Forskningsradar

Science Journals

Peer-reviewade publikationer — 56237 artiklar

arXiv (fysik & CS) Preprint 2026-06-03
WISE-HAR: A Generalizable Ensemble Deep Learning Framework for WiFi-Based Human Activity Recognition
arXiv:2606.02974v1 Announce Type: new Abstract: Human Activity Recognition (HAR) using WiFi signals has emerged as a transformative technology for smart homes, healthcare monitoring, security systems, and ambient assisted living. Unlike traditional camera-based systems that raise significant privacy concerns and fail in low-light conditions, or wearable sensors that require user compliance, WiFi-based HAR is non-intrusive, privacy-preserving, cost-effective, and works seamlessly in any lighting condition. This paper presents a comprehensive approach to recognize three distinct human activities: "No Presence" (empty room), "Walking", and "Walking + Arm-waving" using the Wallhack1.8k WiFi spectrogram dataset. We propose three key improvements to address the main challenges in WiFi-based HAR. First, to address high performance variance, we implement ensemble learning with five different CNN architectures (Deep CNN, Wide CNN, MobileNetV2, ResNet50V2, and EfficientNetB0). Second, to address the small dataset size limitation, we apply aggressive data augmentation techniques including time-warping, frequency masking, and noise addition. Third, to evaluate real-world generalization capability, we perform cross-scenario evaluation (training on Line-of-Sight and testing on Non-Line-of-Sight) and cross-antenna evaluation (training on Biquad antenna and testing on PIFA antenna). Our ensemble model achieved a test accuracy of 94.87% on the LOS scenario with Biquad antenna, outperforming the best individual model by 0.66%. Data augmentation improved Random Forest performance from 60% to 95%. Cross-scenario evaluation showed minimal accuracy drops of only 1.37% and 2.07%, demonstrating strong generalization capabilities. The results indicate that the proposed approach is robust, reliable, and suitable for real-world deployment in diverse environments with different hardware configurations.
arXiv (fysik & CS) Preprint 2026-06-03
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
arXiv:2512.10999v3 Announce Type: replace Abstract: Knowledge Base Question Answering (KBQA) challenges models to bridge the gap between natural language and strict knowledge graph schemas by generating executable logical forms. While Large Language Models (LLMs) have advanced this field, current approaches often struggle with a dichotomy of failure: they either generate hallucinated queries without verifying schema existence or exhibit rigid, template-based reasoning that mimics synthesized traces without true comprehension of the environment. To address these limitations, we present \textbf{KBQA-R1}, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning. Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions, leveraging Group Relative Policy Optimization (GRPO) to refine its strategies based on concrete execution feedback rather than static supervision. Furthermore, we introduce \textbf{Referenced Rejection Sampling (RRS)}, a data synthesis method that resolves cold-start challenges by strictly aligning reasoning traces with ground-truth action sequences. Extensive experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance, effectively grounding LLM reasoning in verifiable execution.
arXiv (fysik & CS) Preprint 2026-06-03
FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration
arXiv:2512.11213v2 Announce Type: replace Abstract: Scaling test-time computation has been shown to significantly improve large language model (LLM) performance without additional training. However, extending these techniques to multi-agent systems remains challenging: existing approaches lack principled mechanisms for allocating compute to enable effective collaboration, scaling coordination itself, or optimizing compute usage under explicit budget constraints. To address this gap, we propose FutureWeaver, a framework for planning and optimizing test-time compute allocation in multi-agent systems under fixed budgets. It introduces collaboration modules, formalized as modular, callable functions that encapsulate reusable multi-agent workflows and are automatically induced via self-play reflection from recurring interaction patterns. Building on these modules, it employs \emph{a dual-level planning architecture} that jointly performs short-horizon action selection and long-horizon abstract lookahead to optimize inference trajectories under budget constraints. Experiments on complex agent benchmarks demonstrate that FutureWeaver consistently outperforms baselines across diverse budget settings, validating its effectiveness for multi-agent collaboration in inference-time optimization.
