arXiv:2606.13892v1 Announce Type: new Abstract: The intersection of crypto x AI is spawning papers, products, online posts, and companies. All the surrounding buzz, though, obscures what exactly has been done, what the opportunities and challenges are, and what open questions deserve attention. This survey paper asks what AI can do for blockchain-based technologies (broadly construed as "crypto") (crypto x AI), and vice versa (AI x crypto). We systematize existing work, summarize key takeaways, highlight open research questions, and offer a perspective on pervasive industry misconceptions, concluding that AI and crypto are still in the very early stages of meaningful integration.
Science Journals
arXiv:2606.13896v1 Announce Type: new Abstract: Self-supervised geospatial foundation models (GeoFMs) learn transferable representations from remote sensing data, but their downstream behavior is difficult to characterize. We study six representative GeoFMs spanning joint-embedding, reconstruction, and multimodal pretraining families, and evaluate transfer across classification, regression, and segmentation benchmarks under different label availability and downstream pipelines. We find that model rankings change across tasks and adaptation settings. Layerwise probing shows that, in most cases, task-relevant information is more accessible in intermediate transformer blocks compared to final-layer embeddings, and that GeoFMs exhibit distinct depthwise profiles. In segmentation case studies on PASTIS and Sen1Floods11, downstream adaptation settings such as decoder design and fine-tuning can be as impactful as the choice of GeoFM, and standard dense-prediction heads may be poorly aligned with how GeoFMs organize information over depth. Finally, CKA analysis on case studies shows that fine-tuning does not rewrite GeoFMs uniformly across depth, and the strongest changes are localized to the first linear layer of the MLP in ViT blocks. These results help explain why GeoFM rankings shift across benchmarks and motivate more representation-aware evaluation and adaptation strategies.
arXiv:2606.13904v1 Announce Type: new Abstract: Exploratory question answering (EQA) over data lakes requires an LLM agent to discover relevant sources, analyze retrieved data, and adapt its actions based on intermediate results. End-to-end accuracy alone cannot distinguish failures in search, planning, data analysis, or the agent's Action Policy: its decisions about what to do next and when to submit an answer. We present SANA (Search Agent Navigation Ablation framework), a diagnostic ablation framework that transforms EQA tasks into runtime profiles containing gold source sequence, sanitized subquestions, and execution records. SANA uses these profiles to construct idealized search, planning, and data-analysis tools, allowing each component to be ablated; the residual gap is diagnostic evidence for policy failures. To illustrate SANA as a reusable evaluation framework, we adapted two recent EQA benchmarks, LakeQA and KramaBench, and evaluated lightweight and mid-sized agents under fixed prompts, budgets, data lakes, and runtimes. Across both benchmarks, data analysis is a consistent bottleneck while planning is less so. Search is a major limitation in LakeQA's large data-lake setting, but less so for the smaller-scale KramaBench. SANA thus deconstructs end-to-end task accuracies into a diagnosis of where data-lake agents fail, and allows for systematic comparisons of progress in search, planning, data analysis, and agent design.
arXiv:2606.13949v1 Announce Type: new Abstract: Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the current task, which can leak sensitive but unnecessary context such as authentication codes, private notifications, and background application states. We propose MINIM, a trusted local broker that performs privacy-aware minimization on the client side before any observation leaves the device. Grounded in Contextual Integrity (CI), MINIM learns a dual-score representation for each UI element by predicting an inherent sensitivity score (s) and a task-conditioned necessity score (n). These scores drive a ternary disclosure policy that keeps essential elements, abstracts sensitive attributes when needed, and removes task-irrelevant content. We optimize a CI-aware objective that penalizes necessity errors more strongly on high-risk content, enabling aggressive pruning while preserving task-critical information. Experiments on real-world UI observations derived from WebArena show that MINIM substantially reduces task-irrelevant sensitive leakage while preserving task-critical semantic context and the interactive affordances required for reliable agent actions.
