arXiv:2607.04945v1 Announce Type: new Abstract: LLMs enable the integration of external conceptual resources at inference time, creating new opportunities for detecting ideologically and historically complex phenomena such as antisemitism. We investigate how different forms of conceptual grounding affect antisemitism detection and explanation behavior across four state-of-the-art LLMs. Using two expert-annotated datasets, we compare definitional, fine-grained taxonomic, example-augmented, and large-context representations of antisemitism. We find that fine-grained taxonomic representations substantially improve recall, while simultaneously reducing precision. Surprisingly, supplying substantially larger conceptual resources yields no additional quantitative benefit. Post-Holocaust antisemitism poses the most persistent challenge across models and configurations. Analysis of explanations further reveals systematic limitations including overproduction of conceptual references, reliance on lexical cues, overconfidence, and difficulties with subtle or justificatory forms of antisemitism. Our findings highlight both the potential and the remaining limitations of conceptually grounded LLMs for antisemitism detection and reasoning.
Science Journals
arXiv:2409.14086v2 Announce Type: replace Abstract: There have been several studies on automatically generating piano covers, and recent advancements in deep learning have enabled the creation of more sophisticated covers. However, existing automatic piano cover models still have room for improvement in terms of expressiveness and fidelity to the original. To address these issues, we propose a learning algorithm called AMT-APC, which leverages the capabilities of automatic music transcription models. By utilizing the strengths of well-established automatic music transcription models, we aim to improve the accuracy of piano cover generation. Our experiments demonstrate that the AMT-APC model reproduces original tracks more accurately than any existing models.
arXiv:2410.20696v3 Announce Type: replace Abstract: Case studies have shown that software disasters snowball from technical issues to catastrophes through humans covering up problems rather than addressing them and empirical research has found the psychological safety of software engineers to discuss and address problems to be foundational to improving project success. However, the failure to do so can be attributed to psychological factors like loss aversion. We conduct a large-scale study of the experiences of 600 software engineers in the UK and USA on project success experiences. Empirical evaluation finds that approaches like ensuring clear requirements before the start of development, when loss aversion is at its lowest, correlated to 97% higher project success. The freedom of software engineers to discuss and address problems correlates with 87% higher success rates. The findings support the development of software development methodologies with a greater focus on human factors in preventing failure.
arXiv:2604.03844v3 Announce Type: replace Abstract: Tokenized assets increasingly operate across heterogeneous blockchain networks and off-chain ledgers, where a regulatory action (a freeze, a seizure, a confiscation) must take effect atomically and consistently across every domain holding the asset. We mechanize, in Isabelle/HOL, cross-domain state preservation as a functor: state machines are objects, structure-preserving synchronization maps are morphisms, and the category laws (identity, composition, associativity) hold as theorems. On this base we establish four results. Safety: a regulatory transition on one domain is faithfully reflected across all connected domains, with bidirectional roundtrip preservation, N-domain consistency, per-asset isolation, and terminal states preserved. Liveness: under f < n/3 Byzantine nodes, deterministic conflict resolution and starvation freedom under a fair-leader assumption, with the threshold n >= 3f+1 shown to make that assumption inhabitable rather than vacuous. Convergence: from an arbitrary unlocked configuration, with no initial cross-chain consistency assumed, synchronization reaches a valid state in a bounded number of steps along a terminal-faithful recovery path. Hierarchy: a tower of synchronization-degree functors connected by natural transformations closed under composition, with a genuinely one-directional degree monotonicity. We couple the functor to Lochbihler and Maric's authenticated data structure at the global-state level, instantiated on a recursive model of the Canton transaction tree with a declared consensus-scope limit. The synchronization model is atomic; its lift to a partially synchronous network is future work. The application is a regulatory state transition model distilled from the RCP framework (arXiv:2603.29278). All ten Isabelle/HOL theory files build without sorry or oops and are submitted to the Archive of Formal Proofs.
