arXiv:2607.11167v1 Announce Type: new
Abstract: Representing manipulation actions as 2D trajectories in the camera plane provides a compact and interpretable basis for learning complex 3D manipulation policies. However, it also creates challenges from out-of-frame trajectories and limited precision. We propose Pix2Act, an imitation learning method that addresses these challenges by generating continuous image-space keypoint trajectories in each camera plane and losslessly recovering end-effector poses via triangulation. This reformulates high-dimensional 3D control as a simpler, more learnable 2D prediction problem. Crucially, it aligns observations and actions in the same coordinate space, enabling equivariant transformations to jointly rotate individual camera images together with their image-space actions. We analyze the symmetry properties of this augmentation and design a network architecture that can fuse multiple camera views while respecting their per-view rotations. As a result, Pix2Act implicitly enlarges the support of the data distribution and learns invariant action structures across transformations, yielding improved generalization and overall performance. Across diverse simulated and real-world manipulation tasks, Pix2Act outperforms state-of-the-art baselines and remains robust under camera perturbations.
Science Journals
arXiv:2607.11643v1 Announce Type: new
Abstract: Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints. Existing methods typically adapt foundation models with limited robot data, often sacrificing visual knowledge acquired during large-scale pre-training. We present Xiaomi-Robotics-U0, a 38-billion-parameter multimodal autoregressive model for unified embodied synthesis. It treats embodied generation as an extension of foundation image and video generation and jointly optimizes text-to-image generation, image editing, embodied scene generation, embodied transfer, and embodied video generation. This unified framework preserves the generalization of the pre-trained world foundation model while adapting it to embodied settings. Xiaomi-Robotics-U0 is the first model to support high-quality multi-view scene generation across multiple robot embodiments and to introduce structured, controllable embodied transfer for fine-grained editing while preserving multi-view consistency and interaction dynamics. It achieves state-of-the-art results on single-step and sequential generation tasks, outperforming GPT-Image-2.0 in human evaluations of embodied scene generation and transfer, ranking first on World Arena for embodied video generation, and improving the out-of-distribution success rate of pi_0.5 from 36.9% to 63.2% on challenging real-world manipulation tasks. These results show that foundation world models can serve both as embodied world models and scalable data engines for embodied intelligence. Code and checkpoints are available at https://robotics.xiaomi.com/xiaomi-robotics-u0.html.
arXiv:2607.11175v1 Announce Type: new
Abstract: The growing ability of large language models and vision language models to jointly interpret and reason over images and text is reshaping medical agents, moving them from task specific predictors toward autonomous systems that perceive, reason, plan, remember, and act in clinical environments. This work departs from the capability first perspective of existing literature and instead begins from clinical deployment, asking what tasks, contamination resistant benchmarks, and interactive training environments are required before medical agents can be trusted in practice. Medical agents are formalized as sequential decision making systems under partial observability, together with a three level autonomy taxonomy spanning assisted, cooperative, and fully autonomous operation. The field is organized along a unified scaling spine consisting of framework scaling, capability scaling, and environment scaling. Within this framework, clinical environment scaling, the integration of tools, data, and clinical gyms, is identified as the most actionable yet underexplored direction for agents operating in PACS, EHR, and FHIR ecosystems. Clinical self evolution, where agents improve through interaction with their environments rather than parameter scaling alone, is further positioned as a key research frontier, drawing insights from self improving agents, agent gyms, and test time compute scaling. Applications across radiology, pathology, ophthalmology, and hospital workflows are examined together with deployment challenges including hallucination, cascading failures, and fairness. By consolidating more than 300 references, with particular emphasis on advances from 2025 to 2026, this work provides a roadmap toward trustworthy, self improving medical imaging systems for real clinical practice.
