Papers

Cybersecurity education is facing more challenges as AI-driven attacks are becoming increasingly realistic and difficult to detect. Traditional video-based cybersecurity training in higher education often suffers from both low engagement and limited effectiveness. This dilemma motivates educators to explore innovative approaches, such as AI-powered gamification, which can deliver engaging, meaningful, and personalized learning experiences. By presenting content in a more interactive and user-friendly way, these methods have the potential to significantly improve both learner engagement and educational outcomes. This paper explores AI-powered gamification in cybersecurity education through the development of several short, mobile-friendly games. These games cover a range of topics from password security to text and phone scam recognition, incorporate multiple gamification strategies, including quiz-based, narrative-based, and simulation-based designs, as well as interactive formats such as TikTok Mini-Games. We conducted a two-tiered evaluation with 59 college students (comprising 9 technical experts and 50 general users), and the results indicate the potential of AI-powered gamification to improve engagement and increase attention to cybersecurity topics in higher education.

LLM-based agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file modification, information leakage, and unauthorized actions. Existing guardrails often evaluate completed trajectories, leaving pre-execution monitoring of step-level actions underexplored. We propose StepGuard, a step-level guard model that can audit completed agent trajectories and check tool actions before they are executed. To train StepGuard, we introduce StepGen, an automatic data engine that generates safe and unsafe trajectories with the same context but different actions at the risky step. To further reduce over-defense and under-defense, we propose Balance-GRPO, which dynamically balances learning between safe and unsafe actions based on their observed accuracy. Experiments show that StepGuard achieves the highest average accuracy among open-weight guard models, with performance comparable to GPT-5.4. When used to guard agents on AgentDojo and AgentDyn, StepGuard reduces mean attack success rate by 77.3% relative to the no-guard setting, while mean utility drops by only 2.8 percentage points.

We study the fully dynamic edge orientation problem, focusing on worst-case time bounds. An undirected graph undergoes edge insertions and deletions, and the goal is to maintain an orientation with small maximum outdegree (hereafter, outdegree) and small worst-case update time. The outdegree of any orientation is at least $\alpha-1$, where $\alpha$ is the graph's arboricity, i.e., the minimum number of forests into which its edge set can be partitioned. When $\alpha = O(1)$, it is long known that both the outdegree and the worst-case update time can be bounded by $O(\log n)$. Despite numerous follow-ups, no $o(\log^3 n)$ worst-case update time is known for maintaining constant outdegree, even for very basic graph families—with a notable exception, forests. For forests, a simple folklore algorithm maintains outdegree 2 via random walks: When an insertion creates a vertex of outdegree 3, the algorithm repeatedly chooses a uniformly random outgoing edge until reaching a vertex of outdegree at most 1, and then flips the resulting directed path. As the underlying graph is cycle-free, the path length is easily shown to be $O(\log n)$ in expectation, and also with high probability for polynomially long update sequences. We prove that this simple random walk paradigm extends to outerplanar graphs. Our algorithm maintains constant outdegree with $O(\log n)$ worst-case update time, where the time bound holds in expectation, and also with high probability for polynomially long update sequences. We give a tight analysis: outdegree 4 is achievable with $O(\log n)$-length paths, while outdegree 3 incurs $\mathtt{poly}(n)$-length paths. We also extend the argument to $K_{2,t}$-minor-free graphs, for any $t \ge 2$, with the outdegree bound depending only on $t$ and with the same update time guarantees. The locality of [...]

Brain stroke, known for its high mortality and incidence rates, poses significant health risks and requires rapid intervention for survival. Early diagnosis and preventive measures can greatly reduce life loss and disabilities. Recent advancements in deep learning have led to novel computer-aided diagnostic techniques for early stroke detection. This study proposes an intelligent system that predicts potential strokes using eleven features, evaluated through seven supervised machine learning algorithms. The process includes a literature review, dataset visualization, data preprocessing, and model evaluation. Ensemble methods like Random Forest, Stacking Classifier, and Bagging Classifier achieved high accuracies of 99.52%, while Decision Tree reached 98.24%. Other models, including KNN and TabNet, demonstrated reliable performance, achieving accuracies of 96.73% and 96.49%, respectively. The custom feedforward model achieved 94.91%, while SVC and logistic regression had lower accuracies at 88.06% and 77.03%. The results highlight the effectiveness of ensemble methods in stroke classification.