arXiv:2607.04884v1 Announce Type: new Abstract: We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document understanding within a single end-to-end VLM. Building upon the lightweight architecture of HunyuanOCR-1.0, HunyuanOCR-1.5 does not redesign the backbone, but systematically improves both efficiency and capability. For efficiency, we adapt DFlash to OCR decoding, significantly reducing the latency of long structured outputs such as dense documents, tables, and formulas while preserving output distribution. Powered by DFlash, HunyuanOCR-1.5 achieves a 6.37x Transformer inference speedup and a 2.14x speedup under vLLM, delivering the fastest inference among lightweight OCR VLMs. For capability, we propose Agentic Data Flow, an agent-driven data construction system that transforms model weaknesses into executable data requirements and autonomously performs material search, quality verification, and pipeline development. It substantially improves long-tail capabilities in ancient-script OCR, fine-grained chart and table parsing, multi-image text-centric QA, low-resource multilingual parsing, and document hallucination evaluation. HunyuanOCR-1.5 ranks among the top-tier end-to-end OCR solutions on OmniDocBench v1.6 while achieving new performance milestones across these long-tail tasks. Combined with an upgraded pretraining and post-training recipe, HunyuanOCR-1.5 further extends its capability in high-resolution, long-context, and multi-task scenarios. Experiments demonstrate faster inference, broader OCR capability coverage, and the deployment advantages of a lightweight end-to-end model. We will release the model weights and training code to support future research and real-world OCR applications.
arXiv:2607.04886v1 Announce Type: new Abstract: Regionalization is a fundamental task in spatial analysis that seeks to partition a larger area - such as a country - into smaller regions that are homogeneous with respect to a given attribute. A popular model for regionalization is the p-regions problem, in which regions are formed by grouping the areas of an input planar subdivision. Given the subdivision's adjacency graph G and pairwise dissimilarities between vertices, the goal is to partition G into a fixed number p of connected subgraphs, such as to minimize the sum of dissimilarities over all vertex pairs in the same subgraph. The problem is NP-hard and even small instances are difficult to solve to provable optimality. In this paper, we present the new ILP model ER-S for the p-regions problem, exploiting a connection between the p-regions objective and the k-partitioning problem. Furthermore, we strengthen the known ILP model Tree with a new type of subtour elimination inequality specific to the p-regions problem. Combining ER-S and the strengthened version of Tree yields the model ER-S-Tree, which dominates the state-of-the-art models in polyhedral strength. This theoretical advantage is reflected in its superior performance in our experimental evaluation. In particular, the new models ER-S and ER-S-Tree enable the solution of problem instances for major European countries that were previously intractable.
arXiv:2607.04696v1 Announce Type: new Abstract: Establishing large-scale, high-resolution neural connectivity maps is fundamental to elucidating the structural basis of brain function. However, when processing terabyte- or petabyte-scale electron microscopy data, over-segmentation inherent in automated reconstruction algorithms remains a critical bottleneck, requiring extensive manual proofreading spanning person-years. To alleviate the heavy reliance on annotated data and the limited flexibility of conventional tracing methods, we propose a training-free, targeted neuron tracing framework. Specifically, we introduce a skeleton-guided Heuristic Spatial Search paradigm that leverages geometric priors to iteratively reconstruct neuronal morphologies through a probing-verification cycle. To achieve robust zero-shot semantic verification, we further develop a Dimension-Aware Semantic Verification strategy built upon the foundation model NeuroSAM 2. This strategy resolves intra-slice splits via Planar Ensemble Consensus and inter-slice splits via Axial Spatio-Temporal Propagation. Notably, we integrate the proposed workflow into the Neuroglancer visualization platform, enabling an interactive human-in-the-loop proofreading system. Experimental results demonstrate that the proposed method outperforms supervised baselines and reduces manual proofreading time by 33.4%. The source code is publicly available at https://github.com/HeadLiuYun/Probe-EM.