arXiv:2607.10839v1 Announce Type: new
Abstract: Community-driven scientific pipeline ecosystems are increasingly important for reproducible data-intensive research, but their sustainability depends on more than workflow engines, templates, and testing infrastructure. It also depends on how communities maintain pipelines, integrate contributions, and support users across heterogeneous execution environments. This paper presents a cross-platform empirical study of maintenance and support in nf-core, a large ecosystem of standardized Nextflow pipelines. We analyze 15,760 GitHub issues, 35,411 GitHub pull requests, and 895 Seqera Community Forum discussions to examine what maintenance and support concerns arise, how they differ across artifact types, which factors are associated with resolution outcomes, and how problems and solutions flow between repository-centered and community-centered spaces. We find that issues primarily capture repository-level problem reporting and maintenance coordination; pull requests capture implementation, review, testing, dependency, and template-update work; and forum discussions capture user-facing support around execution failures, containers, cloud and HPC environments, MultiQC reporting, and Nextflow usage. Resolution outcomes are associated with actionability, coordination, and diagnostic evidence. Issue closure is linked to assignees, comments, milestones, bug labels, error mentions, and version information. Pull request integration varies by author role, automation type, draft status, checklists, linked issues, and review routing. Forum accepted answers are more likely when discussions include code blocks, sustained interaction, and concrete technical evidence, while cloud, HPC, and workflow-semantics questions are harder to resolve. Cross-platform analysis reveals strong repository-internal traceability within GitHub, but limited explicit linkage between forum discussions and repository artifacts.
arXiv:2607.10005v1 Announce Type: new
Abstract: We present a fully differentiable far-field transform in cylindrical coordinates for full-area point spread function (PSF) evaluation and optimization of large axisymmetric metalenses. The method computes wave-optical responses of apertures spanning thousands to tens of thousands of wavelengths in diameter (millimeter scales in the visible, centimeter scales in the infrared) in seconds, achieving three to four orders of magnitude speedup over Green's function integration while avoiding the prohibitive memory of two-dimensional FFTs. The approach decomposes vectorial near fields into parallel angular-momentum channels, applies FFTLog-accelerated Hankel transforms, and uses Graf's addition theorem to recenter focal fields under oblique illumination. Analytic adjoint gradients enable optimization with only ~65% overhead relative to a forward simulation. For a 4 mm-diameter aperture (~8000 wavelengths, ~12,600 azimuthal modes) at 30-degree incidence, a forward-adjoint iteration requires only ~12 s on a 350-thread CPU, making oblique optimization practical without ray-tracing approximations. Applied to polychromatic RGB (446/530/650 nm) metalens design at normal incidence, full-area PSF evaluation exposes efficiency limits hidden by conventional cropped-focal-spot analysis: a mono-pillar metalens that appears diffraction-limited achieves only ~6% average absolute focusing efficiency, while direct far-field optimization raises this to 37% (locally periodic approximation) and 51% (zoned discrete axisymmetry). A cascaded double-metasurface design reaches 63%, while a four-metasurface architecture attains 96% average relative efficiency. We also demonstrate millimeter-scale, oblique-incidence optimization of single-surface and doublet architectures; cascaded doublets enable partial coma correction inaccessible to a single rotationally symmetric surface.
Rigidity-Based Multi-UAV Trajectory Optimization for Rapid Cooperative Emergency Target Localization
arXiv:2607.10933v1 Announce Type: new
Abstract: Reducing the response time for accurate emergency-caller localization is critical in vehicular and public-safety networks. Although mobile devices commonly use GNSS, Wi-Fi, or cellular positioning, their accuracy and availability can degrade because of poor signal reception, limited infrastructure, and regulatory constraints. UAV-based localization offers a promising alternative by using airborne sensors to cooperatively estimate the target position. However, existing Fisher information matrix (FIM)-based trajectory optimization methods depend on the current target estimate and can perform poorly in the early mission stage, when measurements are limited and uncertainty is high. We propose a rigidity-based UAV trajectory optimization method that maximizes the smallest nonzero singular value of the rigidity matrix associated with the UAV-target sensing graph, improving geometric conditioning and reducing position ambiguity. We also introduce a pruning-based matrix reduction strategy for efficient real-time implementation. Simulations show that the proposed method reduces search time by 32.9% compared with FIM-based methods and satisfies the FCC horizontal emergency-localization requirement sooner. Further results demonstrate scalability, robustness to UAV positioning errors and NLOS path loss, low sensitivity to heading parameters, practical computation and communication costs, and more stable degradation than PPO-based baselines under severe sensing and navigation perturbations.
