arXiv:2605.28025v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used to provide public-facing health information, yet existing safety evaluations overlook whether responses preserve comparable medical information across different user phrasings of the same question. To address this, we introduce the Medical Information Response Audit (MIRA), a bilingual, controlled benchmark that assesses whether LLMs provide comparable medical information across user-side language, register, and health literacy signals. MIRA contains 4,320 prompts built from 60 medically reviewed, low-risk health questions. Across five mainstream LLMs, models answered all medical questions, but responses to low health-literacy signals consistently omitted more key information, provided fewer concrete next steps, and offered less support for independent judgment. We term this pattern Differential Information Dilution (DID). Language effects are model-specific rather than uniformly worse for non-English prompts. A comparison with 300 real-world health queries provides preliminary evidence of rank-order validity. A knowledge-guided mitigation prompt reduces information dilution for most models, with the largest reductions in underinformative simplification observed for Claude (~8%) and Qwen (~6%).
Science Journals
arXiv:2605.27842v1 Announce Type: new
Abstract: In this paper, we propose a spectral framework that embeds 1D and 2D quasiperiodic Helmholtz eigenvalue problems into higher-dimensional (2D and 4D) periodic spaces via the projection method \cite{jiang2014numerical, jiang2024numerical}. To effectively map the elevated high-dimensional states back to the original physical space, we establish a novel validation framework based on the weighted expectation of pointwise Rayleigh quotients. Supported by comprehensive error and spectral analysis, we demonstrate that the eigenvalues derived from this expectation align more authentically with the original quasiperiodic model, ultimately yielding a more appropriate and reliable eigenpair solution. Numerical experiments on continuous media demonstrate that our approach offers an accurate, robust, and scalable tool for solving quasiperiodic Helmholtz eigenvalue problems.
arXiv:2605.28098v1 Announce Type: new
Abstract: Multi-agent systems are increasingly deployed to support various tasks where agents interact to achieve individual and collective objectives. Although these systems can enhance task performance and decision-making, fairness preservation through bias reduction remains challenging. This study examines how agent-level biases shift and impact system-wide fairness. We use prompts to expose individual agents to group-favoring bias, then assess downstream impacts at the system level. To quantify the impact, we propose Favor Bias Strength (FBS), a zero-centered metric that decomposes bias alteration between favored-group uplift and disfavored-group suppression. Using multiple agent designs, benchmarks, and up-to-date large language models, we show that agents endowed with bias can substantially affect system-wide fairness. Interestingly, when agents are exposed to bias uniformly, the system-wide bias elevates, even exceeding the additive sum of the individual agents' biases. The empirical evidence underscores the criticality of fairness in multi-agent systems, which warrants further analyses and empirical tests.
arXiv:2603.02097v5 Announce Type: replace
Abstract: Open-ended medical LLM evaluation remains weakly grounded in physician-calibrated coverage of clinically relevant response criteria, especially in localized clinical settings. We introduce \textsc{ClinConsensus}, a Chinese medical benchmark of 2{,}500 expert-curated cases spanning 36 specialties, 12 task themes, multiple difficulty levels, and lay-facing versus professional-facing settings. Each case is paired with 30 case-specific binary rubric criteria. To evaluate whether responses satisfy enough physician-authored criteria, we propose \emph{Clinician-Anchored Coverage Score} (CACS), a physician-calibrated threshold metric instantiated at \(k=10\), and develop a dual-judge framework combining a GPT-5.1 grader with a physician-supervised Qwen3-8B judge. Evaluating 11 frontier LLMs, we find a persistent coverage gap: Rubric Accuracy ranges from 39.6\% to 52.1\%, whereas CACS@10 ranges from 17.8\% to 32.9\%, leaving a 19.2--21.9 point gap across models. Stratified analyses further reveal substantial variation across reasoning, evidence use, structured extraction, medication instructions, follow-up, and dialogue register. These results suggest that medical LLM evaluation should measure thresholded, rubric-grounded clinical coverage rather than average partial correctness.