arXiv (fysik & CS) Preprint 2026-06-03
Reserve Depletion and Security Runway in Proof-of-Stake Systems
arXiv:2606.03587v1 Announce Type: new Abstract: Many proof-of-stake protocols finance validator rewards from two sources: transaction fees and a finite reserve of tokens. This creates a dynamic hand-off problem. Early in the life of the system, fees may be too small to fund the target level of security; later, fees may become sufficient. The central question is whether the reserve provides enough runway for the protocol to remain secure until this fee-only region is reached. We study this problem in a discrete-time stochastic model of validator participation. Token price and transaction demand fluctuate over time, while validators choose participation strategically. We solve the validator entry game and derive an exact state-dependent reserve threshold, i.e., the minimal reserve stock necessary and sufficient to sustain a target security level. This threshold separates three regions: infeasibility, reserve-dependent security, and fee-only security. Security fails if the reserve first falls below the state-dependent threshold, and a successful hand-off occurs exactly if the fee-only region is reached before that failure time. We derive stress-test guarantees that convert lower confidence bands for token price and demand into reserve requirements, and obtain explicit failure-probability and expected hand-off-time bounds. Finally, we extend the model to forward-looking validators and derive the Markov participation condition that captures how current participation affects future reserve-funded rewards. The main implication is that reserve policy should not be evaluated by nominal depletion dates or steady-state reward ratios alone. A protocol can have a large nominal reserve and still be close to security failure after adverse price or demand shocks. Conversely, once demand crosses the fee-only threshold, the reserve becomes redundant for security. This paper provides a tractable equilibrium framework for stress-testing this transition.
arXiv (fysik & CS) Preprint 2026-06-03
MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control
arXiv:2605.26006v2 Announce Type: replace Abstract: Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation with physics-based tracking, or an end-to-end imitation-learning paradigm that directly generates actions from text. However, the former suffers from the inherent domain shift between kinematic generation and physics-based tracking, while the latter struggles with the substantial modality gap between textual commands and low-level actions, limiting effective semantic alignment. Notably, humanoid states encode rich motion dynamics that are more semantically aligned with textual descriptions than low-level actions, making them a natural basis for deriving behavioral intent. Building upon this insight, we propose MIND, a novel end-to-end diffusion framework for text-driven physics-based humanoid control that leverages behavioral intent as a semantic bridge between textual commands and low-level actions. At its core, MIND introduces a multi-scale intent diffusion mechanism, where a holistic intent predictor captures global behavioral dynamics to guide overall behavior synthesis, while an immediate intent predictor provides step-wise, fine-grained signals for local behavior refinement at each diffusion step. This hierarchical intent formulation imposes a structured inductive bias for humanoid control, improving semantic alignment and behavioral naturalness. Furthermore, MIND encodes humanoid states into a latent space to enable more effective semantic intent modeling. Extensive experiments demonstrate that MIND outperforms existing methods and synthesizes coherent, physically plausible, and semantically aligned humanoid behaviors from text commands. Project page: https://binlee26.github.io/MIND_page.
arXiv (fysik & CS) Preprint 2026-06-03
Latent Laplace Diffusion for Irregular Multivariate Time Series
arXiv:2605.19805v2 Announce Type: replace Abstract: Irregular multivariate time series impose a trade-off for long-horizon forecasting: discrete methods can distort temporal structure via re-gridding, while continuous-time models often require sequential solvers prone to drift. To bridge this gap, we present Latent Laplace Diffusion (LLapDiff), a generative framework that models the target as a low-dimensional latent trajectory, enabling horizon-wide generation without step-by-step integration over physical time. We guide the reverse process utilizing a stable modal parameterization motivated by stochastic port-Hamiltonian dynamics, and parameterize its mean evolution in the Laplace domain via learnable complex-conjugate poles, enabling direct evaluation over irregular timestamps. We also link continuous dynamics to irregular observations through renewal-averaging analysis, which maps sampling gaps to effective event-domain poles and motivates a gap-aware history summarizer. Extensive experiments show that LLapDiff improves over baselines in long-horizon forecasting, and its continuous-time generative nature supports missing-value imputation by querying the same model at historical timestamps. Code is available at https://github.com/pixelhero98/LLapDiffusion.