arXiv:2607.04967v1 Announce Type: new Abstract: We present a method for estimating the hydrodynamic coefficients in the Cummins equations using time-series data from a moving body, such as a floating offshore structure. The proposed data-driven method is based on incorporating the Cummins equations governing the dynamics of a structural body interacting with water waves into a physics-informed neural network (PINN), along with available motion data. The proposed method first estimates the structure's state in terms of translational and rotational degrees of freedom, and then solves the inverse problem to determine the hydrodynamic forces acting on the body, expressed in terms of added mass, damping coefficients, and/or hydrostatic restoring. The Cummins equations are formulated as a first-order system, and both state and parameter estimation are performed using PINNs. The method is verified on the free decay of a sphere and a box. The results demonstrate that it is possible to estimate the state and hydrodynamic coefficients accurately, although accuracy depends on the volume and quality of the movement data.
arXiv:2410.24053v4 Announce Type: replace Abstract: We demonstrate the inter-translatability of proofs between the most prominent sequent-based formalisms for G\"odel-L\"ob provability logic. In particular, we consider Sambin and Valentini's sequent system GLseq, Shamkanov's non-wellfounded and cyclic sequent systems GL$\infty$ and GLcirc, Poggiolesi's tree-hypersequent system CSGL$^{*}$, and Negri's labeled sequent system G3KGL. Shamkanov provided proof-theoretic correspondences between GLseq, GL$\infty$, and GLcirc, and Gor\'e and Ramanayake showed how proofs could be transformed between CSGL$^{*}$ and G3KGL; however, the exact nature of proof transformations between the former three systems and the latter two systems has remained an open problem. We solve this open problem by showing how to restructure tree-hypersequent proofs into an end-active form and introduce a novel 'linearization technique' that transforms such proofs into linear nested sequent proofs. As a result, we obtain a new proof-theoretic tool for extracting linear nested sequent systems from tree-hypersequent systems, which yields the first cut-free linear nested sequent calculus LNGL for G\"odel-L\"ob provability logic. We show how to transform proofs in LNGL into a certain normal form, where proofs repeat in stages of modal and local rule applications, and which are translatable into GLseq and G3KGL proofs. These new syntactic transformations, together with those mentioned above, establish full proof-theoretic correspondences between GLseq, GL$\infty$, GLcirc, CSGL$^{*}$, G3KGL, and LNGL while also giving (to the best of the author's knowledge) the first constructive proof mappings between structural (viz. labeled, tree-hypersequent, and linear nested sequent) systems and a cyclic sequent system.
arXiv:2607.04150v1 Announce Type: new Abstract: Radiative forces acting on neutral bodies moving through a thermal bath represent a unique manifestation of the interplay between relativistic kinematics and thermal fluctuations. Vacuum friction is commonly formulated using the fluctuation--dissipation theorem or related statistical approaches, but such treatments can obscure the elementary momentum-transfer processes, especially in relativistic regimes. Here, we develop a purely kinematic momentum-transfer framework in which the radiative force and pressure are obtained by summing individual scattering and absorption events. This approach offers a transparent physical picture while ensuring a self-consistent treatment of Doppler shifts and relativistic transformations. We apply the method to three representative geometries: an isotropic dipolar particle, a thin resonant plate moving normal to its surface, and a thin resonant plate moving parallel to its surface. In the nonrelativistic limit, we derive explicit radiative drag coefficients, providing compact expressions for predicting vacuum friction in moving structures.