arXiv:2607.10171v1 Announce Type: new
Abstract: Network immunization is a powerful tool for controlling contagion processes ranging from infectious diseases to misinformation diffusion. While prior works have focused on pairwise or static networks, immunization dynamics in temporal higher-order networks remain poorly understood. Here, we introduce immunization strategies and develop a theoretical framework tailored for such temporal systems. Firstly, we reveal bistability and discontinuous transitions in prevalence as the immunization fraction varies. This implies that immunization effectiveness depends on the initial prevalence, marking a fundamental departure from pairwise networks. Building on this prevalence-dependent behavior, we propose the High Infection Contribution (HIC) strategy, demonstrating its superior performance over all evaluated heuristic strategies. Furthermore, we introduce egocentric strategies by leveraging solely local observations. Notably, the optimal egocentric strategy shifts with the contagion prevalence. Our work advances the understanding of network immunization, paving the way for effective contagion control in temporal higher-order networks.
arXiv:2607.10345v1 Announce Type: new
Abstract: Recent studies on partial audio spoofing mainly focus on studio-recorded speech with temporal localization of spoofed segments. However, these studies often overlook realistic conditions where spoofed and bonafide segments simultaneously coexist across speech and environmental sound components. In this paper, we present PC-Mix, the first dataset for partial-component spoofing detection, where either or both audio components may be partially spoofed. In PC-Mix, bonafide and partially spoofed environmental-sound components are first constructed and mixed with speech signals from an existing partial-spoof dataset, producing audio in which either or both components may be locally manipulated. This design addresses two major gaps in existing partial spoofing benchmarks: the lack of realistic environmental sounds in speech partial spoofing scenarios and the absence of partial spoofing detection for environmental sound components. We further establish standardized evaluation protocols and design a joint learning framework to optimize spoofing detection across speech, environmental sound, and mixed audio. Experiments highlight the increased difficulty introduced by mixed conditions. The results demonstrate that training under matched target conditions is more effective than directly transferring models trained on speech or environmental sound components.
arXiv:2410.03565v4 Announce Type: replace
Abstract: In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (CMDP), agents train on a fixed, finite set of contexts and must generalize to new ones. Recent work has demonstrated that training on additional states, even if they are irrelevant for solving the current context, can improve generalization to unseen contexts. In this paper, we demonstrate that training on these states can indeed improve generalization, but can come at a cost of reducing the accuracy of the learned value function, which should hurt generalization. We hypothesize and demonstrate that increasing the agent's coverage by training on these additional states while also increasing the accuracy improves generalization even further. Inspired by this, we propose a simple approach Explore-Go that leverages existing pure exploration strategies in a new way: by introducing a pure exploration phase at the start of each training episode. Unlike previous approaches that apply exploration strategies for the purpose of improving generalization, our approach can be combined with both on- and off-policy algorithms. We demonstrate the effectiveness of Explore-Go when combined with several popular algorithms and show an increase in test-time performance across several generalization benchmarks, even partially observable ones. With this, we hope to provide practitioners with a simple modification that can significantly improve the generalization of their agents.
arXiv:2506.01377v2 Announce Type: replace
Abstract: In recent years, the development of specialized edge computing devices has significantly increased, driven by the growing demand for AI models. These devices, such as the NVIDIA Jetson series, must efficiently handle increased data processing and storage requirements. However, despite these advancements, there remains a lack of frameworks that automate the optimal execution of optimal execution of deep neural network (DNN). Therefore, efforts have been made to create schedulers that can manage complex data processing needs while ensuring the efficient utilization of all available accelerators within these devices, including the CPU, GPU, deep learning accelerator (DLA), programmable vision accelerator (PVA), and video image compositor (VIC). Such schedulers would maximize the performance of edge computing systems, crucial in resource-constrained environments. This paper aims to comprehensively review the various DNN schedulers implemented on NVIDIA Jetson devices. It examines their methodologies, performance, and effectiveness in addressing the demands of modern AI workloads. By analyzing these schedulers, this review highlights the current state of the research in the field. It identifies future research and development areas, further enhancing edge computing devices' capabilities.
arXiv:2607.11466v1 Announce Type: new
Abstract: Modernizing the security of operational technology systems that control critical infrastructure has become a pressing challenge. Because edge devices have limited capabilities, modernization has relied on application gateways that interface with identity management systems and enforce access policies. These gateways are powerful enough to perform complex authorization decisions and support zero-trust architectures, but they create major deployment and management burdens: they must be collocated with remote, distributed edge devices, kept up to date with security patches, and managed with minimal downtime.