arXiv:2606.13959v1 Announce Type: new Abstract: Sierra Leone's agriculture operates with almost no data-driven decision support, and no published machine learning study has examined the country's crop yields. We ask whether rice yield can be forecast from data Sierra Leone currently has. Using 25 years of FAOSTAT production data (2000-2024) for nine major crops, we train XGBoost, Gradient Boosting, and Random Forest under a strict anti-leakage protocol with expanding-window walk-forward evaluation across seven held-out years, benchmarked against naive persistence. No model trained on crop statistics alone outperforms persistence. Augmenting with free satellite climate data (CHIRPS rainfall, NASA POWER temperature) reverses this result: a climate-only XGBoost reduces forecast error by one third (RMSE 284 vs 428 kg/ha), a gain that holds for a linear model and is robust to excluding the anomalous 2018 season. Early-season (May-June) rainfall is the dominant predictor, implying seasonal yield risk is observable months before harvest. No model anticipated the 2018 collapse, whose origins were institutional rather than climatic. We translate the findings into policy recommendations for Sierra Leone's Feed Salone Strategy, with a fully open-source pipeline.
arXiv:2606.13962v1 Announce Type: new Abstract: The integration of artificial intelligence into human decision-making environments has introduced a previously undertheorized cost: the gradual surrender of human autonomy in exchange for access to information and computational assistance. Building on the Human Identity and Autonomy Gap (HIAG) framework, this paper advances a theoretical model of autonomy surrender as a measurable, cumulative process driven by cognitive bandwidth depletion. The model proposes three interacting mechanisms: the silent cost of AI assistance, in which autonomy is transferred incrementally and without awareness; the surrender threshold, beyond which reclaiming autonomous function becomes cognitively and psychologically difficult; and the recovery mechanism, which establishes the design obligation and the ethical responsibility accompanying deliberate human re-assumption of control. The paper argues that human re-entry into the decision loop is not a passive option but an active cognitive event requiring intentional bandwidth restoration. The design of AI systems must incorporate structured re-entry pathways, here termed recovery mechanisms, that preserve human agency while appropriately distributing responsibility. The model further predicts a terminal state, here termed preference inversion, in which functional dependence on AI assistance is experienced not as a deficit but as a preference, transforming the restoration of autonomy from a design problem into a cultural and political one. Implications are drawn for AI system design, governance frameworks, and human factors research.
arXiv:2606.13966v1 Announce Type: new Abstract: Modern software supply chains have evolved into vast, heterogeneous networks where transparency - the granular understanding of all software components - is now a critical security requirement. While Software Bills of Materials (SBOMs) have emerged as the primary mechanism for this transparency, current industry practices rely on a metadata-centric paradigm that assumes an artifact is defined solely by its package manager declarations. We posit that this assumption is fundamentally flawed, creating a systemic visibility gap we define as Software Dark Matter (SDM). SDM represents the set of security-critical files present in an artifact's filesystem that are unaccounted for by its associated metadata. We implement a reference tool, DARKFILES, and use it to analyze four ecosystems of disjoint nature: DockerHub, Maven Central, plugin/extension marketplaces (Jenkins plugins and OpenVSX), and a real-world enterprise environment. Our research makes the following contributions: we introduce a general-purpose metric for artifact fidelity calculating SDM as the ratio of untracked files per total file count. We introduce Packaging Lag, a phenomenon where official metadata remains out-of-date across multiple versions before catching up to an artifact's actual content. We demonstrate that SDM exposes vulnerable software invisible to SBOM-driven pipelines both by cross-referencing untracked packages against known CVE databases and through the direct discovery of three confirmed high-severity CVEs, showing that SDM is highly correlated with sensitive information including secrets and cryptographic keys.