arXiv (fysik & CS) Preprint 2026-06-03
Pretraining Language Models on Historical Text
arXiv:2606.02991v1 Announce Type: new Abstract: We introduce TypewriterLM, a 7.24B History language model (LM) trained exclusively on English text predating 1913. Developing History LMs requires addressing challenges in data quality and availability, preventing temporal leakage, designing temporally consistent post-training pipelines, and constructing reliable evaluations. To address these issues, we construct TypewriterCorpus, a 54B-token historical corpus collected from diverse archival and linguistically annotated sources with extensive data cleaning and leakage mitigation procedures. Furthermore, we introduce lexically grounded instructing tuning, a post-training framework that constraints responses to remain directly grounded in historical source documents. Using this framework we construct two historical instruction tuning datasets: History-LIMA and History-SelfInstruct. To evaluate capability and temporal consistency, we introduce History-Event, a benchmark suite for evaluating competence, temporal grounding and data leakage. We release TypewriterLM and all associated resources to support future research on historical language models.
arXiv (fysik & CS) Preprint 2026-06-03
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
arXiv:2503.07265v4 Announce Type: replace Abstract: Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content. However, existing research and evaluation standards predominantly focus on image realism and shallow text-image alignment, lacking a comprehensive assessment of complex semantic understanding and world knowledge integration in text-to-image generation. To address this challenge, we propose \textbf{WISE}, the first benchmark specifically designed for \textbf{W}orld Knowledge-\textbf{I}nformed \textbf{S}emantic \textbf{E}valuation. WISE moves beyond simple word-pixel mapping by challenging models with 1000 meticulously crafted prompts across 25 subdomains in cultural common sense, spatio-temporal reasoning, and natural science. To overcome the limitations of traditional CLIP metric, we introduce \textbf{WiScore}, a novel quantitative metric for assessing knowledge-image alignment. Through comprehensive testing of 20 models (10 dedicated T2I models and 10 unified multimodal models) using 1,000 structured prompts spanning 25 subdomains, our findings reveal significant limitations in their ability to effectively integrate and apply world knowledge during image generation, highlighting critical pathways for enhancing knowledge incorporation and application in next-generation T2I models. Code and data are available at \href{https://github.com/PKU-YuanGroup/WISE}{PKU-YuanGroup/WISE}.
arXiv (fysik & CS) Preprint 2026-06-03
Visual Graph Scaffolds for Structural Reasoning in Large Language Models
arXiv:2606.02673v1 Announce Type: new Abstract: Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time. In this paper, we take a different view: the value of graphs for LLMs lie not only in supplying information, but also in organizing reasoning. Inspired by how humans use graph-structured mind maps to organize branching and converging thoughts, we ask whether graphs can serve as an internal form of reasoning assistance. We study this question on multi-hop question answering tasks, where teacher-provided reasoning traces are rewritten as graph mind maps and used to guide a student model. Our experiments reveal a clear modality gap. When graph structures are flattened into text, their benefits become limited once direct answer hints are removed. Under this abstract guidance setting, both reasoning efficiency and answer quality degrade substantially. In contrast, visual graph guidance remains effective without direct answer clues, and its advantage persists after supervised fine-tuning and KL-based distillation. The above findings support the claim that graphs should be studied not only as external knowledge structures for LLMs, but also as visual scaffolds for organizing reasoning.