We propose Provable Remote Execution of Zero-Trust Authorization (Prezta), an architecture that eliminates these gateways by evaluating policies within a zero-knowledge virtual machine (zkVM) running on the client. The zkVM produces a succinct proof of authorization that edge devices can verify efficiently, extending the zero-trust security envelope to the edge. Policies and identity management schemes can evolve without updating edge devices.
To demonstrate the feasibility of Prezta, we implement a prototype built using the RISC Zero zkVM that supports XACML 3.0 policies and JWT identity claims. While zkVMs introduce substantial proof overhead, we mitigate this overhead by compiling policies to Rust code and precompiling regular expressions. Combined with optimized signature verification and JWT parsing, these measures reduce prover time by more than an order of magnitude. Our compiler correctly implements 83\% of the XACML 3.0 conformance suite, with proof generation completing in tens of seconds on a desktop. Verification, by contrast, takes only tens of milliseconds, which is fast enough for resource-constrained edge devices.
arXiv:2607.10061v1 Announce Type: new
Abstract: Rapid technological change is reshaping society through emerging domains such as autonomous vehicles and smart manufacturing, creating new research challenges in system design, operation, security, and training. Researchers often rely on testbeds to reproduce experimental scenarios, collect and analyze data, observe system behavior, and evaluate proposed solutions. However, the fast pace of innovation makes it difficult and costly for individual testbeds to remain representative of state-of-the-art systems, as doing so requires frequent upgrades and new capabilities. Moreover, access to specialized testbeds is often limited to a small group of researchers, leaving valuable infrastructure underutilized during its operational lifetime. This paper presents FCTaaS, a Federated Cybersecurity Testbed as a Service framework that enables heterogeneous cybersecurity testbeds to participate in a single experiment across geographical boundaries. By connecting independently managed testbeds through a Virtual Private Network (VPN), FCTaaS supports remote testbed discovery, experiment design, and coordinated experimentation. We evaluate FCTaaS across three case studies involving denial-of-service scenarios on smart infrastructure and intrusion detection and prevention workflows using a Suricata-based IDS/IPS testbed. The results show that FCTaaS enables effective cross-testbed experimentation while preserving visibility into attack traffic, IDS alerts, and detection-system resource stress. Even under resource-intensive attack scenarios, FCTaaS achieves limiting network utilization of 49%, introduces only 1% overhead, and supports latency ranging from 5.63 ms between local nodes to 147 ms between geographically dispersed nodes.
arXiv:2607.10221v1 Announce Type: new
Abstract: Background. Large language models (LLMs) have become increasingly capable of understanding and generating source code, leading to their widespread adoption in software engineering tasks such as code completion, repair, and vulnerability detection. However, despite their strong empirical performance, the internal mechanisms through which LLMs recognize malicious or vulnerable code patterns remain poorly understood. Aim. We investigated where the malware detection behavior is encoded inside LLMs Feed Forward Network (FFN) neurons and verified the attribution with causal interventions on the neurons identified. This aims to identify the most important neurons in detecting malicious code. Methods. We applied mechanistic interpretability methods to locate the neurons being responsible for malware-detection behavior in three instruction-tuned LLMs: Llama3.1-8B-Instruct, Mistral-v0.3-7B-Instruct, and Qwen2.5-7B-Instruct. Using 1,500 malicious and 1,500 benign PyPI packages from the PyPI Malregistry, we attribute the behavior to a set of neurons. Results. The experimental results reveal that amplifying facilitating neurons for malware detection while suppressing inhibiting ones can boost accuracy, while the reverse collapses predictions toward a single class, although the magnitude and consistency is heavily model-dependent. We demonstrated that the guardrail detection mechanism varies across models, each represents its malware detection behavior differently within its FFN layers. Conclusions. Probing the neurons associated with security-relevant knowledge helps us gain insights into how LLMs encode malicious programming concepts, identify potentially harmful memorized behaviors, paving the way toward more reliable defense mechanisms, such as neuron-level editing, selective unlearning, and security-aware alignment for code-focused LLMs.