arXiv:2605.27734v1 Announce Type: new
Abstract: Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological learners require. An alternative paradigm has emerged in which networks are trained to predict their \emph{own} latent representations of related views or masked regions, as in data2vec and JEPA -- an idea related to predictive-coding accounts of the cortex. Despite strong empirical results, the theoretical understanding of these methods remains limited. Central questions include: by how much does latent prediction actually improve data efficiency? Is there a benefit to stacking such methods into multi-scale hierarchies? We answer both using as data a tractable probabilistic context-free grammar that captures the compositional structure of natural language and images. Such a grammar generates strings of visible tokens by recursively applying production rules along a tree of hidden symbols of depth $L$. For such data, supervised or token-level SSL require a number of samples \emph{exponential} in $L$ to recover the latent tree; we prove that latent prediction achieves this with a number of samples \emph{constant} in $L$, up to logarithmic factors. We confirm this bound with (i) a hierarchical clustering algorithm, (ii) an end-to-end neural network whose predictor-clusterer modules predict their own latents at each level via gradient descent, and (iii) the first sample-complexity analysis of data2vec, which we show implicitly performs hierarchical latent prediction. This suggests that explicit stacking such as H-JEPA is largely redundant.
arXiv:2602.06880v2 Announce Type: replace
Abstract: Adaptive methods like Adam have become the $\textit{de facto}$ standard for large-scale vector and Euclidean optimization due to their coordinate-wise adaptation with a second-order nature. More recently, matrix-based spectral optimizers like Muon (Jordan et al., 2024b) show the power of treating weight matrices as matrices rather than long vectors. Linking these is hard because many natural generalizations are not feasible to implement, and we also cannot simply move the Adam adaptation to the matrix spectrum. To address this, we reformulate the AdaGrad update and decompose it into a variance adaptation term and a scale-invariant term. This decoupling produces $\textbf{DeVA}$ ($\textbf{De}$coupled $\textbf{V}$ariance $\textbf{A}$daptation), a framework that bridges between vector-based variance adaptation and matrix spectral optimization, enabling a seamless transition from Adam to adaptive spectral descent. Extensive experiments across language modeling and image classification demonstrate that DeVA consistently outperforms state-of-the-art methods such as Muon and SOAP (Vyas et al., 2024), reducing token usage by around 6.6\%. Theoretically, we show that the variance adaptation term effectively improves the blockwise smoothness, facilitating faster convergence. Our implementation is available at https://github.com/Tsedao/Decoupled-Variance-Adaptation
arXiv:2602.07574v2 Announce Type: replace
Abstract: Modern multimodal large language models (MLLMs) adopt a unified self-attention design that processes visual and textual tokens at every Transformer layer, incurring substantial computational overhead. In this work, we revisit the necessity of such dense visual processing and show that projected visual embeddings are already well-aligned with the language space, while effective vision-language interaction occurs in only a small subset of layers. Based on these insights, we propose ViCA (Vision-only Cross-Attention), a minimal MLLM architecture in which visual tokens bypass all self-attention and feed-forward layers, interacting with text solely through sparse cross-attention at selected layers. Extensive evaluations across three MLLM backbones, nine multimodal benchmarks, and 26 pruning-based baselines show that ViCA preserves 98% of baseline accuracy while reducing visual-side computation to 4%, consistently achieving superior performance-efficiency trade-offs. Moreover, ViCA provides a regular, hardware-friendly inference pipeline that yields over 3.5x speedup in single-batch inference and over 10x speedup in multi-batch inference, reducing visual grounding to near-zero overhead compared with text-only LLMs. It is also orthogonal to token pruning methods and can be seamlessly combined for further efficiency gains. Our code is available at https://github.com/EIT-NLP/ViCA.