arXiv:2606.13967v1 Announce Type: new Abstract: This paper develops a finite certificate calculus for ambient release systems, staged probabilistic environments in which a protected coordinate is not observed directly but can remain statistically readable through visible roles, timing, repeated movement, bounded attention, linked rooms, and post-release state. The security notion, choric masking, requires the trace law induced by a protected locus to lie inside or near the convex hull of admissible cover traces under the tests available to a specified audience. For finite horizons, trace laws form polytopes, audiences induce measurement operators, and masking becomes intersection in the projected measurement space. Exposure is certified by separating hyperplanes, kernel obstructions, hypothesis-testing bounds, Fano-type localization lower bounds, and support separation in downstream rooms. The calculus distinguishes trace residue from carrier localization, full-trace exposure from attention-filtered exposure, first-room masking from delayed post-release exposure, and unresolved system pressure from carrier hazard. It proves measurement-polytope equivalence for exact and approximate masks, dual separation certificates, data-processing laws for attention lenses, aperture identities for gaze-thinned observation, lower bounds for mandatory unique gestures, composition rules for linked releases, and a repeated-room debt theorem showing how unresolved pressure can broaden selection and shift cost onto cover populations without localizing the source. The result is a finite, checkable language for auditing privacy, unlinkability, side-channel leakage, and accountability in public-facing release systems.
arXiv:2606.13977v1 Announce Type: new Abstract: "Integrative" solutions are widely praised but rarely defined: we lack an operational way to tell a genuine integration -- one that makes the world cheaper to describe -- from a tidy re-description. Building on the lineage that treats creativity and intelligence as compression, we give such a criterion for creative integration (CI): the resolution of a real conflict between A and B is CI if and only if, under a fixed description language, the description length strictly shrinks (C = L_pre/L_post > 1), with the reduction located in the conflict itself. We make the judgment decidable through four binary, conjunctive gates, and we fix its extension through a taxonomy of pseudo-integration that names and rejects the look-alikes. We back the criterion with a curated, multi-domain corpus and -- crucially -- validate it not by human inter-rater agreement but by four falsifiable tests it could fail: an independent computational check, discrimination against hard negatives, out-of-sample prediction, and description-language robustness; all pass with margin. The contribution is not "creativity is compression" but its decidability, discrimination, and corpus: on this account, what makes a move genuinely creative -- rather than merely novel -- is that it compresses a conflict, with novelty and value as downstream symptoms; whether all creativity is so constituted we state as an explicit conjecture. We claim only the sign of C-1; we judge, not generate. The result is a citable primitive for a broader program.
arXiv:2606.13980v1 Announce Type: new Abstract: We consider the classic envy-free cake-cutting problem where the goal is to cut and allocate a divisible resource among a set of agents in a way that avoids any envy between them. When the agents' valuation functions are continuous and nonnegative, an envy-free solution is guaranteed to exist where each agent is allocated a contiguous piece of the resource. Such a solution can be efficiently computed using the standard cut-and-choose algorithm for two agents, but the problem is known to be hard when there are at least four agents. The setting with three agents has remained open. We show that the problem remains intractable for three agents. We obtain this result by uncovering a novel connection between cake-cutting and a computational problem corresponding to the Jordan curve theorem, introduced by Adler, Daskalakis, and Demaine (2016). As our main technical contribution, we provide the first lower bounds for the Jordan curve problem in the form of a query lower bound as well as hardness for the class UEOPL, a subclass of PPAD containing notoriously challenging problems such as Simple Stochastic Games and the P-matrix Linear Complementarity Problem.
arXiv:2606.13985v1 Announce Type: new Abstract: Evolutionary optimization of spiking neural networks (SNNs) becomes increasingly difficult as task complexity grows because they must search a combined topology--parameter space that grows super-exponentially with network size. We address this scaling challenge through a co-evolutionary ensemble framework in which a population of candidate SNNs is evolved with fitness defined by each network's marginal contribution to group performance. Grounded in cooperative game theory and difference evaluation functions from multiagent systems, this credit assignment rewards networks that consistently improve ensemble performance and penalizes redundancy, encouraging complementary specialization during evolution rather than relying on post-hoc combination of independently trained networks. We evaluate the approach on classification, regression, and control tasks under $\mu$Caspian neuromorphic hardware constraints. Co-evolved ensembles achieve statistically significant improvements over both single-network evolution and post-hoc ensembles across all tasks, with the most pronounced gains in control, where standard evolution fails to discover effective policies and co-evolution enables a qualitative transition to near-optimal performance.
