI-learned representations and then used as controls in causal analysis. We study when this approach is valid and develop a practical framework for causal inference with learned representations. For a broad class of estimands, an imperfect representation distorts the target causal parameter by the product of two representation errors: one in the outcome regression and one in the balancing weight (or Riesz representer). This yields three constructive results. First, cross-fitted double machine learning (DML) provides valid Wald inference for the representation-dependent target. When representation errors are small, the same interval covers the causal parameter, and it can even attain the semiparametric efficiency bound. Second, fold-wise representation learning (or fine-tuning) is compatible with DML inference for the causal parameter. To this end, we develop convex- and star-aggregation pipelines for learning and combining representations. Third, when representation errors are substantial, we can provide interpretable sensitivity regions and root-$n$ inference for their endpoints. In a multi-modal demand application, seven representation-specific estimates and their star aggregate all imply a negative near-unit elasticity for rank-based price response, and the result remains robust over the reported sensitivity grid.

Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter bound knowledge and their susceptibility to hallucinating information. Retrieval Augmented Generation (RAG) addresses these issues by incorporating external retrieval into the generation process, grounding model outputs in verifiable and up to date sources. While prior surveys primarily focus on core RAG architectures and standard pipelines, recent research explores broader challenges and capabilities that extend beyond these foundational designs. This survey provides a consolidated and structured examination of contemporary RAG developments, organizing the field into a four axis taxonomy: improving retrieval efficiency, strengthening robustness and security, supporting user driven and interactive workflows, and enabling multi step or complex reasoning. We formalize key components of the RAG framework and review methods spanning dense and sparse retrieval, fusion strategies, embedding optimizations, and reinforcement learning based retrieval policies, highlighting how these advances influence practical deployment and system design. We also synthesize evaluation practices, domain specific applications, and architectural variants such as Naive, Advanced, and Modular RAG. Finally, we outline persistent challenges related to retrieval quality, reliability, domain adaptation, scalability, and explainability, and identify opportunities for building RAG systems that are more reliable, adaptable, and transparent.

Topology is, by its nature and design, suited to structure that is nonlinear, multiscale, and nonstationary - however, within machine learning, its use remains largely confined to topological data analysis. We advocate that tools from low-dimensional topology which have remained almost exclusively contained within the domain of pure mathematics (such as Morse theory) offer a strong, complementary, and yet virtually unexplored perspective on the hidden structure of data-generating processes and learning tasks built upon them. Here we introduce concepts from cobordism theory and harness tools from discrete Morse theory to improve the performance of graph diffusion models through our pipeline MG-Diff. Further, we derive theoretical guarantees and sufficient conditions so that under a positive decision-gap, the Morse-theoretic tools and their application for induced diffusion guidance are stable under small perturbations. Finally, we illustrate the utility of discrete Morse theory in application to graph diffusion models for spatio-temporal graph forecasting and graph regeneration, and argue that these applications are only a small window into the part of what low-dimensional topology can offer to the field of machine learning.

Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and updating evidence across time and sources to form, revise and justify a patient’s problem representation and a defensible plan. This structured narrative review maps three literatures: medical education assessment instruments, clinical LLM benchmarks published from 2023 onwards, and general-domain methods for evaluating long-form generation. We examine six dimensions: problem representation, temporal synthesis, differential and management reasoning, counterfactual reasoning, calibrated uncertainty, and reasoning faithfulness. Preprints are included and flagged. No single instrument covers all six dimensions. Problem representation and differential or management reasoning are reasonably covered, although reliability varies by instrument and setting. TIMER-Eval targets temporal synthesis, and ER-Reason assesses sequential diagnostic belief updating. Dedicated uncertainty and counterfactual evaluations are emerging, but their applicability to longitudinal free-text reasoning remains limited. Factual completeness is well theorised in general-domain evaluation, with early clinical evidence of important omissions. Faithfulness remains the weakest dimension, with one identified clinical causal-ablation study on multiple-choice questions. Existing tools should be combined through binary rubric items, separate completeness and correctness scores, case-specific importance weighting with non-compensable safety caps, temporal order-consistency checks, and chance-corrected reliability reporting. Further design work is needed for calibrated uncertainty, counterfactual reasoning and faithfulness over longitudinal free-text records. This review provides a design rationale, not a validated instrument.

Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant observations incur substantial token overhead. We introduce PyRUA-Lean, an interactive code-execution framework that couples feedback-driven primitive composition with selective observation: the agent composes classical robot primitives and learned vision-language-action (VLA) policies into Python cells that perform conditional checks and local retries, returning only explicitly requested images and state feedback for replanning. Across 700 simulated task instances from LIBERO-PRO, RoboTwin 2.0, and RoboCasa365, we compare PyRUA-Lean with a tool-calling baseline using the same GPT-6 Astra planner and underlying robot primitives. Under equal LLM-call budgets, PyRUA-Lean increases overall success from 63.1% to 71.7%. On instances solved by both agents, it uses 49% fewer LLM calls and 65% fewer input tokens.