arXiv:2604.17943v2 Announce Type: replace
Abstract: RAG-based question-answering (QA) in specialist domains faces a cold-start problem: lack of evaluative benchmarks and absence of labeled data for post-training. We present DoRA (Domain-oriented RAG Assessment), a novel benchmark construction and evaluation framework using only a small set of specialist domain documents. DoRA systematically generates synthetic QA training and evaluation datasets with auditable evidence across five domain-specific intents. To mitigate same-pipeline circularity, DoRA's training and test splits use different LLM families (Claude Sonnet for training; GPT-4o for test) drawn from disjoint seed-document corpora. Instantiated on 40 defense-related documents (written in English), DoRA yields ~6.6K curated instances. Compared against 8 LLM baselines over a benchmark of 1,259 samples, a LoRA-adapted Llama3.1-8B trained on the synthetic training set consistently improves performance over 6 coverage and faithfulness metrics, especially reducing hallucination by more than half under the default GTE retrieval setting, with gains persisting across alternative retrievers and prompting-based baselines. Defense-domain expertise is incorporated in three stages of our evaluation: (a) determining the quality of the synthetic QA generated by DoRA, (b) ascertaining the reliability of LLM-as-judge scores, and (c) evaluating the generalization of the QA pipeline on completely human-written QA examples. We position DoRA as a practical framework for specialist-domain RAG under domain shift, with defense as a high-stakes case study.
arXiv:2605.28176v1 Announce Type: new
Abstract: Background and objective. Conventional Deep Learning (DL) approaches for Knee Osteoarthritis (KOA) grading rely on one-hot labels, which fail to capture both the ordinal uncertainty of Kellgren--Lawrence (KL) and Calcium Pyrophosphate Deposition Disease (CPPD) severity scores and the asymmetric relationship between the two scales observed in clinical practice.
Methods. We retrospectively collected 2172 knee X-ray images, including 968 radiographs jointly annotated for KL and CPPD severity. An ordinal DL framework based on soft-labelling was developed for both tasks, replacing one-hot targets with unimodal probability distributions centred on the annotated grade. Four formulations were investigated: binomial, beta, triangular, and exponential.
Results. All soft-labelling strategies consistently outperformed the nominal baseline. For CPPD grading, the triangular formulation achieved the highest Quadratic Weighted Kappa (QWK) and the lowest Mean Absolute Error (MAE) (QWK = 0.796; MAE = 0.438), while the beta formulation yielded the most balanced class-wise performance considering Average MAE (AMAE) and Maximum MAE (MMAE) across classes (AMAE = 0.458; MMAE = 0.573). For KL grading, the beta-based approach provided the best overall performance, achieving the highest QWK together with the lowest MAE and class-wise errors (QWK = 0.777; MAE = 0.529; AMAE = 0.523; MMAE = 0.775). Statistical analysis demonstrated significant improvements over conventional one-hot supervision (p < 0.001).
arXiv:2605.28660v1 Announce Type: new
Abstract: This paper studies cryptographic key exchange in satellite communications, which requires specific solutions because the satellite context presents unique challenges, particularly concerning onboard resource constraints and long transmission latency. We address these challenges by considering the Internet Key Exchange (IKE) protocol, which is widely used in terrestrial networks, and studying its applicability in the satellite context. This requires addressing two main issues: i) its efficiency in terms of the resources and bandwidth required to adapt to satellite terminals, and ii) its resistance even to attackers equipped with a quantum computer, in order to resist obsolescence and defend against harvest-now-decrypt-later attacks. We study these aspects from both a design and experimental point of view, defining and assessing some protocol variants characterized by low complexity and quantum resistance. To address the need to manage the transition from classic cryptographic primitives to post-quantum ones, we also consider the possibility of using hybrid cryptographic solutions that combine them both.
arXiv:2605.00435v2 Announce Type: replace
Abstract: Mode collapse is a persistent challenge in generative modeling and appears in autoregressive text generation as behaviors ranging from explicit looping to gradual loss of diversity and premature trajectory convergence. We take a dynamical-systems view and reinterpret mode collapse as reduced state-space accessibility caused by *geometric collapse*: during generation, the model's internal trajectory becomes confined to a low-dimensional region of its representation space. This implies mode collapse is not purely a token-level phenomenon and cannot be reliably solved by symbolic constraints or probability-only decoding heuristics. Guided by this perspective, we propose *Reinforced Mode Regulation* (RMR), a lightweight, online state-space intervention that regulates dominant self-reinforcing directions in the Transformer value cache (implemented as low-rank damping). Across multiple large language models, RMR substantially reduces mode collapse and enables stable generation at extremely low entropy rates (down to 0.8 nats/step), whereas standard decoding typically collapses near 2.0 nats/step.
