arXiv:2607.08948v1 Announce Type: new
Abstract: Robotic manipulators excel in structured environments but face substantial challenges in unstructured and dynamic settings. This paper presents SplatCtrl, a unified framework for real-time scene reconstruction and reactive robot motion generation to enable collision-free robotic arm control in previously unseen and continuously changing environments. Building on 3D Gaussian Splatting (3D-GS), we introduce a hybrid voxel-based filtering and dynamic Gaussian relocation strategy that supports efficient scene reconstruction from RGB-D streams while accommodating environmental changes. For safe and reactive control, we further propose a method for deriving continuous signed distance functions from isotropic Gaussians, providing stable and differentiable collision probability estimates that bridge classical distance fields with the modern implicit representation. These continuous distance metrics are incorporated into control barrier functions, resulting in a unified perception-action coupling framework that supports smooth and reliable real-time motion generation in response to scene changes. Experimental validation in simulation, on physical robot, and within shared human-robot workspace demonstrates the framework's effectiveness, achieving integrated scene reconstruction and reactive control in uncertain, and dynamic environments.
Science Journals
arXiv:2508.20134v2 Announce Type: replace
Abstract: Programming quantum circuits at the OpenQASM level is essential for achieving hardware-aware optimization and reliable execution on noisy intermediate-scale quantum (NISQ) devices, yet it remains challenging due to the need for domain-specific planning, iterative code synthesis, and low-level calibration. In this paper, we present QAgent, the first autonomous multi-agent framework for end-to-end OpenQASM code generation. QAgent integrates schema-aware task planning, example- and tool-driven code synthesis, and hardware-aware calibration within a unified planning-synthesis-calibration workflow. The system leverages retrieval-augmented generation (RAG) to access structured kernel knowledge, examples, and backend constraints, and employs coordinated multi-agent reasoning with iterative execution feedback to ensure correctness. We evaluate QAgent on 12 representative quantum kernels and their compositions across five large language models (LLMs). Results show that QAgent improves Pass@1 accuracy by 47-70% on single-kernel tasks and achieves over 88% accuracy on multi-kernel workflows for large models, substantially outperforming existing baselines. Furthermore, under realistic hardware frequency drift, QAgent maintains near-unit execution fidelity through automated calibration, whereas SDK-based LLM methods suffer significant degradation. These results demonstrate that integrating planning, synthesis, and calibration is critical for reliable quantum program generation. The implementation of QAgent is open-sourced at https://github.com/fuzhenxiao/QAgent
arXiv:2607.08970v1 Announce Type: new
Abstract: Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model. We introduce MultiView-Bench, a diagnostic benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension. Unlike existing datasets that focus on pixel-level mapping or camera-relative navigation, MultiView-Bench requires models to decouple object positioning from transient perspectives and ground them in a fixed global coordinate system. This capability serves as a prerequisite for VLMs before being deployed for downstream tasks such as mechanical part assembly. Our systematic evaluation of frontier VLMs reveals consistent failure modes: strong performance on 2D planar relations from a single image, but marked difficulty with 3D spatial relations and with aggregating information across views. We further identify biases in VLMs, such as struggles with unconventional axis directions and sensitivity to object colorways and texture variations. Acknowledging these limitations, we propose ViewNavigator, a multi-agent framework that actively selects informative viewpoints, perceives, and fuses multi-view evidence, improving diverse base models on MultiView-Bench even under a strict budget-matched comparison (and by 3-5x for the full agent).
arXiv:2607.08974v1 Announce Type: new
Abstract: Vision-language-action models (VLAs) inherit semantic capabilities from pretrained VLMs, yet large-scale post-training on robot data and architectural modifications can reshape the backbone so extensively that it becomes difficult to isolate what the VLM contributes to control. Directly converting pretrained VLMs into VLAs with minimal architectural change offers a more transparent path to understanding how VLM capabilities transfer across model scales. The core obstacle is output-distribution mismatch: predicting actions as bare numeric token sequences moves generation away from the VLM's pretrained language distribution, degrading the capabilities we seek to preserve. To address this, we propose CLAP (Causal Language-Action Prediction), which prepends each numeric action sequence with a natural-language action description, causally conditioning precise action-token prediction on a language-action plan without modifying the backbone architecture. With single-epoch fine-tuning alone, 2B CLAP achieves 90.8% on LIBERO (+14.9 pt over VLA-0) and improves robustness on LIBERO-PRO under language, object, and spatial perturbations. We will release CLAP at 0.8B, 2B, and 4B as an open-weight, multi-scale compact VLA family from a single VLM lineage, enabling controlled analysis of VLM-to-VLA capability transfer.