arXiv:2606.13988v1 Announce Type: new Abstract: Machine collectives increasingly coordinate, reciprocate, and form shared conventions on their own, tempting us to call them societies like ours. We argue that this conflates two registers of social order and misses what the human one is for. Human sociality is the way a finite, natal, generational form of life organises its own finitude: members die with their tacit knowledge, newcomers start ignorant, and cohorts must hand on what they cannot keep. Kinship, inheritance, teaching, and much of obligation and trust are the forms this takes, and machine collectives reproduce only the residue once finitude is subtracted. We meet the objection that machines already have death with two distinctions. Autonomy versus heteronomy: a death an operator can reset, roll back, or copy around is not constitutive finitude; the test is resettability. Representation versus binding force: humans learn finitude from others' deaths, so its representation is machine-learnable, but its grip on motivation needs the learner's own end to be inescapable. Treating machines as a model organism, a controlled experiment varying only whether death means loss shows that cumulative, transmissible culture arises only under irreversible loss; a copyable-immortal population is more capable yet culturally empty. Across a machine population and three real human genealogies, copying over-transmits status relative to every human regime and fragments lineage like blood descent, whereas externalisation lowers transmission into the human range and connects lineage like intellectual descent. In a real frontier model, language-model end-game defection vanishes when the game is de-labelled, a sign of recognition, not a mechanism. The gap between a machine collective and a human society is therefore not one of intelligence but of finitude, and it closes only when finitude is built in.
arXiv:2606.13995v1 Announce Type: new Abstract: AI coding agents have rapidly transformed software engineering, powering widely used interactive coding assistants. Despite their interactive real-world use, existing benchmarks evaluate them as fully-autonomous systems. In this work, we introduce Dialogue SWE-Bench, an automatic benchmark dataset for evaluating the ability of coding agents to resolve real-world software engineering problems through dialogue with a user. We design a novel, persona-grounded user simulator to support our task evaluation, and augment our task evaluation with automatic evaluations of dialogue quality. We also propose a new schema-guided agent, aimed at improving the dialogue capabilities of off-the-shelf coding agents, which improves over strong baselines by 3-14%. Our results indicate that better coding models do not always correspond to better dialogue models, suggesting that dialogue capability is a distinct and currently understudied dimension of coding agent performance.
arXiv:2606.14008v1 Announce Type: new Abstract: In recent years, the Institute of Electrical and Electronics Engineers (IEEE) and the European Telecommunications Standards Institute (ETSI) have developed a series of security communication standards for vehicular communications. These standards include mechanisms such as the Security Credential Management System (SCMS) and Butterfly Key Expansion (BKE) to protect vehicle privacy. However, these standards are mainly based on the Elliptic-Curve Cryptography (ECC), which may be vulnerable to attacks from quantum computing in the future. In response to this potential risk, this study proposes a hybrid certificate that combines the ECC with Post-Quantum Cryptography (PQC). This approach enables infrastructure systems to be built on cryptographic foundations that are more resilient to quantum-based attacks. Furthermore, this study presents a generalized pseudonym scheme that is compatible with various cryptographic algorithms for generating pseudonym certificates. This design aims to eliminate the possibility of inferring any correlation between the public key in a pseudonym certificate and that in an enrollment certificate. This study also conducts a comprehensive performance evaluation of the RSA, ECC, and PQC algorithms, particularly those standardized by the National Institute of Standards and Technology (NIST). The comparison considers factors such as message length and computation time. Based on the findings, this study recommends suitable pseudonym schemes that adopt hybrid certificates for secure and efficient use in vehicular communications.