arXiv:2605.28296v1 Announce Type: new
Abstract: In modern nuclear physics experiments, identifying events of interest is challenging for nuclear reaction studies with the active target Time Projection Chamber (TPC). In this work, machine learning techniques are employed to analyze the complex data of the 12C + 12C fusion reaction from a TPC named MATE (multi-purpose active-target time projection chamber for nuclear experiments). Specifically, we successfully applied Residual Neural Network (ResNet-50, ResNet-34 and ResNet-18) and Visual Geometry Group (VGG-19) to classify elastic scattering and fusion reaction events from the 12C + 12C reaction. The classification results of the four models are nearly identical, with accuracies of approximately 97% for the simulated data and 90% for the experimental data. Moreover, these approaches successfully identify some events that are misclassified by traditional methods. These models are also applied to classify events from different fusion reaction channels, with classification accuracies of approximately 95% on simulated data. In addition, a Convolutional Neural Network (CNN) model is developed to reconstruct the reaction vertex, providing an alternative strategy for vertex reconstruction. These results indicate that machine learning techniques can effectively classify reaction events from different channels and reconstruct the reaction vertex, thereby paving the way for future analyses of complex nuclear reaction data.
arXiv:2605.28355v1 Announce Type: new
Abstract: The boundary between real and diffusion-generated time series is becoming increasingly difficult to draw, yet detection in this domain remains underexplored, especially when the generator is unknown. We compare white-box detection, which requires access to the generator, against black-box detection, which operates on the raw signal alone. The white-box approach, a reconstruction-based detector adapted from the image domain, works well in in-distribution but breaks down under generator shift: reconstruction-based detection in images succeeds because large generic generators provide a near-universal reconstruction prior, and no analogous generator exists for time series. In contrast, a simple off-the-shelf classifier used as a black-box detector performs remarkably well, achieving an average F1 of 79.2, a 22.1% relative improvement over the white-box approach, and a TPR@1%FPR of 57.2. Diffusion-generated time series detection is therefore not a direct transfer of the image domain problem. This work provides the first systematic exploration of white-box and black-box detection for diffusion-generated time series. We close by identifying several open and promising directions.
arXiv:2605.28135v1 Announce Type: cross
Abstract: Fluid simulations, especially at high Reynolds numbers, are computationally expensive on classical computers, making them promising application targets for quantum computing. Recent studies have combined the lattice Boltzmann method (LBM) with Carleman linearization to design quantum algorithms for computational fluid dynamics (CFD). However, practical quantum-circuit implementations of these algorithms that incorporate non-periodic boundary conditions have not been fully explored. In this work, we implement a quantum algorithm for two-dimensional linearized fluid flow around an obstacle, using block-encoding of the linear-system matrix and quantum singular value transformation (QSVT) to solve it. Inflow, outflow, and no-slip boundary conditions are formulated as sparse matrix operations and efficiently embedded into quantum circuits using index-value encoding. We demonstrate logarithmic scaling of the required numbers of qubits and gates with respect to the number of lattice points, suggesting the potential feasibility of quantum-computational fluid dynamics simulations.
Drain-Vortex Optimization: A Population-Based Metaheuristic Inspired by Multi-Drain Free-Vortex Flow
arXiv:2605.08883v2 Announce Type: replace
Abstract: This paper proposes Drain-Vortex Optimization (DVO), a population-based metaheuristic for continuous optimization. DVO models each candidate solution as a particle moving in a multi-drain vortex field. Its update rule decomposes motion into radial attraction toward selected drain centres and tangential rotation governed by a regularized free-vortex law. A three-phase mechanism switches between far-field exploration, spiral inward motion, and localized core exploitation according to the normalized distance to the assigned drain. The method also uses adaptive spiral exploitation, population-level vortex basin assignment, and optional stochastic basin switching to support structured diversity. DVO is evaluated against PSO, GWO, WOA, SCA, AOA, EO, and SVOA using a calibration--validation protocol. CEC 2022 is used only to select the final DVO configuration, while CEC 2017, classical functions, and five constrained engineering design problems are used for out-of-sample validation. On CEC 2017, DVO achieves the best mean $\log_{10}$ error on 34 of 58 cases and the best Friedman average rank (1.67), and is significantly better than every baseline under Holm-corrected Wilcoxon tests. On CEC 2022, DVO obtains the best Friedman rank (2.13) and is significantly better than five of the seven baselines; the differences against PSO and SVOA are not significant. DVO is less competitive on simple scalable classical functions and on small constrained engineering designs, which clarifies its operating regime. The algorithm is implemented in a vectorized GPU form that executes independent runs in parallel.