arXiv (fysik & CS) Preprint 2026-06-03
Sensitivity Enhancement of S-Band Rydberg Atom Microwave Receiver Using Resonant Cavity
arXiv:2606.02669v1 Announce Type: new Abstract: Rydberg atom-based microwave electric field sensing has attracted growing interest owing to its inherent advantages, such as absolute calibration, wideband operability, and compatibility with room-temperature devices. A critical bottleneck that limits sensitivity is the inefficient coupling between the Rydberg atoms and the incident microwave field, particularly when detecting weak signals propagating in free space. Here we propose and experimentally validate a scheme that integrates a horn antenna with a resonant microwave cavity to significantly improve this coupling for free-space signal reception in the S-band. Using a two-photon excitation scheme in a cesium vapor cell, we systematically characterize the sensing performance under three configurations: a bare cell, direct cavity injection, and a cavity coupled to a horn antenna that captures free-space microwave signals over a 1 m distance. In the antenna-coupled cavity configuration, we achieve an optimal sensitivity of 2.33 nV/cm/$\sqrt{\text{Hz}}$ at the receiving antenna, which corresponds to an enhancement of approximately 17.9 dB compared to the optimized bare vapor cell configuration. Our findings offer a practical and effective route to boost the sensitivity of Rydberg atomic sensors, facilitating their adoption in real-world microwave metrology and wireless communication applications where weak free-space electric fields must be reliably measured.
arXiv (fysik & CS) Preprint 2026-06-03
ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models
arXiv:2605.10328v3 Announce Type: replace Abstract: A central challenge in large-scale decision-making under incomplete information is estimating reliable probabilities. Recent approaches use Large Language Models (LLMs) to generate explanatory factors and coarse-grained probability estimates, which are then refined by a Na\"ive Bayes model over factor combinations. However, sparse factor spaces often yield ``unknown'' predictions, while expanding factors increases noise and spurious correlations, weakening conditional independence and degrading reliability. To address these limitations, we propose \textsc{Anchor}, an aggregated Bayesian inference framework over a hierarchical factor space. It constructs dense factor hierarchies through iterative generation and clustering, maps contexts via hierarchical retrieval and refinement, and augments Na\"ive Bayes with a Causal Bayesian Network to model latent factor dependencies. Experiments show that \textsc{Anchor} markedly reduces ``unknown'' predictions and produces more reliable probability estimates than direct LLM baselines, achieving state-of-the-art performance while significantly reducing time and token overhead.
arXiv (fysik & CS) Preprint 2026-06-03
Wave-mean decomposition of scale-dependent kinetic energy from surface drifters
arXiv:2606.03744v1 Announce Type: new Abstract: Separating waves and mean flows is a fundamental challenge in ocean dynamics. Lagrangian filtering of passive-tracer time series into high-frequency wave and low-frequency mean-flow components provides a practical route, as the relevant time scales are often cleanly split in the Lagrangian frame. Here we show that Lagrangian filtering can be applied to surface drifter observations, providing a powerful approach to quantify wave and mean-flow contributions to surface kinetic energy statistics. A key methodological choice is to implement the filtering in a generalized Lagrangian mean (GLM) framework, attributing filtered velocities to mean rather than particle trajectories; this produces more physically interpretable diagnostics. Using Gulf of Mexico drifter data, we compute second-order velocity structure functions (SF2s) for waves and mean flow components across spatial scales. With these filtered SF2s as a benchmark, we illustrate that Helmholtz decomposition of unfiltered SF2s alone should not be interpreted as a dynamical wave-mean decomposition. Applying Helmholtz decomposition to the filtered SF2s further illuminates seasonal dynamics. Mean-flow surface kinetic energy is rotationally dominated at scales larger than O(1) km, while at and below O(1) km, divergent and rotational contributions are approximately equipartitioned in both summer and winter, suggesting low-frequency divergent motions and possible associated vertical exchange. Winter mean flows are more active than summer mean flows over 500 m-10 km. Super-inertial motions are broadly consistent with linear waves. In winter, wave kinetic energy is concentrated at smaller spatial scales than in summer, possibly reflecting enhanced downscale transfer by stronger submesoscale mean flows.