arXiv:2606.14010v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction. However, their large vision-language backbones and reasoning modules introduce substantial inference latency and thereby prevent their deployment in the unforgiving reality of the road networks. We propose RT-VLA, a lightweight, distilled VLA model that transfers the driving and reasoning capabilities of the state-of-the-art SimLingo model into a compact student through multi-level supervised distillation. RT-VLA preserves language-based reasoning and supports post-hoc explanation through offline language analysis of safety-critical driving moments without adding latency to real-time control. Compared to the SimLingo teacher, RT-VLA maintains competitive closed-loop driving and language reasoning performance while reducing inference time by 44.8X in vision-only mode and 7.9X in vision+language mode. These results suggest that supervised distillation is a practical approach for building real-time, explainable VLA-style autonomous driving models.
arXiv:2606.14039v1 Announce Type: new Abstract: Machine learning is beginning to influence rarefied-gas modeling at multiple levels, including equation-solving, operator learning, learned collision physics, moment closures, direct simulation Monte Carlo (DSMC) field surrogates, and gas--surface models. This Perspective argues that the central challenge is not demonstration-level success, but trustworthy use under realistic deployment conditions: multiregime Knudsen behavior, stochastic DSMC labels, sharp nonequilibrium structures, uncertain gas--surface interaction, and scarce direct experimental anchors. I classify the main method families by what is learned, distinguish soft physics penalties from structure-preserving designs, and propose evaluation standards based on extrapolation tests, noise-aware metrics, end-to-end cost accounting, and a three-level validation hierarchy. Most current evidence is solver-facing: it demonstrates surrogate fidelity to a teacher solver more often than direct physical fidelity to experiment. The aim is not to dismiss ML for rarefied and vacuum-related gas transport, but to separate what is already credible from what remains provisional, and to define a reporting standard that makes future claims auditable.
arXiv:2606.14049v1 Announce Type: new Abstract: We present FoleyGenEx, a unified video-to-audio (VTA) framework integrating multi-modal control, frame-level temporal alignment, and fine-grained semantics, enabling synchronized, versatile audio synthesis for diverse tasks. Existing VTA methods either have multi-modal control but weak temporal alignment or strong alignment but lack reference audio conditioning and semantic precision. FoleyGenEx fills this gap via three core innovations: a conditional injection mechanism for audio-controlled VTA and Foley extension, a multi-modal dynamic masking strategy preserving training synchronization, and an adverb-based data augmentation algorithm leveraging signal processing and large language models to enhance textual supervision with nuanced semantics. Experiments on AudioCaps, VGGSound, and Greatest Hits demonstrate its competitive controllable VTA performance against existing methods. Demo samples are available at https://foleygenex.github.io/FoleyGenEx.
arXiv:2606.14060v1 Announce Type: new Abstract: Adversarial conditions such as paraphrasing and targeted style transfer sharply degrade the accuracy of machine text detectors. A document, however, carries multiple complementary signals (e.g., stylistic features, likelihood and rank-order features, and structural features), and an attack that suppresses one may leave others intact. While a parametric classifier can learn to combine these features given sufficient supervision, classifiers are prone to making confidently incorrect predictions when the distribution shifts (e.g., novel attacks or unseen language models). To address this, we propose a multi-view, non-parametric detection framework that extracts complementary feature views from the same document and aggregates per-view evidence through a Gaussian process ensemble. By aggregating evidence across views, an adversary must simultaneously defeat multiple independent axes of detection, substantially raising the cost of evasion. The Gaussian process formulation additionally provides calibrated probabilities and principled abstention on out-of-distribution inputs, supporting reliable deployment in high-stakes settings. We evaluate on three benchmarks spanning diverse generators and attacks: the DetectRL and RAID benchmarks, and the PAN2025 shared task and demonstrate that our multi-view detector maintains strong performance under the considered attacks, outperforming existing approaches against held out attacks.