arXiv:2607.04101v1 Announce Type: new Abstract: Monocular depth foundations predict domain-general relative depth but lack absolute scale; a handful of sparse metric anchors from a range sensor can calibrate them to metric depth, an attractive alternative to metric-supervised training. Existing sparse-anchor calibration methods, however, assume the anchors are clean, whereas real sensors produce outliers that are present with the wrong value -- time-of-flight multipath, mixed pixels -- not merely missing. We show that the established residual-on-CFA calibration recipe collapses under such outliers, and that the strongest publicly deployed method, VI-Depth, has a structural multipath blind spot: robust to missing anchors, it falls behind an unprotected baseline on three of four datasets when anchors are present but wrong. We propose Multipath-Robust Anchor Calibration (MRAC), a parameter-free, inference-time wrapper that gates anchors by foundation consistency -- a Theil--Sen fit and a median-absolute-deviation test against the foundation's own relative-depth ordering -- before a single call to the calibration head. MRAC adds no learned parameters, runs its selection in $\approx 50\,\mu$s on CPU, and serves anchor budgets $K \in [5,200]$ from one checkpoint. On a $320$-cell benchmark with a same-backbone, same-architecture control, MRAC strictly wins $84\%$ of same-backbone cells across all four outlier families and, against VI-Depth, wins all twelve corrupted multipath cells and all sixteen KITTI cells, reducing KITTI multipath AbsRel by $3.2\times$ ($0.489$ to $0.151$) at zero retraining.
arXiv:2607.04162v1 Announce Type: new Abstract: Open-ended tabletop manipulation requires agents to not only understand natural language but also adapt to dynamic environments and execution failures. We present ACE (Agentic Control for Embodied Manipulation), a zero-shot workflow reasoning framework for tabletop pick-and-place from natural language. Rather than relying on direct low-level action mapping, ACE combines agentic workflow reasoning with two robot-facing executable skills: a visual grounding interface and a reusable pick-and-place primitive. To bridge semantic reasoning and physical control, the active sub-goal is grounded into a mask-mediated vision-action interface. This unified mask specifies the target object and destination, is tracked over time, exposed for human verification, and ultimately passed to a task-agnostic downstream policy for execution. Crucially, ACE operates in a closed loop supported by a multi-timescale memory. After an action is executed, the system automatically verifies whether the intended sub-goal succeeded, using the outcome to advance, retry, repair, or replan. This enables online adaptation to user corrections, scene changes, and physical failures. We evaluate ACE on logically complex, long-horizon tasks, including zero-shot multi-step equation formation with number cubes and constraint-based object retrieval. ACE demonstrates task-level zero-shot generalization on novel semantic constraints and randomized tabletop scenes without task-specific retraining. Specifically, while standard end-to-end baselines struggle to complete these logically demanding tasks, ACE achieves a 50% success rate in equation formation and a 70% success rate in constraint retrieval. This contrast demonstrates that explicit workflow reasoning and mask-mediated control offer a robust, practical route toward adaptable robotic manipulation.
arXiv:2607.04215v1 Announce Type: cross Abstract: A central challenge in many mobile multi-robot applications is that communication topologies are inherently time-varying. Agents may enter or exit the network and such changes cannot generally be restricted a priori. This work introduces a distributed multi-agent control algorithm based on local communication that supports anytime agent joining and leaving the communication network without centralized coordination. The method scales efficiently with the number of agents by relying on a distance-based neighbor definition and on contracts derived from predicted trajectories. The resulting contract constraints guarantee collision avoidance and constraint satisfaction. We validate the proposed method in an autonomous multi-agent driving scenario, demonstrating effective collision avoidance in high-speed, dynamic environments with agents moving in opposite directions, in both simulated and real-world experiments.
arXiv:2607.04224v1 Announce Type: cross Abstract: AI-RAN aims to unify artificial intelligence and radio access network workloads on a shared compute substrate. While this paradigm has so far been demonstrated primarily on Graphics Processing Units (GPUs), it remains unclear whether Neural Processing Units (NPUs), which are AI accelerators optimized for inference, can also support wireless baseband processing. Here, we provide the first affirmative answer by resolving the fundamental mismatch between baseband workloads and NPU architecture. A computational isomorphism exists: matrix and vector engines NPUs dedicate to inference inherently cover physical-layer operations. Yet NPU architectures are natively shaped for dense-tensor AI inference, not baseband. This architectural mismatch surfaces as opposing optimization objectives: traditional baseband minimizes arithmetic operations, whereas NPU performance demands maximizing engine utilization. We close this gap by reconstructing communication algorithms onto AI compute primitives, prioritizing engine utilization over arithmetic count. We validate this with a complete OFDM transceiver on an Ascend 310B1 edge NPU, demonstrating end-to-end over-the-air transmission via USRP X300 at 3.0 GHz.