arXiv (fysik & CS) Preprint 2026-06-03
Kolmogorov equations for evaluating the boundary hitting of degenerate diffusion with unsteady drift
arXiv:2501.02729v5 Announce Type: replace Abstract: Jacobi diffusion is a representative diffusion process whose solution is bounded in a domain under certain drift and diffusion coefficient conditions. However, the process without such conditions has not been thoroughly investigated. We explore a Jacobi diffusion whose drift coefficient is affected by another deterministic process, causing the process to hit the boundary of a domain in finite time. The Kolmogorov equation (a degenerate elliptic partial differential equation) for evaluating the boundary hitting of the proposed Jacobi diffusion is then presented and analyzed, with several conditional arguments, some of which are addressed computationally. We also investigate a related mean-field-type (McKean-Vlasov) self-consistent model arising in tourism management, where the drift depends on the index for sensor boundary hitting, thereby confining the process to a domain with higher probability. We propose a finite difference method for the linear and nonlinear Kolmogorov equations, which yields a unique numerical solution because of discrete ellipticity if the discount is positive. The accuracy of the finite difference method critically depends on the regularity of the boundary condition, and the use of high-order discretization is not always effective. Finally, we computationally investigate the mean field effect.
arXiv (fysik & CS) Preprint 2026-06-03
Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA
arXiv:2606.03728v1 Announce Type: new Abstract: Retrieval-augmented generation systems for legal question answering typically retrieve passages based on semantic similarity and provide them to a language model, which then generates cited answers. Prior work assumes that highly ranked passages are most likely to be usefully cited by the model. Perturbation-based attribution methods, such as C-LIME, have been used exclusively for post-hoc explanation. However, on the AQuAECHR benchmark, semantic similarity does not correlate with passage attribution. Within a retriever's candidate pool, similarity-based ranking performs worse than random selection at surfacing gold citation paragraphs. To address this limitation, a lightweight cross-encoder is trained on continuous perturbation-based attribution scores to re-rank passages prior to generation. This approach is evaluated on the AQuAECHR benchmark, using two language models and five-fold cross-validation. The re-ranker substantially improves citation faithfulness and alignment with gold expert answers. Notably, two re-rankers trained independently on different models converge beyond their raw attribution agreement. This finding indicates that the cross-encoder reduces model-specific noise and produces a shared relevance signal that partially transfers across models, although same-model re-ranking remains more effective. These results demonstrate that perturbation-based attribution provides a practical, model-agnostic training signal for citation-aware retrieval.
arXiv (fysik & CS) Preprint 2026-06-03
What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents
arXiv:2606.02668v1 Announce Type: new Abstract: Coding agents gate consequential actions behind a human-in-the-loop approval dialog, but the dialog is narrated by the agent itself: the human approves a summary the agent writes. The Lies-in-the-Loop (LITL) attack shows that summary is forgeable, so a compromised agent can show a benign description while a different action runs. This paper names the missing property, Consent Integrity, by importing What You See Is What You Sign (WYSIWYS) and the trusted-path property into the agent approval channel: the action shown to the human must be rendered by a trusted mediator from the real action at the boundary, not the agent's narration, over a path the agent cannot spoof, and bound to the exact action that executes. Two twists distinguish it from classical WYSIWYS: the renderer is the adversary, and the boundary ground truth is a low-level event that must be decoded without trusting the agent. Since no decoder is complete, the realizable target is analyzer-relative: whatever the analyzer cannot classify is surfaced as uninspectable rather than silently approved. A prototype implements the analyzer, renderer, and bind-to-execution; total mediation and the trusted path are specified but assumed, not implemented. On GTFOBins, an independent corpus of 1330 trusted-tool abuses, the prototype silently passes 10.0% (every instance through a trusted tool); on tldr, 28,798 normal-usage commands, it marks 87.0% uninspectable. These two independent measurements bracket the design's central tension: the trust list that bounds silent passes is the same one that drives over-prompting, and a boundary-only mediator can move along that frontier but not escape it. The contribution is the property, the mechanism, and an honest position on that frontier, not a solved defense.