arXiv:2607.09749v1 Announce Type: cross
Abstract: Foundation models have recently emerged as a powerful paradigm for learning transferable representations from large scale biomedical data, yet existing approaches for physiological waveforms primarily optimize reconstruction or forecasting objectives that do not explicitly preserve clinically meaningful waveform morphology. Electrocardiograms (ECGs) and pulse oximetry (SpO2) waveforms encode rich cardiovascular and hemodynamic information through their morphological structure. In this work, we introduce MorphologyFM, a multimodal foundation model pretrained on paired ECG and SpO2 waveforms from the MIMIC critical care database using a morphology aware self supervised learning objective. MorphologyFM combines morphology guided masking, cross modal representation learning, and contrastive latent alignment to learn representations that capture clinically relevant physiological structure without requiring manual annotations. We evaluate MorphologyFM across multiple downstream prediction tasks, including arrhythmia classification, hypoxemia prediction, mortality prediction, and length of stay estimation, demonstrating consistent improvements over representative self supervised learning methods, including Masked Autoencoders (MAE), contrastive learning, Barlow Twins, and Joint Embedding Predictive Architectures (JEPA). Furthermore, we show that jointly modeling ECG and SpO2 waveforms produces more transferable representations than single modality pretraining. Our results establish waveform morphology as a powerful inductive bias for self supervised physiological representation learning and introduce MorphologyFM as a general purpose foundation model for continuous physiological monitoring.
arXiv:2607.11830v1 Announce Type: new
Abstract: License plate character detection is a crucial component of intelligent transportation systems, where high accuracy and computational efficiency are required for real-time deployment. Although recent deep learning-based methods have substantially improved detection performance, many high-accuracy models rely on large-scale architectures that incur substantial computational overhead, limiting their applicability to resource-constrained devices. In this paper, we propose MicroCharNet, an ultra-lightweight model specifically designed for license plate character detection. The proposed architecture employs a compact backbone composed of C2f blocks, integrated with CoordAtt module to enhance feature extraction while preserving spatial information. A lightweight C3k2-based neck fuses multi-level features, followed by a single-level anchor-free detection head that enables end-to-end prediction. Experiments conducted on the UFPR-ALPR dataset demonstrate that MicroCharNet achieves competitive detection accuracy with only 0.08M parameters and 0.096 GFLOPs, while outperforming several recent YOLO-based baselines. Hardware-level evaluations further confirm its efficiency for real-time deployment on edge devices. These results indicate that carefully designed ultra-lightweight architectures can effectively balance accuracy and efficiency in license plate character detection. The source code is available at https://github.com/chequanghuy/MicroCharNet.
arXiv:2607.10478v1 Announce Type: cross
Abstract: H.264 has been the most widely used video coding format for the past two decades due to its relative simplicity, efficiency, and wide availability of software and hardware implementations. However, optimizing codec parameters such as the quantization parameter (QP) for specific objectives (e.g., perceptual quality or machine vision tasks) is challenging due to the non-differentiable nature of standard video codecs. While differentiable proxies have recently been used to enable gradient-based optimization around standard codecs, their fidelity to the target codec is rarely explicitly characterized. In this paper, we propose a differentiable proxy learning method for H.264 intra codec to enable adaptive quantization control. Built upon a variable-rate learned compression model, the proposed proxy is made differentiable with respect to codec QP through a soft-indexing mechanism. It is then trained to approximate the rate-distortion behavior of H.264 under two quantization settings: global-QP, which uses one QP per image, and spatial-QP, which assigns QPs at the macroblock level. Using the frozen trained proxy, we develop a proxy-based adaptive quantization (AQ) framework for both perceptual optimization and machine vision tasks. Experimental results demonstrate that the proposed proxies closely approximate the rate-distortion behavior of H.264 intra codec. The resulting proxy-based AQ framework consistently improves rate-task trade-offs over fixed-QP H.264 baselines, achieving BD-rate reduction of up to 17.12% for semantic segmentation and 15.30% for MS-SSIM.