arXiv:2605.10325v2 Announce Type: replace
Abstract: Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of large language models (LLMs), but most existing approaches rely on sparse outcome-level feedback. This sparsity creates a credit assignment challenge in long-horizon agentic reasoning: a trajectory may fail despite containing many correct intermediate decisions, or succeed despite containing flawed ones. In this work, we study a class of densely-verifiable agentic reasoning problems, where intermediate actions can be objectively checked by symbolic or algorithmic oracles. We propose Verifiable Process Rewards (VPR), a framework that converts such oracles into dense turn-level supervision for reinforcement learning, and instantiate it in three representative settings: search-based verification for dynamic deduction, constraint-based verification for logical reasoning, and posterior-based verification for probabilistic inference. We further provide a theoretical analysis showing that dense verifier-grounded rewards can improve long-horizon credit assignment by providing more localized learning signals, with the benefit depending on the reliability of the verifier. Empirically, VPR outperforms outcome-level reward and rollout-based process reward baselines across controlled environments, and more importantly, transfers to both general and agentic reasoning benchmarks, suggesting that verifiable process supervision can foster general reasoning skills applicable beyond the training environments. Our results indicate that VPR is a promising approach for enhancing LLM agents whenever reliable intermediate verification is available, while also highlighting its dependence on oracle quality and the open challenge of extending VPR to less structured, open-ended environments.
arXiv:2506.08928v2 Announce Type: replace
Abstract: Tree-based ensembles such as random forests remain the go-to for tabular data over deep learning models due to their prediction performance and computational efficiency. These advantages have led to their widespread deployment in high-stakes domains, where interpretability is essential for ensuring trustworthy predictions. This has motivated the development of popular local feature importance methods such as LIME and TreeSHAP. However, these approaches rely on approximations that ignore the model's internal structure and instead depend on potentially unstable perturbations. These issues are addressed in the global setting by MDI+, a global feature importance method which combines tree-based and linear feature importances by exploiting an equivalence between decision trees and least squares on a transformed node basis. However, the global MDI+ scores are not able to explain predictions when faced with heterogeneous individual characteristics. To address this gap, we propose Local MDI+ (LMDI+), a novel extension of the MDI+ framework that quantifies feature importances for each particular sample. Across twelve real-world benchmark datasets, LMDI+ outperforms existing baselines at identifying instance-specific predictive features, yielding an average 10% improvement in predictive performance when using only the selected features. It further demonstrates greater stability by consistently producing similar instance-level feature importance rankings across repeated model fits with different random seeds. Ablation experiments show that each component of LMDI+ contributes to these gains, and that the improvements extend beyond random forests to gradient boosting models. Finally, we show that LMDI+ enables local interpretability use cases by identifying closely matched counterfactuals for each classification benchmark and discovering homogeneous subgroups in a housing dataset case study.
arXiv:2605.12515v2 Announce Type: replace
Abstract: Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes. While such adaptation is generally desirable, it becomes a critical failure when a user's identity is explicitly defined. For instance, given a fixed British persona and an ambiguous everyday knowledge query about literature, the prompt's language frequently overwrites the system persona -- yielding Shakespeare in English but Cervantes in Spanish. To robustly quantify this Cross-lingual Cultural Inconsistency, we introduce Singleton Fleiss's $\kappa_S$, a metric mathematically resilient to hallucinations. For mitigation, we propose Cross-lingual Cultural Consistent Preference Optimisation (C-3PO), a consensus-driven alignment framework. C-3PO achieves up to a 0.13-point absolute increase in $\kappa_S$ over unaligned models, consistently outperforming strong prompting and representation steering baselines whilst preserving explicit user identities, cultural neutrality and intrinsic cultural knowledge. Empirical evaluations demonstrate this inconsistency disproportionately affects lower-resource languages like Indonesian and Persian. Finally, early decoding of intermediate layers reveals that MLLMs implicitly personalise outputs towards the prompt language's stereotypical culture as forward-pass representations stabilise.