Given oracle access to an unknown unitary $U=e^{iH}$ , the fractional query problem asks how many queries are required to implement a noninteger power $U^t=e^{itH}$, $0<t<1$, when the spectrum is separated from the branch cut by a gap $\delta$. Quantum singular value transformation gives an upper bound of $O\text{\hspace{0.17em}⁣}(\frac{1}{\delta }\log \frac{1}{\epsilon })$ queries for approximation error $\epsilon$. We prove a matching lower bound for arbitrary query algorithms. Our argument reduces any $N$-query circuit to the approximation of $e^{it\theta }$ by a trigonometric polynomial with degree bounded by $O(N)$, together with Remez inequality. This allows us to establish the lower bound of ${\mathrm{\Omega }}_{\tau }\text{\hspace{0.17em}⁣}(\frac{1}{\delta }\log \frac{1}{\epsilon })$. Consequently, the optimal query complexity for fractional query problem is ${\mathrm{\Theta }}_{\tau }\text{\hspace{0.17em}⁣}(\frac{1}{\delta }\log \frac{1}{\epsilon })$, showing that the known QSVT construction is asymptotically optimal. We also give an alternative lower bound proof based on constructing a linear functional that annihilates the approximant space, yielding a ${\mathrm{\Omega }}_{\tau }\text{\hspace{0.17em}⁣}(\log \frac{1}{\epsilon })$ bound uniform to $\delta$.

Universal channel coding enables communication without a complete description of the channel. For classical channels, universal codes can attain both capacity and the optimal high-rate reliability. We show that this compatibility fails for classical-quantum channels in general; that is, the optimal reliability in the channel-aware scenario is not always achievable with universal coding due to the ignorance of the unitary rotation of the output system. We exhibit a family of classical-quantum channels for which one cannot achieve the channel-aware optimal reliability by a fixed coding scheme. We further derive a converse bound on the reliability for unitary-invariant decoders, a natural assumption for the universal coding scheme, that can be strictly smaller than the optimal channel-aware error exponent. Conversely, we construct a channel-independent encoder-decoder pair and establish a universally achievable bound on the reliability that matches this converse bound in the high-rate regime, thereby characterizing the optimal universal reliability. Specifically, the channel-aware and universal exponents are governed by the Petz and sandwiched Rényi divergences, respectively. These divergences coincide for commuting outputs but differ for noncommuting ones, explaining why universality preserves optimal reliability classically but can reduce it quantumly. Our results showcase the fundamental reliability cost of performing the classical-quantum channel coding task universally.

Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of Vision Foundation Models (VFMs) yields semantically rich representations that support diverse future scene understanding tasks. However, existing approaches rely on two-stage pipelines, where VFM features are first compressed using fixed dimensionality reduction (e.g., PCA) or independently trained autoencoders, and a separate predictor is trained on top of the resulting frozen latent space. This decoupling between representation learning and temporal prediction, as well as approaches that apply predictors directly on raw VFM features, provides no guarantee that the latent space is structured for predictable dynamics. In this work, we propose Latent-Foresight, an end-to-end framework that jointly learns a latent tokenizer and a flow-based generative dynamics model, explicitly shaping the representation to support temporal predictability. To enable stable joint optimization, we introduce several key design choices that prevent latent collapse and align reconstruction with generative objectives. Extensive experiments show that our approach learns more temporally coherent latent representations and consistently outperforms two-stage baselines across multiple future scene understanding tasks and prediction horizons, while eliminating separate training stages, including during high-resolution adaptation. We provide the implementation code and model weights at https://github.com/Sta8is/Latent-Foresight

Robotic simulation and virtual reality increasingly require object assets that capture not only visual geometry but also the physical cues underlying tactile and thermal interaction. Existing 3D datasets and reconstruction methods primarily represent object-scale geometry and visual appearance, overlooking microscale surface structure for high-fidelity haptic rendering and transient temperature dynamics for temperature-aware interaction. We present TouchTherm, a framework for constructing simulation-ready visuo-tactile-thermal object assets from real-world objects. For visual and tactile reconstruction, we combine structured-light scanning with multiview normal maps obtained from photometric stereo. The normal maps are registered to the scanned geometry and transformed into tangent space to recover local micro-height fields for optical tactile rendering, while the coarse mesh handles collision detection. For thermal reconstruction, we capture synchronized multiview infrared videos of natural cooling following controlled heating and reconstruct a physics-regularized dynamic thermal field. Experiments on 20 objects show that the reconstructed micro-height fields preserve dominant surface structures and recover higher-frequency details beyond the coarse geometry, while the thermal fields achieve held-out surface-temperature MAEs of 0.465 degrees C and 0.592 degrees C at 30 s and 45 s, respectively. The resulting tactile assets support synthetic-to-real object recognition from tactile observations, while a glove-based VR system demonstrates spatially and temporally varying thermal feedback. These results highlight the potential of TouchTherm for multimodal sensory simulation and temperature-aware virtual interaction.