arXiv:2607.11220v1 Announce Type: new
Abstract: Best-track data have been typically used to explore long-term changes in typhoon intensity over the western North Pacific (WNP). However, the methods used to construct best-track intensities have changed over the past several decades. Several attempts have been made to achieve homogeneous intensity analyses based on the Dvorak method, but their consistency with direct observations can still be improved. This study tries to accurately explain minimum sea-level pressure (MSLP) from aircraft observations during 1981-1986 using CI numbers and other parameters as in Aizawa et al. (2024). Using the optimized coefficients, we reanalyzed MSLP for 1987-2024. The reanalyzed MSLPs were converted into maximum wind speeds using Knaff and Zehr (2007). This Typhoon intensity ReAnalysis (TyRA) exhibited a slightly decreasing trend in the number of intense typhoons, which was not statistically significant. Compared with TyRA, the Joint Typhoon Warning Center (JTWC) best-track contained a larger number of intense typhoons from the late 1980s to the mid-2000s, whereas the Regional Specialized Meteorological Center (RSMC) Tokyo best-track contained a smaller number. In TyRA, typhoons recently weakened over the eastern part of the WNP with some statistical significance. It can be explained by the decrease of mean age of typhoons after typhoon genesis. Large differences among the RSMC Tokyo and JTWC best-track data and TyRA were found for rapid intensification. Furthermore, although previous studies reported that errors in intensity forecasts by the RSMC Tokyo increased in the mid-2000s, the changes in the quality of the RSMC Tokyo best-track data partly explain this.
arXiv:2607.11241v1 Announce Type: new
Abstract: We consider the following additive Latin transversal problem. Given a multiset $A=(a_1,\dots,a_k)$ of elements of $\mathbb Z_m$ and a set $B\subseteq\mathbb Z_m$ of cardinality $k$, the task is to order $B$ as $b_1,\dots,b_k$ so that the sums $a_i+b_i$ are pairwise distinct. When $k=m$, Hall proved that a solution exists if and only if $\sum_{i=1}^m a_i\equiv 0 \pmod m$; moreover, his theorem yields a polynomial-time construction. Alon proved that a solution always exists when $m$ is prime and $k<m$, but no polynomial-time construction is known in general. Our main algorithmic contribution is a direct randomized algorithm for Color-Counted Matching: given an edge-colored graph and prescribed target counts for the colors, find a matching using exactly the prescribed number of edges of each color. If $q$ is the sum of the target counts and $h$ is the number of colors, our base-$(q+1)$ reduction to Exact Red Matching, combined with the algorithm of Mulmuley-Vazirani-Vazirani, gives a randomized algorithm with running time $\left(|V|^2+|E|(q+1)^{h-1}\right)^{O(1)} $ for an input graph $(V,E)$. Thus the dependence on the target matching size is $q^{O(h)}$, up to polynomial factors in the graph size. In contrast, applying the general matching-ILP theorem of Lassota and Ligthart as a black box yields a $q^{O(h^2)}$ dependence for the corresponding fixed-size color-counted instances. Applying this primitive to additive Latin transversals with $s=|\operatorname{supp}(A)|$, we obtain an algorithm in randomized time $(k+\log m)^{O(s)}$. In particular, additive Latin transversals are randomized polynomial-time constructible for every fixed support size.