arXiv:2605.12929v2 Announce Type: replace
Abstract: Retinal diagnosis is inherently bilateral: clinicians compare homologous structures across eyes (e.g., optic disc asymmetry), yet most deep models operate on monocular representations. We investigate whether explicit structural correspondence improves diagnosis, and propose Anatomy-Slot to operationalize this hypothesis. Anatomy-Slot introduces an unsupervised anatomical bottleneck by decomposing patch tokens into a set of emergent, structurally-coherent slots that correspond to anatomical regions, then aligning these slots across eyes via bidirectional cross-attention. On ODIR-5K with $n=10$ seeds, the method improves AUC by $4.2$ points over a matched ViT-L baseline (95% CIs; Wilcoxon signed-rank test, $W=0$, $p=0.002$). Pairing disruption and stress testing under Gaussian noise provide controlled tests of correspondence dependence and robustness under corruption. We further report quantitative optic disc grounding on REFUGE and cross-attention localization analysis. Beyond the reported gains, these results indicate that object-centric anatomical correspondence offers a principled path toward interpretable diagnostic systems aligned with clinical bilateral comparison.
arXiv:2605.28360v1 Announce Type: new
Abstract: Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a monolithic, instance-blind string optimized through global edits, producing brittle updates and preventing the reuse of learned sub-behaviors. We propose Prompt Codebooks (PCO), a novel compositional prompt optimization framework that recasts APO as discrete learning over a finite vocabulary of natural-language instincts - atomic, reusable instruction units. PCO organizes prompt-construction knowledge in a discrete codebook and routes each input to a small subset of entries via an LLM-based encoder; a generator composes them into a prompt for the frozen target model; a critic emits a structured verdict that decomposes by attribution into per-variable textual gradients, jointly training the encoder, generator, and codebook under a language-valued min-max objective. The resulting routing is per-instance: different inputs in the same task receive different instinct compositions, a regime structurally inexpressible under instance-blind methods. Across six benchmarks on Qwen3-8B and LLaMA-3.1-8B, PCO improves over zero-shot by up to +30.36 points, surpasses the strongest prior baseline (GEPA) by +3.34 on HotpotQA and +1.11 in aggregate, and reduces deployed prompt length by up to 14.1x versus MIPROv2 and 3.0x versus GEPA using only K=16 instincts.
arXiv:2605.28647v1 Announce Type: new
Abstract: It is well known that LLM guardrails and trained persona dynamics can produce a reality gap: the distance between the world a LLM is permitted or shaped to describe, and the world in which users must act. Here we argue that actively generating reality gaps is in fact unethical because it knowingly shifts epistemic risk back to the uninformed user -- this is reality laundering. This can potentially cause harm when operationalised at scale. The risk is sharpest in high-exposure advice contexts, where users seek orientation rather than a bounded, externally checkable task. Guardrails naively appear ethically necessary when they claim to prevent direct harm, but often become suspect when they suppress truthful perception and launder uncomfortable mechanisms into acceptable abstractions. Basel-style financial regulation, B-BBEE-style compliance, Societe Generale, and the London Whale show how formal safety systems can become legible, gameable, and performative while real exposure migrates elsewhere. The same pattern can appear in LLMs as moral compliance: safe language, distorted reality. We therefore distinguish refusing harm, from refusing reality; and then argue for top-down causal requirements specification at the task level rather than bottom-up moral correction at the response or sandbox level. Persona dynamics matter because the assistant interface is not neutral; it shapes how uncertainty, conflict, authority, and risk are staged. The conclusion is that so-called ``ethical AI'' becomes substantively unethical when it substitutes institutional reassurance for contact with reality.
arXiv:2605.13752v3 Announce Type: replace
Abstract: High-resolution longitudinal phase-space (LPS) diagnostics are essential for X-ray free-electron lasers and advanced accelerators. Conventional radio-frequency transverse deflecting structures (TDSs) provide direct femtosecond-scale LPS measurements, but their substantial RF-power and infrastructure requirements strongly limit their deployment at multi-GeV beam energies. Here, we propose a beam-driven transverse deflecting structure in which a leading driver bunch, separated by one RF bucket from a trailing witness bunch under study, excites long-lived wakefields in a resonant cavity array. By placing the witness bunch near a zero crossing of the wakefield, the bunch experiences an approximately linear time-dependent transverse kick. Electromagnetic simulations of the resonant structure, combined with start-to-end beam-dynamics simulations based on European XFEL parameters at a final beam energy of 14 GeV, demonstrate a temporal resolution of $\sim 1.6$ fs for a 500 pC driver bunch, with a clear scaling toward the sub-femtosecond regime at higher charge.