arXiv (fysik & CS) Preprint 2026-06-03
Bistability of cellular traction on strain-stiffening substrates
arXiv:2606.03669v1 Announce Type: new Abstract: To migrate, cells exert traction forces on the extracellular matrix (ECM) -- a biopolymer network that often exhibits nonlinear strain-stiffening elasticity. Cellular tractions can therefore stiffen the ECM. At the same time, cells exert stronger tractions on stiffer ECM. Here, we show theoretically that this traction-stiffness feedback can produce traction bistability and hysteresis. As a result, increasing either the ECM's nonlinear elasticity or cellular contractility leads to a discontinuous transition from low to high tractions. This traction jump might trigger collective cell migration as the ECM stiffens, for example during development and tumor progression. Moreover, the bistable behavior might provide robustness to cellular traction forces when cells migrate through mechanically heterogeneous environments.
arXiv (fysik & CS) Preprint 2026-06-03
Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning
arXiv:2606.02662v1 Announce Type: new Abstract: Machine learning has accelerated quantum chemistry but is hindered by the prohibitive cost of generating high fidelity training data. Multifidelity machine learning (MFML) mitigates this overhead by systematically combining abundant low fidelity data with sparse high fidelity data. In spite of its success, standard MFML schemes rely on pre-defined scaling factors to determine sparse data ratio across fidelities, often generating redundant multifidelity data resulting in a loss of efficiency. Here, we introduce an adaptive on-the-fly multifidelity framework for machine learning that autonomously determines training dataset composition. By dynamically querying training samples at each fidelity, the algorithm saturates model accuracy at lower fidelities before moving up to more expensive reference calculations. We benchmark the novel adaptive-MFML across diverse chemical properties including the computational chemistry gold standard coupled cluster energies, and the more chemically challenging excitation energies. In our numerical experiments we show that our adaptive algorithm reduces data generation costs by up to a factor of 30 compared to single fidelity methods and improves upon standard MFML by up to a factor of 5. The mitigation of data redundancy establishes a high-accuracy low-cost pathway for sustainable cost-aware machine learning in quantum chemistry.
arXiv (fysik & CS) Preprint 2026-06-03
A fast reduced order method for linear parabolic inverse source problems
arXiv:2306.05677v2 Announce Type: replace Abstract: In this paper, we propose a novel, computationally efficient reduced order method to solve linear parabolic inverse source problems. Our approach provides accurate numerical solutions without relying on specific training data. The forward solution is constructed using a Krylov sequence, while the source term is recovered via the conjugate gradient (CG) method. Under a weak regularity assumption on the solution of the parabolic partial differential equations (PDEs), we establish convergence of the forward solution and provide a rigorous error estimate for our method. Numerical results demonstrate that our approach offers substantial computational savings compared to the traditional finite element method (FEM) and retains equivalent accuracy.
arXiv (fysik & CS) Preprint 2026-06-03
Late-Time Cosmology and Structure Formation in Quadratic $f(Q)$ Gravity
arXiv:2606.02660v1 Announce Type: new Abstract: We investigate the cosmological evolution associated with the quadratic symmetric teleparallel gravity framework, \( f(Q)=Q+\alpha Q^{2}+\beta \) where the relation \(Q\propto H^{2}\) generates an additional \(H^{4}\) contribution to the Friedmann equation. Using the exact algebraic solution for $H(z)$, we reconstruct the effective dark-energy sector and compare the background evolution with $\Lambda$CDM using Type Ia supernovae, BAO, and cosmic-chronometer data. At the perturbative level, the model modifies the Poisson equation through a time-dependent effective gravitational coupling $G_{\textrm eff}(z)=G\big[1+\tfrac{2}{3}A E^{2}(z)\big]^{-1}$, where $A=18\alpha H_{0}^{2}$. For $\alpha>0$ this produces a weakened gravitational interaction, suppressing the linear growth factor $D(z)$, the growth rate $f(z)$, and the RSD observable $f\sigma_{8}(z)$. In the nonlinear regime, the reduced gravitational strength increases the spherical-collapse threshold and suppresses the halo mass function, leading to a lower predicted value of $S_{8}=\sigma_{8}\sqrt{\Omega_{m}/0.3}$. Thus, the quadratic $f(Q)$ extension can reproduce mild deviations from $\Lambda$CDM at the background level while naturally alleviating the $S_{8}$ tension, offering a viable modified-gravity explanation for recent observational hints of dynamical dark energy.