The Bayesian Ideal Observer (IO) establishes the theoretical upper bound on task performance for binary detection tasks. However, analytical computation of the IO test statistic is generally intractable. Numerical approaches based on Markov-chain Monte Carlo (MCMC) methods, including their recent deep generative model-based extensions, typically require extensive posterior sampling for each test image. Supervised learning has also been investigated to approximate the IO performance. However, such methods are typically trained for a specific detection task and signal and may require retraining when the task or signal changes. The score function, defined as the gradient of the log probability density, encodes the local geometry of the data distribution and is a fundamental quantity in modern score-based generative modeling. This work reformulates the IO test statistic in terms of the score function and introduces a score-based ideal observer (SIO). The proposed SIO uses a denoising convolutional neural network trained exclusively on signal-absent images to estimate the signal-absent score function. Once trained, the resulting score model can be used to approximate the IO test statistic for detection tasks involving arbitrary additive signals, without per-image posterior sampling or signal-specific retraining. Numerical studies consider a signal-known-exactly (SKE) detection task with a stochastic lumpy-background model. The results demonstrate that the proposed SIO can closely approximate the IO performance.

As generative AI (genAI) systems become embedded in education, employment, healthcare, and creative industries, the impact and engagement among marginalized groups have become both a widespread discourse and a focus in scholarly research. As a starting point, we examine public discourse and empirical research to explore the impact of genAI systems on Black communities. We conducted a systematic literature review (SLR) of 91 empirical papers alongside a media discourse frame analysis of 28 public resources, applying Entman's framing theory to map how each corpus defines problems, attributes causes, and proposes treatments. Our SLR reveals that scholarly research concentrates heavily on technical bias detection, reducing Blackness to measurable variables rather than engaging with cultural practices, structural conditions, or Black knowledge systems. Our frame analysis reveals that public discourse attributes genAI-related harm to historical and systemic forces, while scholarly research stops its causal accounts at the dataset and its treatment recommendations at technical reform. We demonstrate that this misalignment is structurally produced: anti-Blackness operates simultaneously across both registers, generating a shared evacuation of Black epistemic agency. We argue for frame analysis as an AI ethics methodology capable of surfacing what technical evaluation forecloses.

As language-model agents become more capable of iterative search, corpus access is shifting from retrieval toward interaction. Agents can explore the corpus, inspect documents, and use newly discovered evidence to decide what to examine next. Yet accessible evidence may still fail to become usable within a finite interaction budget. We call this progressive failure Evidence Blindness: supporting documents may never enter view, may remain unopened, or may fail to expose the decisive evidence even after being opened. A key reason is that agents often have to infer useful evidence directions during interaction, spending limited budget on deciding where to search next. Existing approaches either leave corpus structure largely implicit or reconstruct useful directions at query time. AtlasNav instead organizes reusable cross-document structure before any query arrives. It builds a persistent multi-view Corpus Atlas, which each query can navigate adaptively while still accessing the original documents directly. On BrowseComp-Plus, AtlasNav outperforms the previous state-of-the-art interactive corpus access method across different backbones. On DeepSeek, it improves strict accuracy by 7.47 points while reducing query-time inference cost by 30.22%.AtlasNav also reduces Evidence Blindness, realizes complete evidence earlier, remains robust to corpus-structure and scale shifts on PhantomWiki, and achieves leading performance on heterogeneous enterprise data.

Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedure prediction. Dense transformer decoders share the same feed-forward networks across tasks, which can entangle task behavior and make controlled capability expansion difficult. Sparse Mixture-of-Experts (MoE) decoders provide conditional computation, but token-level learned routing is not naturally aligned with task-level procedural objectives. We propose MoTE (Mixture of Task Experts), a decoder architecture that converts large language model feed-forward networks into task-specific experts while keeping the multimodal backbone shared. Each example follows one sample-level task route, so active task-expert computation remains independent of the number of stored task experts. We instantiate this design as VideoLLM-MoTE and evaluate it on five COIN benchmarks using explicit task routes. The five-expert model activates ~2B LLM parameters per sample and achieves higher average top-1 accuracy than recent VideoLLM baselines. Under the same expert topology, it improves over dense all-expert activation and learned sparse-routing controls. These results show that task-structured routing provides an interpretable and compute-efficient decoder alternative for multi-task video-language learning.

Many disentanglement methods represent generative factors using Euclidean product coordinates, although the underlying factor spaces may wrap, collapse, or have position-dependent geometry. We introduce factor-space structure, which combines factor domains, generator-induced identifications, and position-dependent scales to distinguish topologically equivalent spaces with different factor geometries. We show that statistical independence does not imply uniform product geometry: independent hue and scale can affect observations at different, scale-dependent rates, producing anisotropy that no fixed rescaling can remove. We propose the Factor-Space Topographic Map (FactoMap), which learns interpretable prototypes indexed by a structured factor-space lattice. Topographic learning transfers the lattice's periodicity, collapses boundaries, and non-uniform extent to the representation. Experiments show that matching this structure better preserves factor continuity and improves disentanglement of the underlying factors.

Healthcare organisations use digital systems to exchange information from clinical cases. Medical centres with digital production facilities create device designs during care. These designs and production records often remain at the site that made them. Other sites may struggle to find a suitable design or learn what happened when staff used it. Mobile medical centres may also lose access when they work away from hospital systems. This paper proposes an artifact-centred model for a federated exchange infrastructure that lets hospitals and mobile medical centres share and improve medical knowledge while controlling their own records and decisions. An integrative literature review screened 910 records and mapped 240 publications across six questions. We read 72 publications in detail to trace the path from local use to a decision about shared knowledge. The review found no common process that links a record of local use to a decision about changing the knowledge shared with later users. The model keeps case data at each site and records which artifact version informed each use. Federation lets sites share reviewed versions and return records from use for review. Mobile units can receive artifacts before deployment and record their use while offline. After reconnecting, they can exchange these records with other sites. Point-of-care manufacturing shows how a medical device knowledge artifact connects a design to production records while the care site controls product release. Federation could form a governed learning network where one site's experience improves medical knowledge artifacts used elsewhere while authority remains local.

Text-to-CAD aims to generate executable CAD programs from natural-language descriptions. However, real-world descriptions are often underspecified and omit critical spatial constraints required for valid CAD construction, a challenge that has been largely overlooked by existing methods. In this paper, we argue that missing spatial constraints should be inferred with respect to the underlying construction structure and informed by reusable design experience. Based on this insight, we propose ExpConCAD, an experience-enhanced framework for implicit spatial constraint completion. ExpConCAD first recovers the intended construction structure and constraint scopes, then retrieves relevant constraint-completion experience for similar scopes to complete the missing spatial constraints, and finally generates executable CadQuery programs. Extensive experiments demonstrate the effectiveness of ExpConCAD and provide insights into the role of construction structure understanding and experience memory in spatial constraint completion. Our code is available at: https://github.com/Hotjiashell/ExpConCAD.

Multi-teacher distillation has emerged as a way to combine complementary teacher models into a single student model that exhibits the strengths of all its teachers. The student is trained to mimic the output of the teachers on a set of images, typically the union of the individual teacher's training sets, assuming this data is available. In this paper, we question that assumption and explore alternative options. We first study how far one can go when distilling from teachers fed with different types of noise. Then, we show that information contained in the teachers can be leveraged to tailor the noise for multi-teacher distillation: we propose a method that, thanks to decorrelation losses at both patch and image levels, generates teacher-specific, improved samples optimized for data-free distillation. Experiments show that our most effective samples, IDeaL, lead to strong students that successfully capture complementary information from the teachers, yielding surprisingly competitive results that substantially narrow the gap with students distilled from real images. Moreover, given a limited budget of 1K images for distillation, students distilled using our IDeaL samples match or surpass the performance of those distilled using a 1K-image subset of ImageNet.