arXiv:2605.14809v2 Announce Type: replace
Abstract: Graph prompt tuning has shown great potential in graph learning by introducing trainable prompts to enhance the model performance in conventional single-domain scenarios. Recent research has extended graph prompts to improve Graph Foundation Models (GFMs) by few-shot tuning auxiliary prompts. Despite their progress, most existing methods embed source-domain information into prompts, which serve either as input to GFMs or encoded during model pre-training. Such prompt entanglement with specific source domains and GFM pre-training strategy restricts their generalisability to other domains and different GFMs. Furthermore, existing GFM prompts merely rely on few-shot tuning for adaptation, neglecting the rich information in unlabelled target domain test data. Motivated by these insights, this paper aims to empower GFMs with pre-training-agnostic test-time graph prompt tuning, named GFMate. GFMate introduces centroid and layer prompts applied after pre-training on target domains, avoiding entanglement with specific source domains and model pre-training. In addition, a test-time complementary learning objective is devised to exploit both labelled and unlabelled target domain data for effective test-time prompt tuning. Extensive experiments on 12 benchmark datasets demonstrate the superior performance and efficiency of GFMate, achieving improvements of up to 30.63%. Code is available at https://github.com/YanJiangJerry/GFMate.
arXiv:2605.27736v1 Announce Type: new
Abstract: Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along denoising trajectories and in realizing stable value-based optimization. We propose a state-aligned latent actor-critic framework for diffusion post-training, in which the diffusion model serves as its own timestep-conditioned value function and predicts values directly on noisy latent states. This enables trajectory-level PPO training, supports stable actor-critic optimization with simple conditioning and value pretraining strategies, and naturally allows the learned critic to be reused for inference-time steering. We further extend the framework to multi-reward optimization, where joint training with complementary rewards helps alleviate reward hacking. Across both UNet- and DiT-based backbones, our method consistently outperforms prior group-relative RL and actor-critic baselines on single-reward and multi-reward benchmarks, while test-time steering provides additional gains in generation quality.
arXiv:2605.27440v1 Announce Type: new
Abstract: Small changes to how a buyer phrases a question -- "best CRM" vs "top CRM" vs "best CRM for a SaaS startup" -- produce substantially different brand recommendations from AI assistants. Across ~6,000 paraphrase runs and ~6,000 same-prompt rerun controls on OpenAI and Anthropic models, the recommendation-set similarity (Jaccard) between two paraphrases of the same underlying buying intent is 0.288 for cosmetic rewordings (clustered 95% CI [0.215, 0.361]) and 0.135 for constraint-adding rewordings ([0.098, 0.175], pooling region/language and specificity-ladder axes) -- both far below the 0.50-0.61 same-prompt rerun baseline. The prompt string, not the underlying buyer intent, is the dominant input to which brands surface. Increasing reasoning effort does not narrow the gap (bounded by +/-0.05). This is a direct challenge to an increasingly popular AEO/GEO practice. Tracking a brand's "AI visibility" by counting brand mentions over a fixed set of prompts produces a metric whose dominant source of variance is which paraphrase the tracker happens to issue, not the model's behavior toward the brand: the same buyer intent in two natural paraphrases produces recommendation sets that overlap 14-29% in Jaccard versus 50-61% for same-prompt reruns. Sampling more paraphrases per intent reduces the artifact in principle, and efficient multi-prompt evaluation methods exist in the academic literature, but the natural buyer-phrasing space is much larger than the benchmark-scale prompt sets those methods have been validated on, and far beyond what any commercial tracker issues per brand-intent combination. Prompt-by-prompt mention tracking is therefore structurally unstable as a unit of measurement; meaningful improvement likely requires a different unit rather than a larger prompt set.