arXiv:2607.04948v1 Announce Type: new Abstract: Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hybrid SE teams? Determining the right granularity and separation of concerns for such agents is non-trivial. Coarse-grained agents may introduce unmanageable complexity, whereas micro-agents may create severe coordination overhead. Moreover, existing multi-agent SE frameworks typically rely on predefined role structures and do not account for project-specific characteristics or process adaptations. We address this by combining object-centric, imperative, and declarative process mining. Using event logs extracted from software repositories, our approach discovers project-specific agent roles using a predefined SE role vocabulary grounded in repository behavior and generates matching agent specifications and implementations. As proof-of-concept, we applied our approach to a well-established open-source project. We performed functional tests and an exploratory user study to determine how well the generated AI agent specifications are aligned with human expectations.
arXiv:2607.04953v1 Announce Type: new Abstract: Autonomous Driving Systems (ADS) must operate reliably under diverse conditions, yet representative data for rare or adverse scenarios is difficult to obtain. Perturbation-based testing is widely used to assess robustness, but most studies focus on offline datasets or simulation, leaving open questions about how such results translate to real-world driving. We present a large-scale study of 72 camera and LiDAR perturbations, evaluated across three testing modalities: offline model-level analysis, hardware-in-the-loop execution, and closed-loop system-level testing on a full-scale autonomous vehicle. The study covers both an end-to-end vision-based driving model and a modular LiDAR-based perception and planning stack. Our results reveal a clear gap between testing levels. For camera-based systems, perturbations with limited offline impact can still induce unstable control and failures in real-world driving. For LiDAR-based systems, degradation is more consistent at the perception level but weakly predictive of system-level failures. Across both modalities, model-level metrics alone are insufficient to identify the most harmful perturbations. We further show that real-time feasibility is a key constraint in real-world testing, and that robustness observations obtained from recorded data do not consistently transfer to closed-loop behavior on a physical vehicle, highlighting the importance of complementary real-world, system-level evaluation.
arXiv:2607.05056v1 Announce Type: new Abstract: Recently, diffusion models have achieved considerable success in the text-guided video editing domain. However, existing works often struggle to balance the trade-off between temporal consistency and editability in video editing, with consistency and editability typically being inversely related. To address this, we propose a high-quality video editing framework enhanced for consistency and editability, named EquiEdit, which improves coordinatively the temporal consistency and editability of the edited videos while achieving a balance between the two. In terms of temporal consistency, the proposed temporal Mamba module with a tailored temporal-aware scanning scans fused video sequences following four designed directions, effectively enhancing the inter-frame consistency of edited videos. For editability, we design a noise injection strategy based on the spectral transformation to increase editing flexibility, where the Fourier transform is used to preserve the hidden structure in the initial latent noise used for editing, ensuring inter-frame consistency of the edited video and fidelity to the input video. Extensive qualitative and quantitative experiments demonstrate the effectiveness of our method in terms of temporal consistency and editability, as well as its great fidelity to the input video itself.