Discovering stable neuron behavior across entire domains remains a challenge in mechanistic interpretability. Existing methods often rely on instance-level point estimates or computationally expensive procedures, which either obscure population-level variability or limit scalable domain-wide analysis. We present RACE (Residual Alignment for Consistency Estimation), a forward-pass statistical framework that evaluates the domain-wide functional consistency of Transformer neurons. Compared with gradient-based point estimates, RACE produces neuron rankings that yield more domain-specific effects under perturbation. Token-distribution shifts support the connection between the selected neurons and the target domain, while scoring requires roughly one-hundredth of the computational overhead of the gradient-based methods. Code is available at https://github.com/Nexround/RACE.

Intrusion detection research in Industrial Control Systems (ICS) heavily depends on public datasets, yet no prior work has systematically assessed whether the collective dataset corpus supports current evaluation claims. This paper addresses this gap through a meta-review of 18 studies between 2019 and 2026, from which 83 ICS, or ICS directly related, cybersecurity datasets are identified, harmonised, and characterised using a unified five-dimensional taxonomy. The taxonomy reveals that the corpus is structurally skewed: 85.5% of datasets concentrate on late-stage OT Disruption tactics, cross-stage IT/OT progression sequences are present in only 8.4% of cases, field-device evidence at Level 0 of the Purdue hierarchy is effectively absent, and operationally sourced data accounts for only 15.7% of the collection. A parallel audit of evaluation practices shows that zero report streaming evaluation, fewer than half apply disciplined train/test partitioning, and only two satisfy reproducibility requirements. Furthermore, a taxonomy-evaluation coupling analysis shows that dataset imbalances constrain the scope and feasibility of several evaluation practices. Based on these findings, we identify three structural imbalances: i) architectural shallowness, ii) progression compression, and iii) cross-domain substitution, and derive a coordinated research agenda which covers cross-stage corpus construction, temporally structured benchmarking, event-level label standards, and governance frameworks for operational data sharing.

Seagrass meadows are crucial blue-carbon habitats, and mapping their extent is a prerequisite for coastal management and carbon inventory. Optical satellite sensors cover large areas but cannot reach deep or turbid water, whereas side-scan sonar (SSS) images the seabed at high resolution and at any depth. Interpreting SSS, however, still relies on dense manual annotation, which is slow and costly. We address this by adapting a weakly supervised semantic segmentation framework to SSS benthic habitat mapping, so that pixel-level maps are learned from image-level labels alone. The framework couples a ViT-based encoder-decoder with a classification branch, extracts class activation maps, and refines them into pseudo-labels with a dense conditional random field that we tune for the noise and weak boundaries of acoustic imagery. It follows an iterative self-training scheme, together with a sampling strategy to cope with the strong class imbalance of the data. We also study the effect of different loss functions on segmentation quality, finding Lovász-Softmax loss the most effective. On a held-out transect, the refined pseudo-labels reached an mIoU of 89.3% against the ground truth, and the segmentation branch, trained without any pixel-level labels, reached 87.6%. Self-supervised pretraining on unlabelled SSS added a further 3% in mean intersection-over-union. Field trials further demonstrate the generalizability of the trained model. These results show that accurate and label-efficient benthic habitat mapping from side-scan sonar is feasible at the scale needed for coast-wide seagrass monitoring.

Evaluating Retrieval-Augmented Generation (RAG) systems requires assessing not only end-to-end correctness but also how individual components interact and how errors propagate through the pipeline. We introduce a Bayesian evaluation framework that jointly models retrieval success, abstention behavior, and answer correctness, factorized according to the pipeline's information flow. The model distinguishes task success. Whether the user received a correct answer (from generator success) and whether the generator behaved appropriately given the retrieval outcome. We apply the framework to 27 RAG configurations across three datasets, three retrievers, and three generators, and show that the conditional decomposition reveals substantial behavioral differences between systems that appear equivalent under marginal metrics. We further analyze the annotation allocation problem, demonstrating that retrieval-success annotations are more informative than task-success annotations for estimating policy adherence, and provide an information-theoretic explanation for this asymmetry. Finally, we extend the model to incorporate LLM-as-a-judge annotations as calibrated noisy observations, enabling practitioners to combine limited human judgments with cheaper automated assessments within a unified probabilistic model.