Few-shot personalization enables large vision–language models (LVLMs) to learn user-specific visual concepts for applications such as personalized retrieval and subject-aware querying. However, it also creates a privacy risk: an adversary can bind a target identity from a few reference images and subsequently detect that identity in new images through natural-language queries. We introduce Anti-Persona, an image-level defense against unauthorized identity binding and recognition in personalized LVLMs. Our key insight is that identity personalization relies on visual features shared across multiple reference images. We aggregate these features into an identity prototype and optimize visually subtle perturbations that disrupt prototype alignment in the vision-encoder space. Spatial smoothing and low-frequency preservation further promote visual fidelity and practical resilience to image compression. The resulting protection does not depend on a specific prompt and supports both proactive anti-personalization and reactive image protection. Experiments on two representative personalized LVLMs demonstrate protection rates of up to $95.0\mathrm{\%}$ while preserving visual fidelity. The method remains stable across prompt variations and evaluated identity-query tasks, and improves black-box transfer under encoder mismatch.

We prove a generalization of Grauert’s higher coherence theorem for a class of curved differential graded (non-commutative) Fréchet algebras. This allows us to extend the Fourier-Mukai calculus to derived categories arising in many new contexts. We then apply it and prove equivalence of derived categories of dual generalized complex tori using a non-commutative version of the Poincaré line bundle. This lays the foundation for categories of generalized complex branes on generalized complex tori. Examples include complex tori, symplectic tori as well as their non-commutative and B-field deformations.

It remains open whether every $K_t$-minor-free graph is $O(t)$-choosable. Postle proved that every $K_t$-minor-free graph has choice number $O(t(\log \log t{)}^6)$. At the end of an earlier version of a paper establishing an $O(t\log \log t)$ bound on the chromatic number of $K_t$-minor-free graphs, Delcourt and Postle remarked that their methods, combined with Postle’s earlier techniques, yield an $O(t(\log \log t{)}^2)$ bound on the choice number. In this paper, we first prove that every $n$-vertex $K_t$-minor-free graph has choice number $O(t\log (2+n\mathrm{/}t))$. Using this bound as a key ingredient, we follow the approach outlined by Delcourt and Postle to prove that every $K_t$-minor-free graph is $O(t\log \log t)$-choosable.

Large language models offer a promising foundation for chemical reasoning, bringing together chemical knowledge and multistep problem solving. Chemical intuition can provide an initial sense of plausible outcomes before the details of a solution are fully worked out. Inspired by how such expectations complement explicit analysis, we study how continuous latent thoughts can be trained to anticipate informative aspects of future solutions without verbalizing every intermediate step. We introduce Latent JEPA, a framework that combines autoregressive learning with joint-embedding prediction of one or more future views. For chemical reasoning, we develop textual and molecular prediction objectives that connect latent thoughts to both subsequent reasoning and molecular outcomes. Experiments on ChemCoTBench show gains in molecular optimization and on several editing and reaction metrics. Representation analyses show that future prediction makes latent thoughts more informative about molecular outcomes and strengthens their correspondence with chemical structure. These findings support abstract future prediction as a learning principle for connecting continuous latent reasoning with scientific outcomes.

In this article, we study the invertibility of matrices of the form $A+EDF$, where $A$ and $D$ are square matrices over a unital, not necessarily commutative, ring and $A$ is singular. Under natural hypotheses on kernels and images, we prove that $A+EDF$ is invertible if and only if $D$ is invertible, and obtain an explicit formula for the inverse of $A+EDF$ by purely algebraic methods. When the coefficient ring is stably finite, or more specifically a field, we obtain an invertibility criterion under weaker hypotheses. Our results extend and sharpen a theorem of Eriksson and Nordqvist for complex matrices.