arXiv:2607.08990v1 Announce Type: new
Abstract: Code review is essential for ensuring software quality and supporting collaboration, yet prior work shows that developers can interpret code review comments differently. These differences can hinder effective communication, particularly in collaborative settings. To address this challenge, we explore the potential of personified code review explanations. We report initial findings from an ongoing mixed-methods user study in which developers evaluated persona-aligned review comments across multiple code snippets. Our results suggest that preferences for explanation styles vary across problem-solving styles, experience levels, and roles. Across problem-solving style profiles, developers valued explanatory depth, learning support, practical suggestions, and risk awareness over conciseness, highlighting the need to balance personalization with clarity and trust. Based on these findings, we outline a vision for inclusive, human-centered AI-assisted code review systems that adapt feedback to developers' problem-solving preferences.
arXiv:2607.09011v1 Announce Type: new
Abstract: Exposed documents such as emails, chat threads, tickets, and incident notes routinely leak credentials, but during incident response a leaked secret is only half the story. Responders also need to identify the ``door'' the secret opens: the account, tenant, endpoint, database, cloud resource, or other system that the credential could allow an attacker to access. Traditional secret scanners rely on regular expressions or trained classifiers which work well on well-formatted code, yet they struggle when a credential is fragmented, reformatted, or far from the resource it unlocks, and they report the secret string without naming what it opens. We present Secret Scanner Agent (SSA), a multi-agent large-language-model system that extracts both the secret and its associated door, together with supporting evidence, from unstructured exposed documents. SSA pairs a detection agent that favors recall with a review agent that filters false positives and recovers missing context. Because real credential data is sensitive, we evaluate SSA on synthetic benchmarks we generated that span 23 secret types and multiple document formats, scored with a three-step pipeline of programmatic matching, an LLM judge, and human review. Across six models, multi-agent SSA improves extraction precision over a single-agent variant, with the largest gains on door extraction, by up to 16 percentage points. SSA matches a regular-expression scanner's precision while more than tripling its recall, and against thirteen security analysts it is more precise, recovers nearly twice as many secret--door pairs, and runs five to seventeen times faster. By returning the secret, its door, and supporting evidence in one result, SSA turns credential detection into an actionable finding for triage and remediation.
arXiv:2607.08996v1 Announce Type: new
Abstract: Graph Neural Networks have emerged as a powerful tool for the fast and accurate prediction of various crystal properties. These models often encode domain-specific knowledge into their graph encoding modules, which increases their parameter size and makes their performance heavily dependent on domain expertise. Added to this, explicitly incorporating all chemical and structural features, that might influence a specific crystal property into the GNN encoder, is a challenging task. In this work, we propose a soft prompt learning framework that captures latent features essential for property prediction, which are not explicitly provided to the GNN. We introduce a novel multilevel graph prompt learning framework comprising both node-level and graph-level soft prompts. At the node level, we capture the local chemical semantics of different atom types, while at the graph level, we encode the global structural symmetry of the crystal graph. Our proposed prompt learning framework is lightweight and seamlessly integrates with any existing GNN encoder. Extensive experiments on popular benchmark datasets show that incorporating prompt learning significantly improves (3\% - 15\%) the performance of state-of-the-art GNN models in crystal property prediction tasks. Furthermore, the learned soft prompts enable cross-property knowledge transfer, enhancing prediction performance for properties with limited training data. Code is available at https://github.com/shrimonmuke0202/Prompt.git
arXiv:2607.08997v1 Announce Type: new
Abstract: In this paper we develop the framework of using a parametrized mapping $[\sigma(1), \sigma(2), \cdots, \sigma(n)] \mapsto \sigma(1)z + \sigma(2)z^2 + \cdots \sigma(n)z^n$ to perform runtime analysis on Shellsort. In particular, we show that the worst-case time complexity of Shellsort using Tokuda's gap sequence proposed in 1992 is at least $\Omega(N^{1.26})$ with a generalisation of this result to any strictly decreasing gap sequence where each term at most a fixed distance away from a rational geometric sequence, and we also show that strictly decreasing gap sequences giving worst-case Shellsort time complexities of $O(N \log^c N)$ must have $\Omega(\log N / \log \log N)$ terms of order $\Omega(N / (\log \log N)^c)$.