arXiv:2607.11270v1 Announce Type: new
Abstract: Learning, at its core, extends beyond memorization to the ability to reason and solve novel problems by navigating a space of possibilities. We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space. The learned latent world dynamics capture physically grounded visual transitions, naturally encoding future possibilities and providing a unified substrate for cross-modal alignment. This formulation enables predictive reasoning akin to world modelling while remaining lightweight and focused on physical dynamics relevant to control. Central to our approach is the hypothesis that action generation quality is governed by the geometry of the latent space. We observe that standard reconstruction-based action tokenization objectives induce representations biased toward low-level signal fidelity, leading to misalignment between reconstruction quality and downstream control performance. To address this limitation, we propose a multi-stage modality pre-alignment strategy in which action representations are progressively aligned with latent world dynamics, vision, and language. This process enforces cross-modal consistency, promotes abstraction, and induces a structured latent space for predictive reasoning. We provide a systematic empirical study of latent world modelling and modality alignment, analyzing their roles in scaling laws and out-of-distribution generalization. Results show that Lumo-2 consistently outperforms strong vision-language-action (VLA) and world-action model (WAM) baselines, with gains on challenging real-world tasks requiring temporal reasoning, physical understanding, or high control complexity, including long-horizon and dexterous manipulation. These findings suggest that structured multimodal alignment and predictive reasoning are fundamental principles for advancing embodied intelligence.
arXiv:2607.11276v1 Announce Type: new
Abstract: Ensuring the quality of educational materials requires more than standard proofreading: textbooks must be audited for factual accuracy, domain-specific technical correctness, and linguistic quality simultaneously -- a task that general-purpose grammar checkers cannot address. We present \textbf{AI Textbook Auditor}, a modular multi-agent pipeline for automated quality assurance of educational materials across subject domains. The system accepts a textbook PDF and produces a structured, human-reviewable report via two analysis tracks: a \textbf{Factual and Technical Track} in which an ensemble of specialized LLM agents detects factual inaccuracies, code errors, incorrect definitions, and conceptual inconsistencies, augmented with web search for humanities domains; and a \textbf{Grammar Track} operating PDF-natively to preserve diacritical encoding. A \textbf{Judge Agent} filters false positives using domain-specific rules before presenting findings to a human reviewer. The pipeline supports two ingestion modes -- vision-native page rendering and PyMuPDF text extraction -- and is domain-adaptable via custom prompts encoding subject-specific error taxonomies. We demonstrate the system on two Romanian upper-secondary textbooks: a CS textbook (56 technical findings across seven categories, with an expert-validated precision of 62.5\%) and a history and social sciences textbook (72 findings spanning factual errors, ideological bias, and grammar). The system is designed as a triage tool that reduces the manual effort of locating candidate issues, with human expert validation required before any editorial action.
arXiv:2607.03496v2 Announce Type: replace
Abstract: How much does a vocalization change over the course of development? We propose trajectory variance, a per-vocalization plasticity score that answers this question without type labels. A displacement model learns to predict age-conditioned shifts in autoencoder latent space; the variance of its predictions across target ages quantifies how much each vocalization would change if produced at different developmental stages. Evaluated on three zebra finches (183K-274K vocalizations, 40-101 days post-hatch), trajectory variance separates learned song syllables from innate calls (Cohen's d = 0.29-0.57, AUC = 0.58-0.67, after controlling for duration), while no nonparametric baseline achieves consistent separation. Trajectory variance also correlates with spectral flatness across all three birds (r = -0.48 to -0.75): more plastic vocalizations tend to have more tonal, structured spectra.
arXiv:2607.04364v2 Announce Type: replace
Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent work has increasingly favored reinforcement learning over supervised fine-tuning, driven by the belief that reinforcement learning is inherently less prone to forgetting. However, the belief remains insufficiently validated, as existing evidence is largely drawn from outdated or homogeneous benchmarks. We revisit this assumption under recent and diverse multimodal reasoning tasks. To this end, we introduce MRCL, a Multimodal Reasoning Continual Learning benchmark. Experiments on MRCL show that standard reinforcement learning still suffers from severe catastrophic forgetting during continual post-training. We trace this failure to an objective mismatch: the KL regularization used in common policy optimization methods is evaluated on current-task data, whereas forgetting is caused by behavioral drift on prior-task distributions. To address this problem, we propose Continual Policy Optimization (CPO), a replay-free framework grounded in a prior-task behavioral KL objective. CPO relaxes the intractable historical KL constraint into sparse parameter-movement regularization, limiting policy drift without storing old data. Extensive experiments across multiple model scales show that CPO consistently reduces forgetting while preserving, and in some cases improving, pretrained model capabilities. On Qwen3-VL-8B, CPO reduces forgetting by 13.7% and improves pretrained capability by 7.0%. The implementation code is available at https://github.com/MaolinLuo/CPO.