Ransomware has emerged as a major cybersecurity threat, with incidents increasing in frequency and impact across critical sectors. These attacks are typically launched through phishing emails, malicious downloads, or exploitation of software vulnerabilities to gain system access. Once inside, the malware encrypts files and demands a ransom, often in cryptocurrency, for the decryption key. Conventional detection methods often struggle with novel or scarce samples, leaving systems vulnerable. To address these challenges, this paper proposes a hybrid deep learning framework that combines an Autoencoder Feature Extractor (AFE) with a Model Agnostic Meta Learning (MAML) classifier for few shot malware detection. The AFE generates compact latent features that reduce noise and dimensionality, while the MAML classifier rapidly adapts to new threats using limited labeled data. Experiments conducted on the Ransomware Dataset 2024 demonstrate the effectiveness of the framework in binary classification tasks. Across one to fifty shot settings, the proposed model consistently achieves high accuracy, F1 score, and Matthews Correlation Coefficient values, maintaining reliable classification even under extreme scarcity. These results highlight the model’s robustness and effectiveness in adapting to limited data scenarios, demonstrating the potential of combining feature extraction with meta learning to enhance resilience against malware, particularly in sectors such as healthcare, manufacturing, and public infrastructure, where cyberattacks can cause significant operational and financial disruption.

Sparse expert activation reduces MoE models’ computation, yet expert weights can exceed limited device memory. Offloading makes inference feasible on a compact AI appliance but exposes host-to-device transfers to the inference path. We present MoE-CORE, a system that coordinates expert offloading and residency for memory-constrained MoE inference. It stages complete expert layers in alternating buffers during prefill. During decode, it combines nonuniform layer-wise cache capacity, domain-informed initialization, routing-history-aware replacement, and cross-layer prefetching. The main configuration executes router-selected experts exactly; an optional score-based substitution path handles eligible low-score misses. The main comparison uses 1K- and 128-token output caps for MoE-CORE and vLLM Prefetch, respectively. Across five workloads per model, MoE-CORE records a mean time per output token (TPOT) of 38.0-44.8 ms versus 1268.9-1269.1 ms for the evaluated vLLM Prefetch configuration on DeepSeek-V4-Flash-W4A8; the corresponding values on GLM-5.2-W4A8C8 are 206.6-220.5 and 5941.5-5941.8 ms. Under an 84-GB NPU-memory cap, the best measured DeepSeek GSM8K configuration achieves a TPOT of 21.5 ms with approximate expert substitution and multi-token prediction (MTP) at depth 2. These results support coordinated expert residency and transfer scheduling under a device-memory constraint. The code is here.

Top-two algorithms are simple and effective for fixed-confidence best-arm identification, but their sharp non-asymptotic behavior is still not well understood. We study this problem for Bernoulli bandits through $\beta$-EB-TCI, the empirical-best top-two rule of Jourdan et al., whose challenger is chosen using a Bernoulli transportation cost with a logarithmic count penalty. We prove that, after the empirical leader has become the true best arm and its sampling fraction stays close to $\beta$, the stopping time is $T_{\beta }^{\star }(\mu )\log (1\mathrm{/}\delta )$ up to lower-order concentration terms. We also show that, in this regime, every challenger is sampled linearly often. Thus, for the original algorithm without forced exploration, the main remaining difficulty is to control when the empirical leader becomes permanently correct. These results imply a non-asymptotic high-probability bound for all Bernoulli instances with a unique best arm. If the algorithm satisfies a finite-mean sufficient-exploration condition, the bound further yields the sharp expected sample complexity. In particular, this gives the sharp expectation result for the unguarded Bernoulli rule when all arm means are pairwise distinct, using the sufficient-exploration result of Jourdan et al. Finally, if we add a mild forced-exploration rule that contributes only $O(\sqrt{Kt})$ pulls up to time $t$, we obtain a self-contained expected sample-complexity theorem for any number of arms under the unique-best-arm assumption. We also identify a limitation of proof strategies that try to handle equal suboptimal means through a single index-comparison argument.

In one-shot training-free voice conversion (VC), the source and reference utterances may contain different linguistic content, so reliable frame-level correspondence between them cannot be assumed. We propose StateVC, which jointly defines a common set of local regions from pooled frame-level WavLM representations of the source and reference utterances; we refer to these regions as states. These shared states are obtained by fitting a pair-specific Gaussian mixture model to the pooled representations, without explicit source–reference frame matching. Within each state, StateVC estimates a source-to-reference mean shift in the original WavLM space. Source-frame posterior probabilities then combine the state-specific shifts so that different frames can receive different local updates. For the LibriSpeech one-shot protocol, StateVC achieves the lowest word error rate (WER) and character error rate (CER) among the evaluated systems, at 8.01% and 3.22%, respectively, with a speaker similarity (SIM) of 0.9512. It also achieves the highest mean perceived speaker similarity among the evaluated systems and the highest mean naturalness among the evaluated training-free systems.