arXiv:2607.08998v1 Announce Type: new
Abstract: Accurate noise classification is essential for operating near-term quantum processors, yet existing approaches, such as quantum process tomography, scale exponentially with system size, limiting their practicality for routine calibration. We propose a scalable noise fingerprinting pipeline that combines structured classical shadow tomography with physics-informed feature engineering to identify noise channels from a fixed set of 3-qubit probe circuits. Each sample is represented by a 279-dimensional feature vector constructed from randomized Pauli measurements and derived observables, designed to resolve physically similar noise channels that produce overlapping signatures under generic measurement sets. We evaluate three classifiers, i.e., random forest, extra trees, and a multilayer perceptron, on a dataset of 14,000 labeled samples spanning 10 noise types. The random forest classifier achieves the highest test accuracy of 0.8426 with a macro F1 score of 0.8437, outperforming both baselines. Confusion analysis reveals that many noise types are classified with high reliability, with the remaining confusions occurring between channels sharing similar physical decay mechanisms, motivating future work on richer probe states and noise parameter estimation.
arXiv:2604.17267v2 Announce Type: replace
Abstract: Large Language Models can generate synthetic survey responses at low cost, but their accuracy varies unpredictably across questions. We study the design problem of allocating a fixed budget of human respondents across estimation tasks when cheap LLM predictions are available for every task. Our framework combines three components. First, building on Prediction-Powered Inference, we characterize a question-specific rectification difficulty that governs how quickly the estimator's variance decreases with human sample size. Second, we derive a closed-form optimal allocation rule that directs more human labels to tasks where the LLM is least reliable. Third, since rectification difficulty depends on unobserved human responses for new surveys, we propose a meta-learning approach, trained on historical data, that predicts it for entirely new tasks without pilot data. The framework extends to general M-estimation, covering regression coefficients and multinomial logit partworths for conjoint analysis. We validate the framework on two datasets spanning different domains, question types, and LLMs, showing that our approach captures 61-79% of the theoretically attainable efficiency gains, achieving 11.4% and 10.5% MSE reductions without requiring any pilot human data for the target survey.
arXiv:2607.09000v1 Announce Type: new
Abstract: Recent advances in generative modeling have made generated tabular data a practical solution for privacy-sensitive data sharing, where watermarking enables ownership verification. However, existing watermarking methods fundamentally fail under retraining attacks, in which an adversary retrains a generative model on a watermarked dataset and regenerates high-utility data that no longer carries the watermark. We address this challenge by introducing radioactivity, the property that a watermark remains detectable after generative model retraining, and propose RaMark, a radioactive watermarking method that embeds a sinusoidal dependency as an intrinsic component of the data distribution. By coupling the watermark with the underlying distribution, RaMark ensures that any generative model preserving data utility also has to preserve the watermark. We theoretically show that with high probability removing watermark degrades utility and alters data distribution. Extensive experiments on two real-world tabular datasets, under a large-scale ownership verification setting with $10^5$ independent data owners, demonstrate that RaMark achieves substantially stronger radioactivity than seven state-of-the-art methods and consistently outperforms them against both retraining and data modification attacks.