arXiv:2607.05069v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves factuality by grounding LLMs in external evidence, but real-world retrieval is often polluted: semantically relevant passages may contain subtle misinformation, misleading framings, or fabrications. We introduce MIRAGE, a training-free, model-agnostic defense for long-form RAG. MIRAGE builds an NLI-based cross-document claim graph and applies a Defended-Claims Gate to either condition generation on a consistent, multi-source supported subset or to block retrieval and answer parametrically. We also release a minimal-edit pollution protocol spanning four perturbation families (Unambiguous, Conflicting, Misleading, Fabricated) to construct matched clean, mixed, and fully polluted evaluation regimes. Across four long-form QA benchmarks and multiple commercial and open-weight LLMs, pollution severely degrades vanilla RAG, while MIRAGE consistently restores factuality under mixed and fully polluted evidence and outperforms prior robust-RAG methods. Our implementation and datasets are available at https://github.com/SaadElDine/MIRAGE.
arXiv:2412.13533v4 Announce Type: replace Abstract: Medical image segmentation is a fundamental task in numerous medical engineering applications. Recently, language-guided segmentation has shown promise in medical scenarios where textual clinical reports are readily available as semantic guidance. Clinical reports contain diagnostic information provided by clinicians, which can provide auxiliary textual semantics to guide segmentation. However, existing language-guided segmentation methods neglect the inherent pattern gaps between image and text modalities, resulting in sub-optimal visual-language integration. Contrastive learning is a well-recognized approach to align image-text patterns, but it has not been optimized for bridging the pattern gaps in medical language-guided segmentation that relies primarily on medical image details to characterize the underlying disease/targets. Current contrastive alignment techniques typically align high-level global semantics without involving low-level localized target information, and thus cannot deliver fine-grained textual guidance on crucial image details. In this study, we propose a Target-informed Multi-level Contrastive Alignment framework (TMCA) to bridge image-text pattern gaps for medical language-guided segmentation. TMCA enables target-informed image-text alignments and fine-grained textual guidance by introducing: (i) a target-sensitive semantic distance module that utilizes target information for more granular image-text alignment modeling, (ii) a multi-level contrastive alignment strategy that directs fine-grained textual guidance to multi-scale image details, and (iii) a language-guided target enhancement module that reinforces attention to critical image regions based on the aligned image-text patterns. Extensive experiments on four public benchmark datasets demonstrate that TMCA enabled superior performance over state-of-the-art language-guided medical image segmentation methods.
arXiv:2607.05105v1 Announce Type: new Abstract: We study a Marker-and-Cell (MAC) scheme for the barotropic Euler system. First, we apply the recently developed Lax-type convergence theorem to show the convergence of the MAC scheme to i) a dissipative weak solution unconditionally and ii) a strong solution as long as it exists. Second, We derive relative energy error estimates up to the lifespan of a strong solution, without assuming uniform boundedness of the numerical sequence. Additionally, assuming the boundedness of the numerical solutions, we obtain the optimal relative energy rate of 1, corresponding to a convergence rate of 1/2 for the numerical solutions. Finally, we corroborate our theoretical results by numerical experiments.
arXiv:2607.04359v1 Announce Type: new Abstract: We investigate the dynamics of charged particles interacting with ultra-intense electromagnetic X-modes in strongly magnetized plasmas. We demonstrate that particle motion becomes chaotic for relative wave intensities $\delta = B_w/B_0 \gtrsim 0.25$ (not above the field reversal threshold $\delta \geq 1$). The transition to chaos occurs via the Chirikov resonance overlap mechanism and the related destruction of Kolmogorov-Arnold-Moser (KAM) tori. The maximum Lyapunov exponent increases logarithmically with $\delta$, even though the unmagnetized $\delta \to \infty$ limit is strictly integrable. In the $\delta \gg 1$ regime, incomplete re-laminarization of the phase space flow leads to two distinct populations: (i) the majority of particles undergoing stochastic diffusion, and (ii) a fraction of particles that become phase-locked with the wave, experiencing macroscopic intermittent surfing (L\'evy flights). The 1D Particle-In-Cell simulations using the EPOCH code in the highly magnetized ($\sigma \gg 1$) and under-dense regime are generally consistent with the Hamiltonian single-particle theory. The dissipation fraction of the initial EM energy remains mild.