Requirements elicitation is essential for developing interactive software systems, as it helps ensure that the resulting product meets stakeholder needs. Since elicitation typically relies on natural language (NL), misunderstandings can arise from its inherent ambiguity. Formal specifications can reduce ambiguity but require technical expertise. GUI prototyping therefore provides a valuable alternative by turning requirements into tangible visual artifacts that support communication, elicitation, and validation. However, creating high-fidelity prototypes remains time-consuming and costly. Similarly, requirements verification, which ensures that implementations conform to specified requirements, is still largely manual, while existing automated approaches are often limited to static, rule-based techniques. This work addresses two challenges: (C1) reducing the effort required to transform NL requirements into GUI prototypes, and (C2) reducing the effort required for requirements verification in GUI applications and prototypes. For C1, we introduce novel NL-based GUI retrieval and reranking methods, new benchmarks, and techniques for efficiently adapting LLMs to GUI generation, including proprietary GUI representations. Their effectiveness is demonstrated on a large benchmark with human annotations. For C2, we propose LLM-based methods for verifying semantically complex NL requirements on static GUI prototypes and introduce a multimodal LLM-based agent for verifying complex functional and non-functional requirements in dynamic GUI applications through automatically generated and evaluated interaction trajectories. Overall, the proposed methods substantially reduce manual effort in GUI prototyping and requirements verification.

How can humans make sense of the rapid takeoff of artificial intelligence (AI)? We studied the sensemaking dynamics of AI through an open-ended, mixed-methods study with computational text analysis of millions of AI-related newspaper articles and social media posts grounded in 57 semi-structured interviews with AI professionals in 2021 and 2023–before and after the recent surge of public interest. We identify a range of sociological frames (interpretive schemas that structure collective cognition) and show how AI professionals use frames to address significant cognitive challenges, such as assigning responsibility for societal impacts. We develop a framework of three primary debates across which frames are adopted and contested: (i) the $\textit{method}$ of AI development, between frames of top-down expert systems and bottom-up emergent capabilities, (ii) the $\textit{mind}$ of an AI system, ranging from a passive tool to a humanlike "digital mind," and (iii) the $\textit{morality}$ of how AI is used, particularly the decision of whether to slow down or speed up AI development. As humanity enters the era of transformative AI, technologists and policymakers must account for the framing dynamics that will circumscribe our beliefs, values, and actions.

Large language model (LLM) agents are trained with reinforcement learning (RL) for complex decision-making tasks. However, most RL-trained agents remain episodic and cannot accumulate reusable knowledge across episodes. Recent skill-based approaches, such as SkillRL, attempt to address this issue by extracting skills from raw trajectories, but treat the skill bank as an append-only repository without verifying whether stored skills remain effective. In this paper, we propose SkillForge, a framework for continuous skill evolution that enables skills to be verified and refined through environment interaction. By making skill usage explicit during agent interaction, RL can directly optimize both environment actions and skill invocation decisions. SkillForge further introduces evidence-based skill verification and multi-pathway skill induction, allowing the skill bank to continuously grow while maintaining its quality. Extensive experiments on ALFWorld, WebShop, and AppWorld show that SkillForge consistently outperforms SkillRL, demonstrating the effectiveness of continuously verified skills in training stronger LLM agents.

Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-conservative safety guarantees due to significant relaxation gaps. While the completely positive program (CPP) formulation closes this gap, it is NP-hard to solve. Its cheapest tractable relaxation, the doubly non-negative program (DNN), retains critical constraints as an SDP, but one whose size exceeds the reach of interior-point methods at practical scale. While Burer-Monteiro (BM) factorization has been applied to make SDP-based verification scalable, no such result exists for the strictly tighter DNN formulation. A key obstacle is that additional non-negativity constraints in the DNN cause dual multipliers for optimality certification to be non-unique, making standard certification methods inapplicable. We propose a novel eigenvalue maximization procedure that searches the non-unique multiplier space for a valid certificate, i.e. a global optimality guarantee. Experiments demonstrate that our approach $(\text{DNN})^2$ produces bounds consistently tighter than the standard SDP method, often matching the exact solution, and that our certification procedure confirms global optimality when a valid certificate exists. These results are a key step toward providing tight, certifiable, and computationally scalable verification guarantees needed to deploy neural network controllers and perception modules in safety-critical autonomous systems.

Physical implementations of Turing Machines remain rare, and existing electromechanical demonstrators and mechanical logic games typically require manual operator intervention, either to trigger each computational step or to reconfigure the state table, or both. This restricts prior physical models to short, operator-paced demonstrations and prevents autonomous execution of extended computations. This paper addresses that gap with a hardware Turing Machine that enables autonomous multi-step execution and reprogrammable optical input without manual intervention between programs. The system integrates an Arduino Mega for state-transition logic, dual NEMA 17 stepper motors for bidirectional tape actuation, infrared reflectance sensors for symbol detection, and an ESP32-CAM-based optical punched-card reader for automated state-table loading. Hole detection under non-uniform illumination used a Breadth-First Search flood-fill algorithm with local adaptive thresholding rather than fixed global thresholding, driven by the memory and library constraints of the ESP32-CAM's microcontroller environment; this improved card-decoding accuracy from 75% to 90% (100% with mechanical card flattening) on a 20-card test set. Mechanical evaluation showed fabrication accuracy of +/-0.15 mm, rack-and-pinion positional error below 0.3 mm across 50 trials, and voltage supply stability within +/-0.2 V under full system load. End-to-end computation was validated against a parallel software simulator (tlang), with all hardware outputs matching the simulated reference exactly across multiple test programs. The system advances prior physical Turing Machine demonstrations through autonomous execution, reprogrammable optical input, and quantitative evaluation of its mechanical, optical, and computational performance.

Learning from Demonstration (LfD) allows robots to learn manipulation tasks directly from humans, thereby supporting the versatile application of robots. Most LfD methods do not explicitly model the physical interactions between a robot and its environment, such as the making and breaking of contact, while these are crucial during manipulation tasks. Because the same basic physical interactions recur often, they can be a basis for robust, generalizable, and adaptive task reproduction. We propose an LfD method that explicitly uses what physical interactions take place where and when. Using that information, a hybrid position-force controller tracks demonstrated trajectories until contact-based transition conditions from the demonstrations are met. We evaluate our method in real robot experiments consisting of opening doors and locks, bolt picking and screwing, dislodging, and surface contouring. We show that explicitly modeling physical interactions benefits LfD in four ways. First, by allowing reproduction of complex, sequential, and contact-rich manipulation tasks using only a single demonstration and no prior knowledge of the task. Second, by facilitating robustness to unknown geometric variations in the environment. Third, by facilitating generalization when geometric variations are known. Fourth, by facilitating online adaptation using geometric information explored during task reproduction. We discuss how robustness, generalization, and adaptivity can be explicitly implemented, which is generally lacking in the LfD literature. Thereby, our work aims to close a gap in interpretable few-shot LfD of robotic manipulation.