arXiv:2607.09001v1 Announce Type: new
Abstract: Large language model (LLM)-based audio-visual speech recognition (LLM-AVSR) has recently demonstrated strong robustness in adverse acoustic environments by leveraging complementary audio and visual information. Existing approaches typically employ independently pretrained acoustic and visual encoders, whose outputs are projected and fused as soft prompts to condition an LLM for speech recognition. However, most methods perform multimodal fusion without explicitly addressing the representational discrepancy between audio, visual and text modalities, potentially limiting the effectiveness of cross-modal integration. In this paper, we propose an optimal transport (OT)-based semantic alignment framework for LLM-AVSR. The proposed method explicitly bridges the modality gap by aligning the acoustic and visual representations with reference to the linguistic embedding space of the LLM before multimodal fusion. Specifically, OT is used to estimate probabilistic coupling matrices that characterize structured correspondences between modality-specific features and linguistic embeddings. The resulting OT couplings are further utilized as soft pseudo-labels to supervise contrastive learning, encouraging the extraction of semantically coherent and cross-modal consistent audio-visual representations. By anchoring multimodal features to the linguistic space of the LLM, the proposed framework facilitates more effective multimodal fusion and decoding. We implement the proposed framework using a Whisper-based acoustic encoder, an AV-HuBERT-based visual encoder, and a LLaMA3.2-3B decoder. Experiments conducted on the LRS3-TED benchmark demonstrate consistent improvements over strong baselines and achieve state-of-the-art performance under both clean and noisy evaluation conditions across a wide range of signal-to-noise ratios (SNRs).
arXiv:2607.09641v1 Announce Type: new
Abstract: Financial anomaly detection suffers from extreme class imbalance, causing traditional single-objective algorithms to exhibit ``fraud collapse'', defaulting to the majority class and failing to balance anomaly interdiction with customer friction. To overcome this without distortive data resampling, we propose the Semantic Pareto-DQN, a multi-objective reinforcement learning framework. Our approach synthesizes heterogeneous transaction features into cohesive natural-language narratives, encoded by large language models, thereby producing a robust, scale-invariant state representation. The agent optimizes a vectorial reward that explicitly decouples financial efficacy, operational friction, and semantic discovery. By mapping the continuous Pareto frontier, the system dynamically navigates the asymmetric costs of missed anomalies versus false positives. Empirical evaluations across E-Commerce fraud and UCI Credit datasets show that semantic Pareto-DQN successfully shatters the zero-recall trap. It achieves superior minority-class recall compared to scalarized baselines, providing an alternative to trade bounded operational friction for financial anomaly discovery.
arXiv:2607.09005v1 Announce Type: new
Abstract: Universal machine-learning interatomic potentials provide a promising route for accelerating molecular dynamics simulations of materials, but their transferability to lunar regolith-relevant silicates, oxides, and hydrogen-bearing surface species remains elucidated. Here, we benchmark six foundation models, MACE-MH, MatterSim, SevenNet-0, UPET, UMA, and NequIP-OAM-L, using NVT molecular dynamics simulations of four representative lunar minerals: forsterite, fayalite, ilmenite, and anorthite. Structural fidelity is evaluated using temperature stability, bond-distance statistics, bond-angle distributions, and partial radial distribution functions, with comparison to crystallographic reference data. The models reproduce Si--O, Mg--O, Al--O, and Ca--O local environments reasonably well, while Fe--O and Ti--O coordination environments show broader distributions and larger short-timescale fluctuations, highlighting the need for further validation and fine tuning with additional ground truth data for Fe- and Ti-bearing lunar phases. Hydroxylated surface tests show consistent O--H bond-distance distributions across models and minerals, suggesting that these foundation models may provide useful starting points for screening surface hydroxyl stability and volatile-related processes. Performance benchmarks on a single NVIDIA RTX 4090 show that SevenNet-0, MatterSim, and UPET provide the highest throughput among the six tested models, MACE-MH remains practical at intermediate cost, and UMA and NequIP-OAM-L extend the comparison to newer foundation potentials at higher runtime cost and memory demand. These results provide an initial benchmark for applying universal foundation models to lunar mineral simulations and identify key directions for future ab initio validation, model fine-tuning, and applications to lunar volatile evolution, space weathering, ISRU, and polar sample return studies.