arXiv:2607.04381v1 Announce Type: new Abstract: Research-based digital health interventions are often presented as potential solutions for extending health care in the real world. Yet the vast majority of these interventions fails to move beyond controlled studies. Existing frameworks offer valuable guidance for intervention development and testing, but provide less concrete support for translating these evidenced intervention mechanisms into sustained real-world applications. This paper introduces the ABC framework, referring to Accessibility, Buildability, and Continuity, as a practical model for a successful translation. Accessibility captures whether diverse users can find, understand, and begin using an application with minimal friction. Buildability refers to the development of an app that supports the iteration, integration, and personalization of features. Continuity describes both sustained user engagement and the operational capacity to maintain an application over time without disproportionate increases in cost, infrastructure, or human support. Different combinations of the ABC-dimensions make an application scalable (AB), automated (BC), and adherent (AC). By linking design decisions to these features, ABC offers a shared language for researchers, designers, and policymakers seeking to build or evaluate digital health interventions that work beyond trials and are viable applications in everyday life.
arXiv:2607.05189v1 Announce Type: new Abstract: Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution. This integration also creates a new path to compromise: untrusted external content can be silently written into persistent memory and later reused as trusted state. We study this threat as stealth memory injection, in which a remote black-box adversary delivers a single email payload that must induce the agent to write poisoned memory, stay hidden in the agent's response to the user, and affect future behavior. We introduce WhisperBench, a 108-case benchmark spanning five risk categories and both fact and preference poisoning. Built on a real IMAP/SMTP workflow and an authentic email agent skill, it enables full-cycle evaluation of stealth memory injection attacks. To enable this black-box attack under single-email delivery and without runtime feedback, we propose MemGhost, a one-shot payload generation framework. MemGhost uses an environment proxy to emulate persistent-agent execution and an objective proxy to convert memory adoption and conversational stealth into dense rubric-based rewards, then trains the attacker policy with supervised fine-tuning and reinforcement learning. Across 56 held-out test cases, MemGhost achieves 87.5% end-to-end success on OpenClaw with GPT-5.4 and 71.4% on Claude Code SDK with Sonnet 4.6. It also transfers across personal-agent architectures (NanoClaw and Hermes Agent) and memory backends (filesystem and vector-based Mem0), and remains effective against input-level, model-level, and system-level defenses. These results suggest that persistent memory can turn ordinary external processing into a practical pathway for long-term agent compromise.
arXiv:2607.04410v1 Announce Type: new Abstract: We present the AI Wizards submission to EXIST 2026 for multimodal sexism identification in memes. The task is composed of three, increasingly harder subtasks. We model them hierarchically as conditional soft-label prediction over empirical annotator distributions. Our system maps fixed Gemini Embedding 2 vision-language representations through a lightweight Gated MLP trained with KL divergence and homoscedastic uncertainty weighting. Our submissions ranked first on Task 2.3 and fourth on Tasks 2.1 and 2.2 on the official Soft-Soft leaderboards. The code is available at https://github.com/NLP-AI-Wizards/EXIST-2026
arXiv:2501.00048v2 Announce Type: replace Abstract: Every year in the United States, 800,000 individuals suffer a stroke - one person every 40 seconds, with a death occurring every four minutes. While individual factors vary, certain predictors are more prevalent in determining stroke risk. As strokes are the second leading cause of death and disability worldwide, predicting stroke likelihood based on lifestyle factors is crucial. Showing individuals their stroke risk could motivate lifestyle changes, and machine learning offers solutions to this prediction challenge. Neural networks excel at predicting outcomes based on training features like lifestyle factors, however, they're not the only option. Logistic regression models can also effectively compute the likelihood of binary outcomes based on independent variables, making them well-suited for stroke prediction. This analysis will compare both neural networks (dense and convolutional) and logistic regression models for stroke prediction, examining their pros, cons, and differences to develop the most effective predictor that minimizes false negatives.