Morphological transforms are long-standing tools for shape and mask processing, but the de facto reference implementation in the Python ecosystem, i.e. scipy.ndimage, is CPU-only, single-array, and therefore unusable inside a GPU training loop without an expensive device-to-host round trip. GPU vision libraries built on PyTorch cover a narrow subset of these operators, typically restricted to two spatial dimensions and flat structuring elements. We present TorchMorph, a lightweight PyTorch extension that closes this gap. TorchMorph exposes 22 public operators covering binary morphology, greyscale morphology, exact and approximate distance transforms, and entropy-regularised optimal transport, all implemented as fused CUDA kernels that operate directly on (B, C, Spatial...) CUDA tensors with up to eight spatial dimensions. The API deliberately mirrors scipy.ndimage argument-for-argument, including border modes, structuring-element origins and pre-allocated outputs, so that existing pipelines port with a change of import. We describe the layered architecture and the kernel designs behind each operator family. Against single-threaded CPU references, batched execution reaches up to 1.1e3 times the throughput of scipy.ndimage on greyscale morphology and up to 350x on exact Euclidean distance transforms, while the Sinkhorn solver runs up to 42x faster than POT. Binary and chamfer operators reproduce their SciPy counterparts exactly, and every float-valued operator agrees with the CPU reference to within 1.8e-6 absolute error. TorchMorph is released under the MIT licence at https://intcomp.github.io/tm.

Self-improving LLM agents refine answers, not the process that produces those answers. Systems that add a meta-level hold that level fixed, and those that edit themselves must leave part of their own editing machinery untouched to stay stable, capping the meta-depth they realize at roughly two. We present Meta$^n$, which keeps the meta-operation fixed and recurses on its input instead. That operation, $\Omega$, is applied repeatedly to its own products, reading the traces of the solver stack below together with the code that produced them, then writing the next layer as a strategic pre-process and a library of callable helpers. Because $\Omega$ never changes, it cannot destabilize the system, and because its input strictly grows, each layer reasons from a higher vantage than the last. Depth is set by convergence rather than fixed in advance, and an evolutionary archive searches over layer chains. Across two backbones, Meta$^n$ outperforms prior self-improving agents on all eight benchmark families. The sharpest case is ARC-AGI-2, built to resist skill memorization, where it alone scores above zero. Ablations indicate that most of the gain from recursion comes from the conditioning each layer passes to the next, and distinct layer roles emerge with depth although no prompt prescribes them. Code available at https://github.com/minnesotanlp/meta-n

We settle the minimax-optimal alternating regret, a regret notion motivated by alternating learning dynamics in games, for both online linear optimization (OLO) and online convex optimization (OCO). For OLO over the probability simplex $\Delta_d$, we give an algorithm with $O(\log d)$ alternating regret that remains a constant for any time horizon $T$, and a matching lower bound. Our constant regret bound significantly improves previous results with $O(\log ^{2/3}d \cdot T^{1/3})$ regret [Cevher, Cutkosky, Kavis, Piliouras, Skoulakis, Viano, NeurIPS 2023, Hait, Li, Luo, Zhang, COLT 2025]. As a result, we obtain alternating learning dynamics with $O(\log d /T)$ convergence to Nash equilibria in two-player zero-sum games and $O(\log d /T)$ convergence to coarse correlated equilibria in two-player general-sum games. This is the first uncoupled learning dynamics with $O(1/T)$ convergence to CCE in two-player general-sum games, while all prior works suffer additional $\log T$ factors. For general OCO over a $d$-dimensional compact convex set, we give an algorithm with $O(d\log (1+T/d))$ alternating regret, improving the previous best of $\widetilde{O}(d^{2/3}T^{1/3})$. We also prove a matching lower bound of $\Omega(d\log (1+T/d))$, showing that the $\Omega(\log T)$ factor is unavoidable.

Emotion preference learning uses pairwise comparisons between candidate descriptions to align multimodal large language models (MLLMs) with human judgments of open-ended emotion descriptions and to train reward models that capture human emotional preferences. However, conventional pairwise supervision is often sparse, typically providing only a single negative description for each positive description, and therefore offers limited coverage of the diverse ways in which an emotion description can be incorrect. In particular, models may be insufficiently exposed to semantically fluent but emotionally inconsistent descriptions. Beyond this data-level limitation, relying on a single MLLM judge introduces a distinct model-level concern: its judgments can be affected by model-specific biases when interpreting fine-grained or ambiguous multimodal emotional cues. To address these limitations, we propose Error-Augmented Preference Optimization (EAPO), a framework for improving the reliability of MLLM-based emotion preference judgment at both the data and model levels. First, we construct an error-augmented dataset by generating multiple controlled and emotion-aware negative descriptions from each preferred description. We then adapt multiple independent MLLM judges to this richer supervision and aggregate their preference margins using margin-calibrated soft fusion, which maps heterogeneous margins to a common scale before aggregation. Experiments on the MER2026-EmoPrefer Challenge dataset and our error-augmented dataset demonstrate that EAPO improves emotion preference prediction and enhances the robustness of MLLM judges when evaluating fluent descriptions that conflict with the video's multimodal emotional evidence. Our code is available at https://github.com/slash1028/EAPO-EmoPrefer.