arXiv:2607.09548v1 Announce Type: new
Abstract: Aerial manipulation with multirotor platforms enables physical interaction in complex environments, but rotor-induced airflow remains a critical limitation for tasks involving airflow-sensitive targets or surroundings. This paper presents an optimization-based design framework for modular aerial manipulators that jointly considers task wrench feasibility, end-effector placement, and airflow exposure constraints. We first introduce a novel categorization of target-side airflow tolerance and formulate the corresponding exposure requirements as geometric constraints. To efficiently model rotor-induced airflow, we introduce a compact cone-sphere envelope that approximates the spreading structure of a quadrotor's airflow while preserving computational tractability for optimization. Building on this formulation, we propose a reconfiguration optimization that adapts a modular aerial manipulator to diverse task wrench requirements while enforcing both target-side airflow exposure and intra-platform airflow interference constraints. Unlike prior designs that assume a fixed end-effector location, the proposed framework optimizes the end-effector placement together with the platform configuration. Scalability experiments and ablation studies validate the effectiveness of the proposed framework.
arXiv:2607.09015v1 Announce Type: new
Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing. Unlike classical contextual bandits that rely solely on bandit feedback and assume conditional independence across arms, our setting allows context-dependent inter-arm correlations and auxiliary reward information that may be noisy or misspecified. We propose algorithms that leverage such surrogate rewards through two complementary designs. A coupled reward-mixing approach pools true and surrogate rewards to accelerate learning when surrogate signals are reliable, while a decoupled prediction-mixing approach maintains separate estimators for bandit feedback and surrogate rewards and adaptively combines their predictions. This decoupling yields robustness to surrogate misspecification, recovering regret guarantees comparable to reward-only bandit methods in the worst case, while achieving improved regret when surrogate predictions are sufficiently informative. We provide theoretical regret analyses for both approaches and evaluate them on LLM routing benchmarks under varying accuracy versus cost trade-offs. The results demonstrate improved sample efficiency and consistently better accuracy-cost trade-offs compared to standard contextual bandit baselines and strong static routing methods.
arXiv:2603.16006v3 Announce Type: replace
Abstract: We extend the Fokker-Planck framework of Froseth (2026, arXiv:2603.05283) to populations of investors with heterogeneous, persistent return-generating ability. When the drift coefficient in the Langevin equation for log-wealth varies across investors, the proportional wealth tax remains a uniform drift shift but ceases to be neutral in the economic sense: its real incidence differs across ability types, and the stationary wealth distribution changes shape. We derive the extended Fokker-Planck equation on the joint space of log-wealth and ability, characterise the conditions under which the drift-shift symmetry breaks, and identify the consequences for asset prices and portfolio allocations. The analysis connects the neutrality results of Froseth (2026, arXiv:2603.05264) and the Fokker-Planck dynamics of Froseth (2026, arXiv:2603.05283) to the heterogeneous-returns literature, notably the "use-it-or-lose-it" mechanism of Guvenen, Kambourov, Kuruscu, Ocampo-Diaz and Chen (2023).
arXiv:2607.09025v1 Announce Type: new
Abstract: Artificial intelligence (AI) is shifting scientific discovery from task-specific workflows towards autonomous systems that organize exploration with experimental and human feedback in open-ended candidate spaces. Evolutionary computation (EC) provides a computational basis for feedback-driven discovery because population-based search can maintain diverse scientific candidates while steering exploration through accumulated evidence. However, EC predominantly focuses on candidate refinement for predefined problems, whereas cumulative discovery requires experience retention. To bridge this gap, this review introduces evolutionary intelligence (EI) for scientific discovery. EI characterizes scientific AI systems that sustain exploration by linking candidate refinement with experience retention across evolutionary cycles. We introduce a five-dimensional analytical framework that asks what evolves, how candidates change, why candidates are selected, where feedback originates, and when evolution occurs. This framework clarifies how EI transforms isolated search trajectories into cumulative scientific insight. We further demonstrate this paradigm across diverse discovery modes, from evolving concrete scientific entities to orchestrating automated research workflows. Finally, we identify critical bottlenecks regarding evaluation, process traceability, and shared infrastructure, providing a concrete roadmap for advancing the transition from EC to EI in scientific discovery.