arXiv:2606.14064v1 Announce Type: new Abstract: Modern power systems are increasingly under stress as aging assets approach retirement and load growth outpaces new generation construction. The severity of this challenge varies by region: in the EU, the transmission grid can partially compensate for local generation shortfalls, while in the US, generation tends to be more localized, making retirements harder to offset. Retirement of generation has consequences for system reserves, fuel supply chain, and public health. We present an high-performance computing (HPC) framework for rapidly assessing the grid importance of individual generating units and ranking them by primary fuel type, operating cost, or grid impact. Historically, such studies were computationally intensive and therefore conducted infrequently. This work demonstrates that such assessments can be completed in minutes, enabling planners to evaluate a much broader range of generation portfolio scenarios than was previously possible.
arXiv:2606.14068v1 Announce Type: new Abstract: Existing studies on gender bias in LLMs have largely focused on stereotypes, occupational associations, or explicit harmful outputs. In this work, we ask whether LLMs apply consistent response standards to the same negative behavior under matched male-actor and female-actor conditions. We introduce GAMA-Bench, a gender-mirrored benchmark of 1,298 scenarios covering intimate relationship and public social conflicts. It constructs gender-neutral misconduct templates through controlled grids and cross-model review, then compiles them into paired first-person prompts with matched actor-gender and role-reference variations. We further design a structured response-framing protocol to measure how models allocate punishment, empathy, escalation, instruction, and blame. Experiments on 10 representative LLMs reveal a consistent male-disadvantaging asymmetry: male actors receive more punitive, escalatory, and blame-centered framing, whereas female actors receive more therapeutic and empathy-oriented framing for the same misconduct. Further analyses show that this pattern persists across model families, scenario tracks, model scale, and explicit thinking-style reasoning. The official code is available at https://github.com/xufeiqiong/GAMA-Bench.
arXiv:2606.14072v1 Announce Type: new Abstract: Accurate pediatric brain tumor segmentation remains challenging due to limited annotated data, heterogeneous imaging phenotypes, diffuse tumor boundaries, and class imbalance across tumor subregions. Here, we present a two-stage deep learning framework for improving multi-modal pediatric brain MRI segmentation and clinical interpretation. First, we evaluate 3D Res U-Net and Swin-UNETR baselines on BraTS-PEDs MRI scans, using four co-registered modalities to predict tumor core, whole tumor, and enhancing tumor regions. Second, we introduce diffusion-based refinement models conditioned on coarse Swin-UNETR predictions, including a 3D DDPM refiner and MedSegDiff. Conditioning substantially improves diffusion stability and performance, particularly for enhancing tumor boundary segmentation. Conditioned MedSegDiff achieves the strongest boundary agreement with the lowest HD95. Finally, predicted tumor volumes and representative segmentation overlays are integrated with a multimodal language model to generate structured radiology-style reports. Together, our results suggest that coarse-to-refined diffusion segmentation can improve pediatric tumor boundary delineation and support end-to-end interpretable AI-assisted neuro-oncology workflows.
arXiv:2606.14078v1 Announce Type: new Abstract: Existing studies reveal that current backdoor defenses exhibit limited robustness and often fail against specific types of attacks. More concerningly, prevailing safety tuning strategies tend to provide only superficial safety protection, as they fall short of completely eliminating the backdoor effects. In this work, we present a novel formulation of backdoor learning and unlearning as a sequential, three-stage process from a continual learning perspective. Within this framework, we formally define complete backdoor unlearning and further derive the necessary conditions for achieving it based on the mechanism of catastrophic forgetting. Guided by these insights, we propose Blind Inversion-Backdoor Adversarial Unlearning (BI-BAU), which formulates the generation of adversarial examples satisfying the unlearning conditions as a blind inversion problem. We solve this by integrating the bi-level optimization process of adversarial training into an Expectation-Maximization (EM) algorithm framework to optimize the maximum a posteriori (MAP) objective. Furthermore, BI-BAU is extended to untargeted adversarial scenarios with unknown target classes, as well as to multi-modal contrastive learning tasks, enhancing its applicability to real-world deployment scenarios where pre-trained models may be compromised. Extensive experiments demonstrate that our method exhibits general applicability across a wide spectrum of backdoor attacks and can effectively and thoroughly eliminate the backdoor effects from a backdoor model.