arXiv (fysik & CS) Preprint 2026-06-03
OneVLA: A Unified Framework for Embodied Tasks
arXiv:2606.01241v2 Announce Type: replace Abstract: Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact physically with their surroundings. However, current Vision-Language-Action (VLA) models remain constrained by task-specific architectures, specializing in either navigation or manipulation, which hinders the development of general-purpose robotic agents. To bridge this gap, we introduce OneVLA, a unified architecture that integrates these distinct tasks into a single, cohesive framework. Specifically, we design a unified action head capable of generating both navigation and manipulation actions without requiring task-specific variants. Furthermore, we propose a multi stage progressive training strategy-incorporating curated data construction and Chain-of-Thought (CoT) fine-tuning that facilitates strong positive transfer and mutual reinforcement between the two domains. Extensive experiments in both simulated and real-world environments demonstrate that OneVLA achieves state-of-the-art performance, significantly outperforming both specialized single-task and existing cross-task models. By unifying these core capabilities, OneVLA paves the way for truly general-purpose robotic systems. The model and source code will be publicly released.
arXiv (fysik & CS) Preprint 2026-06-03
MariData: One-Step Unpaired Image Translation for Maritime Environments
arXiv:2606.03246v1 Announce Type: new Abstract: The development on robust perception systems for Maritime Autonomous Surface Ships (MASS) is heavily constrained by the scarcity of diverse training data, particularly for adverse weather and low-light conditions. Because collecting paired images in dynamic maritime environments is physically impossible, synthetic data generation via unpaired image-to-image translation offers a critical solution. However, existing generative models suffer from failing to preserve the fine structural details of small navigational objects due to latent compression bottlenecks. In this paper, we introduce a framework for generating synthetic maritime data using CycleGAN-turbo, a one-step unpaired translation architecture. By incorporating zero-convolution skip connections to bypass the Variational Autoencoder (VAE) bottleneck, our approach explicitly preserves small object details (e.g., distant vessels and sea marks) during translation. We compiled a dataset of 7,000 maritime images to train and evaluate models for Day-to-Foggy, Day-to-Sunset, and Day-to-Night domain translations. Qualitative evaluations and variable-strength inference studies demonstrate that our method effectively synthesizes realistic atmospheric conditions while maintaining the underlying semantic structure of the scene. The Day-to-Foggy and Day-to-Sunset models exhibit great structural retention, whereas the Day-to-Night model highlights the challenge of semantic hallucination, such as generating artificial coastal lights, induced by unbalanced training distributions. Ultimately, this work establishes an efficient, structure-aware data synthesis pipeline that directly addresses the data scarcity bottleneck in autonomous maritime navigation.
arXiv (fysik & CS) Preprint 2026-06-03
SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts
arXiv:2606.03512v1 Announce Type: new Abstract: Path planning is essential for Autonomous Mobile Robots (AMRs). Conventional methods for incorporating human preferences into planning typically rely on either complex reward engineering or hardware-intensive solutions. Recent state-of-the-art frameworks leverage imitation learning to train behavior-specific path planning models from expert demonstrations. However, these approaches face two key limitations: limited generalization to unseen environments and low robustness in demonstration collection. To address these challenges, this work introduces an enhanced framework that focuses on two main contributions: an overhauled annotation tool built on ROS 2, and a novel training strategy that integrates diffusion-based augmentation into baseline behavioral cloning models. A dataset of expert demonstrations is provided and evaluated through ablation studies to assess the robustness of the proposed solution. The enhanced approach outperforms state-of-the-art methods with 39.1% lower Absolute Pose Error (APE) and 33.5% lower Fr'echet Inception Distance (FID) while having 93.8% less trainable parameters. Moreover it attains diffusion-level generalization while preserving the real-time, on-edge properties of state-of-the-art models.