arXiv:2607.08902v1 Announce Type: cross
Abstract: A model predictive controller (MPC) is used to construct a virtual assistant to aid a physician in prescribing cortisol replacement therapy for patients with adrenal insufficiency (AI). AI, also known as hypocortisolism, is a condition that occurs due to a low concentration of cortisol. This hormonal imbalance significantly impacts the individual's ability to regulate stress, metabolism, and immune responses. Thus, it is essential to maintain cortisol levels within a healthy range. The production of cortisol is governed by the hypothalamus-pituitary-adrenal (HPA) axis, a part of the endocrine system. In this paper, a novel mathematical model of the HPA axis is proposed that incorporates the endogenous circadian rhythm. This model simulates two conditions of hypocortisolism: primary and secondary AI. Adrenal insufficiency cannot be cured, but it can be treated with cortisol replacement therapy. The standard practice is to prescribe a therapeutic dose of hydrocortisone (HC). To evaluate the accuracy of the proposed HPA axis model, an open-loop cortisol replacement strategy with a fixed dosage is used to simulate both primary and secondary AI. The simulation results show that, analytically, it is possible to arrive at a fixed working cortisol replacement strategy. However, this strategy, though effective, is not optimal. To obtain optimal cortisol replacement strategies, an MPC is proposed. An important feature of MPC is that constraints on allowable cortisol replacement dosages can be rigorously addressed. This controller can serve as a virtual assistant to physicians in prescribing daily cortisol replacement therapy.
arXiv:2605.01985v2 Announce Type: replace
Abstract: We introduce \emph{Plausible Deniability in Fully Homomorphic Computation} (PD-FHC), a framework enabling users to outsource Boolean computations to an untrusted cloud while maintaining both computational privacy against honest-but-curious providers and plausible deniability against coercive adversaries. We define the notion of a \emph{Deniable Computation Medium} (DCM) and a \emph{Deniable Computation Scheme} (DCS) as medium-independent abstractions, then instantiate them using RGB images with Fredkin-gate circuits. One real circuit and several decoys share a single fixed Fredkin-gate wiring. Embedded control bits decide what each gate computes at each pixel, so the same wiring evaluates the real function at the real positions and decoy functions elsewhere. The cloud applies this one wiring to every pixel identically, processing all circuits in a single pass. Under coercion, the user reveals a decoy with verifiable results while the real circuit stays hidden. We formalize multi-round coercion games with existence and circuit-discovery advantages. For the image instantiation, we prove \emph{information-theoretic position privacy} under a \emph{matched-marginal condition}: when the real, decoy, and fill bits are drawn from a common per-position law and placed at random, the embedded LSB plane is exchangeable, so an honest-but-curious provider gains no advantage over guessing at locating the real positions, for any such law and not only the uniform one. We are explicit that this is a condition Alice enforces, that it is distinct from steganalytic undetectability, and that the latter requires the embedded law to match the declared service's legitimate-input law.
arXiv:2607.08943v1 Announce Type: cross
Abstract: We determine the asymptotics of a game inspired by classic vector balancing problems in combinatorial discrepancy theory. In this game, which we call the online Koml\'os game, two players, Paul and Carol, update the state vector $y$ in $\mathbb{R}^m$, initially placed at $0$. At each round, Paul chooses freely a set of $n$ vectors in the Euclidean unit ball, and Carol chooses, for each such vector, whether to leave it unchanged or reverse its sign. The resulting vectors are all added to $y$, and the game proceeds to a new round. After $T$ rounds, the game ends, and the $\ell_\infty$ norm of the state vector $y$ is determined. Paul's objective throughout the game is to maximize this norm, and Carol's objective is to minimize it. As $T$ gets large, we establish that the leading order term of the value of this game is $\sqrt{T/2\tau}$, where $\tau$ is the extinction time of the unit cube in $\mathbb{R}^m$ under a curvature-based flow characterized by the values of $m$ and $n$. When $n\geq m-1$, this flow is the mean curvature flow, and we show that $1/\sqrt{2\tau} =\Theta(\sqrt{\log m})$. Our results build upon the work of Kohn and Serfaty on deterministic games and mean curvature flow, combined with Banaszczyk's $\ell^2$ analogue of the Beck-Fiala theorem. As the large $T$ limit of the online Koml\'os game amounts to a localization of the classic Koml\'os problem, we hope this work can shed light on this and other vector balancing problems. Our results generalize to the version of the online Koml\'os game with the final value given by an arbitrary norm in $\mathbb{R}^m$.