We show that there exists a polynomial-time algorithm to find a stable matching in network hypergraphic preference systems. The key connection that drives the algorithm was discovered by chatting with ChatGPT-5.6 Sol Max. We verified it independently and present the details in our own words.

EEG foundation models pretrained via self-supervised learning promise transferable representations, but their generalization remains limited, especially across diverse clinical datasets. Full fine-tuning is impractical for resource-constrained clinical settings due to high computational requirements. In this work, we investigate whether parameter-efficient self-supervised adaptation, updating only 9% of parameters suffices to align representations to target tasks. We evaluate our method on two state-of-the-art models with different pretraining objectives: BIOT (contrastive) and CBraMod (masked reconstruction), and evaluate on three clinical EEG datasets for abnormality detection (TUAB), event classification (TUEV), and seizure detection (CHB-MIT) under both in-distribution and out-of-distribution conditions. SSL adaptation yields consistent gains over linear probing, up to 20x AUCPR. Under a fixed compute budget, peak performance requires only 20–50% of available unlabeled data. Critically, when total window count is fixed, performance remains invariant to patient count, suggesting that performance is dependent on overall temporal window diversity only. Our findings demonstrate that parameter-efficient adaptation enables effective deployment of EEG Foundation models (EEG-FM) with minimal computational overhead and data collection burden. Code available at: https://github.com/c3n-group/efficient-eeg-adapt

Polygonal synthesis generates audio by traversing the perimeter of a polygon with a phasor; prior work uses a constant angular velocity, whereas the proposed system adopts constant arc-length (perimeter) velocity. Existing formulations operate on regular, parametrically defined polygons, producing smooth timbral transitions within a single family of shapes. This paper generalizes polygonal synthesis around a unified arc-length engine: vertex data of any origin feed the same DSP pipeline. First, we adapt the oscillator to accept arbitrary vertex configurations from an external buffer, opening the possibility for a broad class of closed polygons – regular, irregular, or star-shaped – to function as a waveform generator. Second, a hybrid interpolation algorithm enables smooth morphing between polygons with unequal vertex counts, passing through intermediate shapes that have no parametric description. Third, we extend the paradigm to three dimensions: a convex polyhedron rotated about three axes is sliced by a fixed horizontal plane, and the resulting cross-section yields a continuously variable polygon controlled by the solid's orientation. The system runs in RNBO (Cycling~'74) with a geometry caching strategy that avoids per-sample recomputation. Antialiasing combines a four-point polyBLAMP correction derived from runtime Bézier tangents with adaptive oversampling, adapting the correction geometrically to general vertex configurations without per-shape analytical derivation.

Harbor seals track hydrodynamic trails with their vibrissae, enabling passive perception of moving targets in dark or turbid water. Inspired by this capability, we present compact fiber Bragg grating (FBG) whiskers for underwater robots. Like seal whiskers, they have a non-uniform taper and elliptical cross-section. Controlled towing experiments show a monotonic relative-flow response from 0.1 to 0.6 m/s, a strong reduction of self-induced oscillation relative to a cylindrical baseline, and a pronounced dependence on angle of attack. Experiments with a pitching foil show that the whiskers can detect the characteristic vortices shed by a stationary or moving source, detectable several seconds after the source has passed. Using this information, a single front-mounted whisker enabled a small underwater robot to distinguish between continuing straight and executing a turn, selecting the correct branch in 17 of 20 trials (85.0%) from whisker signals alone. These results connect bioinspired hydrodynamic sensing to robot action and suggest the utility of whiskers for tracking underwater objects.