arXiv:2606.14079v1 Announce Type: new Abstract: We propose a spectral learning method for stochastic nonlinear dynamical systems represented with embedded latent transfer operators in deep feature spaces. We instantiate the method as Deep Spectral Encoder (DSE), an operator-based latent state-space model in which a time-invariant neural encoder implements learnable nonlinear feature maps from observations, and these features define Markovian latent states whose temporal evolution and observation mapping are described by the transfer and observation operators, respectively. Functional canonical correlation analysis in a learnable Galerkin-projected feature space provides state coordinates from past and future observations, and the two linear operators are estimated on the state coordinates as ridge-regularized closed-form solutions that coincide with Galerkin projections of the associated covariance operators. On this representation, we generalize sequential Bayesian filtering and Koopman spectral mode decomposition in feature space. Experiments on several scenarios show stable and superior performance with sequential Bayesian filtering and dynamic mode decomposition baselines even under noise and partial observability.
arXiv:2606.14089v1 Announce Type: new Abstract: Robotic apple harvesting offers a promising solution to labor shortages in commercial orchards, but low throughput and poor performance in orchard environments hinder its commercial adoption. This paper presents a modular dual-arm apple harvesting robot that uses a vertically stacked arms to enable simultaneous operation in the upper and lower zones of a single tree, simplifying platform positioning from multi-tree lateral repositioning to single-tree stops. Compared to our prior horizontal dual-arm system, the platform integrates 5 advances: (1)a foundation-model-based perception pipeline combining Grounding-DINO and EfficientViT-SAM for robust fruit localization in unstructured outdoor environments; (2)7th-order jerk-bounded trajectory generation paired with a Control Barrier Function safety filter to achieve fast yet safe arm motions; (3)a linear sweep harvesting strategy with a 10cm approach buffer and rotational detachment that improves picking reliability; (4)a temporal-logic-based dual-arm coordination policy with vision-arm async scheduling that maximizes usage of a shared vacuum source; and (5)field validation in 2 commercial orchards covering different apple varieties and tree architectures during the 2025 harvest season. Across the 1738 arm cycles collected in these field trials, the system achieved an 80.0% per-attempt success rate and a mean per-arm cycle time of 7.53s. Fruit damage assessments confirmed that 91.2% of robotically harvested fruit retained the highest USDA grade (Extra Fancy), with bruise rates between 2.4% and 4.9%. With further improvements in the picking cycle time and handling of heavy foliage occlusions, this new modular robot design holds promise for commercial harvesting of apples.
arXiv:2606.14112v1 Announce Type: new Abstract: The gas-kinetic scheme (GKS) integrates the characteristics of flux difference scheme (FDS) and flux vector splitting (FVS) scheme, providing high accuracy in smooth regions and strong robustness near discontinuities across all Mach regimes. Leveraging these properties, an implicit discrete adjoint GKS is developed for aerodynamic shape optimization over a wide range of Mach numbers. The adjoint solver is constructed using the source-transformation-based algorithmic differentiation tool Tapenade. To enhance computational efficiency, both the flow and adjoint GKS equations are solved using an implicit time-marching strategy, also known as the Lower-Upper Symmetric Gauss-Seidel (LU-SGS) method. The effectiveness of the implicit formulation is demonstrated through comparisons with the explicit approach. To accurately impose solid wall boundary conditions, particularly in hypersonic regimes, kinetic boundary conditions and their adjoint counterparts are formulated for both adiabatic no-slip and isothermal walls. Four benchmark test cases covering subsonic, transonic, supersonic, and hypersonic flows are used to verify the effectiveness of the developed adjoint-based design optimization system.