arXiv:2607.09030v1 Announce Type: new
Abstract: This paper proposes a novel continuous aperture array (CAPA)-assisted integrated communication and navigation (ICAN) framework for low Earth orbit (LEO) satellite constellations. Within this framework, an electromagnetic-based collaborative transmission model is developed, in which multiple satellites equipped with CAPAs simultaneously radiate downlink data streams and navigation reference signals over shared spectrum. Building upon this, the achievable communication rate and the navigation Cramer-Rao bound (CRB) are derived, which explicitly characterize the intrinsic coupling between the dual-function beamformers and system performance. To improve the positioning accuracy with communication quality of service guarantee, a joint beamforming optimization problem is formulated to minimize the average CRB subject to transmit power budgets and minimum rate constraints. To tackle the inherent infinite-dimensionality of the CAPA beamformer design, an ICAN channel subspace is introduced to equivalently transform the formulation into a tractable finite-dimensional problem, which is then efficiently solved via an iterative convex optimization algorithm. Finally, numerical results demonstrate that the proposed CAPA-assisted beamforming design algorithm significantly outperforms conventional discrete phased array architectures and other benchmark schemes, yielding notable improvements in ICAN performance.
arXiv:2607.09067v1 Announce Type: new
Abstract: Text-to-image diffusion models exhibit unprecedented generative capability and contain rich intermediate representations that can be useful for discriminative vision tasks. Motivated by this observation, we study a focused question: how can the denoising dynamics of a pretrained diffusion model be adapted to support discriminative representation learning while preserving its generative behavior under parameter-efficient updates? We present D$^3$CL as an investigation of this question. Our key observation is that noisy latents at different diffusion timesteps can be interpreted as stochastic views of the same underlying image, enabling a contrastive objective to be coupled with the standard denoising reconstruction loss. This formulation provides a simple way to probe the interaction between generative denoising and discriminative representation learning without training from scratch. To keep the adaptation lightweight, we apply LoRA updates to a pretrained Stable Diffusion backbone while freezing the original model parameters. D$^3$CL provides strong empirical evidence that reconstruction and noise-level contrastive objectives can be complementary: on ImageNet-1K, it obtains 80.1% linear-probing accuracy and an FID of 5.56 for $256 \times 256$ unconditional generation. Additional ablations on the design space suggest that the usefulness of diffusion features depends on where and how denoising states are sampled. These results establish D$^3$CL as a parameter-efficient adaptation framework for pretrained diffusion models, showing that noise-level contrastive learning can structure denoising representations for discriminative tasks while maintaining generative performance.
arXiv:2607.09038v1 Announce Type: new
Abstract: We revisit the problem of matching on the line with ordinal preferences. In the classic setting, there are $n$ agents and $n$ items in a shared unknown line metric, and the goal is to find a low-cost perfect matching using only the agents' rankings of the items by distance. A mechanism has distortion $\alpha$ if it always outputs a matching whose cost is within a factor of $\alpha$ of the optimum, in every consistent line metric.
In the learning-augmented setting, the mechanism is also supplied with a prediction that conveys additional information about the instance. The quality of this prediction is unknown, and the goal is to optimize the mechanism's distortion when the prediction is accurate (consistency), while preserving worst-case guarantees when the prediction is arbitrarily inaccurate (robustness). We propose a mechanism that takes a matching as its prediction and guarantees $1$-consistency and $3$-robustness. By recovering an optimal matching when the prediction is perfectly accurate while retaining the optimal prediction-free distortion guarantee when it is arbitrarily inaccurate, we resolve an open question of Filos-Ratsikas et al. (IJCAI, 2025).
arXiv:2603.17717v4 Announce Type: replace
Abstract: Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. In this paper, we address two tasks, in the first unified multi-modal NIDS dataset, which incorporates flow-level data, packet payload information and temporal contextual features, from the reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019, with the same feature space. In the first task we use machine learning (ML) algorithms, with stratified cross validation, in order to prevent network attacks, with stability and reliability. In the second task we use adversarial learning algorithms to generate synthetic data, compare them with the real ones and evaluate their fidelity, utility and privacy using the SDV framework, f-divergences, distinguishability and non-parametric statistical tests. The findings provide stable ML models for intrusion detection and generative models with high fidelity and utility, by combining the Synthetic Data Vault framework, the TRTS and TSTR tests, with non-parametric statistical tests and f-divergence measures.