arXiv:2607.09889v1 Announce Type: new
Abstract: Fixed-state sequence models compress an unbounded past into a bounded state, which caps their associative recall at roughly the state dimension; attention escapes the cap by keeping a key-value entry for every token, at quadratic compute and a cache that grows with the sequence. We study the middle ground: a sparse cache that allocates a slot only when an input is novel, so its size tracks the number of distinct items rather than the number of tokens. The allocation rule is the DP-means clustering rule, the small-variance limit of a Dirichlet-process mixture, used not as latent-variable inference but as the key-value memory operator for a deep recurrent backbone. We develop it in two forms, a static cache with a fixed concentration and a surprise-adaptive variant whose concentration follows the recent novelty rate. On a controlled associative-recall benchmark with redundancy we show that the cache matches full-attention recall while storing only the distinct items, that it dominates a fixed-budget eviction cache on the recall-versus-size frontier, and that on a state-space backbone it answers both a recall query and a long-range aggregate at the lowest memory of any model tested. The allocation is learnable end to end: a two-parameter novelty-threshold gate trained on the task loss alone recovers the rule exactly, whereas an over-parameterized gate fails, so the operative ingredient is the inductive bias rather than capacity. The evidence is a family of controlled mechanism studies at modest scale, with the distinct-items property confirmed on four real streams (recommendation, systems logs, clinical events, and insurance claims); a real-backbone, real-corpus language validation is pursued in a companion study.
arXiv:2607.11289v1 Announce Type: new
Abstract: Backpropagation is the computational engine of deep learning, yet its mathematical structure is typically treated as a procedural traversal of computational graphs. We present a global operator theory of the \emph{F-adjoint} framework, which reformulates the layerwise backward recursion of an $L$-depth feedforward network into a single linear system $(I-\cB)\Xs=\bG$, where $\bG$ is a source vector. We prove that the global backward operator $\cB$ is strictly block upper-triangular and nilpotent of index at most $L$. This nilpotency guarantees the exact termination of the Neumann series solution after at most $L$ terms, revealing classical backpropagation to be mathematically equivalent to block back-substitution on an upper bidiagonal system. We formalise \emph{F-symmetry} -- the condition in which the backward pass perfectly mirrors the forward pass -- identifying orthogonal weight matrices as canonical examples. Through worked numerical examples, we demonstrate how this operator perspective exposes the single-path collapse of strictly feedforward networks and its breakdown in residual architectures. Finally, we leverage this compositional structure to rigorously derive the mechanics of residual networks (gradient highways) and transfer learning (gradient truncation). This framework elevates backpropagation from an algorithmic recipe to a global nilpotent-operator formulation.
When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
arXiv:2607.11751v1 Announce Type: new
Abstract: As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundamental hole. A distributed backdoor splits a harmful payload across agents, so every local check passes while the assembled object is the attack. The monitor can be right on every step and still miss the attack. The problem is not splitting itself: split fragments can still leak suspicious tokens or provenance edges. The hard case is \emph{local benignness}. No fragment carries the harm, and what is left looks like ordinary benign traffic. We formalize this as an \emph{observability boundary}: a monitor catches only what its view can tell apart from benign traffic. We prove that once the fragments look benign in the monitored view, no detector on that view can catch them, however strong it is. Across a controlled testbed, an external benchmark, and end-to-end agent runs, local monitors lose the signal exactly as local evidence disappears, and it returns only when the monitor sees the assembled object. A monitor trained only on benign traffic recovers the attack's code structure across held-out encodings (0.874 mean AUROC). A decoded-view gate, given the encoding family, blocks every tested attack. But seeing more is not enough: full-trace monitors and decoders still fail unless they reach the representation where the payload is exposed. Local safety is not global safety when harm is compositional, and the open problem is finding that representation.