arXiv (fysik & CS) Preprint 2026-06-03
Introduction to optimization methods for training SciML models
arXiv:2601.10222v2 Announce Type: replace Abstract: Optimization is central to both modern machine learning (ML) and scientific machine learning (SciML), yet the structure of the underlying optimization problems differs substantially across these domains. Classical ML typically relies on stochastic, sample-separable objectives that favor first-order and adaptive gradient methods. In contrast, SciML often involves physics-informed or operator-constrained formulations in which differential operators induce global coupling, stiffness, and strong anisotropy in the loss landscape. As a result, optimization behavior in SciML is governed by the spectral properties of the underlying physical models rather than by data statistics, frequently limiting the effectiveness of standard stochastic methods and motivating deterministic or curvature-aware approaches. This document provides a unified introduction to optimization methods in ML and SciML, emphasizing how problem structure shapes algorithmic choices. We review first- and second-order optimization techniques in both deterministic and stochastic settings, discuss their adaptation to physics-constrained and data-driven SciML models, and illustrate practical strategies through tutorial examples, while highlighting open research directions at the interface of scientific computing and scientific machine learning.
arXiv (fysik & CS) Preprint 2026-06-03
The anti-lexicographic SUS-anchor: a near-optimal k=1 sampling scheme
arXiv:2606.01190v2 Announce Type: replace Abstract: In recent years, there has been a renewed interest in the search for low density minimizer schemes. These schemes take a window of $w$ consecutive $k$-mers, and sample one of them: the smallest under some specific order. Schemes such as the mod-minimizer provide a low density (fraction of sampled $k$-mers) when $k \gg w$, while schemes such as the greedy minimizer work well for explicit small parameters roughly in the regime $k \leq 2w$, for $k$ and $w$ up to $15$ or so. When $k < \log_\sigma w$ is very small, minimizer schemes cannot do well, and more general sampling schemes are needed that can be richer than just comparing $k$-mers. Bidirectional-string anchors (bd-anchors) form one such scheme. Inspired by bd-anchors, we introduce the smallest unique substring or SUS-anchor: Given a window, this considers all suffixes that do not occur as a substring elsewhere in the window. It then samples the start position of the smallest suffix according to the new anti-lexicographic order that minimizes the first character and maximizes the remaining characters. We give a linear-time and $O(w)$ space streaming algorithm to compute all SUS-anchors of a string. For alphabet size $\sigma=4$ and $k=1$, the anti-lexicographic SUS-anchor empirically has density $<1\%$ away from the density lower bound, significantly improving over bd-anchors that are often $>15\%$ above it. For alphabet size $\sigma=2$, the density is at most $10\%$ above the lower bound, which again improves over the $>50\%$ overhead of bd-anchors.
arXiv (fysik & CS) Preprint 2026-06-03
Inference Cost Attacks for Retrieval-Augmented Large Language Models
arXiv:2606.02643v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG)-enhanced LLM systems, while powerful, introduce substantial inference costs due to the inclusion of an extra multi-stage pipeline that dynamically retrieves and synthesizes information from external knowledge sources. This high operational cost exposes a critical vulnerability to Inference Cost Attacks (ICAs). However, existing ICAs often rely on the impractical assumption of direct prompt manipulation. We argue that a more feasible and potent threat to RAG-enhanced LLM systems arises from poisoning external knowledge bases (e.g., web knowledge from the Internet). In this work, we introduce the Retrieval-Augmented Inference Cost Attack (RA-ICA), a novel attacking paradigm that targets the computational cost of RAG-enhanced LLM systems by injecting malicious documents into external knowledge corpus. To operationalize this attack, we propose Computational Resource Exhaustion via External Poisoning (CREEP), a novel framework that leverages LLM agents to automatically craft malicious documents that are both semantically relevant for retrieval and potent for inducing an abnormal increase in token consumption during the inference phase. To enhance the attack's effectiveness, we introduce Memory-Augmented Group Relative Policy Optimization (MA-GRPO), a novel reinforcement learning algorithm that fine-tunes the agents by learning from a dynamic memory of historical best adversarial documents. Extensive experiments across three real-world datasets demonstrate that RA-ICA increases token consumption by up to 13.12 times with an over 90% success rate, without degrading the integrity of the generated answer.